JP2016208355A - Image monitoring device, image monitoring method, and image monitoring program - Google Patents

Abstract

An image monitoring device capable of recording an image on a recording device for a long time without limiting the monitoring target area.
An image monitoring apparatus determines an image quality based on at least one of a size of a detection target and a density of the detection target in the image, and an image acquisition unit that acquires an image of a monitoring target area. A quality determination unit; and an image conversion unit that converts the image acquired by the image acquisition unit so as to achieve the image quality determined by the image quality determination unit, and outputs the converted image.
[Selection] Figure 2

Description

  The present invention relates to an image monitoring apparatus, an image monitoring method, and an image monitoring program, and more particularly to an image monitoring apparatus, an image monitoring method, and an image monitoring program that can change image quality.

  2. Description of the Related Art Conventionally, an image monitoring apparatus that detects a detection target such as a person or a vehicle from an image captured by an imaging apparatus and monitors a monitoring target area using the detection result has been developed.

  In general, an image captured by an image monitoring apparatus is recorded in a recording apparatus or the like. However, since the recording capacity of the recording apparatus is limited, the image is recorded after performing processing such as compressing the image.

  Japanese Patent Application Laid-Open No. 2004-151867 discloses an image in which the image quality when an unqualified person enters the monitoring target area can be higher than the image quality when an unqualified person does not enter the monitoring target area. A monitoring device is disclosed. As a result, it is possible to record images on the recording device for a long time while maintaining high quality for highly important images.

JP 2011-168773 A

  However, in the image monitoring apparatus described in Patent Document 1, a device such as a card reader must be provided separately in order to determine whether the person is a qualified person or an unqualified person. That is, a person who is authenticated by holding an IC card over a card reader installed in the vicinity of the monitored area is determined as a qualified person, and other persons are determined as unqualified persons. For this reason, the monitoring target area is limited to a specific place such as a warehouse where a card reader is installed or a restricted access area, and cannot be used for monitoring a place where an unspecified number of persons such as roads come and go. There is a problem.

  The present invention has been made to solve the above-described problems, and an object of the present invention is to provide an image monitoring device and the like that can record an image on a recording device for a long time without limiting the monitoring target area. And

  (1) In order to achieve the above object, an image monitoring apparatus according to an aspect of the present invention includes an image acquisition unit that acquires an image obtained by imaging a monitoring target area, the size of the detection target in the image, and the detection target Based on at least one of the densities, an image quality determination unit that determines image quality, and the image acquired by the image acquisition unit so as to be the image quality determined by the image quality determination unit, An image conversion unit for outputting the image.

  (10) In addition, an image monitoring method according to another aspect of the present invention includes an image acquisition step of acquiring an image obtained by imaging a monitoring target area, and at least one of the size of the detection target and the density of the detection target in the image. An image quality determination step for determining an image quality based on the image quality, and converting the image acquired in the image acquisition step so as to be the image quality determined in the image quality determination step, and the converted image And an image conversion step of outputting.

  (11) Further, an image monitoring program according to yet another aspect of the present invention includes an image acquisition step of acquiring an image obtained by imaging a monitoring target area, and at least the size of the detection target and the density of the detection target in the image. On the basis of the image quality determination step for determining the image quality, the image acquired in the image acquisition step to be converted to the image quality determined in the image quality determination step, and the converted image A program for causing a computer to execute an image conversion step of outputting an image.

  Note that the present invention can be realized as a semiconductor integrated circuit that realizes part or all of the image monitoring apparatus, or as an image monitoring system including the image monitoring apparatus.

  According to the present invention, it is possible to record an image on a recording device for a long time without limiting the monitoring target area.

It is a figure which shows the structure of the image monitoring system which concerns on Embodiment 1 of this invention. It is a block diagram which shows the structure of the image monitoring system which concerns on Embodiment 1 of this invention. It is a flowchart of the process which the image monitoring apparatus which concerns on Embodiment 1 of this invention performs. It is a flowchart which shows the detail of the image quality determination process (S4 of FIG. 3) which concerns on Embodiment 1 of this invention. It is a figure which shows an example of the image with the small size of a person area. It is a figure which shows an example of the image with the large size of a person area. It is a figure which shows an example of the image which two or more persons are reflected. It is a figure which shows an example of the table data which defined the relationship between image quality, BPP, resolution, and a frame rate. It is a flowchart which shows the detail of the image quality determination process (S4 of FIG. 3) which concerns on Embodiment 2 of this invention. It is a figure which shows an example of an image with a high density of a person. It is a figure which shows an example of an image with a low density of a person. It is a flowchart which shows the detail of the image quality determination process (S4 of FIG. 3) which concerns on Embodiment 3 of this invention. It is a figure which shows an example of the table data which defined the relationship between image quality, BPP, resolution, and a frame rate. It is a flowchart of the process which the image monitoring apparatus which concerns on Embodiment 4 of this invention performs. It is a figure which shows an example of the table data which defined the relationship between image quality, BPP, and resolution. It is a figure which shows an example of the table data which defined the relationship between a moving speed and a frame rate.

  First, embodiments of the present invention will be listed and described.

  (1) An image monitoring apparatus according to one aspect of the present invention is based on an image acquisition unit that acquires an image obtained by imaging a monitoring target area, and at least one of the size of the detection target and the density of the detection target in the image. An image quality determination unit that determines image quality, and an image conversion unit that converts the image acquired by the image acquisition unit so as to be the image quality determined by the image quality determination unit, and outputs the converted image With.

  According to this configuration, it is possible to output an image by changing the image quality based on the size of the detection target in the image or the density of the detection target. That is, the image quality can be changed and an image can be output without using a special device such as a card reader as in the prior art. The output image can be recorded in a recording device. For this reason, it is possible to record an image on the recording device for a long time without limiting the monitoring target area, regardless of the monitoring target area.

  (2) The image quality determination unit may determine the image quality higher as the size of the detection target is smaller.

  According to this configuration, the image quality can be determined high when the size of the detection target is small, and the image quality can be determined low when the size of the detection target is large. If the detection target appears small because the detection target is located far from the camera, the image can be recorded on the recording device while maintaining high image quality. For this reason, even when the image recorded in the recording device is reproduced, the user can confirm the detection target in detail. On the other hand, when the detection target is large because the detection target is located near the camera, the image quality can be reduced and the recording apparatus can record the image. When the detection target is large, the detection target can be sufficiently recognized even if the image quality is lowered. For example, when the detection target is a person, the face of the person can be determined even if the image quality is lowered. For this reason, when the image recorded on the recording device is reproduced, the image can be recorded on the recording device for a long time while maintaining the image quality that allows the user to confirm the detection target in detail.

  (3) When the image includes a plurality of detection targets, the image quality determination unit may determine the image quality higher as the minimum value of the size of the detection target is smaller.

  According to this configuration, when a plurality of detection targets appear in the image, the image quality can be determined based on the minimum size of the detection targets. For example, when two detection targets of different sizes are included in an image, if the image quality is determined based on the size of the larger detection target, the image quality may be determined low. As a result, a low-quality image is recorded in the recording device. In such a case, even if the image recorded in the recording apparatus is reproduced, the user can confirm in detail the detection target having a large size, but cannot confirm the detection object in small size in detail. However, in this configuration, since the image quality is determined based on the minimum size of the detection target, the user can check all the detection targets in detail when the image recorded in the recording device is reproduced. .

  (4) The image quality determination unit may determine the image quality higher as the density of the detection target is higher.

  According to this configuration, the image quality can be determined high when the density of the detection target is high, and the image quality can be determined low when the density of the detection target is low. When the density is high, the detection targets may overlap in the image, and some of the detection targets may be hidden by other detection targets. In this configuration, in such a case, an image can be recorded on the recording device while maintaining high image quality. For this reason, when the image recorded in the recording apparatus is reproduced, the user can see in detail the portion where the detection target overlaps, so that the detection target can be confirmed in detail. On the other hand, when the density of the detection targets is low, the possibility that the detection targets overlap in the image is lower than when the density is high. For this reason, even if the image quality is deteriorated, the detection target can be sufficiently recognized. For example, when the detection target is a person, the face of the person can be determined even if the image quality is lowered. For this reason, when the image recorded on the recording device is reproduced, the image can be recorded on the recording device for a long time while maintaining the image quality that allows the user to confirm the detection target in detail.

  (5) The image conversion unit may convert the image acquired by the image acquisition unit such that the lower the image quality determined by the image quality determination unit, the smaller the number of bits per pixel.

  According to this configuration, an image with a smaller number of bits per pixel can be recorded in the recording device as the image quality is lower. Therefore, an image can be recorded on the recording device for a long time.

  (6) The image conversion unit may convert the image acquired by the image acquisition unit such that the lower the image quality determined by the image quality determination unit, the lower the resolution.

  According to this configuration, the lower the image quality, the lower the resolution can be recorded on the recording device. Therefore, an image can be recorded on the recording device for a long time.

  (7) The resolution may be determined such that a person's face as the detection target in the converted image has a predetermined size or more necessary for identifying the person's face.

  According to this configuration, when the detection target is a person, the face of the person can be identified from the converted image even if the image quality is determined to be low. For this reason, it can be prevented that the image quality becomes too low and the human face cannot be identified.

  (8) The image conversion unit may convert the image acquired by the image acquisition unit such that the lower the image quality determined by the image quality determination unit, the lower the frame rate.

  According to this configuration, the lower the image quality, the lower the frame rate image can be recorded in the recording device. Therefore, an image can be recorded on the recording device for a long time.

  (9) The image conversion unit may convert the image acquired by the image acquisition unit so that the frame rate becomes lower as the moving speed of the detection target decreases.

  According to this configuration, as the moving speed of the detection target decreases, an image with a lower frame rate can be recorded on the recording device. When the moving speed of the detection target is low, the detection target can be tracked because the detection target is included in the images of a plurality of frames even if the frame rate is lowered. On the other hand, when the moving speed of the detection target is high, the frame rate is increased. For this reason, even in this case, the detection target can be tracked.

  (10) An image monitoring method according to another aspect of the present invention is based on an image acquisition step of acquiring an image obtained by imaging a monitoring target area, and at least one of the size of the detection target and the density of the detection target in the image. And converting the image acquired in the image acquisition step so that the image quality determined in the image quality determination step and the image quality determined in the image quality determination step, and outputting the converted image Image conversion step.

  According to this configuration, it is possible to output an image by changing the image quality based on the size of the detection target in the image or the density of the detection target. That is, the image quality can be changed and an image can be output without using a special device such as a card reader as in the prior art. The output image can be recorded in a recording device. For this reason, it is possible to record an image on the recording device for a long time without limiting the monitoring target area, regardless of the monitoring target area.

  (11) An image monitoring program according to yet another aspect of the present invention includes an image acquisition step of acquiring an image obtained by imaging a monitoring target area, and at least one of a size of the detection target and a density of the detection target in the image. Based on the image quality determination step for determining the image quality, the image acquired in the image acquisition step is converted so as to be the image quality determined in the image quality determination step, and the image after the conversion is converted A program for causing a computer to execute an image conversion step to be output.

  According to this configuration, it is possible to output an image by changing the image quality based on the size of the detection target in the image or the density of the detection target. That is, the image quality can be changed and an image can be output without using a special device such as a card reader as in the prior art. The output image can be recorded in a recording device. For this reason, it is possible to record an image on the recording device for a long time without limiting the monitoring target area, regardless of the monitoring target area.

[Details of the embodiment of the present invention]
Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Each of the embodiments described below shows a preferred specific example of the present invention. Numerical values, shapes, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are merely examples, and are not intended to limit the present invention. The invention is specified by the claims. Therefore, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims indicating the highest concept of the present invention are not necessarily required to achieve the object of the present invention. It will be described as constituting a preferred form.

  In addition, you may combine arbitrarily at least one part of embodiment described below.

(Embodiment 1)
In the first embodiment, an image monitoring system that determines image quality based on the size of a monitoring target included in an image obtained by capturing a monitoring target area and records an image of the determined image quality in a recording apparatus will be described.

[1-1. Overall system configuration]
FIG. 1 is a diagram showing a configuration of an image monitoring system according to Embodiment 1 of the present invention.

  The image monitoring system 1 is a system that records an image obtained by imaging the monitoring target area A. The image monitoring system 1 includes a camera 10, an image monitoring device 20, and a recording device 30.

  The camera 10 is, for example, a video camera for monitoring purposes that is installed outdoors or indoors for the purpose of crime prevention and images the monitoring target area A. The camera 10 captures a moving image. FIG. 1 shows an example in which the camera 10 is installed on the road as a monitoring target. For example, the camera 10 is installed on a utility pole, a dedicated columnar jig, or the like.

  The image monitoring device 20 is connected to the camera 10 via a communication line 40 such as the Internet or a LAN (Local Area Network), determines image quality from an image captured by the camera 10, and outputs an image of the determined image quality It is a device to do. The image monitoring apparatus 20 is configured by a computer including, for example, a CPU (Central Processing Unit) and a RAM (Random Access Memory). Note that the image monitoring apparatus 20 and the camera 10 may be directly connected by a cable.

  The recording device 30 is connected to the image monitoring device 20 with a cable and records an image output from the image monitoring device 20. The recording device 30 is configured by a nonvolatile memory such as a flash memory, an HDD (Hard Disk Drive), or the like. Note that the recording device 30 may be configured by a volatile memory such as a DRAM (Dynamic Random Access Memory). Further, the image monitoring apparatus 20 and the recording apparatus 30 may be connected via a communication line such as the Internet or a LAN.

[1-2. Configuration of image monitoring system]
FIG. 2 is a block diagram illustrating a configuration of the image monitoring system 1.

  The image monitoring apparatus 20 includes an image acquisition unit 21, an image processing unit 22, an image quality determination unit 23, and an image conversion unit 24.

  The image acquisition unit 21 acquires an image obtained by capturing the monitoring target area A from the camera 10 via the communication line 40 and outputs the acquired image to the image processing unit 22. That is, the image acquisition unit 21 includes a communication interface for connecting to the communication line 40.

  The image processing unit 22 performs preprocessing on the image acquired by the image acquisition unit 21, and outputs the preprocessed image to the image quality determination unit 23 and the image conversion unit 24. For example, the image processing unit 22 removes noise such as high-sensitivity noise included in an image by applying a noise removal filter such as a Gaussian filter or a median filter to the image. Further, the image processing unit 22 corrects the distortion of the image using the distortion aberration caused by the lens of the camera 10 measured in advance.

  The image quality determination unit 23 determines the image quality of the image output from the image monitoring device 20 based on the image output from the image processing unit 22. That is, the image quality determination unit 23 determines the image quality based on the size of the detection target in the image. Specifically, the image quality determination unit 23 determines the image quality higher as the size of the detection target is smaller. In the following description, the detection target is described as a person.

  The image conversion unit 24 converts the image output from the image processing unit 22 so that the image quality determined by the image quality determination unit 23 is obtained, and outputs the converted image. The image conversion unit 24 includes a communication interface for connecting to the recording device 30. An image conversion method by the image conversion unit 24 will be described later.

  The recording device 30 includes an image acquisition unit 31 and a recording unit 32.

  The image acquisition unit 31 acquires the image output from the image monitoring device 20 and writes the acquired image in the recording unit 32. The image acquisition unit 31 includes a communication interface for connecting to the image monitoring apparatus 20.

  The recording unit 32 is configured by a nonvolatile memory such as a flash memory, an HDD, or the like. The recording unit 32 may be configured by a volatile memory such as a DRAM.

[1-3. Processing flow of image monitoring device]
Next, image conversion processing by the image monitoring device 20 will be described. FIG. 3 is a flowchart of processing executed by the image monitoring apparatus 20.

  The image acquisition unit 21 acquires an image obtained by capturing the monitoring target area A from the camera 10 via the communication line 40, and outputs the acquired image to the image processing unit 22 (S1). The camera 10 will be described below assuming that an image having a resolution of 1920 × 1080 (pixel) is output at a frame rate of 30 fps (frames per second).

  The image processing unit 22 performs preprocessing on the image acquired by the image acquisition unit 21, and outputs the preprocessed image to the image quality determination unit 23 and the image conversion unit 24 (S2). Preprocessing removes noise in the image and corrects image distortion.

  The image quality determination unit 23 acquires the image output from the image processing unit 22, and detects an area of a person existing in the image (hereinafter referred to as “person area”) based on the acquired image (S3). . For example, the image quality determination unit 23 detects a person region by the background difference method. That is, the image quality determination unit 23 holds an image (hereinafter referred to as “background image”) of the monitoring target area A in which a person captured in advance by the image monitoring apparatus 20 does not appear. The image quality determination unit 23 creates a difference image between the image acquired from the image processing unit 22 and the background image, and creates a binary image by binarizing each pixel value of the difference image with a predetermined threshold value. . Thereafter, the image quality determination unit 23 detects a person region by performing a labeling process on the binary image. Thereby, one unique label is attached to one person area. If the size of the region is too small, it may be regarded as noise and not labeled. This can prevent the noise area from being erroneously determined as a person area.

  In addition, the detection of the person area is not limited to the background difference method, but a luminance change area is detected by taking a difference between images of frames that are temporally forward and backward, and a person area is detected from the change area. An inter-frame difference method may be used.

  The image quality determination unit 23 determines the image quality of the image output by the image conversion unit 24 based on the detected size of the person area (S4).

  FIG. 4 is a flowchart showing details of the image quality determination process (S4 in FIG. 3).

  The image quality determination unit 23 determines whether or not there is a person in the image as a result of detecting the person area (S11). For example, the image quality determination unit 23 determines that there is a person in the image if the number of labels is 1 or more, and determines that there is no person in the image if the number of labels is 0.

  If it is determined that there is a person in the image (YES in S11), the image quality determination unit 23 determines whether the size of the person area in the image is small (S12). That is, the image quality determination unit 23 determines that the size of the person area is small when the size of the person area is equal to or smaller than a predetermined size threshold, and the size of the person area when the size of the human area is larger than the predetermined size threshold. Is not small (large). FIG. 5 shows an example of an image with a small person area size, and FIG. 6 shows an example of an image with a large person area size. If two or more persons are shown in the image as shown in FIG. 7, the size of the smallest person area 50 is set as the size of the person area of the image.

  If it is determined that the size of the person area is small (YES in S12), the image quality determination unit 23 determines the image quality to be “high” (S13). The image quality is assumed to be higher in the order of “high”, “medium”, and “low”. That is, for an image having a small person area size as shown in FIG. 5, the image quality is determined to be “high”.

  When it is determined that the size of the person area is large (NO in S12), the image quality determination unit 23 determines the image quality to be “medium” (S14). That is, for an image having a large person area size as shown in FIG. 6, the image quality is determined to be “medium”.

  When it is determined that there is no person in the image (NO in S11), the image quality determination unit 23 determines the image quality to be “low” (S15).

  Referring to FIG. 3 again, the image conversion unit 24 determines BPP (bits per pixel), resolution, and frame rate when outputting an image based on the image quality determined by the image quality determination unit 23 ( S5). FIG. 8 is a diagram illustrating an example of table data defining the relationship between image quality, BPP, resolution, and frame rate.

  BPP indicates the number of bits per pixel. It is a numerical value corresponding to a compression rate when an image is compressed in accordance with a standard such as H.264 / MPEG-4 AVC. The higher the image quality, the larger the BPP value. In the table shown in FIG. 8, when the image quality is “high”, “medium”, and “low”, the BPP is set to 0.194, 0.139, and 0.111, respectively.

  The resolution indicates the number of pixels in the horizontal and vertical directions of the image. The higher the image quality, the higher the resolution. In the table shown in FIG. 8, when the image quality is “high”, “medium”, and “low”, the resolution is set to “1920 × 1080”, “1280 × 720”, and “720 × 480”, respectively. . Here, “x × y” indicates that the number of pixels in the horizontal direction is x and the number of pixels in the vertical direction is y. In order to identify a person's face, the face needs to be projected with a size of at least about 80 × 80 pixels. For this reason, the resolution is such that the person's face in the image after being converted by the image conversion unit 24 is equal to or larger than a predetermined size (here, 80 × 80 pixels) necessary for identifying the person's face. Determined.

  The frame rate indicates the number of frames per second of the image output from the image conversion unit 24. The higher the image quality, the higher the frame rate is set. In the table shown in FIG. 8, when the image quality is “high”, “medium”, and “low”, the frame rates are set to 30, 15, and 5, respectively.

  Note that the bit rate of the image (the number of transmission bits per second) is calculated by the following equation 1.

Bit rate = BPP × number of pixels in the horizontal direction × number of pixels in the vertical direction × fps (Formula 1)
For example, the bit rate when the image quality is “low” is 0.111 × 720 × 480 × 5 = 0.192 (Mbps).

  The image conversion unit 24 converts the image output from the image processing unit 22 according to the determined BPP, resolution, and frame rate (S6). That is, the image conversion unit 24 reduces the image so that the determined resolution is obtained. The resolution of the image output from the image processing unit 22 is 1920 × 1080. For this reason, when the image quality is “high”, the image is not reduced. However, when the image quality is “medium” or “low”, the resolutions of the images are “1280 × 720” and “720 ×”, respectively. The image is reduced to 480 ”. The image may be reduced by thinning out pixels.

  In addition, the image conversion unit 24 thins out images so that the determined frame rate is obtained. Since the frame rate of the image output from the image processing unit 22 is 30 fps, frame decimation is not performed when the image quality is “high”, but every other frame when the image quality is “medium”. By selecting an image, frame decimation is performed and the frame rate is set to 15 fps. When the image quality is “low”, frames are thinned out by selecting an image every 5 frames, and the frame rate is set to 5 fps.

  Further, the image conversion unit 24 compresses the image so that the determined BPP is obtained. For example, when the image quality is “high”, the image is compressed so that the BPP is 0.194.

  The image conversion unit 24 outputs the converted image (S7). The image output by the image conversion unit 24 is acquired by the image acquisition unit 31 and recorded in the recording unit 32.

[1-4. Effects of Embodiment 1]
As described above, according to the first embodiment, the image monitoring apparatus 20 can change the image quality based on the size of the detection target in the image captured by the camera 10 and output the image. In other words, the image monitoring device 20 can output an image with a changed image quality without using a special device such as a card reader as in the prior art. The image output from the image monitoring device 20 can be recorded in the recording device 30. For this reason, the image monitoring apparatus 20 can record an image on the recording apparatus 30 for a long time in any monitoring target area A, without limiting the monitoring target area A.

  Further, the image quality determination unit 23 determines the image quality based on the minimum size of the detection target when a plurality of detection targets appear in the image. For example, when two detection targets of different sizes are included in an image, if the image quality is determined based on the size of the larger detection target, the image quality may be determined low. As a result, a low-quality image is recorded in the recording device 30. In such a case, even if the image recorded in the recording device 30 is played back, the user can confirm in detail the large detection target, but cannot confirm the small detection target in detail. . However, since the image quality is determined based on the minimum size of the detection target in the first embodiment, when the image recorded in the recording device 30 is reproduced, the user confirms all the detection targets in detail. be able to.

  Further, an image with a smaller BPP can be recorded in the recording device 30 as the image quality is lower. Therefore, an image can be recorded in the recording device 30 for a long time.

  Further, an image with a lower resolution can be recorded in the recording device 30 as the image quality is lower. Therefore, an image can be recorded in the recording device 30 for a long time.

  Further, the resolution of the image after the conversion by the image conversion unit 24 is equal to or larger than a predetermined size (80 × 80 pixels in the first embodiment) necessary for the human face to identify the human face. Determined. For this reason, even if the image quality is determined to be low, the face of a person can be identified from the converted image. For this reason, it can be prevented that the image quality becomes too low and the human face cannot be identified.

  Further, the lower the image quality, the lower the frame rate image can be recorded in the recording device 30. Therefore, an image can be recorded in the recording device 30 for a long time.

(Embodiment 2)
In the second embodiment, an image monitoring system that determines image quality based on the density of a monitoring target included in an image obtained by capturing a monitoring target area and records an image of the determined image quality in a recording apparatus will be described. In the following description, detailed description of the same configuration or processing as in the first embodiment will not be repeated.

[2-1. Overall system configuration]
The overall configuration of the image monitoring system according to Embodiment 2 is the same as the overall configuration of the image monitoring system 1 according to Embodiment 1 shown in FIG.

[2-2. Configuration of image monitoring system]
The configuration of the image monitoring system according to the second embodiment is the same as the configuration of the image monitoring system 1 according to the first embodiment shown in FIG. However, the configuration of the image quality determination unit 23 is different from that of the first embodiment.

  The image quality determination unit 23 determines the image quality of the image output from the image monitoring device 20 based on the image output from the image processing unit 22. That is, the image quality determination unit 23 determines the image quality based on the density of the detection target in the image. Specifically, the image quality determination unit 23 determines the image quality higher as the detection target density is higher. Here, the density is the number of people per unit area of the image. For example, when the size of the image is the unit area, the number of persons included in the image is the density. In the following description, the detection target is described as a person.

[2-3. Processing flow of image monitoring device]
Next, image conversion processing by the image monitoring device 20 will be described. The flowchart of the processing executed by the image monitoring apparatus 20 according to the second embodiment is the same as that shown in FIG. However, the image quality determination process (S4 in FIG. 3) is different from the first embodiment.

  FIG. 9 is a flowchart showing details of the image quality determination process (S4 in FIG. 3).

  The image quality determination unit 23 determines whether or not there is a person in the image as a result of detecting the person area (S21).

  When it is determined that there is a person in the image (YES in S21), the image quality determination unit 23 determines whether the density of the person in the image is high (S22). That is, the image quality determination unit 23 determines that the density of the person is high when the density of the person is equal to or higher than the predetermined density threshold, and the density of the person is not high when the density of the person is smaller than the predetermined density threshold ( Low). FIG. 10 is a diagram illustrating an example of an image having a high density of people. When the density of people is high, the people may overlap each other and part of the person's face may be hidden by other people. FIG. 11 is a diagram illustrating an example of an image with a low human density. When the density of persons is low, the possibility that the persons overlap in the image is lower than when the density is high.

  Note that, even if human regions overlap as shown in FIG. 10, individual human regions can be separated and extracted using the similarity of motion vectors.

  When it is determined that the density of the person is high (YES in S22), the image quality determination unit 23 determines the image quality to be “high” (S23). The image quality is assumed to be higher in the order of “high”, “medium”, and “low”. That is, the image quality is determined to be “high” for an image having a high human density as shown in FIG.

  When it is determined that the density of the person is low (NO in S22), the image quality determination unit 23 determines the image quality to be “medium” (S24). That is, the image quality is determined to be “medium” for an image with a low human density as shown in FIG.

  When it is determined that there is no person in the image (NO in S21), the image quality determination unit 23 determines the image quality to be “low” (S25).

[2-4. Effects of Embodiment 2]
The second embodiment has the same effect as the first embodiment.

  In particular, the image quality determination unit 23 determines the image quality high when the density of the detection target is high, and determines the image quality low when the density of the detection target is low. When the density is high, the detection targets may overlap in the image, and some of the detection targets may be hidden by other detection targets. In the second embodiment, an image can be recorded in the recording device 30 while maintaining high image quality in such a case. For this reason, when the image recorded in the recording device 30 is reproduced, the user can see in detail the portion where the detection target overlaps, so that the detection target can be confirmed in detail. On the other hand, when the density of the detection targets is low, the possibility that the detection targets overlap in the image is lower than when the density is high. For this reason, even if the image quality is deteriorated, the detection target can be sufficiently recognized. For example, when the detection target is a person, the face of the person can be determined even if the image quality is lowered. Therefore, when the image recorded in the recording device 30 is reproduced, the image can be recorded in the recording device 30 for a long time while maintaining the image quality that allows the user to confirm the detection target in detail.

(Embodiment 3)
In the third embodiment, an image monitoring system that determines image quality based on both the size and density of a monitoring target included in an image obtained by capturing an image of the monitoring target area, and records an image of the determined image quality in a recording apparatus To do. In the following description, the detailed description of the same configuration or processing as in the first and second embodiments will not be repeated.

[3-1. Overall system configuration]
The overall configuration of the image monitoring system according to Embodiment 3 is the same as the overall configuration of the image monitoring system 1 according to Embodiment 1 shown in FIG.

[3-2. Configuration of image monitoring system]
The configuration of the image monitoring system according to the third embodiment is the same as the configuration of the image monitoring system 1 according to the first embodiment shown in FIG. However, the configurations of the image quality determination unit 23 and the image conversion unit 24 are different from those of the first embodiment.

  The image quality determination unit 23 determines the image quality of the image output from the image monitoring device 20 based on the image output from the image processing unit 22. That is, the image quality determination unit 23 determines the image quality based on the size and density of the detection target in the image. Specifically, the image quality determination unit 23 determines the image quality higher as the size of the detection target is smaller and the density is higher, and determines the image quality lower as the size of the detection target is larger and the density is lower. To do. In the following description, the detection target is described as a person. In the first and second embodiments, the image quality is set to three levels of “high”, “medium”, and “low”, but in the third embodiment, the image quality is set to five levels from level 1 to level 5.

  The image conversion unit 24 converts the image output from the image processing unit 22 so that the image quality determined by the image quality determination unit 23 is obtained, and outputs the converted image. Except for the image quality being in five stages, it is the same as in the first and second embodiments.

[3-3. Processing flow of image monitoring device]
Next, image conversion processing by the image monitoring device 20 will be described. The flowchart of the process executed by the image monitoring apparatus 20 according to the third embodiment is the same as that shown in FIG. However, the image quality determination process (S4 in FIG. 3) and the BPP, resolution and frame rate determination process (S5 in FIG. 3) are different from those in the first embodiment.

  FIG. 12 is a flowchart showing details of the image quality determination process (S4 in FIG. 3).

  The image quality determination unit 23 determines whether or not there is a person in the image as a result of detection of the person area (S31).

  If it is determined that there is a person in the image (YES in S31), the image quality determination unit 23 determines whether the size of the person area in the image is small (S32). That is, the image quality determination unit 23 determines that the size of the person area is small when the size of the person area is equal to or smaller than a predetermined size threshold, and the size of the person area when the size of the human area is larger than the predetermined size threshold. Is not small (large).

  When it is determined that the size of the person area is small (YES in S32), the image quality determination unit 23 determines whether the density of the person in the image is high (S33). That is, the image quality determination unit 23 determines that the density of the person is high when the density of the person is equal to or higher than the predetermined density threshold, and the density of the person is not high when the density of the person is smaller than the predetermined density threshold ( Low).

  When it is determined that the density of the person is high (YES in S33), the image quality determination unit 23 determines the image quality to “level 1” (S34). The image quality is assumed to be high in the order of “level 1”, “level 2”, “level 3”, “level 4”, “level 5” (in order of increasing numerical value indicating the level). In other words, the image quality is determined to be “level 1” for an image having a small person area size and a large person density. Here, the size of the person area indicates the minimum value among the sizes of the plurality of person areas in the image, as in the first embodiment.

  If it is determined that the density of the person is low (NO in S33), the image quality determination unit 23 determines the image quality to “level 3” (S35).

  If it is determined that the size of the person area is large (NO in S32), the image quality determination unit 23 determines whether the density of persons in the image is high (S36).

  When it is determined that the density of the person is high (YES in S36), the image quality determination unit 23 determines the image quality to “level 2” (S37).

  If it is determined that the density of the person is low (NO in S36), the image quality determination unit 23 determines the image quality to be “level 4” (S38).

  When it is determined that there is no person in the image (NO in S31), the image quality determination unit 23 determines the image quality to “level 5” (S39).

  After determining the image quality, the image conversion unit 24 executes BPP, resolution and frame rate determination processing (S5 in FIG. 3). FIG. 13 is a diagram illustrating an example of table data defining the relationship between image quality, BPP, resolution, and frame rate. For example, when the image quality is “level 1”, the BPP, resolution, and frame rate are determined to be “0.194”, “1920 × 1080”, and “30”, respectively.

[3-4. Effects of Embodiment 3]
The third embodiment has the same effect as the first and second embodiments.

  In addition, since the image quality is determined using both the size and density of the detection target, the image quality can be determined at a more detailed level.

(Embodiment 4)
In the first to third embodiments, the image quality is determined from the size or density of the detection target, and the BPP, resolution, and frame rate at the time of image conversion are determined based on the image quality. The fourth embodiment is different from the first to third embodiments in that the frame rate is not determined based on the image quality, but is determined based on the moving speed of the detection target. In the following description, detailed description of the same configuration or processing as in the first to third embodiments will not be repeated.

[4-1. Overall system configuration]
The overall configuration of the image monitoring system according to Embodiment 4 is the same as the overall configuration of the image monitoring system 1 according to Embodiment 1 shown in FIG.

[4-2. Configuration of image monitoring system]
The configuration of the image monitoring system according to the fourth embodiment is the same as the configuration of the image monitoring system 1 according to the first embodiment shown in FIG. However, the configurations of the image quality determination unit 23 and the image conversion unit 24 are different from those of the first embodiment.

  Similar to the first embodiment, the image quality determination unit 23 determines the image quality of the image output from the image monitoring device 20 based on the image output from the image processing unit 22. That is, the image quality determination unit 23 determines the image quality higher as the size of the detection target is smaller. In the following description, the detection target is described as a person.

  In addition, the image quality determination unit 23 detects the moving speed of the person. For example, the image quality determination unit 23 obtains a movement vector by tracking the person area by a method such as template matching, and detects the moving pixel amount of the person area per unit time as the movement speed.

  The image conversion unit 24 determines the BPP and the resolution based on the image quality determined by the image quality determination unit 23. Further, the image conversion unit 24 determines the frame rate based on the moving speed of the person area detected by the image quality determination unit 23. That is, the image conversion unit 24 determines the frame rate to be lower as the moving speed of the person area is lower. The image conversion unit 24 converts the image output from the image processing unit 22 in accordance with the determined BPP, resolution, and frame rate.

[4-3. Processing flow of image monitoring device]
Next, image conversion processing by the image monitoring device 20 will be described. FIG. 14 is a flowchart of processing executed by the image monitoring apparatus 20.

  The processes from the image acquisition process (S41) to the image quality determination process (S44) are the same as the processes from the image acquisition process (S1) to the image quality determination process (S4) shown in FIG.

  The image conversion unit 24 determines the BPP and resolution when outputting the image based on the image quality determined by the image quality determination unit 23 (S45). FIG. 15 is a diagram illustrating an example of table data defining a relationship between image quality, BPP, and resolution. For example, when the image quality is “medium”, the image conversion unit 24 determines the BPP and the resolution as “0.139” and “1280 × 720” by referring to the table data, respectively.

  The image quality determination unit 23 detects the moving speed of the person for each person area from the image output from the image processing unit 22 (S46). When there are a plurality of persons, the maximum value of the movement speed of the person is detected as the movement speed.

  The image conversion unit 24 determines the frame rate of the output image based on the moving speed detected by the image quality determination unit 23 (S47). FIG. 16 is a diagram illustrating an example of table data defining the relationship between the moving speed and the frame rate. The moving speed is divided into three stages of “large”, “medium”, and “small”. The image conversion unit 24 assigns the moving speed to “large”, “medium”, or “small” by performing threshold processing. That is, the image conversion unit 24 uses the first speed threshold and the second speed threshold that is smaller than the first speed threshold, and sets the movement speed to “large” when the movement speed is equal to or higher than the first speed threshold. to decide. If the moving speed is less than the first speed threshold and greater than or equal to the second speed threshold, the moving speed is determined to be “medium”. If the moving speed is less than the second speed threshold, it is determined that the moving speed is “low”. With reference to the table data shown in FIG. 16, the image conversion unit 24 determines the frame rate as 30 fps when the moving speed is “high”, and determines the frame rate when the moving speed is “medium”. Is determined to be 15 fps, and when the moving speed is “low”, the frame rate is determined to be 5 fps.

  The image conversion process (S48) and the image output process (S49) are the same as the image conversion process (S6) and the image output process (S7) shown in FIG.

[4-4. Effects of Embodiment 4]
The fourth embodiment has the same effects as the first to third embodiments.

  In addition, in the fourth embodiment, an image with a lower frame rate can be recorded in the recording device 30 as the moving speed of the detection target decreases. When the moving speed of the detection target is low, the detection target can be tracked because the detection target is included in the images of a plurality of frames even if the frame rate is lowered. On the other hand, when the moving speed of the detection target is high, the frame rate is increased. For this reason, even in this case, the detection target can be tracked.

  Further, when a plurality of detection targets are shown in the image, the frame rate is determined based on the maximum speed of the detection targets. For example, when two detection objects with different moving speeds are included in an image, if the frame rate is determined based on the smaller moving speed, the frame rate is determined to be low. A low image is recorded in the recording device 30. In such a case, when the image recorded in the recording device 30 is reproduced, the user can confirm in detail while tracking a detection target having a low moving speed on the image. On the other hand, a detection target with a high moving speed disappears from the screen immediately, so that the detection target cannot be traced and cannot be confirmed in detail. However, since the frame rate is determined based on the maximum speed of the detection target in the fourth embodiment, when the image recorded in the recording device 30 is reproduced, the user checks while tracking all the detection targets. be able to.

[5. Addendum]
The image monitoring system including the image monitoring apparatus according to the embodiments of the present invention has been described above, but the present invention is not limited to these embodiments.

  For example, in the configuration of the image monitoring device 20 illustrated in FIG. 2, the image processing unit 22 is not an essential component and may not be provided in the image monitoring device 20. Thereby, in the process which the image monitoring apparatus 20 shown in FIG.3 and FIG.14 performs, you may abbreviate | omit pre-processing (S2, S42). If the image processing unit 22 is not provided, the image acquisition unit 21 outputs the image acquired from the camera 10 to the image quality determination unit 23 and the image conversion unit 24. The image quality determination unit 23 and the image conversion unit 24 execute respective processes based on the image output from the image acquisition unit 21.

  In the fourth embodiment, the image quality is determined based on the size of the person area as in the first embodiment. However, the image quality may be determined based on the density of the person as in the second embodiment. Then, as in the third embodiment, the image quality may be determined based on both the size of the person area and the density of the person.

  Further, the image monitoring device 20 may be specifically configured as a computer system including a microprocessor, a ROM (Read Only Memory), a RAM, a hard disk drive, a display unit, a keyboard, a mouse, and the like. A computer program is stored in the RAM or hard disk drive. The image monitoring apparatus 20 achieves its functions by the microprocessor operating according to the computer program. Here, the computer program is configured by combining a plurality of instruction codes indicating instructions for the computer in order to achieve a predetermined function.

  Furthermore, some or all of the constituent elements constituting the image monitoring apparatus 20 may be configured by a single system LSI (Large Scale Integration). The system LSI is an ultra-multifunctional LSI manufactured by integrating a plurality of components on a single chip, and specifically, a computer system including a microprocessor, ROM, RAM, and the like. . A computer program is stored in the RAM. The system LSI achieves its functions by the microprocessor operating according to the computer program.

  Furthermore, some or all of the constituent elements constituting the image monitoring apparatus 20 may be configured as an IC card that can be attached to and detached from the image monitoring apparatus 20 or a single module. The IC card or module is a computer system that includes a microprocessor, ROM, RAM, and the like. The IC card or the module may include the super multifunctional LSI described above. The IC card or the module achieves its function by the microprocessor operating according to the computer program. This IC card or this module may have tamper resistance.

  Further, the present invention may be the method described above. Further, the present invention may be a computer program that realizes these methods by a computer, or may be a digital signal composed of the computer program.

  Furthermore, the present invention provides a non-transitory recording medium that can read the computer program or the digital signal, such as a flexible disk, a hard disk drive, a CD-ROM, an MO, a DVD, a DVD-ROM, a DVD-RAM, and a BD. (Blu-ray (registered trademark) Disc), or recorded in a semiconductor memory or the like. Further, the digital signal may be recorded on these non-temporary recording media.

  In the present invention, the computer program or the digital signal may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, a data broadcast, or the like.

  Furthermore, it is possible to arbitrarily combine at least a part of the embodiment and the modified example.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the meanings described above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

  INDUSTRIAL APPLICABILITY The present invention is useful when used in an image monitoring device that converts video in order to record video captured by a surveillance camera in a recording device for a long time.

DESCRIPTION OF SYMBOLS 1 Image monitoring system 10 Camera 20 Image monitoring apparatus 21, 31 Image acquisition part 22 Image processing part 23 Image quality determination part 24 Image conversion part 30 Recording apparatus 32 Recording part 40 Communication line 50 Person area

Claims (11)

An image acquisition unit for acquiring an image obtained by imaging the monitoring target area;
An image quality determination unit that determines image quality based on at least one of a size of a detection target in the image and a density of the detection target;
An image monitoring apparatus comprising: an image conversion unit that converts the image acquired by the image acquisition unit so as to achieve the image quality determined by the image quality determination unit, and outputs the converted image. The image monitoring apparatus according to claim 1, wherein the image quality determination unit determines the image quality higher as the size of the detection target is smaller. The image monitoring apparatus according to claim 2, wherein when the detection target is included in the image, the image quality determination unit determines the image quality higher as the minimum value of the size of the detection target is smaller. The image monitoring apparatus according to claim 1, wherein the image quality determination unit determines the image quality higher as the density of the detection target is higher. The image conversion unit converts the image acquired by the image acquisition unit such that the lower the image quality determined by the image quality determination unit, the smaller the number of bits per pixel. The image monitoring apparatus according to claim 1. The image conversion unit converts the image acquired by the image acquisition unit such that the lower the image quality determined by the image quality determination unit is, the lower the resolution is. The image monitoring apparatus described. The image monitoring according to claim 6, wherein the resolution is determined such that a face of the person as the detection target in the converted image has a predetermined size or more necessary for identifying the face of the person. apparatus. The said image conversion part converts the said image which the said image acquisition part acquired so that a frame rate becomes lower, so that the said image quality determined by the said image quality determination part is low. The image monitoring apparatus according to 1. The image monitoring according to any one of claims 1 to 8, wherein the image conversion unit converts the image acquired by the image acquisition unit so that a frame rate is lower as a moving speed of the detection target is lower. apparatus. An image acquisition step of acquiring an image obtained by imaging the monitoring target area;
An image quality determining step for determining an image quality based on at least one of a size of a detection target in the image and a density of the detection target;
An image monitoring method comprising: an image conversion step of converting the image acquired in the image acquisition step so as to achieve the image quality determined in the image quality determination step and outputting the converted image. An image acquisition step of acquiring an image obtained by imaging the monitoring target area;
An image quality determining step for determining an image quality based on at least one of a size of a detection target in the image and a density of the detection target;
An image for causing a computer to execute the image conversion step of converting the image acquired in the image acquisition step so as to achieve the image quality determined in the image quality determination step and outputting the image after conversion Monitoring program.