JP6954749B2 - Adhesion detection device - Google Patents

Description

The present disclosure relates to a technique for detecting foreign matter adhering to the surface of a distance sensor that detects a distance to an object by transmitting a transmitted wave and detecting a reflected wave.

In Patent Document 1 below, as an adhesion detection device for detecting foreign matter adhering to the surface of an ultrasonic distance sensor, a reverberation time indicating the duration of reverberation is observed, and when the reverberation time is longer than a specified value, A technique for determining that there is a foreign substance has been proposed.

JP-A-2002-148347.

The technique of Patent Document 1 has a problem that the reverberation time is unlikely to be longer than the specified value depending on the adhered object, and the adhesion of foreign matter may not be determined normally. In particular, if the foreign matter is snow and covers the ultrasonic distance sensor, the reverberation time is specified even though the transmitted wave and reflected wave are difficult to detect due to the sound absorption by the snow. It cannot be determined that there is a foreign substance before it is longer than the value, and an abnormal state cannot be detected and notified to the user or the like.

In the present disclosure, in an adhesion detection device that detects foreign matter adhering to the surface of a distance sensor that detects the distance to an object by transmitting a transmitted wave and detecting a reflected wave, it is possible to more accurately detect the adhering of foreign matter. Providing technology to do.

The adhesion detection device (10) of the present disclosure includes an image acquisition unit (S130), a surface extraction unit (S140), and an adhesion detection unit (S120, S180).
The image acquisition unit is configured to acquire a captured image including a target surface representing the surface of the distance sensor or the surface of the corresponding object corresponding to the distance sensor. The surface extraction unit is configured to extract the image surface position representing the position of the target surface in the captured image. The adhesion detection unit detects the adhesion of foreign matter to the surface of the distance sensor by comparing the reference position indicating the position of the target surface when the foreign matter is not attached at the position prepared in advance with the image surface position. It is configured as follows.

According to such an adhesion detection device, the surface of the distance sensor is compared with the reference position indicating the position of the object surface when no foreign matter is attached and the image surface position indicating the position of the object surface in the captured image. Since the adhesion of foreign matter to the object is detected, the presence or absence of foreign matter adhesion can be detected more accurately.

In addition, the reference numerals in parentheses described in this column and the scope of claims indicate the correspondence with the specific means described in the embodiment described later as one embodiment, and the technical scope of the present disclosure is defined. It is not limited.

It is a block diagram which shows the structure of the adhesion detection system. It is an image diagram (rear camera) which shows an example of the imaging range of the imaging unit. It is an image diagram (front camera) which shows an example of the imaging range of the imaging unit. It is a flowchart of the foreign matter adhesion detection processing. It is a graph which shows an example of the reverberation waveform before gain increase. It is a graph which shows an example of the reverberation waveform after gain increase.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.
[1. Embodiment]
[1-1. composition]
The adhesion detection system 1 is a system mounted on a vehicle such as a passenger car and detects an object existing around the vehicle such as an obstacle by ultrasonic sensors 41 and 42. In particular, the adhesion detection system 1 of the present embodiment has a function of detecting foreign matter adhering to the surfaces 52 of the ultrasonic sensors 41 and 42.

Here, the foreign matter corresponds to a flying object that may be encountered while the vehicle is running, such as snow, mud, volcanic ash, sand, and water droplets.
The adhesion detection system 1 shown in FIG. 1 includes a control device 10. Further, the adhesion detection system 1 may include an imaging unit 31, a transmitting circuit unit 32, a receiving circuit unit 33, and a plurality of ultrasonic sensors 41 and 42.

The imaging unit 31 is configured as a well-known camera for photographing the surroundings of the vehicle and monitoring the surroundings of the vehicle. In the present embodiment, the imaging unit 31 is also used as a camera for detecting the adhesion of foreign matter. As shown in FIG. 1, the imaging unit 31 is arranged so that the surfaces 52 of the ultrasonic sensors 41 and 42, the corresponding objects corresponding to the distance sensors, and obstacles such as surrounding vehicles are included in the imaging range 51. Will be done.

The corresponding object corresponding to the distance sensor is an object located around the distance sensor such as the ultrasonic sensors 41 and 42, and the state of the surface of this object and the state of the surface of the distance sensor are substantially the same. Represents an object that can be estimated. As shown in FIG. 2, the corresponding object corresponding to the specific distance sensor may include a bumper edge or the like which is an end portion of the bumper.

That is, even if the imaging unit 31 does not directly image the surfaces 52 of the ultrasonic sensors 41 and 42, the surface 52 of the ultrasonic sensors 41 and 42 is arranged at a position substantially close to the surface of the bumper 53. It suffices to image the bumper edge. In this case, assuming that the surface 52 of the ultrasonic sensors 41 and 42 is imaged by the image of the bumper edge, the ultrasonic sensors 41 and 42 are determined by determining the presence or absence of foreign matter adhering to the bumper edge. It is possible to estimate the presence or absence of foreign matter adhering to the surface 52 of the surface 52.

FIG. 2 is an example of a captured image when the imaging unit 31 is arranged as a rear camera. For example, the imaging unit 31 is arranged as a front camera, and as shown in FIG. 3, an image captured by the front camera is used. You may. In the example shown in FIG. 3, the image pickup unit 31 is arranged so that the end portion of the number plate in the vehicle and obstacles such as surrounding vehicles are included in the image pickup range 51. The "end of the number plate" includes a number plate stay which is a member for holding the number plate. In this case as well, as in the case of the bumper edge, even if the imaging unit 31 does not directly image the surface 52 of the ultrasonic sensors 41 and 42, it suffices to image the end portion of the number plate.

The transmission circuit unit 32 is a circuit that generates a power waveform for generating ultrasonic waves from ultrasonic sensors 41 and 42. The transmission circuit unit 32 generates a power waveform in response to a command from the control device 10. The reception circuit unit 33 is a circuit that converts the analog reception signal obtained by the ultrasonic sensors 41 and 42 into a digital value indicating a voltage and outputs the signal.

Ultrasonic sensors 41 and 42 are well-known ultrasonic sensors that detect the distance to an object by transmitting ultrasonic waves that are transmitted waves and detecting reflected waves. The ultrasonic sensors 41 and 42 are embedded in the bumper 53, and ultrasonic waves are transmitted and received on the surface 52 of the ultrasonic sensors 41 and 42.

The ultrasonic sensors 41 and 42 output ultrasonic waves having a predetermined frequency by driving the piezoelectric element with the power waveform generated by the transmission circuit unit 32. Further, the ultrasonic sensors 41 and 42 are configured to be able to receive the reflected wave of the output transmitted wave and the transmitted wave of another ultrasonic sensor, and when these transmitted waves and reflected waves are received, the piezoelectric element vibrates. By being made to output an analog reception signal.

The control device 10 is mainly composed of a well-known microcomputer having a CPU 11 and a semiconductor memory (hereinafter, memory 12) such as a RAM, a ROM, and a flash memory. Various functions of the control device 10 are realized by the CPU 11 executing a program stored in a non-transitional substantive recording medium. In this example, the memory 12 corresponds to a non-transitional substantive recording medium in which a program is stored.

Moreover, when this program is executed, the method corresponding to the program is executed. The non-transitional substantive recording medium means that electromagnetic waves are excluded from the recording medium. Further, the number of microcomputers constituting the control device 10 may be one or a plurality.

As shown in FIG. 1, the control device 10 has an edge detection unit 21, an adhesion determination unit 22, and a plurality of ultrasonic sensor control units 26A and 26B as a configuration of functions realized by the CPU 11 executing a program. A plurality of reflected wave measurement units 27A and 27B, and a plurality of reverberation calculation units 28A and 28B are provided. Ultrasonic sensor control units 26A and 26B, reflected wave measurement units 27A and 27B, and reverberation calculation units 28A and 28B are provided for each ultrasonic sensor 41 and 42.

The method for realizing these elements constituting the control device 10 is not limited to software, and some or all of the elements may be realized by using one or more hardware. For example, when the above function is realized by an electronic circuit which is hardware, the electronic circuit may be realized by a digital circuit including a large number of logic circuits, an analog circuit, or a combination thereof.

In the function as the edge detection unit 21, the captured image obtained from the image pickup unit 31 is image-processed to extract points where the characteristics of adjacent pixels are relatively significantly different as edges.

The function as the adhesion determination unit 22 recognizes a region divided by a large number of continuously arranged edges as an object, recognizes the position and type of the object, and adheres foreign matter to the surfaces 52 of the ultrasonic sensors 41 and 42. To recognize.

In the function as the ultrasonic sensor control units 26A and 26B, a drive signal for driving the ultrasonic sensors 41 and 42 is output to the transmission circuit unit 32, and the timing at which the drive signal is output is determined by the reflected wave measurement unit 27A. , 27B is output.

The function of the reflected wave measuring units 27A and 27B extracts the reflected wave including reverberation from the digital values corresponding to the outputs of the ultrasonic sensors 41 and 42. For example, a digital value obtained by removing a digital value when a drive signal is output from a large number of obtained digital values is extracted as a reflected wave including reverberation.

The functions of the reverberation calculation units 28A and 28B perform processing to remove the reverberation from the reflected wave including the reverberation, and generate the reflected wave not including the reverberation. The reverberation can be defined as, for example, the output within a preset time after the output of the drive signal is finished. In the foreign matter adhesion detection process described later, a process of measuring the time from the end of the output of the drive signal to the actual decrease in the output is also performed.

[1-2. process]
The foreign matter adhesion detection process executed by the control device 10 will be described with reference to the flowchart of FIG. The foreign matter adhesion detection process is, for example, a process that is started when the power of the vehicle is turned on and then repeatedly performed. In the foreign matter adhesion detection process, an example of a procedure for carrying out the functions of the edge detection unit 21, the adhesion determination unit 22, the ultrasonic sensor control units 26A and 26B, the reflected wave measurement unit 27A and 27B, and the reverberation calculation unit 28A and 28B described above. Is shown.

In the foreign matter adhesion detection process, first, in S110, the control device 10 acquires the vehicle speed V, which is the traveling speed of the own vehicle. The vehicle speed V can be obtained from a well-known vehicle speed sensor or the like.
Subsequently, in S120, the control device 10 determines whether or not the vehicle speed V is equal to or higher than a preset threshold value Vth. When the control device 10 determines in S120 that the vehicle speed V is not equal to or higher than the threshold value Vth, the control device 10 returns to S110.

That is, when the vehicle speed V is equal to or higher than the threshold Vth, there is a possibility that the own vehicle is traveling in an area where the color of the road surface is close to white, such as a concrete paved area such as a parking lot or an area where a lot of snow is piled up. It is highly likely that you are driving on an asphalt-paved road with a low road surface and a dark road surface. When driving on an asphalt-paved road, even if the body color of the own vehicle is white, it is easy to detect the contrast difference between the end of the bumper or the end of the number plate and the road surface. Therefore, in the present embodiment, the adhesion of foreign matter is detected when the vehicle speed V is equal to or higher than the threshold value Vth. However, adhesion of foreign matter may be detected when the vehicle speed V is less than the threshold value Vth.

On the other hand, when the control device 10 determines in S120 that the vehicle speed V is equal to or higher than the threshold value Vth, the control device 10 shifts to S130 and acquires an image captured by the imaging unit 31. This captured image includes surfaces 52 of ultrasonic sensors 41 and 42. Further, the captured image includes, for example, an end portion of a bumper or an end portion of a number plate in a vehicle.

Subsequently, in S140, the control device 10 extracts the image surface position from the captured image. The image surface position indicates the position of the surface 52 of the ultrasonic sensors 41 and 42, and in the present embodiment, indicates the position of the end portion of the bumper and the end portion of the number plate in the vehicle.

In this process, for example, the edges in the captured image are extracted, and the set of edges close to the shape of the surface 52 of the ultrasonic sensors 41 and 42 prepared in advance and the set of edges closest to the reference position is the set of the surface 52. Position. Here, the reference position is a continuous arrangement of a set of edges prepared in advance, and represents a position where the set of edges is lined up as a position of the surface 52 when no foreign matter is attached to the surface 52.

Subsequently, in S150, the control device 10 extracts an object / foreign matter from the captured image. In this process, each of the regions partitioned by the edges by connecting the extracted edges is recognized as an object or a foreign substance.

The object represents an object located within the detection range of the ultrasonic sensors 41 and 42. Objects located within the detection range include objects such as other vehicles, buildings, and curbs located around the own vehicle. The position of foreign matter and objects is also recognized.

Subsequently, in S160, the control device 10 specifies the type of foreign matter. Here, in the memory 12, image features representing homogeneity such as shape, color, brightness, unevenness, size, etc. are recorded in advance for each type of foreign matter, and in this process, the memory 12 is referred to. By doing so, the type of the extracted foreign matter is specified. Similarly, the type of the object is specified. In particular, in the present embodiment, it is specified whether or not the foreign matter is snow.

Subsequently, in S170, the control device 10 compares the image surface position with the reference position. That is, the position of the surface 52 obtained from the captured image is compared with the position of the surface 52 when no foreign matter is attached to the surface 52.

Subsequently, in S180, the control device 10 determines whether or not the difference between these positions is equal to or greater than a preset threshold value.
When the control device 10 determines in S180 that the difference between these positions is less than the threshold value, the control device 10 shifts to S210, and the control device 10 sets the sensitivities of the ultrasonic sensors 41 and 42 to normal values, and then shows FIG. Ends the foreign matter adhesion detection process.

On the other hand, when the control device 10 determines in S180 that the difference between these positions is equal to or greater than the threshold value, is it in a state of shifting to S220 and changing the sensitivity of the ultrasonic sensors 41 and 42 to a higher level? Judge whether or not.

When the control device 10 determines in S220 that the sensitivities of the ultrasonic sensors 41 and 42 have been changed to a higher level, the control device 10 shifts to S230 and determines whether the reverberation time is equal to or longer than the preset reference time. Judge whether or not. Here, as shown in FIGS. 5 and 6, the reverberation time is preset to a digital value indicating the output from the ultrasonic sensors 41 and 42 after the transmission of the transmitted wave is stopped from the ultrasonic sensors 41 and 42. Indicates the time required to fall below the threshold value.

Before the gain in the receiving circuit unit 33 is increased, as shown in FIG. 5, the reverberation time depends on whether snow as a foreign substance adheres to the surface 52 of the ultrasonic sensors 41 and 42 and when it does not adhere to the surface 52. No major changes are seen. On the other hand, after the gain in the receiving circuit unit 33 is increased, as shown in FIG. 6, snow as a foreign substance may or may not be attached to the surfaces 52 of the ultrasonic sensors 41 and 42. There is a relatively large change in reverberation time. That is, it can be seen that it becomes easier to detect the adhesion of snow by using the reverberation time.

That is, when the foreign matter is snow and covers the ultrasonic distance sensor, the reverberation time is difficult to detect due to the influence of the transmitted wave and the reflected wave being absorbed by the snow. It cannot be determined that there is a foreign substance without making it longer than the specified value, and it is not possible to detect an abnormal state and notify the user or the like. However, as in the present embodiment, when a foreign substance is detected by an image, if the gain in the receiving circuit unit 33 is increased, it becomes easier to detect the change in the reverberation. It can be easily detected.

Therefore, when the control device 10 determines that the sensitivity of the ultrasonic sensors 41 and 42 is not changed in S220 but is a normal value, the control device 10 shifts to S240 and the sensitivity of the ultrasonic sensors 41 and 42 is changed. To change. In this process, when a foreign substance is detected, the sensitivity of the ultrasonic sensors 41 and 42 is changed to be higher by increasing the gain by the receiving circuit unit 33. The sensitivity may be changed depending on the type of foreign matter and the thickness of the foreign matter. The thickness of the foreign matter can be determined, for example, by the size of the difference between the reference position and the image surface position. When setting different sensitivities depending on the type of foreign matter, prepare a table in advance that associates the type of foreign matter with the changed sensitivity, and set the corresponding sensitivity in the table according to the type of foreign matter. You just have to do it.

When the control device 10 determines in S230 that the reverberation time is equal to or longer than the preset reference time, the control device 10 shifts to S280 and changes the sensitivities of the ultrasonic sensors 41 and 42 according to the type of foreign matter.

On the other hand, when the control device 10 determines in S230 that the reverberation time is not equal to or longer than the preset reference time, the control device 10 ends the foreign matter adhesion detection process of FIG.
Subsequently, in S250, the control device 10 acquires the output from the ultrasonic sensors 41 and 42. At this time, the transmitted wave by another ultrasonic sensor 41, 42 arranged adjacent to a certain ultrasonic sensor 41, 42 is also detected, and the transmitted wave by another ultrasonic sensor 41, 42 is obtained together with the position of the object. Detect whether or not it can be done.

Subsequently, in S260, the control device 10 determines whether or not the image object detected by the image exists and the ultrasonic object detected by the ultrasonic wave exists.
When the control device 10 determines in S260 that the image object exists and the ultrasonic object exists, the control device 10 shifts to S270 and detects the transmitted waves of the adjacent ultrasonic sensors 41 and 42. It is determined whether or not the state has been set.

On the other hand, when the control device 10 determines in S260 that the image object does not exist or the ultrasonic object does not exist, the control device 10 shifts to S280 and the ultrasonic sensors 41 and 42 cannot be used. After outputting to that effect, the foreign matter adhesion detection process of FIG. 4 is terminated.

When the control device 10 determines that the transmitted wave of the adjacent ultrasonic sensors 41 and 42 is not detected in S270, the control device 10 shifts to S280 and outputs that the ultrasonic sensors 41 and 42 cannot be used. After that, the foreign matter adhesion detection process of FIG. 4 is completed.

On the other hand, when the control device 10 determines in S270 that the transmitted waves of the adjacent ultrasonic sensors 41 and 42 are detected, the control device 10 ends the foreign matter adhesion detection process of FIG.
[1-3. effect]
According to the embodiment described in detail above, the following effects are obtained.

(1a) The above-mentioned adhesion detection system 1 is a system configured to detect adhesion of foreign matter to the surface 52 of a distance sensor that detects a distance to an object by transmitting a transmitted wave and detecting a reflected wave. Then, the following processing is performed as a function executed by the control device 10.

That is, the control device 10 is configured to acquire an captured image including the surfaces 52 of the ultrasonic sensors 41 and 42. Further, it is configured to extract the image surface position representing the position of the surface 52 of the ultrasonic sensors 41 and 42 in the captured image. Further, the surface 52 of the ultrasonic sensors 41, 42 is compared with the reference position representing the surface 52 of the ultrasonic sensors 41, 42 when the position is prepared in advance and no foreign matter is attached to the surface 52 of the image. It is configured to detect the adhesion of foreign matter to the surface.

According to such an adhesion detection system 1, a reference position representing the position of the surface 52 of the ultrasonic sensors 41 and 42 when no foreign matter is attached and the position of the surface 52 of the ultrasonic sensors 41 and 42 in the captured image. Since the adhesion of foreign matter to the surface 52 of the ultrasonic sensors 41 and 42 is detected by comparing with the image surface position representing the above, the presence or absence of foreign matter adhesion can be detected more accurately.

(1b) In the above-mentioned adhesion detection system 1, the control device 10 extracts foreign matter in the captured image by image processing the captured image, and refers to the memory 12 in which the type of foreign matter and the image feature are associated in advance. By doing so, the type of foreign matter that matches the image features of the extracted foreign matter is specified.

According to such an adhesion detection system 1, it is possible to specify the type of foreign matter by using the image feature.
(1c) In the above-mentioned adhesion detection system 1, the control device 10 identifies whether or not the extracted foreign matter is snow by referring to a database to which the image features when the foreign matter is snow are associated in advance. do.

According to such an adhesion detection system 1, it is possible to specify whether or not the type of foreign matter is snow.
(1d) In the above-mentioned adhesion detection system 1, the control device 10 acquires an captured image including the end portion of the bumper in the vehicle, and extracts the end portion of the bumper in the captured image as the image surface position. Then, as the reference position, the position of the end of the bumper at the position prepared in advance and when the foreign matter is not attached is used, and the adhesion of the foreign matter is detected by comparing the reference position with the image surface position. ..

According to such an adhesion detection system 1, foreign matter is detected by using the position of the end portion of the bumper, so that an existing imaging device such as a camera for peripheral monitoring, which includes the end portion of the bumper within the imaging range 51, can be used. Adhesion of foreign matter can be detected using the obtained captured image.

(1e) In the above-mentioned adhesion detection system 1, the control device 10 acquires an captured image including the end portion of the number plate in the vehicle, and extracts the end portion of the number plate in the captured image as the image surface position. Then, as the reference position, the position of the end of the number plate at the position prepared in advance and when the foreign matter is not attached is used, and the adhesion of the foreign matter is detected by comparing the reference position with the image surface position. do.

According to such an adhesion detection system 1, foreign matter is detected by using the position of the end portion of the number plate, so that foreign matter can be detected under the same conditions regardless of the color of the vehicle.
(1f) The above-mentioned adhesion detection system 1 is mounted on a vehicle, and the control device 10 acquires the traveling speed of the own vehicle representing the vehicle on which the adhesion detection system 1 is mounted, and the traveling speed of the own vehicle is set in advance. Detects the adhesion of foreign matter when the speed is higher than the set speed.

According to such an adhesion detection system 1, the adhesion of foreign matter is detected when the traveling speed of the own vehicle is equal to or higher than a preset speed and it is relatively easy to obtain a contrast with surrounding objects such as a road surface. , Foreign matter can be detected with high accuracy.

(1g) In the above-mentioned adhesion detection system 1, the control device 10 outputs that the distance sensor cannot be used when a foreign matter is detected.
According to such an adhesion detection system 1, when the distance sensor cannot be used, it is possible to output to that effect.

(1h) In the above-mentioned adhesion detection system 1, the control device 10 changes the sensitivity of the distance sensor to a higher level when a foreign matter is detected.
According to such an adhesion detection system 1, the distance sensor can be used by changing the sensitivity depending on the degree of adhesion of the foreign matter even when the foreign matter adheres.

(1i) In the above-mentioned adhesion detection system 1, the distance sensor is configured as an ultrasonic sensor, and the control device 10 sets the reverberation time of the transmitted ultrasonic wave and the reverberation time of the transmitted ultrasonic wave in advance when the sensitivity of the ultrasonic sensor is changed to be higher. Compare with the set reference time. Then, when the reverberation time is equal to or longer than the reference time, it outputs that the ultrasonic sensor cannot be used.

According to such an adhesion detection system 1, it is possible to determine whether or not an ultrasonic sensor can be used by comparing the reverberation time with a reference time, and if it cannot be used, output that fact. Can be done.

(1j) In the adhesion detection system 1 described above, the control device 10 extracts an object representing an object located within the detection range of the distance sensor by performing image processing on the captured image. Then, when the distance sensor cannot detect the object, it outputs that the distance sensor cannot be used.

According to such an adhesion detection system 1, when the distance sensor cannot detect the object even though the object is present in the captured image, it outputs that the distance sensor cannot be used. Can be done.

(1k) In the above-mentioned adhesion detection system 1, the control device 10 detects a transmitted wave by another distance sensor arranged adjacent to the distance sensor. Then, when the transmitted wave by another distance sensor cannot be detected, it outputs that the distance sensor cannot be used.

According to such an adhesion detection system 1, when the transmitted wave by another distance sensor arranged adjacent to the distance sensor cannot be detected, it is possible to output that the distance sensor cannot be used.

[2. Other embodiments]
Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and can be implemented in various modifications.

(2a) In the above embodiment, the adhesion of foreign matter is detected by comparing the reference position with the image surface position, but the present invention is not limited to this. For example, the adhesion of foreign matter may be detected by changing to this configuration, or by taking into consideration the smoothness of the position of each edge at the image surface position in addition to this configuration. The smoothness of the position of each edge indicates the degree to which each edge is arranged in a curved line or a straight line represented by a predetermined function.

According to such an adhesion detection system, the smoothness of the position of each edge at the image surface position is also taken into consideration, so that foreign matter can be detected more accurately.
(2b) In the above embodiment, the sensitivity of the ultrasonic sensors 41 and 42 is changed to be higher by increasing the gain by the receiving circuit unit 33, but the present invention is not limited to this. For example, the intensity of the transmitted wave may be increased, or the dynamic range of the receiving circuit unit 33 may be changed.

(2c) Ultrasonic sensors 41 and 42 are adopted as distance sensors in the above embodiment, but the present invention is not limited to these. For example, it may be a radio wave type radar sensor or a laser sensor having a configuration for transmitting and receiving electromagnetic waves such as radio waves and light. When the distance sensor is covered with a bumper 53 or the like, the surface 52 of the distance sensor represents the surface of a member through which the transmitted wave or the reflected wave passes. In this case, the surface 52 includes, for example, a housing that covers the ultrasonic sensors 41, 42, a protective member that protects the surface of the ultrasonic sensors 41, 42, a housing member that houses the ultrasonic sensors 41, 42, and the like. Applicable.

(2d) A plurality of functions possessed by one component in the above embodiment may be realized by a plurality of components, or one function possessed by one component may be realized by a plurality of components. .. Further, a plurality of functions possessed by the plurality of components may be realized by one component, or one function realized by the plurality of components may be realized by one component. Further, a part of the configuration of the above embodiment may be omitted. In addition, at least a part of the configuration of the above embodiment may be added or replaced with the configuration of the other above embodiment. It should be noted that all aspects included in the technical idea specified from the wording described in the claims are embodiments of the present disclosure.

(2e) In addition to the above-mentioned adhesion detection system 1, a device such as a control device 10 which is a component of the adhesion detection system 1, a program for operating a computer as the adhesion detection system 1, and a semiconductor memory in which this program is recorded. The present disclosure can also be realized in various forms such as a non-transitional actual recording medium such as, an adhesion detection method, and the like.

[3. Correspondence between the configuration of the embodiment and the configuration of the present disclosure]
Of the processes executed by the control device 10 in the above embodiment, the process of S110 corresponds to the speed acquisition unit referred to in the present disclosure, and the processes of S120 and S180 in the above embodiment correspond to the adhesion detection unit referred to in the present disclosure. Further, in the above embodiment, the processing of S130 corresponds to the image acquisition unit referred to in the present disclosure, and in the above embodiment, the processing of S140 corresponds to the surface extraction unit referred to in the present disclosure.

Further, in the above embodiment, the processing of S150 corresponds to the foreign matter extraction unit and the object extraction unit referred to in the present disclosure, and in the above embodiment, the processing of S160 corresponds to the type identification unit referred to in the present disclosure. Further, in the above embodiment, the processing of S180, S260, S270, and S280 corresponds to the impossible output unit referred to in the present disclosure, and in the above embodiment, the processing of S220 and S230 corresponds to the time comparison unit referred to in the present disclosure.

Further, in the above embodiment, the processing of S240 corresponds to the sensitivity changing unit referred to in the present disclosure, and in the above embodiment, the processing of S250 corresponds to the transmission wave detecting unit referred to in the present disclosure.

1 ... Adhesion detection system, 10 ... Control device, 11 ... CPU, 12 ... Memory, 21 ... Edge detection unit, 22 ... Adhesion determination unit, 26A, 26B ... Ultrasonic sensor control unit, 27A, 27B ... Reflected wave measurement unit, 28A, 28B ... Reverberation calculation unit, 31 ... Imaging unit, 32 ... Transmission circuit unit, 33 ... Reception circuit unit, 41 ... Ultrasonic sensor, 52 ... Surface, 53 ... Bumper.

Claims (12)

An adhesion detection device (10) configured to detect the adhesion of foreign matter to the surface (52) of a distance sensor (41, 42) that detects the distance to an object by transmitting a transmitted wave and detecting a reflected wave. There,
An image acquisition unit (S130) configured to acquire an captured image including a target surface representing the surface of the distance sensor or the surface of a corresponding object corresponding to the distance sensor.
A surface extraction unit (S140) configured to extract an image surface position representing the position of the target surface in the captured image, and a surface extraction unit (S140).
In the captured image, the foreign matter adheres to the surface of the distance sensor by comparing the reference position representing the position of the target surface when the foreign matter does not adhere at the position prepared in advance with the image surface position. Adhesion detection units (S120, S180) configured to detect
A foreign matter extraction unit (S150) configured to extract foreign matter in the captured image by image processing the captured image, and a foreign matter extraction unit (S150).
A type identification unit (S160) configured to identify the type of foreign matter that matches the image feature of the extracted foreign matter by referring to a database in which the type of foreign matter and the image feature are associated in advance.
With
The type identification unit identifies whether or not the extracted foreign matter is snow by referring to a database to which the image features when the foreign matter is snow are associated in advance.
Adhesion detection device configured to. An adhesion detection device (10) configured to detect the adhesion of foreign matter to the surface (52) of a distance sensor (41, 42) that detects the distance to an object by transmitting a transmitted wave and detecting a reflected wave. There,
The adhesion detection device is installed in the vehicle and
An image acquisition unit (S130) configured to acquire an captured image including a target surface representing the surface of the distance sensor or the surface of a corresponding object corresponding to the distance sensor.
A surface extraction unit (S140) configured to extract an image surface position representing the position of the target surface in the captured image, and a surface extraction unit (S140).
In the captured image, the foreign matter adheres to the surface of the distance sensor by comparing the reference position representing the position of the target surface when the foreign matter does not adhere at the position prepared in advance with the image surface position. Adhesion detection units (S120, S180) configured to detect
A speed acquisition unit (S110) that acquires the traveling speed of the own vehicle representing the vehicle equipped with the adhesion detection device, and
Equipped with a,
The image acquisition unit is configured to acquire an captured image including an end portion of a bumper or an end portion of a number plate in a vehicle.
The surface extraction unit is configured to extract the end portion of the bumper or the end portion of the number plate in the captured image as the image surface position.
When the traveling speed of the own vehicle is equal to or higher than a preset speed, the adhesion detection unit is a position prepared in advance as the reference position and is the end portion of the bumper or the end portion of the bumper when no foreign matter is attached. Adhesion of foreign matter is detected by comparing the reference position with the image surface position using the position of the end of the number plate.
Adhesion detection device configured to. An adhesion detection device (10) configured to detect the adhesion of foreign matter to the surface (52) of a distance sensor (41, 42) that detects the distance to an object by transmitting a transmitted wave and detecting a reflected wave. There,
An image acquisition unit (S130) configured to acquire an captured image including a target surface representing the surface of the distance sensor or the surface of a corresponding object corresponding to the distance sensor.
A surface extraction unit (S140) configured to extract an image surface position representing the position of the target surface in the captured image, and a surface extraction unit (S140).
In the captured image, the foreign matter adheres to the surface of the distance sensor by comparing the reference position representing the position of the target surface when the foreign matter does not adhere at the position prepared in advance with the image surface position. Adhesion detection units (S120, S180) configured to detect
Equipped with a,
The adhesion detection unit detects the adhesion of foreign matter by comparing the reference position with the image surface position and also considering the smoothness of the position of each edge at the image surface position.
Adhesion detection device configured to. The adhesion detection device according to claim 2 or 3.
A foreign matter extraction unit (S150) configured to extract foreign matter in the captured image by image processing the captured image, and a foreign matter extraction unit (S150).
A type identification unit (S160) configured to identify the type of foreign matter that matches the image feature of the extracted foreign matter by referring to a database in which the type of foreign matter and the image feature are associated in advance.
Adhesion detection device further equipped with. The adhesion detection device according to claim 4.
The type identification unit is an adhesion detection device configured to identify whether or not the extracted foreign matter is snow by referring to a database to which image features when the foreign matter is snow are associated in advance. .. The adhesion detection device according to claim 1 or 3.
The adhesion detection device is installed in the vehicle and
A speed acquisition unit (S110) that acquires the traveling speed of the own vehicle representing the vehicle equipped with the adhesion detection device, and
With more
The image acquisition unit is configured to acquire an captured image including an end portion of a bumper or an end portion of a number plate in a vehicle.
The surface extraction unit is configured to extract the end portion of the bumper or the end portion of the number plate in the captured image as the image surface position.
When the traveling speed of the own vehicle is equal to or higher than a preset speed, the adhesion detection unit is a position prepared in advance as the reference position and is the end portion of the bumper or the end portion of the bumper when no foreign matter is attached. Adhesion of foreign matter is detected by comparing the reference position with the image surface position using the position of the end of the number plate.
Adhesion detection device configured to. The adhesion detection device according to claim 1 or 2.
The adhesion detection unit is configured to detect the adhesion of foreign matter by comparing the reference position with the image surface position and also considering the smoothness of the position of each edge at the image surface position. .. The adhesion detection device according to any one of claims 1 to 7.
When a foreign matter is detected by the adhesion detection unit, an impossible output unit (S180, S260, S270, S280) configured to output that the distance sensor cannot be used, and
Adhesion detection device further equipped with. The adhesion detection device according to any one of claims 1 to 8.
Sensitivity changing unit (S240) configured to change the sensitivity of the distance sensor to a higher level when a foreign substance is detected by the adhesion detecting unit.
Adhesion detection device further equipped with. The adhesion detection device according to claim 9, which cites claim 8.
The distance sensor is configured as an ultrasonic sensor.
Time comparison units (S220, S230) configured to compare the reverberation time of transmitted ultrasonic waves with a preset reference time when the sensitivity of the ultrasonic sensor is changed to a higher level.
With more
The impossible output unit is an adhesion detection device configured to output that the ultrasonic sensor cannot be used when the reverberation time is equal to or longer than the reference time. The adhesion detection device according to claim 9 or 10, which cites claim 8.
An object extraction unit (S150), which extracts an object representing an object located within the detection range of the distance sensor by image processing the captured image.
With more
The impossible output unit is an adhesion detection device configured to output that the distance sensor cannot be used when the distance sensor cannot detect the object. The adhesion detection device according to any one of claims 9 to 11, which cites claim 8.
Transmission wave detection unit (S250) that detects the transmission wave by another distance sensor arranged adjacent to the distance sensor.
With more
The impossible output unit is an adhesion detection device configured to output that the distance sensor cannot be used when the transmitted wave by the other distance sensor cannot be detected.

Images