JP2018147353A - Intersection detecting apparatus, measuring vehicle, intersection detecting program, and data management apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To detect automatically a range of an intersection from an image showing a road surface.SOLUTION: A sidetrack detecting unit 110 detects, from a road surface image showing a road surface of a road, a sidetrack drawn on the road surface. A candidate region detecting unit 120 detects, from the road surface image, a candidate region which is a region in which the detected sidetrack is stopped. An intersection region determining unit 130 determines whether or not the detected candidate region is an intersection region including an intersection. If it is determined that the detected candidate region is the intersection region, then an intersection range specifying unit 140 specifies the intersection region in which the intersection is positioned, from the detected candidate region.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for detecting a range of an intersection from an image showing a road surface.

A system for diagnosing road soundness for each route is called a road surface property measurement system.
In the road surface property measurement system, a road surface image showing the road surface is used, and cracks, rutting and flatness of the road are measured.
The road surface property measurement is performed for each road administrator such as a country, a prefecture, or a municipality. That is, national road measurement, prefectural road measurement, and city road measurement are performed by different road authorities.
Therefore, there may be a case where an intersection where a plurality of roads managed by different road authorities intersect is excluded from the measurement target.
In that case, the road administrator identifies the range of the intersection from the road image by visual observation, and much labor and time are spent on the work for identifying the intersection.

  Patent Document 1 discloses a technique for obtaining a distribution of road surface property values from data indicating traveling road surface properties.

JP 2016-217084 A

  It takes a lot of labor and time to specify the range of the intersection from the road image by visual observation.

  It is an object of the present invention to enable automatic detection of an intersection range from an image showing a road surface.

The intersection detection device of the present invention is
A side line detection unit that detects a side line drawn on the road surface from a road surface image showing a road surface;
A candidate area detection unit that detects a candidate area that is an area where the detected side line is interrupted from the road surface image; and
An intersection area determination unit that determines whether the detected candidate area is an intersection area including an intersection;
When it is determined that the detected candidate area is the intersection area, an intersection range specifying unit that specifies an intersection range where the intersection is located from the detected candidate area is provided.

  According to the present invention, an intersection range can be automatically detected from an image showing a road surface.

1 is a configuration diagram of an intersection detection device 100 according to Embodiment 1. FIG. 5 is a flowchart of an intersection detection method in the first embodiment. The flowchart of the side line detection process (S110) in Embodiment 1. FIG. FIG. 4 shows a road surface image 200 in the first embodiment. FIG. 5 shows a histogram 210 in the first embodiment. 6 is a flowchart of candidate area detection processing (S120) in the first embodiment. FIG. 6 shows a candidate area C in the first embodiment. The flowchart of the intersection area | region determination process (S130) in Embodiment 1. FIG. FIG. 6 shows a length L of a candidate area C in the first embodiment. The figure which shows the upstream area Up and the downstream area | region Lo in Embodiment 1. FIG. FIG. 6 is a diagram showing a region F immediately before in the first embodiment. The flowchart of the intersection range specific process (S140) in Embodiment 1. FIG. FIG. 4 is a diagram showing an intersection range 204 in the first embodiment. FIG. 4 is a diagram showing an intersection range 204 in the first embodiment. FIG. 4 is a diagram showing an intersection range 204 in the first embodiment. FIG. 4 is a diagram showing an intersection range 204 in the first embodiment. The flowchart of the intersection range emphasis process (S150) in Embodiment 1. FIG. FIG. 5 is a diagram showing an emphasized intersection range 204 in the first embodiment. The block diagram of the road surface property measuring system 300 in Embodiment 2. FIG. The block diagram of the mapping measurement unit 320 in Embodiment 2. FIG. The block diagram of the road surface property measurement unit 330 in Embodiment 2. FIG. The block diagram of the road surface property measurement unit 330 in Embodiment 2. FIG. The hardware block diagram of the intersection detection apparatus 100 in embodiment.

  In the embodiments and the drawings, the same reference numerals are assigned to the same elements and corresponding elements. Description of elements having the same reference numerals will be omitted or simplified as appropriate. The arrows in the figure mainly indicate the flow of data or the flow of processing.

Embodiment 1 FIG.
An embodiment for automatically detecting the range of an intersection from an image showing a road surface will be described with reference to FIGS.

*** Explanation of configuration ***
Based on FIG. 1, the structure of the intersection detection apparatus 100 is demonstrated.
The intersection detection device 100 is a computer including hardware such as a processor 901, a memory 902, an auxiliary storage device 903, and an input / output interface 904. These hardwares are connected to each other via signal lines.

The processor 901 is an IC (Integrated Circuit) that performs arithmetic processing, and controls other hardware. For example, the processor 901 is a CPU (Central Processing Unit), a DSP (Digital Signal Processor), or a GPU (Graphics Processing Unit).
The memory 902 is a volatile storage device. The memory 902 is also called main memory or main memory. For example, the memory 902 is a RAM (Random Access Memory). Data stored in the memory 902 is stored in the auxiliary storage device 903 as necessary.
The auxiliary storage device 903 is a nonvolatile storage device. For example, the auxiliary storage device 903 is a ROM (Read Only Memory), a HDD (Hard Disk Drive), or a flash memory. Data stored in the auxiliary storage device 903 is loaded into the memory 902 as necessary.

  The input / output interface 904 is a port to which an input device and an output device are connected. For example, the input / output interface 904 is a USB terminal, the input device is a keyboard and a mouse, and the output device is a display. USB is an abbreviation for Universal Serial Bus.

  The intersection detection apparatus 100 includes a side line detection unit 110, a candidate region detection unit 120, an intersection region determination unit 130, an intersection range identification unit 140, and an intersection range enhancement unit 150, which are elements realized by software.

The auxiliary storage device 903 stores an intersection detection program that realizes the side line detection unit 110, the candidate region detection unit 120, the intersection region determination unit 130, the intersection range specifying unit 140, and the intersection range enhancement unit 150. The intersection detection program is loaded into the memory 902 and executed by the processor 901.
Further, the auxiliary storage device 903 stores an OS (Operating System). At least a part of the OS is loaded into the memory 902 and executed by the processor 901.
That is, the processor 901 executes the intersection detection program while executing the OS.
Data obtained by executing the intersection detection program is stored in a storage device such as the memory 902, the auxiliary storage device 903, a register in the processor 901, or a cache memory in the processor 901.

The memory 902 functions as a storage unit 191 that stores data. However, another storage device may function as the storage unit 191 instead of the memory 902 or together with the memory 902.
The input / output interface 904 functions as a display unit 192 that displays an image or the like on a display. The input / output interface 904 functions as a receiving unit that receives input and an output unit that outputs data.

  The intersection detection apparatus 100 may include a plurality of processors that replace the processor 901. The plurality of processors share the role of the processor 901.

  The intersection detection program can be stored in a computer-readable manner in a non-volatile storage medium such as a magnetic disk, an optical disk, or a flash memory. A non-volatile storage medium is a tangible medium that is not temporary.

*** Explanation of operation ***
The operation of the intersection detection device 100 corresponds to an intersection detection method. The procedure of the intersection detection method corresponds to the procedure of the intersection detection program.

Based on FIG. 2, the intersection detection method will be described.
In step S110, the side line detection unit 110 detects a side line from the road surface image.
The road surface image is an image showing the road surface of the road.
A side line is a line drawn on the road surface along the length direction of the road.

In step S120, the candidate area detection unit 120 detects a candidate area from the road surface image.
The candidate area is an area where the detected side line is interrupted.

In step S130, the intersection area determination unit 130 determines whether the candidate area is an intersection area for each detected candidate area.
The intersection area is an area including the intersection.

In step S140, the intersection range specifying unit 140 specifies an intersection range from the candidate areas for each candidate area that is an intersection area.
The intersection range is a range where the intersection is located.

  In step S150, the display unit 192 displays the road surface image in a state where the intersection range is emphasized.

Next, each detail from step S110 to step S150 is demonstrated.
The side line detection process (S110) will be described based on FIG.
In step S111, the side line detection unit 110 detects a white line from the road surface image.
The road surface image is stored in the storage unit 191 in advance.

Details of step S111 will be described below.
As shown in FIG. 4, white lines such as a side line 201, a pedestrian crossing 202, and a stop line 203 are drawn on the road surface reflected in the road surface image 200. Types of the side line 201 include a side line, a center line, and a lane separation line.
The side line detection unit 110 detects white lines such as the side line 201, the pedestrian crossing 202, and the stop line 203 from the road surface image 200.
Specifically, the side line detection unit 110 detects a portion having a luminance higher than the luminance threshold from the road surface image 200 as a white line. That is, the side line detection unit 110 detects a white line from the road surface image 200 by binarizing the road surface image 200 based on the luminance of each pixel of the road surface image 200.

For example, the luminance threshold value may be calculated as follows.
First, the side line detection unit 110 generates a histogram 210 as shown in FIG. 5 based on the luminance of each pixel of the road surface image 200.
Then, the side line detection unit 110 determines the luminance threshold value 211 based on the generated histogram 210. In FIG. 5, the luminance threshold value 211 is the luminance that is the boundary of the upper X percent. X percent is a predetermined ratio.

Returning to FIG. 3, step S112 will be described.
In step S112, the side line detection unit 110 selects a white line drawn along the length direction of the road from the white line detected in step S111. The selected white line is the side line 201.

  A side line is detected by the side line detection process (S110). A side line is a line drawn on the road surface along the length direction of the road. In other words, the side line is a white line drawn parallel to the traveling direction of the road. The traveling direction of the road is the direction in which the vehicle travels on the road.

  In the side line detection process (S110), the side line detection unit 110 may detect a white line and a side line by a conventional technique.

Based on FIG. 6, the candidate area detection process (S120) will be described.
In step S121, the candidate area detection unit 120 refers to the road surface image along the length direction of the road.
Specifically, the candidate area detection unit 120 refers to the road surface image 200 line by line in the direction of the arrow in FIG.

In step S122, the candidate area detection unit 120 determines whether the side line is interrupted.
If the side line is interrupted, the process proceeds to step S123.
When the reference to the road surface image is finished without the side line being interrupted, the candidate area detection process (S120) ends.
For example, in FIG. 7, the side line 201 is interrupted at the line R1. Therefore, the candidate area detection unit 120 determines that the side line 201 is interrupted at the line R1 when referring to the line next to the line R1.

  In step S123, the candidate area detection unit 120 continues referring to the road surface image from the location where the side line is interrupted.

In step S124, the candidate area detection unit 120 determines whether the side line appears again.
If the side line appears again, the process proceeds to step S125.
When the reference to the road image is finished without the side line appearing again, the candidate area detection process (S120) ends.
For example, in FIG. 7, the side line 201 reappears at line R2. Therefore, the candidate area detection unit 120 determines that the side line 201 appears again on the line R2 when referring to the line R2.

In step S125, the candidate area detection unit 120 generates candidate area information and stores the generated candidate area information in the storage unit 191.
The candidate area information is information indicating a candidate area.
The candidate area is an area where the side line is interrupted. Specifically, the candidate area is an area from a location where the side line is interrupted to a location where the side line appears again.
For example, in FIG. 7, the candidate area C is an area from the line R1 to the line R2, and the candidate area information is information indicating the line R1 and the line R2.
After step S125, the process proceeds to step S121, and the candidate area detection unit 120 continues referring to the road surface image from the location where the side line appears again.

  One or more candidate areas are detected by the candidate area detection process (S120), and candidate area information is generated for each candidate area.

Based on FIG. 8, an intersection area | region determination process (S130) is demonstrated.
In step S131, the intersection area determination unit 130 selects one piece of unselected candidate area information.
In the description from step S132 to step S136, the candidate area information means the candidate area information selected in step S131, and the candidate area means the candidate area indicated by the candidate area information selected in step S131.

In step S132, the intersection area determination unit 130 calculates the length of the candidate area based on the candidate area information. The calculated length is the length of the candidate area in the road length direction. For example, in FIG. 9, the length of the candidate area C is the length L from the line R1 to the line R2.
Then, the intersection area determination unit 130 determines whether the length of the candidate area is included in the allowable length range. The allowable length range is a predetermined range. For example, the allowable length range is 8 meters or more and 25 meters or less. 8 meters is a length corresponding to 2 lanes, and 25 meters is a length corresponding to 3 lanes.
If the length of the candidate area is included in the allowable length range, the process proceeds to step S133.
If the length of the candidate area is not included in the allowable length range, the intersection area determination unit 130 determines that the candidate area is not an intersection area. In this case, the process proceeds to step S135, and the candidate area information is deleted in step S135. As a result, an area having no length corresponding to the intersection is excluded from the candidate areas for the intersection. For example, a region where the side line is interrupted because the side line is blurred is excluded from the intersection candidate regions.

In step S133, the intersection area determination unit 130 determines whether there is a pedestrian crossing in the candidate area.
Specifically, the intersection area determination unit 130 performs the determination as follows.
First, the intersection area determination unit 130 extracts an upstream area and a downstream area from candidate areas. The upstream region is a region on the upstream side (entrance side) in the traveling direction of the road, and the downstream region is a region on the downstream side (exit side) in the traveling direction of the road.
Next, the intersection area determination unit 130 determines whether there is a pedestrian crossing in the upstream area. Furthermore, the intersection area determination unit 130 determines whether there is a pedestrian crossing in the downstream area. Specifically, the intersection area determination unit 130 determines whether there is a stripe pattern of white and gray. Crosswalks can be detected by conventional techniques. When there is a pedestrian crossing, the intersection area determination unit 130 adds information indicating a range where the pedestrian crossing is located to the candidate area information.
If there is a pedestrian crossing in at least one of the upstream area and the downstream area, the intersection area determination unit 130 determines that the candidate area has a pedestrian crossing.
When there is no pedestrian crossing in either the upstream region or the downstream region, the intersection region determination unit 130 determines that there is no pedestrian crossing in the candidate region.

For example, in FIG. 10, the upstream region Up is a region from the line R1 to the line R1 ′, and the downstream region Lo is a region from the line R2 ′ to the line R2.
The upstream area Up and the downstream area Lo have an extraction length r1 in the road length direction. The extraction length r <b> 1 is a length corresponding to the width W of the pedestrian crossing 202. The extraction length r1 is determined in advance.
In the upstream region Up, the pedestrian crossing 202 is located in a range from the line V1 to the line V2. In the downstream area Lo, the pedestrian crossing 202 is located in a range from the line V3 to the line V4. Therefore, there is a pedestrian crossing 202 in the candidate area C.

Returning to FIG. 8, the description of step S133 is continued.
When there is a pedestrian crossing in the candidate area, the intersection area determination unit 130 determines that the candidate area is an intersection area. In this case, the process proceeds to step S136.
If there is no pedestrian crossing in the candidate area, the process proceeds to step S134.

In step S134, the intersection area determination unit 130 determines whether there is a stop line in the immediately preceding area corresponding to the candidate area. The immediately preceding area corresponding to the candidate area is an area located immediately before the candidate area.
Specifically, the intersection area determination unit 130 performs the determination as follows.
First, the intersection area determination unit 130 extracts a previous area corresponding to the candidate area from the road surface image 200.
Then, the intersection area determination unit 130 determines whether there is a stop line in the immediately preceding area. Specifically, the intersection area determination unit 130 determines whether there is a white line perpendicular to the side line.

  For example, in FIG. 11, the immediately preceding region F is a region from the line R1 ″ to the line R1, and the immediately preceding region F has an extraction length r2 in the road length direction. A stop line 203 is present in the immediately preceding region F.

Returning to FIG. 8, the description of step S134 is continued.
If there is a stop line in the immediately preceding area corresponding to the candidate area, the intersection area determination unit 130 determines that the candidate area is an intersection area. In this case, the process proceeds to step S136.
If there is no stop line in the immediately preceding area corresponding to the candidate area, the intersection area determination unit 130 determines that the candidate area is not an intersection area. In this case, the process proceeds to step S135.

In step S135, the intersection area determination unit 130 deletes the candidate area information.
As a result, the area that does not correspond to the intersection is excluded from the candidate areas for the intersection.

In step S136, the intersection area determination unit 130 determines whether there is unselected candidate area information.
If there is unselected candidate area information, the process proceeds to S131.
If there is no unselected candidate area information, the intersection area determination process (S130) ends.

  By the intersection area determination process (S130), candidate area information indicating a candidate area that is not an intersection area is deleted, and candidate area information indicating a candidate area that is an intersection area remains.

Based on FIG. 12, the intersection range specifying process (S140) will be described.
In step S141, the intersection range specifying unit 140 selects one piece of unselected candidate area information.
In the description from step S142 to step S147, the candidate area information means the candidate area information selected in step S141, and the candidate area means the candidate area indicated by the candidate area information selected in step S141. The upstream area means an upstream area in the candidate area, and the downstream area means a downstream area in the candidate area.

In step S142, the intersection range specifying unit 140 acquires information indicating the range where the pedestrian crossing is located from the candidate area information. And the intersection range specific | specification part 140 determines whether a pedestrian crossing exists in an upstream area | region or a downstream area | region based on the acquired information.
If the pedestrian crossing is in both the upstream area and the downstream area, the process proceeds to step S143.
If the pedestrian crossing is in the upstream area but not in the downstream area, the process proceeds to step S144.
If the pedestrian crossing is not in the upstream area but is in the downstream area, the process proceeds to step S145.
If there is no pedestrian crossing in either the upstream area or the downstream area, the process proceeds to step S146.

In step S143, the intersection range specifying unit 140 specifies an area from the pedestrian crossing in the upstream area to the pedestrian crossing in the downstream area. The identified area is the intersection range. Specifically, the intersection range is a region from the downstream end of the pedestrian crossing in the upstream region to the upstream end of the pedestrian crossing in the downstream region. The intersection range specifying unit 140 adds information indicating the intersection range to the candidate area.
In FIG. 13, an intersection range 204 is a region from the line V2 to the line V3.

In step S144, the intersection range specifying unit 140 specifies a region from the pedestrian crossing in the upstream region to the downstream end of the candidate region. The identified area is the intersection range. Specifically, the intersection range is a region from the downstream end of the pedestrian crossing in the upstream region to the downstream end of the candidate region. The intersection range specifying unit 140 adds information indicating the intersection range to the candidate area.
In FIG. 14, an intersection range 204 is a region from the line V2 to the line R2.

In step S145, the intersection range specifying unit 140 specifies the region from the upstream end of the candidate region to the pedestrian crossing in the downstream region. The identified area is the intersection range. Specifically, the intersection range is a region from the upstream end of the candidate region to the upstream end of the pedestrian crossing in the downstream region. The intersection range specifying unit 140 adds information indicating the intersection range to the candidate area.
In FIG. 15, an intersection range 204 is a region from the line R1 to the line V3.

In step S146, the intersection range specifying unit 140 specifies the candidate area as an intersection range. The intersection range specifying unit 140 adds information indicating the intersection range to the candidate area.
In FIG. 16, an intersection range 204 is a region from the line R1 to the line R2.

In step S147, the intersection range specifying unit 140 determines whether there is unselected candidate area information.
If there is unselected candidate area information, the process proceeds to step S141.
If there is no unselected candidate area information, the intersection range specifying process (S140) ends.

  By the intersection range specifying process (S140), an intersection range is specified for each candidate region, and information indicating the intersection range is added to the candidate region information for each candidate region.

Based on FIG. 17, the intersection range enhancement process (S150) will be described.
In step S151, the intersection range emphasizing unit 150 selects one piece of unselected candidate area information.
In the description of step S152 and step S153, the candidate area information means the candidate area information selected in step S151, and the candidate area means the candidate area indicated by the candidate area information selected in step S151.

In step S152, the intersection range emphasizing unit 150 acquires information indicating the intersection range from the candidate area information. Then, the intersection range emphasis unit 150 performs enhancement processing on the intersection range indicated by the acquired information.
Emphasis processing is processing that emphasizes the intersection range. For example, the emphasis processing is processing such as shading, edging, and coloring.

In step S153, the intersection range emphasizing unit 150 determines whether there is unselected candidate area information.
If there is unselected candidate area information, the process proceeds to step S151.
If there is no unselected candidate area information, the process proceeds to step S154.

  By the processing from step S151 to step S153, the road surface image is processed into an image in a state where the intersection range is emphasized.

In step S154, the display unit 192 displays a road surface image in a state where the intersection range is emphasized on the display.
For example, the display unit 192 displays a road surface image 200 as shown in FIG. 18 on the display. In FIG. 18, the intersection area 204 is highlighted by shading and fringing.

  By the intersection detection method, the intersection range is detected from the road surface image, and the road surface image is displayed in a state where the intersection range is emphasized.

*** Effects of Embodiment 1 ***
An intersection range can be detected from the road surface image, and the road surface image can be displayed in a state where the intersection range is emphasized.

*** Other configurations ***
When position information such as latitude and longitude is attached to the pixels of the road surface image, the intersection detection device 100 may specify and output the position information of the intersection range.

Embodiment 2. FIG.
A system including the intersection detection device 100 will be described with reference to FIGS.

Based on FIG. 19, the structure of the road surface property measurement system 300 is demonstrated.
The road surface property measurement system 300 includes a measurement vehicle 310, a data management device 340, and an intersection detection device 100.

The measurement vehicle 310 includes a mapping measurement unit 320 and a road surface property measurement unit 330. The mapping measurement unit 320 mounted on the measurement vehicle 310 is called an MMS (Mobile Mapping System).
The mapping measurement unit 320 is a device group for acquiring the MMS measurement data 342. The MMS measurement data 342 is data necessary for creating a road map.
The road surface property measurement unit 330 is a device group for acquiring road surface property measurement data 341. Road surface property measurement data 341 is data necessary for road surface property inspection.
MMS measurement data 342 and road surface property measurement data 341 include measurement times. The measurement time is the time when measurement for obtaining data was performed.

The data management device 340 is a computer that manages road surface property measurement data 341, MMS measurement data 342, and MMS post-processing data 343. The data management device 340 includes hardware such as a processor, a storage device, and an input / output interface. The storage device is a general term for a memory and an auxiliary storage device.
The data management device 340 executes the following data processing by the processor. The processed data is stored in the storage device.
The data management device 340 generates a road surface image by connecting a plurality of line images included in the road surface property measurement data 341. A line image is an image obtained by photographing a road surface with a narrow width.
The data management device 340 performs post-processing on the MMS measurement data 342 to generate MMS post-processing data 343. The MMS measurement data 342 and the MMS post-processing data 343 are collectively referred to as mapping measurement data.
The data management device 340 associates the road surface property measurement data 341, the MMS measurement data 342, and the MMS post-processing data 343 with each other using the respective measurement times.
The data management device 340 outputs road surface property measurement data 341 and MMS post-processing data 343 (or MMS measurement data 342) associated with each other via the input / output interface.

  Road surface property measurement data 341 and MMS post-processing data 343 (or MMS measurement data 342) output from the data management device 340 are input to the intersection detection device 100.

  The intersection detection apparatus 100 executes the intersection detection method according to the first embodiment using the road surface image included in the road surface property measurement data 341.

Based on FIG. 20, the structure of the mapping measurement unit 320 will be described.
The mapping measurement unit 320 includes a receiver 321, a laser scanner 322, a camera 323, and an IMU 324.
The receiver 321 receives a positioning signal transmitted from a positioning satellite. Data obtained by the receiver 321 is referred to as positioning observation data.
The laser scanner 322 irradiates a laser beam around the road and measures a relative distance and a relative direction with respect to a feature around the road. Data obtained by the laser scanner 322 is referred to as feature distance direction data.
The camera 323 takes a picture around the road. An image obtained by the camera 323 is referred to as a captured image.
IMU 324 is an abbreviation for inertial measurement device. The IMU 324 measures the angular velocity and acceleration of the measurement vehicle 310. Data obtained by the IMU 324 is referred to as inertial measurement data.
The MMS measurement data 342 includes positioning observation data, feature distance direction data, captured images, and inertial measurement data.

Based on FIG. 21 and FIG. 22, the structure of the road surface property measurement unit 330 is demonstrated.
The road surface property measuring unit 330 includes a laser scanner 331 (see FIG. 21), a line camera 332 (see FIG. 21), a laser illumination 333 (see FIG. 21), and a displacement meter 334 (see FIG. 22).
The laser scanner 331 irradiates a laser beam toward each point on the road surface and measures a relative distance and a relative direction with respect to each point on the road surface. Data obtained by the laser scanner 331 is referred to as road surface distance direction data.
The line camera 332 captures the road surface one line at a time with a narrow width. An image obtained by the line camera 332 is referred to as a line image. A road surface image is an image obtained by connecting a plurality of line images.
The displacement meter 334 measures the distance from the road surface. Data obtained by the displacement meter 334 is referred to as road surface distance data.

*** Supplement to the embodiment ***
In the embodiment, the function of the intersection detection device 100 may be realized by hardware.
FIG. 23 shows a configuration when the function of the intersection detection device 100 is realized by hardware.
The intersection detection device 100 includes a processing circuit 990. The processing circuit 990 is also called a processing circuit.
The processing circuit 990 is a dedicated electronic circuit that implements the side line detection unit 110, the candidate region detection unit 120, the intersection region determination unit 130, the intersection range identification unit 140, and the intersection range enhancement unit 150.
For example, the processing circuit 990 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, GA, ASIC, FPGA, or a combination thereof. GA is an abbreviation for Gate Array, ASIC is an abbreviation for Application Specific Integrated Circuit, and FPGA is an abbreviation for Field Programmable Gate Array.

  The intersection detection device 100 may include a plurality of processing circuits that replace the processing circuit 990. The plurality of processing circuits share the role of the processing circuit 990.

  The function of the intersection detection device 100 may be realized by a combination of software and hardware. That is, some functions may be realized by software and the remaining functions may be realized by hardware.

  The embodiments are exemplifications of preferred forms and are not intended to limit the technical scope of the present invention. The embodiment may be implemented partially or in combination with other embodiments. The procedure described using the flowchart and the like may be changed as appropriate.

  DESCRIPTION OF SYMBOLS 100 Crossing detection apparatus, 110 Side line detection part, 120 Candidate area detection part, 130 Intersection area determination part, 140 Intersection range specification part, 150 Intersection range emphasis part, 191 Storage part, 192 Display part, 200 Road surface image, 201 Side line, 202 Pedestrian crossing, 203 stop line, 204 intersection range, 210 histogram, 211 brightness threshold, 300 road surface property measurement system, 310 measurement vehicle, 320 mapping measurement unit, 321 receiver, 322 laser scanner, 323 camera, 324 IMU, 330 road surface property Measurement unit, 331 laser scanner, 332 line camera, 333 laser illumination, 334 displacement meter, 340 data management device, 341 road surface property measurement data, 342 MMS measurement data, 343 MMS post-processing data, 901 process 902 memory, 903 auxiliary storage device, 990 processing circuit.

Claims (14)

A side line detection unit that detects a side line drawn on the road surface from a road surface image showing a road surface;
A candidate area detection unit that detects a candidate area that is an area where the detected side line is interrupted from the road surface image; and
An intersection area determination unit that determines whether the detected candidate area is an intersection area including an intersection;
An intersection detection apparatus comprising: an intersection range specifying unit that specifies an intersection range where an intersection is located from the detected candidate area when it is determined that the detected candidate area is the intersection area. The intersection detection device according to claim 1, wherein the side line detection unit detects a white line from the road surface image, and selects a white line drawn along a length direction of the road as the side line from the detected white line. . The intersection detection device according to claim 2, wherein the side line detection unit detects a portion having a luminance higher than a luminance threshold from the road surface image as a white line. The intersection detection device according to claim 3, wherein the side line detection unit generates a histogram based on a luminance of each pixel of the road surface image, and determines the luminance threshold based on the generated histogram. The candidate area detection unit refers to the road surface image along the length direction of the road, and detects, as the candidate area, an area from a location where the side line is interrupted to a location where the side line appears again. The intersection detection apparatus described in 1. The intersection detection device according to claim 1, wherein the intersection area determination unit determines that the candidate area is not the intersection area when the length of the candidate area is not included in the allowable length range. 7. The intersection area determination unit determines whether the candidate area includes a pedestrian crossing, and determines that the candidate area is the intersection area when the candidate area includes a pedestrian crossing. The intersection detection apparatus described in 1. The intersection area determination unit extracts an upstream area that is an upstream area and a downstream area that is a downstream area from the candidate area, and there is a pedestrian crossing in at least one of the upstream area and the downstream area. The intersection detection device according to claim 7, wherein when the pedestrian crossing is present in at least one of the upstream region and the downstream region, it is determined that the candidate region includes a pedestrian crossing. The intersection area determination unit determines whether there is a stop line in the immediately preceding area located immediately before the candidate area. If the candidate area does not include a crosswalk but has a stop line in the immediately preceding area, the candidate area The intersection detection apparatus according to claim 7, wherein the intersection detection area is determined to be the intersection area. The intersection range specifying part is:
When there is a pedestrian crossing in both the upstream region that is the upstream region in the candidate region and the downstream region that is the downstream region in the candidate region, the downstream region from the pedestrian crossing in the upstream region The area up to the pedestrian crossing in is specified as the intersection range,
If there is a pedestrian crossing in the upstream area but there is no pedestrian crossing in the downstream area, the area from the pedestrian crossing in the upstream area to the downstream end of the candidate area is specified as the intersection range,
When there is no pedestrian crossing in the upstream area but there is a pedestrian crossing in the downstream area, the area from the upstream end of the candidate area to the pedestrian crossing in the downstream area is specified as the intersection range,
The intersection detection device according to claim 1, wherein when there is no pedestrian crossing in any of the upstream region and the downstream region, the candidate region is specified as the intersection range. The intersection detection apparatus according to claim 1, further comprising a display unit that displays the road surface image in a state where the intersection range is emphasized.   A measurement vehicle comprising a camera for obtaining a road surface image used in the intersection detection device according to any one of claims 1 to 11. A side line detection unit that detects a side line drawn on the road surface from a road surface image showing a road surface;
A candidate area detection unit that detects a candidate area that is an area where the detected side line is interrupted from the road surface image; and
An intersection area determination unit that determines whether the detected candidate area is an intersection area including an intersection;
An intersection detection program for causing a computer to function as an intersection range identification unit that identifies an intersection range where an intersection is located from a detected candidate area when it is determined that the detected candidate area is the intersection area.   A data management device that associates mapping measurement data obtained by a mobile mapping system and road surface property measurement data including an image showing a road surface with each other using respective measurement times.

Images