JP2018206014A - Traffic information acquisition device, traffic information acquisition system, traffic information acquisition method, and traffic information acquisition program - Google Patents

Abstract

To provide a technology capable of acquiring traffic information for accurately analyzing a factor that causes a traffic event such as a traffic jam or an accident.SOLUTION: A vehicle detection part 21 detects a vehicle 100 which is being traveled along a track. Regarding the vehicle 100 that is detected by the vehicle detection part 21, a vehicle tracking part 22 makes a detection time of the vehicle 100 correspondent to a detection position and generates detection data. An attribute information adding part 23 associates a gradient of a road surface of the track at the detection position of the vehicle 100 with the detection data as one of attribute information.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for acquiring traffic information used for analyzing a cause of a traffic event such as a traffic jam or an accident on a traveling road.

  2. Description of the Related Art Conventionally, there has been a method in which a vehicle travel locus on a travel route of a vehicle such as an expressway or a general road is acquired as traffic information used for analyzing a cause of a traffic event such as a traffic jam or an accident. For example, in Patent Document 1, a plurality of vehicle detectors are arranged in an appropriate interval in the vehicle running direction, and vehicle detection is performed between the vehicle detectors to perform vehicle matching (identification). It is the structure which acquires a locus.

  Moreover, what was described in patent document 2 is a structure which acquires the driving | running | working locus | trajectory of a vehicle by processing the picked-up image (frame image) imaged with each camera and detecting a vehicle using several cameras. . In Patent Document 2, the plurality of cameras are installed such that the imaging area is continuously arranged in the traveling direction of the vehicle.

  Further, Patent Document 3 describes that a camera is attached to an illumination column as a method of installing the camera at a high density in the traveling direction of the vehicle on the traveling path. An illumination pillar is a support | pillar for attaching the illuminating lamp which illuminates a running path from upper direction. For example, on an expressway, the installation interval of the illumination pillars in the traveling direction of the vehicle is several tens of meters.

JP 2000-207675 A JP 2005-353004 A Japanese Patent Laid-Open No. 2004-5206

  However, the gradient of the road surface of the traveling road affects the traveling state of the vehicle on the traveling road. In the configuration described in Patent Documents 1 and 2 described above, linear information such as the gradient of the road surface of the traveling road is not associated with the traveling locus of the vehicle acquired as traffic information. For this reason, in the traffic information acquired with the configuration described in Patent Documents 1 and 2, etc., it is not possible to analyze factors that cause traffic events such as traffic jams and accidents in consideration of the gradient of the road surface of the traveling road. Therefore, in the traffic information acquired with the configuration described in Patent Documents 1 and 2, etc., the cause of traffic events such as traffic jams and accidents cannot be analyzed with high accuracy.

  An object of the present invention is to provide a technology capable of acquiring traffic information capable of accurately analyzing factors that cause traffic events such as traffic jams and accidents.

  In order to achieve the above object, the traffic information acquisition apparatus of the present invention is configured as follows.

  The detection unit detects a vehicle traveling on a road such as an expressway or a general road. The detection unit is configured to process a frame image captured by the camera and detect a vehicle imaged in the frame image. The detection unit may be configured by a vehicle sensor that detects the presence or absence of a vehicle using an ultrasonic sensor, a photoelectric sensor, a loop coil sensor, or the like.

  A tracking part produces | generates the detection data which matched the detection time and detection position of the said vehicle about the vehicle which the detection part detected. The travel locus of the vehicle can be acquired from detection data acquired repeatedly for the vehicle. Then, the attribute information adding unit associates linear information (for example, road surface gradient) of the road surface of the traveling road at the detection position of the vehicle with the detection data as one of the attribute information.

  As a result, it is possible to acquire the travel locus of the vehicle that associates the road surface alignment of the travel path that affects the travel state of the vehicle on the travel path as traffic information. Here, the road surface alignment means, for example, the road surface gradient of the traveling road, the longitudinal gradient of the road surface in the traveling direction of the vehicle, the crossing gradient of the road surface in the width direction of the vehicle on the traveling road, and the like. Furthermore, it may be understood as a meaning including a plane curvature of the traveling road. In other words, the road surface alignment means the information related to the 3D information of the road surface in the three-dimensional map. Therefore, by using this traffic information, it is possible to analyze the factors that cause traffic events such as traffic jams and accidents in consideration of the road surface alignment. That is, it is possible to accurately analyze factors that cause traffic events such as traffic jams and accidents.

  The attribute information adding unit, as linear information of the road surface of the traveling road at the detection position of the vehicle, the gradient of the road surface of the traveling road at the detection position of the vehicle, specifically, the longitudinal gradient of the road surface in the traveling direction of the vehicle on the traveling road It is preferable that the crossing gradient of the road surface in the width direction of the vehicle on the traveling road is associated with the detection data.

  In addition, the attribute information adding unit may associate, as one of the attribute information, the plane curvature of the traveling road, the road surface state, the travel regulation, and the like at the detection position of the vehicle with the detection data. Furthermore, it is also possible to handle the driver's viewing distance and inter-vehicle distance as attribute information. The term “inter-vehicle distance” here is defined as a broad meaning including both the inter-vehicle distance and the vehicle distance in the description of the embodiment. In addition, it is also possible to handle the probe data, which is a vehicle tracking history, as detection data.

  Moreover, you may install a camera in the illumination pillar which attached the illuminating lamp which illuminates a running path.

  Moreover, you may provide the imaging visual field control part which changes the imaging visual field of a camera.

  A plurality of cameras may be arranged in the traveling direction of the vehicle on the traveling path in order to track the vehicle over a wide range. For example, as an example, a detection unit that inputs images from a plurality of cameras and detects a vehicle traveling on the road in each image, and the vehicle ID, detection time, and detection of the vehicle detected by the detection unit A tracking unit that associates a position with each other, identifies detection of the corresponding vehicle, and generates detection data relating to tracking of the vehicle, and attribute information and a tracking unit corresponding to each position on the travel route obtained based on the three-dimensional map data And an attribute information adding unit that associates the detection data generated in step 1 with the detection position of the vehicle in the tracking unit. The attribute information adding unit may be configured as a traffic information acquisition device that associates the road surface alignment of the traveling road at the detection position of the vehicle with detection data as one of the attribute information. Thus, after tracking the vehicle, it is possible to perform detailed analysis on factors that cause traffic events such as traffic jams and accidents in consideration of the road surface alignment.

  The camera may be installed so that the imaging field of view overlaps with the imaging field of another camera.

  According to the present invention, it is possible to acquire traffic information that can accurately analyze factors that cause traffic events such as traffic jams and accidents.

It is the schematic which shows a traffic information acquisition system. It is a figure which shows the example of installation of the camera in a travel path. It is a figure explaining the data structure of 3D map DB. It is a figure explaining the data structure of road regulation information DB. It is a figure which shows an object map. It is a flowchart which shows operation | movement of a traffic information acquisition apparatus.

  Embodiments of the present invention will be described below.

  FIG. 1 is a diagram showing a configuration of a traffic information acquisition system according to this example. The traffic information acquisition system according to this example includes a traffic information acquisition device 1, a camera 2, and an imaging visual field control device 3.

  The traffic information acquisition device 1 acquires traffic information used for analysis of factors that cause traffic events such as traffic jams and accidents on a road (highway, general road, etc.). A traffic information analysis device (not shown) processes the traffic information acquired by the traffic information acquisition device 1 and analyzes factors that cause traffic events. As shown in FIG. 1, a plurality of cameras 2 are connected to the traffic information acquisition apparatus 1.

  As shown in FIG. 2, the cameras 2 are arranged at an appropriate interval (this interval may or may not be constant) in the traveling direction of the vehicle 100 on the traveling path. . The two cameras 2 that are continuous in the traveling direction of the vehicle 100 have overlapping imaging areas as shown in FIG. Here, the section where the imaging areas overlap is referred to as an overlapping section.

  In this example, the camera 2 is attached to the illumination column 2a. The illumination column 2a is a support column to which an illumination lamp that illuminates the traveling path is attached. The illumination pillars 2a are arranged at an appropriate interval (several tens of meters) in the traveling direction of the vehicle 100 on the traveling path. Therefore, the camera 2 can be arranged so that an overlapping section is formed without newly installing a column for attaching the camera 2.

  The camera 2 is attached to the illumination column 2a via a pan head (not shown) that rotates in the pan direction and the tilt direction. The camera 2 also has a zoom control function that changes the imaging magnification in response to an input from an external device. And the power supply cable for lighting an illumination lamp is laid in the illumination pillar 2a. Accordingly, the operation power can be supplied to the camera 2 and the camera platform using the power cable laid on the illumination column 2a.

  For this reason, when constructing the traffic information acquisition system according to this example, it is not necessary to install a support column to which the camera 2 is attached or to lay a power cable for supplying operation power to the camera 2 and the camera platform. That is, it is possible to shorten the time period required for constructing the traffic information acquisition system and reduce the cost required for constructing the traffic information acquisition system.

  The imaging field-of-view control device 3 performs PTZ control for each camera 2 by rotating the pan head on which the camera 2 is attached in the pan direction and the tilt direction and instructing the imaging magnification to the camera 2. . That is, the imaging visual field control device 3 performs control for adjusting the imaging area of each camera 2 for each camera 2. Therefore, when constructing the traffic information acquisition system according to this example, the camera 2 only needs to be attached to the illumination column 2a (the imaging area of the camera 2 does not need to be adjusted). The imaging visual field control device 3 corresponds to the imaging visual field control unit referred to in the present invention.

  Note that the traffic information acquisition system may have a configuration in which the traffic information acquisition device 1 includes the imaging visual field control device 3. In the traffic information acquisition system, one camera installed on the upstream traveling road is installed in a direction perpendicular to the traveling road surface so that the vehicle 100 is imaged from directly above, and image processing technology is used. The vehicle length measuring device that directly measures the vehicle length may be built in the traffic information acquisition system, and either the vehicle detection unit 21 or the vehicle tracking unit 22 has the vehicle length measurement function. Also good. As a method for estimating the vehicle length, correspondence information between the vehicle type and the vehicle length is stored in advance, the vehicle type of the vehicle is determined from an image captured by an arbitrary camera, and the vehicle length of the vehicle is determined by collating with the stored information. It is also possible to have a configuration as desired.

  As shown in FIG. 1, the traffic information acquisition apparatus 1 includes a control unit 11, an image input unit 12, a 3D map database 13 (3D map DB 13), a road regulation information database 14 (road regulation information DB 14), And a weather information acquisition unit 15.

  The control unit 11 controls the operation of each part of the main body of the traffic information acquisition device 1. Further, the control unit 11 includes a vehicle detection unit 21, a vehicle tracking unit 22, and an attribute information addition unit 23. Details of the vehicle detection unit 21, the vehicle tracking unit 22, and the attribute information addition unit 23 will be described later.

  The image input unit 12 can connect a plurality of cameras 2. The image input unit 12 has an interface circuit (not shown) for each camera 2 to be connected. A frame image captured by the connected camera 2 is input to the image input unit 12. The frame rate of the camera 2 is several tens of frames / sec (10 to 30 frames / sec).

  As shown in FIG. 3, the three-dimensional map DB 13 is a database in which records in which position data, travel route ID data, altitude data, gradient data, plane curvature data, and the like are associated are registered. The position data indicates the position, for example, latitude and longitude. The road ID data is a code for identifying the lane. Therefore, for example, in the case of a road with two lanes (traveling lane and overtaking lane), the traveling path ID is different for each lane. The altitude data indicates the altitude (height) of the corresponding position. The gradient data indicates the gradient of the travel path at the corresponding position. The gradient data includes longitudinal gradient data indicating the gradient in the longitudinal direction (the traveling direction of the vehicle 100 in the corresponding lane), and transverse gradient data indicating the gradient in the transverse direction (the width direction of the vehicle 100 in the corresponding lane). The longitudinal gradient is, for example, a positive value when the vehicle front side is higher than the vehicle rear side (when the vehicle 100 is climbing in the traveling direction), and when the vehicle head side is lower than the vehicle rear side (in the vehicle 100 traveling direction). Negative slope). The cross slope is, for example, a positive value when the right side of the vehicle 100 is higher than the left side, and a negative value when the right side of the vehicle 100 is lower than the left side. Moreover, plane curvature data shows the curvature of the lane projected on the horizontal surface. As for the plane curvature, for example, the right curve has a positive value and the left curve has a negative value.

  The 3D map DB 13 is not limited to the data structure shown in FIG. 3, and any data structure can be used as long as it can acquire a travel path ID, elevation, slope, plane curvature, etc. at the position using the position as a key. It may be.

  As shown in FIG. 4, the road regulation information DB 14 is a database in which records in which position data, travel path ID data, speed limit, travel regulation contents, and the like are associated are registered. The position data indicates the position, for example, latitude and longitude. The road ID data is a code for identifying the lane. The speed limit indicates the speed limit of the vehicle 100 at the corresponding position. The travel regulation content indicates traffic regulation (prohibition of overtaking, headband, temporary stop, temporary lane regulation due to construction or accident, etc.) at the corresponding position.

  The road regulation information DB 14 is not limited to the data structure shown in FIG. 4, and any data structure can be used as long as it can acquire the travel route ID, the speed limit, the restriction contents, etc. at the position using the position as a key. There may be.

  Further, the above-described 3D map DB 13 and road regulation information DB 14 may be configured by one database.

  The weather information acquisition part 15 acquires the weather information used for the estimation of the road surface state (for example, dry, semi-humidity, wet) for every area divided beforehand. For example, the meteorological information acquisition unit 15 may be a receiving unit that receives meteorological information distributed by the meteorological observation center, or an input to which an observation signal of a meteorological observation apparatus installed at a meteorological observation point is input. It may be a part or may have both of these functions. Moreover, the structure which acquires the weather information from apparatuses other than the above-mentioned weather observation center and a weather observation apparatus may be sufficient as the weather information acquisition part 15. FIG.

The meteorological information acquired by the meteorological information acquisition unit 15 includes the amount of rainfall, the amount of snowfall, the air volume, and the like. Moreover, it is preferable that the area from which the weather information acquisition unit 15 acquires weather information is a relatively narrow area from the viewpoint of road surface state estimation accuracy. For example, the weather information acquisition unit 15 is 250 m square,
It is preferable to acquire meteorological information for each area divided by a size of 1 km square.

  In addition, from the viewpoint of estimating the road surface condition with higher accuracy, the weather information acquisition unit 15 preferably acquires the weather information of each region at a relatively short time interval. For example, it is preferable that the meteorological information acquisition unit 15 repeatedly acquires the meteorological information for each region every minute for the meteorological information for that minute.

  Next, the vehicle detection part 21, the vehicle tracking part 22, and the attribute information addition part 23 which the control unit 11 has will be described.

  The vehicle detection unit 21 processes the frame image captured by the camera 2 for each camera 2 and detects the vehicle 100 being captured. The vehicle detection unit 21 detects the vehicle 100 captured in the frame image by a known method such as background difference, inter-frame difference, or pattern matching. The vehicle detection unit 21 corresponds to the detection unit referred to in the present invention. As for the vehicle length detection function, the vehicle detection unit 21 may be provided with this function, or a separate function may be added to the control unit, or it may be built in one camera installed on the travel path. Alternatively, it may be provided in an external unit. Regarding vehicle length detection, as described above, one of the cameras installed on the road (vehicle length measurement camera, not shown) is installed in a direction perpendicular to the road surface so that the vehicle 100 is almost An image is taken from directly above, and the vehicle length can be directly measured using an image processing technique. In other words, since the angle of view of the camera is taken in the vertical direction with respect to the road surface, the detected vehicle can be regarded as “crushed from directly above”, and the area occupied by the vehicle having a height of 0 by image processing The vehicle length is measured from the size of the vehicle (length in the running direction). As a specific measurement method by image processing, for example, a rectangle that is inscribed in the detected vehicle is determined, and an angle of view in which the traveling direction is parallel to the long side of the rectangle is selected. Then, by comparing the vertex coordinates of the determined rectangle with the position information assigned to each pixel, the vehicle length can be obtained by calculating the length of the long side of the rectangle. Then, the measured vehicle length information is stored in a storage device (not shown) of the traffic information acquisition device 1.

  The vehicle tracking unit 22 detects, for each vehicle 100 detected by the vehicle detection unit 21, the detection data in which the ID, detection time (frame image capturing time), and detection position (position in real space) of the vehicle 100 are associated. Is generated. For each camera 2, the vehicle tracking unit 22 stores a parameter for converting the position on the frame image captured by the camera 2 into the position on the real space.

  In addition, the vehicle tracking unit 22 includes the vehicle 100 captured in the frame image captured by the upstream camera 2 for the vehicle 100 located in the overlapping region of the two cameras 2 adjacent to each other in the traveling direction of the vehicle 100. The vehicle 100 captured in the frame image captured by the downstream camera 2 is identified. Thereby, even if the vehicle 100 that has processed and tracked the frame image captured by the upstream camera 2 moves outside the imaging area of the upstream camera 2, the vehicle tracking unit 22 has the same vehicle ID. Thus, it is possible to continue the tracking of the vehicle 100 by processing the frame image captured by the downstream camera 2.

  The detection data generated by the vehicle tracking unit 22 indicates the travel locus of each vehicle 100. In other words, the vehicle tracking unit 22 generates data related to the travel locus of the vehicle 100 being tracked. The vehicle tracking unit 22 corresponds to the tracking unit referred to in the present invention. By combining the vehicle tracking information generated for each camera between the cameras, it is possible to track the movement of the vehicle over a wide range, and based on the vehicle position coordinates and vehicle length information specified by the image processing, the surrounding vehicle Distance data can be obtained. Note that the position coordinates of the vehicle can be obtained by image processing in the vehicle detection unit 21 and may be data in which the leading position (vehicle head) in the traveling direction of the vehicle is estimated based on the area occupied by the vehicle in the captured image. However, it may be data that estimates the rear position (vehicle tail) of the vehicle. Furthermore, it may be the intermediate position (center) of the vehicle head and tail estimated based on the image area occupied by the vehicle, and may be specified appropriately. In the embodiment of FIG. 2, since the camera is picked up from behind the vehicle, the position coordinates of the stern are easily obtained.

  The attribute information adding unit 23 has a road surface gradient (longitudinal gradient and crossing gradient) that is linear information of the road surface of the traveling road according to the detection position of the vehicle 100 with respect to the detection data generated by the vehicle tracking unit 22. The plane curvature of the traveling road, the weather condition, the road surface condition, the travel regulation, etc. are added as attribute information. That is, the attribute information adding unit 23 associates (associates) attribute information with the detection data generated by the vehicle tracking unit 22. The detection data associated with the attribute information is registered in the object map shown in FIG. Here, what linked attribute information to detection data is called a detection record.

  FIG. 5 is a diagram showing an object map. As shown in FIG. 5, there are a plurality of vehicles 100 in which detection records are registered in the object map. Each vehicle 100 is registered in a plurality of detection record object maps. Therefore, by extracting the detection records having the same vehicle ID from the object map and arranging the extracted detection records in time series by the detection time, the traveling locus of the vehicle identified by the vehicle ID can be obtained. In addition, altitude data, gradient data, plane curvature data, speed limit, details of regulation, weather, road surface conditions, and the like that are associated with the travel locus are attribute information that affects the travel state of the vehicle 100 on the travel path. Yes. This object map is stored in a storage medium (not shown) such as a hard disk or a memory card.

  As described above, the vehicle tracking unit 22 generates detection data in which the vehicle ID, the detection time, the position, and the travel path ID are associated with each other as illustrated in FIG. For the detection data generated by the vehicle tracking unit 22, the attribute information adding unit 23 shows elevation, gradient (longitudinal gradient, transverse gradient), plane curvature, speed limit, regulation content, weather, road surface condition, etc. Is added as attribute information. That is, the object map shown in FIG. 5 is created by the vehicle tracking unit 22 and the attribute information adding unit 23.

  In addition, the attribute information adding unit 23 can add the driver's viewing distance and the distance (inter-vehicle distance) with other vehicles to the detection data generated by the vehicle tracking unit 22 as attribute information. is there. The driver's visual range can be obtained by substituting into a predetermined arithmetic expression using the road surface gradient (longitudinal gradient and crossing gradient), the plane curvature of the road, etc. according to the detection position of the vehicle 100. It can be obtained by a specific calculation method. The inter-vehicle distance is the distance between the position of one vehicle (own vehicle) tracked by the vehicle tracking unit 22 and the position of another vehicle traveling around the front or rear of the vehicle. The distance information can be obtained by subtracting the vehicle length from the distance.

  The position of the vehicle here is based on the image area occupied by the vehicle in the captured image in the vehicle detection unit 21 by performing image processing on the captured image of the camera 2 captured from the rear side of the vehicle as shown in FIG. Corresponds to the estimated stern position data. If it is a camera that captures images from the front of the vehicle, it is preferable to employ the position data of the vehicle head. The inter-vehicle distance is a distance between the tail of the own vehicle and the head of the following vehicle (another vehicle) when the own vehicle is a front vehicle. On the other hand, it is the distance between the head of the host vehicle and the tail of the preceding vehicle (other vehicle) when the host vehicle is a subsequent vehicle. As described above, the distance between two vehicles (distance between the vehicle heads or distance between the vehicle tails) is obtained by image processing, and information on the inter-vehicle distance is obtained by subtracting the length of the vehicle from the distance. The obtained inter-vehicle distance is converted into data as attribute information. The attribute information added by the attribute information adding unit 23 to the detection data generated by the vehicle tracking unit 22 may not include all the items described above, or include items not illustrated here. It may be. In this invention, when analyzing the cause of traffic events such as traffic jams and accidents, the term “inter-vehicle distance” is defined in a broad sense including the meanings of both inter-vehicle distance and vehicle distance. .

  The control unit 11 executes the traffic information acquisition method according to the present invention. The traffic information acquisition program according to the present invention is executed by the hardware CPU included in the control unit 11.

  The control unit 11 includes a hardware CPU, a memory, and other electronic circuits. The hardware CPU functions as the vehicle detection unit 21, the vehicle tracking unit 22, and the attribute information addition unit 23 described above. Further, the memory has an area for developing the traffic information acquisition program according to the present invention and an area for temporarily storing data generated when the traffic information acquisition program is executed. The control unit 11 may be an LSI in which a hardware CPU, a memory, and the like are integrated.

  Hereinafter, operation | movement of the traffic information acquisition apparatus 1 concerning this example is demonstrated. FIG. 6 is a flowchart showing the operation of the traffic information acquisition apparatus. The traffic information acquisition apparatus 1 performs the process shown in FIG. 6 in parallel for each connected camera 2. Each camera 2 inputs a frame image obtained by imaging an imaging area at a set frame rate to the image input unit 12. The traffic information acquisition apparatus 1 selects a frame image to be processed from the frame images input to the image input unit 12 (s1). The traffic information acquisition device 1 may be configured to sequentially select the frame images input to the image input unit 12 as the frame images to be processed, and the frame images input to the image input unit 12 may be selected at predetermined frame intervals. The frame may be selected as a processing target frame image (for example, at intervals of 2 to 5 frames).

  The traffic information acquisition apparatus 1 performs a vehicle detection process for detecting the captured vehicle 100 on the processing target frame image selected in s1 (s2). The vehicle detection part 21 performs the vehicle detection process concerning s2. The vehicle detection unit 21 may be configured to perform the vehicle detection process related to s2 by any method such as detection of an object based on a known background difference, detection of an object based on an inter-frame difference, and detection of an object based on pattern matching. .

  The traffic information acquisition device 1 generates detection data for each vehicle 100 detected in s2 (s3). The vehicle tracking part 22 performs the process concerning s3. The vehicle tracking unit 22 generates detection data in which the vehicle ID, the detection time, the position, and the travel path ID are associated with each vehicle 100 detected in s2.

  The traffic information acquisition apparatus 1 uses the altitude, the gradient that is linear information of the road surface (longitudinal gradient, crossing gradient), the plane curvature, the speed limit, the restriction content, the weather, and the detection data generated by the vehicle tracking unit 22 in s3. A detection record to which attribute information such as road surface condition, vehicle position, driver's viewing distance, and inter-vehicle distance is added (linked) is generated (s4). The attribute information adding unit 23 performs the process related to s4. The attribute information adding unit 23 registers the detection record data generated in s4 in the object map (s5).

  The traffic information acquisition device 1 registers the detection data generated by the vehicle tracking unit 22 in s3 in the object map, and the attribute information addition unit 23 adds attribute information to the detection data registered in the object map. It may be configured to be registered (added).

  Moreover, the traffic information acquisition apparatus 1 determines the presence or absence of the vehicle 100 located in the overlap area (s6), and if there is a vehicle 100 located in the overlap area, the vehicle 100 located in the overlap area between the cameras 2. An identification process for identifying is performed (s7), and the process returns to s1. In the identification process of the vehicle 100 in s6, ID (vehicle ID) for identifying the vehicle 100 is taken over. That is, the vehicle ID of the vehicle 100 tracked by the vehicle tracking unit 22 is not changed by the camera 2 that captured the vehicle 100.

  If there is no vehicle 100 located in the overlapping area, the traffic information acquisition apparatus 1 returns to s1 without performing the identification process according to s7.

  The traffic information acquisition apparatus 1 registers the detection record of each vehicle 100 that has traveled on the travel path in the object map shown in FIG. 5 by repeating the processes according to s1 to s7 described above.

  For each vehicle 100 tracked by the vehicle tracking unit 22, not only the traveling locus of the vehicle 100 but also the gradient (vertical gradient, transverse gradient) that is linear information of altitude and road surface that affects the traveling state of the vehicle 100 on the traveling path. ), Traffic information in which attribute information such as plane curvature, speed limit, regulation content, weather, road surface condition, vehicle position, driver's viewing distance, and inter-vehicle distance are linked can be acquired from the object map. That is, the traffic information acquisition apparatus 1 can acquire traffic information that can accurately analyze factors that cause traffic events such as traffic jams and accidents. In other words, by using the traffic information acquired by the traffic information acquisition device 1, it is possible to accurately analyze factors that cause traffic events such as traffic jams and accidents.

  In addition, a simulation of the traveling state of the vehicle 100 on the traveling path can be performed with a three-dimensional model based on the traffic information acquired by the traffic information acquisition device 1.

  Moreover, since the camera 2 is configured to be attached to the illumination column 2a as described above, it is not necessary to install a column for attaching the camera 2, and the cost for system construction can be reduced. Moreover, since the imaging visual field control device 3 is configured to adjust the imaging area of the camera 2 attached to the illumination column 2a, it is necessary to adjust the imaging field of the camera 2 when the camera 2 is attached to the illumination column 2a. Absent. For this reason, it is possible to reduce the time required for attaching the camera 2 to the illumination column 2a, and as a result, it is possible to reduce the restriction time for restricting the passage of the vehicle 100 on the travel path.

  In the above example, the traffic information acquisition device 1 is configured to process the frame image captured by each camera 2 and track the vehicle 100. However, the traffic information acquisition device 1 detects and detects the vehicle 100 with a vehicle detector or the like. The structure which tracks the vehicle 100 may be sufficient. In addition, the traffic information acquisition device 1 acquires, as probe data, travel locus data of the own vehicle generated based on the position of the own vehicle detected by the in-vehicle terminal from the in-vehicle terminal mounted on the vehicle, and tracks the vehicle. It may be configured to.

DESCRIPTION OF SYMBOLS 1 ... Traffic information acquisition apparatus 2 ... Camera 2a ... Illumination pillar 3 ... Imaging visual field control apparatus 11 ... Control unit 12 ... Image input part 13 ... 3D map database (3D map DB)
14 ... Road Regulation Information Database (Road Regulation Information DB)
DESCRIPTION OF SYMBOLS 15 ... Weather information acquisition part 21 ... Vehicle detection part 22 ... Vehicle tracking part 23 ... Attribute information addition part 100 ... Vehicle

Claims (16)

A detection unit for detecting a vehicle traveling on the road;
For a vehicle detected by the detection unit, a tracking unit that generates detection data in which a detection time and a detection position of the vehicle are associated with each other;
An attribute information adding unit that associates the attribute information of the travel route with the detection data,
The said attribute information addition part is a traffic information acquisition apparatus linked | related with the said detection data as linear information of the road surface of the said driving | running | working path in the detection position of a vehicle as one of attribute information.   The attribute information adding unit relates to a road surface gradient, which is linear information of a road surface of the traveling road at a detection position of the vehicle, or a longitudinal gradient of the road surface in the traveling direction of the vehicle on the traveling road, or a width direction of the vehicle on the traveling road. The traffic information acquisition apparatus according to claim 1, wherein a road surface crossing gradient is associated with the detection data.   3. The attribute information adding unit according to claim 1, wherein the attribute information adding unit associates, as one of the attribute information, a plane curvature that is linear information of a road surface of the traveling road at a detection position of a vehicle with the detection data. Traffic information acquisition device.   The said attribute information addition part is a traffic information acquisition apparatus in any one of Claims 1-3 which links the road surface state of the said driving | running | working road in the detection position of a vehicle to the said detection data as one of the said attribute information.   The traffic information according to any one of claims 1 to 3, wherein the attribute information adding unit links, as one of the attribute information, a road surface state and weather information of the traveling road at a detection position of a vehicle to the detection data. Acquisition device.   The traffic information acquisition device according to any one of claims 1 to 5, wherein the attribute information adding unit associates, as one of the attribute information, a travel restriction on the travel path at a detection position of a vehicle with the detection data.   The said attribute information addition part is a traffic information acquisition apparatus in any one of Claims 1-6 which links | links the information regarding a distance between vehicles with the said detection data as one of the said attribute information.   The said attribute information addition part is a traffic information acquisition apparatus in any one of Claims 1-7 which links | connects the information regarding a visual distance of a driver with the said detection data as said attribute information. The traffic information acquisition device according to any one of claims 1 to 8,
A camera for imaging the travel path,
The traffic information acquisition device includes:
A captured image input unit to which a frame image obtained by imaging the travel path by the camera is input;
The traffic information acquisition system, wherein the detection unit processes a frame image input to the captured image input unit and detects a vehicle traveling on the traveling road.   The traffic information acquisition system according to claim 9, wherein the camera is installed on an illumination column to which an illumination lamp that illuminates the travel path is attached.   The traffic information acquisition system according to claim 9, further comprising an imaging visual field control unit that changes an imaging visual field of the camera.   The traffic information acquisition system according to any one of claims 9 to 11, wherein a plurality of the cameras are arranged in a traveling direction of the vehicle on the travel path.   The traffic information acquisition system according to claim 12, wherein the camera is installed such that an imaging field of view overlaps an imaging field of view of another camera. A detection step for detecting a vehicle traveling on the road;
For the vehicle detected in the detection step, a tracking step for generating detection data by associating a detection time and a detection position of the vehicle,
An attribute information adding step for associating the attribute information of the travel route with the detection data, and a traffic information acquisition method executed by a computer,
The traffic information acquisition method, wherein the attribute information adding step is a step of associating information relating to the alignment of the road surface of the traveling road at the detection position of the vehicle with the detection data as one of the attribute information. A detection step for detecting a vehicle traveling on the road;
For the vehicle detected in the detection step, a tracking step for generating detection data by associating a detection time and a detection position of the vehicle,
An attribute information adding step for associating the attribute information of the travel route with the detection data, and a traffic information acquisition program for causing a computer to execute the step,
The traffic information acquisition program, wherein the attribute information adding step is a step of associating information related to alignment of the road surface of the traveling road at the detection position of the vehicle with the detection data as one of the attribute information. A detection unit that inputs an image from a plurality of cameras and detects a vehicle traveling on a road in each image;
A tracking unit that associates a vehicle ID, a detection time, and a detection position of the vehicle detected by the detection unit, identifies the corresponding vehicle, and generates detection data related to tracking the vehicle;
Attribute information added to associate attribute information corresponding to each position on the road obtained based on the three-dimensional map data and the detection data generated by the tracking unit based on the vehicle detection position of the tracking unit And comprising
The said attribute information addition part is a traffic information acquisition apparatus linked | related with the said detection data by making the linear of the road surface of the said driving | running | working path in the detection position of a vehicle into one of attribute information.

Images