JP4334744B2 - Traffic flow measuring device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a traffic flow measuring device, and more particularly, has an image processing means for image processing a road overhead image from a camera installed at a high place on the road, and is provided in the direction of the vehicle traffic line of the lane. The present invention relates to a traffic flow measurement device that measures the traffic flow by grasping the presence of vehicles in an area.
[0002]
[Prior art]
Conventionally, by taking a bird's-eye view of a road that the vehicle travels from a TV camera installed at a high roadside such as a signal lamp post, and processing the captured image, the measurement is provided in the direction of the vehicle traffic line in the lane. Traffic flow measuring devices that measure the presence and number of vehicles in the area have been used.
For example, (1) In the “traffic information processing method” described in Japanese Patent Laid-Open No. 11-219493, a road image (background image) in a situation where no vehicle is present is collected in advance using a monocular camera, The presence of the vehicle was detected by comparing with the captured image.
(2) In the “traffic flow monitoring device” described in Japanese Patent Application Laid-Open No. 10-154292, a feature matching on the front and rear surfaces of a vehicle is registered as a template using a monocular camera, and pattern matching processing is performed while updating the template. To track the vehicle.
Further, (3) In the “traffic volume measuring device and traffic light control device” described in Japanese Patent Application Laid-Open No. 11-175883, a plurality of imaging devices that image the same direction on the road are used, and images from the imaging devices are used. The number of existing vehicles has been measured by stereo image processing for three-dimensional measurement based on signals.
[0003]
[Problems to be solved by the invention]
However, in such a conventional traffic flow measuring device, in the case of (1), it is premised that an accurate background image is collected. However, a stable background is obtained on a road where vehicles frequently travel. It is difficult to collect images, and since image processing is performed using images captured by a monocular camera, it is easily affected by the shadows of buildings and roadside trees reflected on the road, and the vehicle cannot be detected accurately. There was a problem.
Also in the case of (2) above, since a monocular camera is used, there is no means for removing the shadow in the vehicle feature quantity registered in the template. There was a problem that the vehicle could not be detected.
Furthermore, in the case of (3) above, since stereo image processing is performed using a plurality of imaging devices, it is possible to cope with the influence of shadows and overlapping of vehicles, and the presence of the vehicle can be accurately detected. Since a plurality of imaging devices are installed or three-dimensional measurement is performed based on the obtained image signal, there is a problem that the cost is increased.
The present invention has been made in view of the above problems, and can accurately detect the presence of a vehicle without being affected by the shadows of buildings and roadside trees reflected on the road and the shadows of moving vehicles, and at a low cost. It aims at providing the traffic flow measuring device which can be realized.
[0004]
[Means for Solving the Problems]
The invention according to claim 1 includes image processing means for performing image processing on a road overhead image from a camera installed at a high place on the road, and the presence of a vehicle in a measurement region provided in the direction of the vehicle traffic line of the lane In the traffic flow measuring apparatus that grasps the situation and measures the traffic flow, the image processing means extracts a forward direction time for extracting only a portion that has changed from dark to light between two continuous road overhead images at predetermined time intervals. A vehicle extraction unit that expands the difference image and the reverse time difference image that extracts only the portion that has changed from light to dark, and extracts the front portion of the moving vehicle based on the image of the portion where the two expansion images overlap It is characterized by having at least.
According to this, the image processing means performs image processing on a road overhead image from a camera at a high place on the road. The image processing means includes at least a vehicle extraction unit, and extracts a forward time difference image that extracts only a portion that changes from dark to bright between two road overhead images that are continuous at predetermined time intervals, and from light to dark. Each of the reverse time difference images that extract only the changed portion is expanded, and the front portion of the moving vehicle is extracted based on the image of the portion where the two expanded images overlap. For this reason, not only the shadows of fixed objects such as buildings and roadside trees reflected on the road can be removed, but also the shadows of mobile vehicles and areas with a uniform density, such as ordinary vehicles, can be removed. By extracting the front part of the vehicle and accurately grasping the presence of the vehicle in the measurement area and measuring the traffic flow, it is possible to reduce the cost because it can be implemented with a monocular camera.
According to a second aspect of the present invention, in the traffic flow measuring device according to the first aspect, the vehicle extraction unit further extracts an image of a portion where the two expansion images overlap as a plurality of images that are continuous at a predetermined interval. The front portion of the moving vehicle is extracted based on the result of logical product of the plurality of images.
According to this, the vehicle extraction unit included in the image processing means further takes out the image of the portion where the two dilated images overlap as a plurality of images that are continuous at a predetermined interval, and takes the logical product of these images. The front part of the moving vehicle is extracted based on the result. For this reason, even if a shadow is divided | segmented by the trailer type truck with a clearance gap between a driver's seat and a loading platform part, for example, the shadow of a boundary part is removable.
[0005]
According to a third aspect of the present invention, in the traffic flow measuring device according to the first aspect, the vehicle extraction unit is based on an image corresponding to a pair of headlamps or a width lamp when performing nighttime image processing. And extracting the front part of the moving vehicle.
According to this, when performing nighttime image processing, the vehicle extraction unit included in the image processing means extracts the front portion of the moving vehicle based on an image corresponding to a pair of headlamps or vehicle width lights. For this reason, during nighttime image processing, each moving vehicle is accurately extracted by recognizing the headlamps and width lights of moving vehicles that are lit at night, and the presence of vehicles in the measurement area is ascertained. And traffic flow can be measured accurately.
According to a fourth aspect of the present invention, in the traffic flow measuring device according to any one of the first to third aspects, the vehicle information extracted from the measurement area of the road overhead image is stored and managed for each vehicle. And the image processing means registers the vehicle information in the vehicle management table each time the vehicle extraction unit extracts a new front surface of the moving vehicle within the measurement area, and moves the vehicle management table. The vehicle coordinates are updated while tracking the front part of the vehicle, and when the front part of the moving vehicle disappears in the middle of the measurement area, it is determined that the vehicle is stopped, and the vehicle coordinates at that time are stored. The vehicle tracking unit is further provided with a vehicle tracking unit that restarts tracking of the front portion of the moving vehicle and updates the vehicle coordinates.
According to this, it has the vehicle management table which memorize | stores and manages for every vehicle the vehicle information extracted from the measurement area | region of a road overhead image. The vehicle tracking unit of the image processing means registers vehicle information in the vehicle management table every time the vehicle extraction unit extracts a new front part of the moving vehicle in the measurement area, while tracking the front part of the moving vehicle. The vehicle coordinates are updated, and if the front part of the moving vehicle disappears in the middle of the measurement area, it is determined that the vehicle is stopped, and the vehicle coordinates at that time are saved.When the movement of the stopped vehicle is resumed, the front part of the moving vehicle is tracked from the saved vehicle coordinates. Restart and update vehicle coordinates. For this reason, it is possible to accurately track each moving vehicle in the measurement region while extracting the moving vehicle described above.
[0006]
According to a fifth aspect of the present invention, in the traffic flow measurement device according to the fourth aspect, the image processing means provides an exit area in the vicinity of the vehicle exit of the measurement area, and the front surface of the moving vehicle is moved by the vehicle tracking section. If it disappears after entering the exit area, a correlation calculation is performed between the background image of the exit area immediately before the front part of the moving vehicle enters the exit area and the image of the current exit area, and the calculation result is a predetermined threshold. If the value exceeds the value, the vehicle information is deleted from the vehicle management table on the assumption that the vehicle has passed, and if the calculation result is equal to or less than a predetermined threshold value, the vehicle information is determined to be left as a part of the vehicle body. It further has a vehicle passage determination unit stored in the management table.
According to this, the image processing means further includes a vehicle passage determination unit. This vehicle passage determination unit provides an exit region near the vehicle exit in the measurement region, and when the front side of the moving vehicle disappears after entering the exit region by the vehicle tracking unit, the vehicle front determination unit immediately before entering the exit region. Perform a correlation calculation between the background image of the exit area and the image of the current exit area, and if the calculation result exceeds a predetermined threshold, delete the vehicle information from the vehicle management table as the vehicle has passed, If the calculation result is less than or equal to a predetermined threshold value, the vehicle information is stored in the vehicle management table assuming that a part of the vehicle body remains. For this reason, the information on the moving vehicles existing in the measurement area is accurately registered and stored in the vehicle management table, and when it passes, it is deleted. Can be grasped accurately.
According to a sixth aspect of the present invention, in the traffic flow measuring device according to the fourth aspect, the image processing means provides an exit area in the vicinity of the vehicle exit of the measurement area. When a vehicle at the time is extracted and the front part of the moving vehicle disappears after entering the exit area by the vehicle tracking unit, the exit area is binarized by brightness, and the ratio of the area with high brightness in the exit area is predetermined. If the vehicle information is below the threshold value, the vehicle information is deleted from the vehicle management table as having passed, and if the vehicle exceeds a predetermined threshold value, the vehicle information is determined to be part of the vehicle body remaining. It further has a vehicle passage judging part stored in a table.
According to this, for vehicle extraction and vehicle tracking at night, headlamps and width lights of moving vehicles are used. When the vehicle width light passes, it disappears from the screen, so it cannot be determined whether or not a part of the vehicle body still remains in the exit area based on the presence of the headlight or the vehicle width light. For this reason, whether or not a part of the vehicle body remains in the exit area at night is determined by the presence or absence of side reflections from the speed light, side light, or headlights in other lanes attached to the vehicle. It is assumed that a part of the vehicle body remains in the exit area when the area occupied by the high brightness area is large.
[0007]
The invention according to claim 7 is the traffic flow measuring device according to any one of claims 4 to 6, wherein the presence of the vehicle in the measurement area based on the vehicle information stored in the vehicle management table, It further comprises a measurement result output unit that obtains at least one measurement result of the number of vehicles present or the number of passing vehicles and outputs the result to the outside.
According to this, the measurement result output unit refers to the vehicle information stored in the vehicle management table, and obtains at least one measurement result of the presence, number of vehicles, or number of passing vehicles in the measurement area. Since it is output to the outside, the above traffic flow measurement result can be used for traffic signal control, for example, or provided to the vehicle-mounted device or the like via an optical beacon.
The invention according to claim 8 is the traffic flow measuring device according to any one of claims 1 to 7, wherein the road overhead image from the camera installed at a high place on the road is an overhead view of the front portion of the moving vehicle. Instead of the image, image processing is performed using an overhead image of the rear surface of the moving vehicle.
According to this, the road overhead image from the camera installed on the highway on the road may be not only an image of bird's-eye view of the front portion of the moving vehicle but also an image of bird's-eye view of the rear surface portion of the moving vehicle. The traffic flow can be accurately measured by performing the same image processing as described above.
The invention according to claim 9 is the traffic flow measuring device according to any one of claims 1 to 7, wherein the road overhead image from the camera installed at a high place on the road is an overhead view of the front portion of the moving vehicle. The opposite simultaneous measurement is made possible by performing image processing with the lane to be viewed and the lane overlooking the rear surface of the moving vehicle within the field of view of the same image.
According to this, the road overhead image from the camera installed on the road high place is an image in which the lane overlooking the front part of the moving vehicle and the lane overlooking the rear part of the moving vehicle are placed in the same image field of view. Processing may be performed, and the opposite simultaneous measurement of traffic flow is possible.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.
FIG. 1 is a block diagram showing a schematic configuration of a traffic flow measuring apparatus 10 according to the present embodiment. 1 includes a camera 12, an image input unit 14, an image storage unit 16, an image processing unit 18, a vehicle management table 20, a measurement result output unit 22, and the like.
The above-described image processing unit 18 is further configured by a vehicle extraction unit 24, a vehicle tracking unit 26, a vehicle passage determination unit 28, and the like.
Here, the camera 12 is a monocular TV camera using a solid-state imaging device (CCD) on the imaging surface, and is disposed at a high position on the roadside such as a lamp post, and has an angle as shown in FIG. 2 or FIG. This is a bird's-eye view of the vehicle traffic path.
The image input unit 14 includes an A / D conversion unit that converts analog image data input from the camera 12 into digital image data.
The image storage unit 16 temporarily stores the image data captured by the camera 12 and converted into digital data, and the image processing in each unit of the image processing unit 18 to be described later and the operation of storing the result are repeated. .
The image processing unit 18 performs image processing using the digital image data stored in the image storage unit 16, so that the presence measurement region (a) 36 set in the captured image as shown in FIGS. The presence state of the moving vehicle in the exit area (b) 38 is grasped. The four lines 30, 32, 34, 35 extending radially in FIGS. 2 and 4 are lines indicating three lanes on one side, and there is an oncoming lane 40 (not shown) on the left side. Specifically, image processing is performed in each of the following units.
The vehicle extraction unit 24 captures captured image data as shown in FIG. 4 at a predetermined time interval, and extracts only a time difference image in the forward direction that extracts only a portion that has changed from dark to bright between two consecutive images (see FIG. 5). ) And a reverse time difference image (see FIG. 6) for extracting only the portion that has changed from light to dark. At this point, the shadow 48 of a fixed building such as a building is removed. Then, when the forward time difference image and the backward time difference image are expanded and added, and binarized with a predetermined threshold value, the horizontal stripe pattern is dense as shown in FIG. A region (for example, a front and rear surface portion of a vehicle having a grill or a bumper) can be extracted, and a region having a uniform density, such as the shadow 44 of the moving vehicle 42, can be removed.
[0009]
In addition, in the case of a trailer type truck having a gap between the cab and the loading platform as shown in FIG. 8A, the vehicle extraction unit 24 can remove the shadow at the boundary when the shadow is divided. It may disappear. In this case, with respect to the processing result as shown in FIG. 7, a plurality of images (FIG. 8 (b) current image result, (c) previous image result, (d) previous image result)) are displayed as images. By sequentially storing them in the storage unit 16 and taking the logical product of these images, it becomes possible to remove shadows and noises at the boundary portions.
Furthermore, in the vehicle extraction unit 24, when extracting a vehicle at night, only a pair of headlamps or a vehicle width lamp (such as a twilight) is reflected in the camera. And the vehicle width lamp is the front part of the moving vehicle (may be the rear part). In addition, since there is no problem of shadows at night, the front part of the moving vehicle can be extracted only by the headlights and the vehicle width lights even in a trailer type truck.
Next, the vehicle tracking unit 26 tracks the front portion of the moving vehicle in the presence measurement area 36 set in the lanes 30, 32, 34, and 35. For example, each time the moving vehicle front portion is extracted in the presence measurement region 36 by the vehicle extraction unit 24, the extracted vehicle information is newly registered in the vehicle management table 20 (see FIG. 3). At that time, the new registration flag in FIG. 3 is set to ON, the movement flag is set to ON, and the current coordinate is registered.
Further, the vehicle tracking unit 26 tracks the front part of the moving vehicle using the vehicle extraction unit 24, and updates the vehicle management table of the vehicle. At that time, the new registration flag in FIG. 3 is turned OFF, the movement flag is turned ON, the previously registered coordinates are moved to the previous coordinates, and the current coordinates are updated.
When the moving vehicle stops in the presence measurement area 36 due to a signal wait or the like, the front portion of the moving vehicle disappears. Therefore, the vehicle tracking unit 26 determines that this is stopped and updates the vehicle management table 20 of the vehicle. To do. At that time, the new registration flag in FIG. 3 is OFF, the movement flag is OFF, and the current coordinates immediately before the stop are stored as they are.
Further, when the stopped vehicle moves again, the vehicle management table 20 of the vehicle is updated. At that time, the new registration flag in FIG. 3 is turned OFF, the movement flag is turned ON, the stored coordinates are moved to the previous coordinates, and the current coordinates are updated.
Such tracking of the vehicle is performed for each moving vehicle (vehicle 1, vehicle 2,...) In the presence measurement region 36.
[0010]
Next, in the vehicle passage determination unit 28, in the daytime, when the front part of the moving vehicle disappears after entering the exit area 38, the whole vehicle has passed or a part of the vehicle body still remains It is not clear. Therefore, in the angle of FIG. 4, the background image of the exit area stored immediately before the vehicle enters the exit area 38 and the current image are obtained using the fact that the inter-vehicle resolution near the exit area 38 is high and the background image is easily available. The correlation calculation with the image of the exit area 38 is performed. As a result, if it exceeds a predetermined threshold value, it means that the correlation is high. Therefore, it is determined that the vehicle has passed, and the vehicle information is deleted from the vehicle management table 20. If the calculation result is equal to or less than the predetermined threshold value, it means that the correlation is low. Therefore, it is determined that a part of the vehicle body remains, and the vehicle management table 20 of the vehicle is stored. The background image is (1) when the front part of the moving vehicle comes immediately before, (2) when there is no vehicle body left in front of it, and (3) the correlation calculation result with the previous background image is predetermined. The update is performed only when the three requirements are satisfied when the threshold value is exceeded.
In addition, in the vehicle passage determination unit 28, when the front part of the moving vehicle disappears after entering the exit area at night, it is clear whether the entire vehicle has passed as in the daytime or a part of the vehicle body remains. is not. Therefore, in the present embodiment, binarization based on the brightness of the exit area 38 is performed, and if the area with high brightness is below a predetermined threshold value other than the coordinate area indicated by the vehicle management table, the speed lamp, side face It is determined that the vehicle has passed without any side reflection or the like due to the lamp or the vehicle headlamp in another lane, and the vehicle information is deleted from the vehicle management table 20. When the high brightness area exceeds a predetermined threshold, there is either a speed light, a side light, or a side reflection by a vehicle headlamp in another lane. Determination is made and the vehicle management table 20 of the vehicle is stored.
[0011]
Next, the operation of the present embodiment will be described.
FIG. 9 is a flowchart for explaining the processing operation of the traffic flow measuring apparatus according to the present embodiment. The traffic flow measuring apparatus according to the present embodiment measures the traffic flow of a moving vehicle in the presence measurement area 36 shown in FIG. 4 based on image data obtained by capturing a three-lane vehicle road with a monocular camera. It performs signal control and provides traffic information to the vehicle-mounted device or the like via an optical beacon.
First, an input image from the camera 12 is processed as a current image (step S100).
Subsequently, in step S102, a set of positive values is obtained. That is, here, the vehicle extraction unit 24 captures captured image data at a predetermined time interval, extracts a forward direction time difference image as shown in FIG. 5 in which a portion that has changed from dark to bright between two consecutive images is extracted, Further, this is expanded.
In step S104, a set of negative values is obtained. That is, here, the captured image data is captured at predetermined time intervals by the vehicle extraction unit 24, and a reverse time difference image as shown in FIG. 6 in which a portion that has changed from light to dark between two consecutive images is extracted, Further, this is expanded.
Then, after adding the above-described forward / reverse time difference dilated images, binarization processing is performed (step S106). Although different from the operation of the present embodiment, the same result can be obtained by taking the logical product of the two images after binarizing the forward / reverse time difference dilated images. That is, here, processing for obtaining an image of the overlapping portion of the forward and reverse time difference dilated images is performed.
[0012]
In the present embodiment, the logical product for the past N times of the binary image obtained in step S106 is calculated so as to be compatible with a trailer type truck having a gap between the driver's seat and the loading platform. Is the front part of the moving vehicle (step S108).
Then, after performing the normalized Y-axis projection processing, binarization is performed again to obtain the leading coordinates for each moving vehicle (step S112).
In step S114, the vehicle management table 20 is sequentially updated while tracking the top coordinates for each moving vehicle. For example, new vehicle registration, moving vehicle coordinate update, or stop vehicle coordinate storage is performed.
In step S116, it is determined whether or not the current coordinate has disappeared. If it has disappeared, the process proceeds to step S118, and it is determined whether or not the previous coordinate was an exit area. Here, if the previous coordinate is the exit area, the process proceeds to step S120, the correlation calculation between the current exit area image and the exit area background image is performed, and the presence or absence of correlation is determined in step S122.
If it is determined in step S122 that there is no correlation, a part of the vehicle body remains in the exit area, so the vehicle management table 20 is updated and the vehicle information is stored (step S124).
If the current coordinate has not disappeared in step S116 described above, or if the previous coordinate is not an exit area in step S118, the process proceeds to step S126.
Further, if it is determined in step S122 that there is a correlation, the passage of the vehicle is confirmed, the vehicle management table 20 is updated, and the vehicle information is deleted from the vehicle management table 20 (step). S128).
In step S126, the measurement result output unit 22 counts the number of passing vehicles within a predetermined time by outputting a detection signal each time a newly registered vehicle rises in the vehicle management table 20. When there is a registered vehicle in the vehicle management table 20, the presence of the vehicle and the number of existing vehicles in the presence measurement area are output.
[0013]
As described above, according to the present embodiment, since a monocular camera is used, the cost can be reduced, and image processing is performed using forward and backward direction time difference images, so that buildings such as buildings and street trees reflected on the road can be used. The presence of the moving vehicle can be accurately sensed without being affected by the shadow and the shadow of the moving vehicle. Therefore, it is possible to perform control and information provision based on accurate entity information by performing traffic signal control using the measurement result by the traffic flow measuring apparatus of the present embodiment or providing traffic information to the vehicle-mounted device.
In the above embodiment, the camera is installed at a position where the front portion of the moving vehicle is imaged and the traffic flow in one side lane is measured. However, the present invention is not limited to this, and the front surface of the moving vehicle is not limited thereto. The opposite simultaneous measurement may be performed by overlooking both the rear and rear portions.
Moreover, in the said embodiment, although the image processing part 18 was comprised with the vehicle extraction part 24, the vehicle tracking part 26, and the vehicle passage determination part 28, it is not necessarily limited to this component, It is also possible to change the constituent elements according to the classification method and processing procedure.
[0014]
【The invention's effect】
As described above, according to the first aspect of the present invention, the image processing unit performs image processing on the road overhead image from the camera at a high place on the road. The image processing means includes at least a vehicle extraction unit, and extracts a forward time difference image that extracts only a portion that changes from dark to bright between two road overhead images that are continuous at predetermined time intervals, and from light to dark. The reverse time difference image for extracting only the changed portion is expanded, and the front portion of the moving vehicle is extracted based on the image of the portion where the two expanded images overlap. For this reason, not only the shadows of fixed objects such as buildings and roadside trees reflected on the road can be removed, but also the shadows of mobile vehicles and areas with a uniform density, such as ordinary vehicles, can be removed. By extracting the front part of the vehicle and accurately grasping the presence of the vehicle in the measurement area and measuring the traffic flow, it is possible to reduce the cost because it can be implemented with a monocular camera.
According to the second aspect of the present invention, the vehicle extraction unit included in the image processing unit further extracts an image of a portion where two expanded images overlap as a plurality of images that are continuous at a predetermined interval, and the plurality of images. The front part of the moving vehicle is extracted based on the result of the logical product. For this reason, even if the shadow is divided by a trailer type truck having a gap between the driver's seat and the cargo bed portion, the shadow at the boundary portion can be removed.
According to the third aspect of the present invention, the vehicle extraction unit included in the image processing means, when performing nighttime image processing, based on images corresponding to a pair of headlamps or vehicle width lights, Extract the front part. For this reason, by recognizing the headlamps and width lights of moving vehicles that are lit at night, it is possible to accurately extract each moving vehicle, grasp the vehicle's presence in the measurement area, and accurately determine the traffic flow. It can be measured.
According to invention of Claim 4, it has a vehicle management table which memorize | stores and manages for every vehicle the vehicle information extracted from the inside of the measurement area | region of a road overhead image. The vehicle tracking unit of the image processing means registers vehicle information in the vehicle management table every time the vehicle extraction unit extracts a new front part of the moving vehicle in the measurement area, while tracking the front part of the moving vehicle. The vehicle coordinates are updated, and if the front part of the moving vehicle disappears in the middle of the measurement area, it is determined that the vehicle is stopped, and the vehicle coordinates at that time are saved.When the movement of the stopped vehicle is resumed, the front part of the moving vehicle is tracked from the saved vehicle coordinates. Restart and update vehicle coordinates. For this reason, it is possible to accurately track each moving vehicle in the measurement region while extracting the moving vehicle described above.
[0015]
According to the fifth aspect of the present invention, the image processing means further includes a vehicle passage determination unit. This vehicle passage determination unit provides an exit region near the vehicle exit in the measurement region, and when the front side of the moving vehicle disappears after entering the exit region by the vehicle tracking unit, the vehicle front determination unit immediately before entering the exit region. Perform a correlation calculation between the background image of the exit area and the image of the current exit area, and if the calculation result exceeds a predetermined threshold, delete the vehicle information from the vehicle management table as the vehicle has passed, If the calculation result is less than or equal to a predetermined threshold value, the vehicle information is stored in the vehicle management table assuming that a part of the vehicle body remains. For this reason, the information on moving vehicles existing in the measurement area is accurately stored in the vehicle management table and deleted when it passes, so the presence of vehicles in the measurement area can be accurately determined simply by looking at the vehicle management table. I can grasp it.
According to the sixth aspect of the present invention, the headlamp or the vehicle width lamp of the moving vehicle is used for vehicle extraction and vehicle tracking at night. When the vehicle headlamp or the vehicle width lamp passes, the vehicle disappears from the screen. Therefore, whether or not a part of the vehicle body still remains in the exit area cannot be determined based on the presence of the headlamp or the vehicle width lamp. For this reason, whether or not a part of the vehicle body remains in the exit area at night is determined by the presence or absence of side reflections from the speed light, side light, or headlights in other lanes attached to the vehicle. It is assumed that a part of the vehicle body remains in the exit area when the area occupied by the high brightness area is large.
According to the seventh aspect of the present invention, the measurement result output unit refers to the vehicle information stored in the vehicle management table, and at least one of the presence, the number of vehicles present, or the number of passing vehicles in the measurement area. Since two measurement results are obtained and output to the outside, the above traffic flow measurement results can be used, for example, for traffic signal control or provided to an in-vehicle device or the like via an optical beacon.
According to the eighth aspect of the present invention, the road overhead image from the camera installed at a high place on the road is not only an image of looking down at the front part of the moving vehicle but also an image of looking down at the rear surface part of the moving vehicle. In this case, the traffic flow can be accurately measured by performing the same image processing as described above.
According to the ninth aspect of the present invention, the road overhead image from the camera installed at a high place on the road is the same image as the lane overlooking the front surface of the moving vehicle and the lane overlooking the rear surface of the moving vehicle. It is possible to perform image processing while keeping it within the field of view, and it is possible to measure traffic flow oppositely simultaneously.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a schematic configuration of a traffic flow measuring apparatus according to the present embodiment.
FIG. 2 is a diagram for explaining an image angle overlooking a vehicle traffic road from a roadside height such as a lamp post and an area division in the image angle.
FIG. 3 is a diagram illustrating an example of a vehicle management table.
FIG. 4 is a diagram illustrating an example of a captured image obtained by overlooking a vehicle traffic path with a camera.
FIG. 5 is a diagram illustrating a forward direction time difference image that extracts only a portion that has changed from dark to bright between two images.
FIG. 6 is a diagram illustrating a backward time difference image in which only a portion that changes from light to dark between two images is extracted.
FIG. 7 is a diagram illustrating an image obtained by dilating a forward direction time difference image and a backward direction time difference image and adding them to a predetermined threshold value after addition.
8A is a diagram showing a trailer type truck having a gap between a driver's cab and a loading platform, FIG. 8B is a diagram of the current image processing result, FIG. 8C is a diagram of the previous image processing result, (D) is the figure of the image processing result two times before, (e) is the figure which took the logical product of the image of (b)-(d).
FIG. 9 is a flowchart illustrating a processing operation of the traffic flow measuring apparatus according to the present embodiment.
[Explanation of symbols]
10 Traffic flow measuring device,
12 cameras,
14 Image input unit,
16 Image storage unit,
18 Image processing unit,
20 Vehicle management table,
22 Measurement result output section,
24 vehicle extraction unit,
26 Vehicle tracking unit,
28 vehicle passage determination unit,
30, 32, 34, 35 lanes,
36 Existence measurement area,
38 exit area,
40 Oncoming lane,
42,46 mobile vehicles,
44, 48 shadows.

Claims (9)

It has image processing means for image processing of a road overhead image from a camera installed at a high place on the road, and measures the traffic flow by grasping the presence of vehicles in the measurement area provided in the direction of the traffic flow of the lane. In the traffic flow measurement device that performs
The image processing means extracts a forward direction time difference image that extracts only a portion that changes from dark to light between two road overhead images that are continuous at a predetermined time interval, and a reverse direction that extracts only a portion that changes from light to dark A traffic flow measurement device comprising at least a vehicle extraction unit that expands each time difference image and extracts a front portion of a moving vehicle based on an image of a portion where the two expansion images overlap. The vehicle extraction unit further extracts a portion where the two expansion images overlap as a plurality of images that are continuous at a predetermined interval, and based on the result of taking the logical product of the plurality of images, the front portion of the moving vehicle The traffic flow measuring device according to claim 1, wherein the traffic flow is extracted. 2. The traffic according to claim 1, wherein when performing nighttime image processing, the vehicle extraction unit extracts a front part of a moving vehicle based on an image corresponding to a pair of headlamps or a vehicle width lamp. Flow measuring device. While having a vehicle management table for storing and managing vehicle information extracted from within the measurement area of the road overhead image for each vehicle,
The image processing means registers the vehicle information in the vehicle management table each time the vehicle extraction unit extracts a new moving vehicle front portion in the measurement area, and tracks the moving vehicle front portion while tracking the moving vehicle front portion. The coordinates are updated, and when the front part of the moving vehicle disappears in the middle of the measurement area, it is determined that the moving vehicle is stopped and the vehicle coordinates at that time are stored. The traffic flow measuring apparatus according to claim 1, further comprising a vehicle tracking unit that restarts and updates the vehicle coordinates. The image processing means provides an exit area in the vicinity of the vehicle exit of the measurement area, and when the moving vehicle front section disappears after entering the exit area by the vehicle tracking unit, immediately before the moving vehicle front section enters the exit area. A correlation calculation is performed between the background image of the exit area of the vehicle and the image of the current exit area, and if the calculation result exceeds a predetermined threshold value, the vehicle information is deleted from the vehicle management table as the vehicle has passed. And a vehicle passage determination unit that stores the vehicle information in the vehicle management table as a part of the vehicle body remaining if the calculation result is equal to or less than a predetermined threshold value. 4. The traffic flow measuring device according to 4. The image processing means provides an exit area in the vicinity of the vehicle exit of the measurement area, extracts the vehicle at night by the vehicle extraction unit of the claim 3, and the front part of the moving vehicle enters the exit area by the vehicle tracking unit. When it disappears later, the exit area is binarized by brightness, and if the proportion of the area with high brightness in the exit area is equal to or less than a predetermined threshold, the vehicle information is determined from the vehicle management table as having passed. 5. A vehicle passage determining unit that deletes the vehicle information and stores the vehicle information in the vehicle management table assuming that a part of the vehicle body remains if the predetermined threshold value is exceeded. The traffic flow measuring device described in 1. Based on the vehicle information stored in the vehicle management table, a measurement result output for obtaining at least one measurement result among the presence of vehicles in the measurement area, the number of vehicles present, or the number of passing vehicles is output to the outside. The traffic flow measuring device according to claim 4, further comprising a unit. The road overhead image from a camera installed at a high place on the road is subjected to image processing using an overhead image of the rear surface of the moving vehicle instead of the overhead image of the front surface of the moving vehicle. The traffic flow measuring device according to any one of? 7. A road overhead image from a camera installed on a high road is obtained by performing image processing by placing the lane overlooking the front of the moving vehicle and the lane overlooking the rear of the moving vehicle in the same image field of view. The traffic flow measuring device according to any one of claims 1 to 7, wherein the opposite simultaneous measurement is enabled.

Images