JP2007026300A - Traffic flow abnormality detector and traffic flow abnormality detection method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a traffic flow abnormality detector and a traffic flow abnormality detection method, capable of rapidly and accurately detecting abnormality of traffic flow even out of a measuring range of traffic flow. <P>SOLUTION: A traffic state quantity measuring part 11 measures, based on a signal SC inputted from a plurality of vehicle detectors monitoring different areas, the traffic state quantity in each of the measuring areas. A traffic flow state determination part 2 determines, based on the measured traffic state quantity, whether the traffic flow in each of the monitoring areas is congested or free. A traffic flow abnormality determination part 3 includes a traffic flaw abnormal state determination part 3a and a traffic flaw abnormal state continuation determination part 3b, and determines, based on combinations of the monitoring areas of the vehicle detectors with the traffic flow states determined by the determination part, whether the traffic flows are in abnormal state or not. A traffic flow abnormality detection part 4 detects abnormality of the traffic flows based on output from the determination part 3. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a traffic flow abnormality detection device and a traffic flow abnormality detection method.

  Conventionally, there has been a method for determining an event such as a sudden event by using section integration processing that integrates information of a plurality of road sensors and continuously outputs vehicle information existing in the entire measurement range (for example, patents) Reference 1).

  However, in the above method, since the event determination within the measurement range by the road sensor is performed, it is necessary to install the road sensor so that the entire region where the event determination is performed becomes the measurement range. Therefore, when the area where the event determination is performed covers a wide area, labor and cost for installing the road sensor increase. Therefore, a method for detecting an abnormality in traffic flow outside the measurement range by the road sensor has been proposed (see, for example, Patent Document 2 and Patent Document 3).

  In the abnormal traffic flow detection device described in Patent Document 2, the traffic state quantity after a predetermined time is predicted from the traffic state quantity detected by the vehicle detector, and the traffic state quantity detected after the predetermined time has a predicted value. It is determined that the traffic flow is abnormal when it is outside the predetermined range.

  Further, the traffic flow measuring device described in Patent Document 3 is based on the measurement value by the first vehicle measuring means arranged on the upstream side of the traffic flow, and the second vehicle measuring means arranged on the downstream side after a predetermined time. Is used to calculate a predicted value of a traffic flow parameter to be measured and to compare the measured value of the second vehicle measuring means with the calculated predicted value to estimate the traffic state.

JP 2003-288862 A Japanese Patent Laid-Open No. 3-209599 JP-A-8-279093

  However, in the above-described conventional traffic flow abnormality detection device, since a predicted value after the elapse of a predetermined time calculated from a certain measured value is used, the calculation accuracy of the predicted value improves the reliability of the traffic flow abnormality determination. There were circumstances that would have had a significant impact. In addition, since the determination is performed using the predicted value, there is a situation that it takes time until the determination.

  The present invention has been made in view of the above-described conventional circumstances, and a traffic flow abnormality detection device and a traffic flow abnormality capable of detecting a traffic flow abnormality quickly and with high accuracy even outside the traffic flow measurement range. An object is to provide a detection method.

  The traffic flow abnormality detection device of the present invention is connected to a plurality of vehicle detectors that monitor different regions, and measures traffic state amount measuring means for measuring the traffic state amount in each of the regions, and the measured traffic state amount. Based on the combination of the traffic flow state determining means for determining whether the traffic flow in each of the regions is a congested flow or a free flow, and the region monitored by the vehicle detector and the determined traffic flow state And a traffic flow abnormal state determination means for determining whether or not the traffic flow is in an abnormal state.

  With this configuration, the abnormal state of the traffic flow is determined based on the combination of the area monitored by the vehicle detector and the determined traffic flow state, so that traffic can be quickly and accurately even outside the measurement range of the traffic flow. Flow anomalies can be detected.

  The traffic flow abnormality detection device according to the present invention is a traffic flow abnormality determination unit that determines whether or not the abnormal state has been maintained for a predetermined time when the traffic flow abnormal state determination unit determines that the traffic flow is in an abnormal state. An abnormal state continuation determination unit is further provided.

  With this configuration, since it is determined whether or not the abnormal state of the traffic flow has been maintained for a predetermined time, it is possible to detect the abnormal traffic flow with higher accuracy.

  Further, in the traffic flow abnormality detection device of the present invention, the plurality of vehicle detectors are provided in order from the upstream side of the road, respectively, a first vehicle detector for monitoring the first region, and a second region. A second vehicle detector for monitoring, and a third vehicle detector for monitoring a third region, wherein the traffic flow abnormal state determination means is configured such that the first region is a traffic jam flow and the second region Are determined to be abnormal in the traffic flow when it is determined that the traffic flow is a traffic jam and the third region is a free flow.

  With this configuration, it is possible to detect a traffic flow abnormality quickly and accurately even outside the traffic flow measurement range.

  Further, in the traffic flow abnormality detection device of the present invention, the plurality of vehicle detectors are provided in order from the upstream side of the road, respectively, a first vehicle detector for monitoring the first region, and a second region. A second vehicle detector for monitoring, and a third vehicle detector for monitoring a third region, wherein the traffic flow abnormal state detecting means is configured such that the first region is a free flow, the second region Are determined to be abnormal in the traffic flow when it is determined that the traffic flow is a traffic jam and the third region is a free flow.

  With this configuration, it is possible to detect a traffic flow abnormality quickly and accurately even outside the traffic flow measurement range.

  Further, in the traffic flow abnormality detection device of the present invention, the traffic state quantity measuring unit measures the traffic volume from the number of vehicles passing through the monitoring area per unit time as the traffic state quantity, and determines the traffic flow state determination The means determines that the traffic flow is a congested flow when the traffic volume is equal to or greater than a traffic jam flow threshold, and a free flow when the traffic is equal to or less than the traffic free flow threshold.

  With this configuration, it is possible to detect a traffic flow abnormality based on the measured traffic volume.

  Further, in the traffic flow abnormality detection device of the present invention, the traffic state quantity measuring means measures an average speed of individual vehicles passing through the monitoring area as the traffic state quantity, and the traffic flow state judging means is If the average speed is equal to or greater than the speed free flow threshold, it is determined to be free flow, and if the average speed is equal to or less than the speed jam flow threshold, it is determined to be jam flow.

  With this configuration, it is possible to detect a traffic flow abnormality based on the measured average speed of the individual vehicle.

  Further, in the traffic flow abnormality detection device of the present invention, each of the vehicle detectors is any one of an imaging device, an ultrasonic vehicle detector, a loop coil vehicle detector, and a tape vehicle detector. Consists of.

  With this configuration, an abnormality in traffic flow can be detected by various vehicle detectors.

  Further, in the traffic flow abnormality detection device of the present invention, the plurality of vehicle detectors include an imaging device, and the traffic state quantity measuring means processes an image taken by the imaging device and measures the traffic state quantity. To do.

  With this configuration, the image picked up by the image pickup apparatus is used, so that the state quantity can be measured from various information obtained from the image.

  Further, in the traffic flow abnormality detection device of the present invention, the traffic state quantity measuring means measures a space occupancy rate of a vehicle in a region imaged by the imaging device as the traffic state quantity, and determines the traffic flow state determination The means determines that the traffic flow is a congested flow when the occupation rate is equal to or greater than the occupation rate traffic congestion determination threshold value, and a free flow when the traffic volume is equal to or less than the occupation rate free flow determination threshold value.

  With this configuration, it is possible to detect an abnormality in traffic flow based on the space occupancy rate of the vehicle in the captured image.

  Further, in the traffic flow abnormality detection device of the present invention, the traffic state quantity measuring means measures a vehicle group speed passing through the monitoring area as the traffic state quantity, and the traffic flow state determining means is the vehicle group When the speed is equal to or greater than the speed free flow determination threshold, it is determined to be free flow, and when the vehicle group speed is equal to or less than the speed congestion flow determination threshold, it is determined to be congestion flow.

  With this configuration, because the vehicle group speed is used as the traffic state quantity, it is possible to detect a traffic flow abnormality with high accuracy even when it is difficult to extract the characteristics of the vehicle such as in a traffic jam.

  The traffic flow abnormality detection method of the present invention is connected to a plurality of vehicle detectors that monitor different areas, and measures a traffic traffic state quantity in each of the areas, and based on the measured traffic state quantity. Whether the traffic flow is abnormal based on a combination of the step of determining whether the traffic flow in each of the areas is a jam flow or a free flow and the position of the vehicle detector and the determined traffic flow state Determining whether or not.

  By this method, the abnormal state of the traffic flow is determined based on the combination of the area monitored by the vehicle detector and the determined traffic flow state. Therefore, the traffic flow can be detected quickly and accurately even outside the measurement range of the traffic flow. Flow anomalies can be detected.

  According to the present invention, it is possible to provide a traffic flow abnormality detection device and a traffic flow abnormality detection method capable of detecting a traffic flow abnormality quickly and with high accuracy even outside the traffic flow measurement range.

  In this embodiment, a road monitoring system that can detect a traffic flow abnormality by photographing a vehicle traveling with a camera installed in a tunnel or the like from behind, performing vehicle feature extraction from the captured image, vehicle recognition, etc. The example of a structure in is shown.

  FIG. 7 is an explanatory diagram showing an outline of a road monitoring system including the traffic flow abnormality detection device according to the embodiment of the present invention. As shown in FIG. 7, the road monitoring system is provided as an imaging device that is an example of a vehicle detector for each predetermined position on the roadside such as in a tunnel on the road 11, and a plurality of cameras 12 that monitor different areas. It has.

  The camera 12 captures a vehicle 13 traveling on the road 11 from behind and outputs a captured image signal SC as an example of a vehicle detection signal. In addition, the road monitoring system includes a traffic flow abnormality detection device 10 that detects a vehicle, calculates a vehicle speed, detects a fallen object, and the like based on a captured image captured by the camera 12, and detects a traffic jam or suddenly. Perform event determination on the target road, such as event detection.

  In the present embodiment, the vehicle is photographed from the rear to prevent halation, smear, and the like due to the vehicle headlight. A vehicle is extracted based on the photographed image from the rear, and the vehicle width, the vehicle length, and the vehicle rear position are detected. Then, the detected vehicle is tracked, and when the tracking is impossible, the stop low-speed vehicle is detected by performing processing described later.

  Next, the traffic flow abnormality detection device 10 according to the embodiment of the present invention will be described. FIG. 1 is a block diagram showing a schematic configuration of a traffic flow abnormality detection device according to an embodiment of the present invention.

  As shown in FIG. 1, the traffic flow abnormality detection device 10 according to the present embodiment determines a traffic flow state based on a traffic state amount measuring unit 1 that measures a traffic state amount and an output of the traffic state amount measuring unit 1. The traffic flow state determination unit 2, the traffic flow abnormality determination unit 3 that determines the presence or absence of a traffic flow abnormality from the traffic flow state determined by the traffic flow state determination unit 2, and the traffic based on the determination by the traffic flow abnormality determination unit 3 And a traffic flow abnormality detection unit 4 for detecting a flow abnormality.

  The traffic state quantity measuring unit 1 includes an image processing unit 1a, a traffic volume calculating unit 1b, a speed calculating unit 1c, and an occupation rate calculating unit 1d. The captured image signal SC is subjected to image processing, and the traffic state quantity in each of the shooting areas of the camera 12 is measured.

  Then, as the traffic state quantity, the traffic volume calculation unit 1b measures the number of vehicles passing through the monitoring area of the camera 12 per unit time, and the speed calculation unit 1c calculates the average speed of the individual vehicles passing through the monitoring area of the camera 12 and The vehicle group speed is measured, and the occupancy rate calculation unit 1d measures the space occupancy rate of the vehicle in the monitoring area of the camera 12. In addition, you may employ | adopt the average value in predetermined time, such as the past 1 minute, for these traffic state quantities, for example.

  The traffic flow state determination unit 2 determines whether the traffic flow in each of the monitoring areas of the camera 12 is a traffic jam flow or a free flow based on the traffic state amount measured by the traffic state amount measurement unit 1.

  The traffic flow abnormality determination unit 3 includes a traffic flow abnormality state determination unit 3a and a traffic flow abnormality state continuation determination unit 3b. The traffic flow abnormal state determination unit 3a determines whether or not the traffic flow is in an abnormal state based on the combination of the position of the monitoring area of the camera 12 and the traffic flow state determined by the traffic flow state determination unit 2. To do. The traffic flow abnormal state continuation determination unit 3b determines whether or not the traffic flow abnormal state has been maintained for a predetermined time when the traffic flow abnormal state determination unit 3a determines that the traffic flow is in an abnormal state. The position of the monitoring area of the camera 12 may be determined by the traffic flow abnormality detection device 10 by adding camera identification information to the signal from the camera 12, or when connecting to each camera via a wired transmission path. The determination may be made based on the connection position of the transmission path in the traffic flow abnormality detection device 10.

  The traffic flow abnormality detection unit 4 detects the traffic flow abnormality when the traffic flow abnormality determination unit 3 determines the traffic flow abnormality. Then, if necessary, information such as the detection time of traffic flow abnormality and the location where a sudden event such as a fallen object or accident causing the traffic flow abnormality occurred is displayed on a display unit (not shown). Output.

  Next, the operation of the traffic flow abnormality detection device of this embodiment will be described. FIG. 2 is a flowchart showing a processing procedure of the traffic flow abnormality detection method according to the embodiment of the present invention.

  As shown in FIG. 2, the traffic state quantity measuring unit 1 performs image processing based on the captured image signal SC from each camera 12, and measures the traffic state quantity for each region (step S201). Details of image processing and traffic state quantity measurement will be described with reference to FIGS.

  Next, the traffic flow state determination unit 2 determines the traffic flow state for each region (step S202). Details of the traffic flow state determination will be described with reference to FIG.

  Then, the traffic flow abnormality state determination unit 3a of the traffic flow abnormality determination unit 3 determines whether or not the traffic flow state of each region determined by the traffic flow state determination unit 2 satisfies the abnormality determination condition (step S203). . Details of the abnormality determination condition will be described with reference to FIG.

  When the traffic flow state of each region satisfies the abnormality determination condition (YES in step S203), the traffic flow abnormal state continuation determination unit 3b determines whether or not the traffic flow abnormal state has continued for a predetermined time (step S204). On the other hand, when the traffic flow state of each area does not satisfy the abnormality determination condition (NO in step S203), the process ends.

  If the traffic flow abnormality state continues for a predetermined time (YES in step S204), the traffic flow abnormality detection unit 4 determines that a traffic flow abnormality has occurred, and detects the traffic flow abnormality (step S205). In this way, the traffic flow abnormality detection device of the present embodiment detects a traffic flow abnormality. In addition, since the traffic flow abnormality is detected when the traffic flow abnormality state continues for a predetermined time, it is possible to prevent the erroneous detection of the traffic flow abnormality caused by the erroneous determination of the traffic flow state, and to detect the traffic flow abnormality with high accuracy. I can do it. In addition, you may set the abnormal condition continuation time for the traffic flow abnormal condition continuation determination part 3b to determine variably according to time etc.

  Next, the traffic state quantity measurement process in step S201 in FIG. 2 will be described. FIG. 3 is a flowchart showing a processing procedure of traffic state quantity measurement according to the embodiment of the present invention.

  As shown in FIG. 3, the image processing unit 1a first creates background image data and background differential image data as initial data (step S301). Here, after power-on or reset, for example, 300 times of captured image data (images for 30 seconds) taken from the camera 12 every 0.1 seconds are averaged to obtain a background image. Also, a background differential image is created by performing differential processing of the background image data. Furthermore, since the brightness of the lighting on the road is different between night and day, the night mode or the day mode is determined based on the background image, and the mode corresponding to the current time is set.

  Next, image data used for image analysis is created from the captured image data SC captured from the camera 12 (step S302). Here, the video signal based on the NTSC signal input from the camera 12 has a vertical direction of 240 lines, a horizontal direction of 320 pixels, a luminance of 256 gradations, and is subjected to AD conversion (analog-digital conversion) for each frame to 320 pixels × 240. Create pixel image data. At this time, only an even field is AD-converted to create one image data every 1/30 seconds. In the subsequent image analysis, three image data of the current image, the image before ΔT, and the image before 2ΔT (here, ΔT = 100 ms) are used.

  Then, image preprocessing such as feature extraction calculation and binarization processing is performed on the created image data to create a feature extraction image from which the features of the vehicle are extracted (step S303). In the feature extraction calculation, differential images obtained by performing feature extraction using each of the four feature extraction methods of the background difference method, the differential background difference method, the frame difference method, and the differential frame difference method are created and synthesized after weighting. To calculate a feature extraction image. Here, in order to increase the processing speed of post-processing, after processing such as feature extraction is performed to create a feature extraction image, the image data of 320 pixels × 240 pixels is compressed to 80 pixels × 60 pixels and features are extracted. Create an extracted compressed image. Further, a light extraction image of 320 pixels × 240 pixels is created from the image data created for image analysis.

  Subsequently, image analysis is performed using the feature extraction compressed image and the light extraction image to extract vehicles and the like (step S304). At this time, the vehicle body analysis is performed using the feature extraction compressed image, and the stern, the vehicle length, and the vehicle width are determined. Further, light analysis is performed using the light extraction image, and the vehicle tail is determined by detecting the light of the vehicle. The vehicle position is determined from the results of the rectangular vehicle body detection by the vehicle body analysis and the vehicle tail detection by the light analysis. Further, the falling object analysis is performed using the feature extraction compressed image, and the position and the vertical and horizontal dimensions of the falling object are determined.

  The occupation rate calculation unit 1c calculates, as the occupation rate, the proportion of the vehicle in one screen of the image captured by the camera 12 from the vehicle extracted in step S304 (step S305).

The traffic volume calculation unit 1a counts as one when the stern detected in step S304 passes a predetermined horizontal line of the image, and calculates the number of vehicles passing per predetermined time as the traffic volume ( Step S306).

  The speed calculation unit 1b adds or newly creates the detected position data of the vehicle to the travel locus data, and adds the detected vehicle position data to the travel locus data for each cycle of this process, thereby tracking the vehicle. I do. Moreover, the moving speed of each detected vehicle is calculated (step S307).

  Further, the speed calculation unit 1b calculates the speed of the vehicle group in the captured image by a method different from the vehicle tracking (step S308). Here, the entire vehicle is regarded as one lump car group from the movement amount of the luminance value of the entire image, and the moving speed of this car group is calculated.

  Then, the image processing unit 1a updates the background image data and the background differential image data to the latest background image for image processing in the next processing cycle (step S309). Further, the night mode or the day mode is determined based on the new background image, and the mode is updated to the current time point. Then, it returns to step S302 and repeats the processing cycle of steps S302-S309 for every predetermined interval (here 100 ms).

  FIG. 4 is a block diagram illustrating a schematic configuration of the image processing unit according to the embodiment of the present invention. As shown in FIG. 4, the image processing unit 1a includes an image input unit 21 for inputting captured image data SC captured by the camera 12, a memory for storing image data, and the like as a functional configuration for performing image preprocessing. The image storage unit 22 is configured, and the image calculation unit 23 is configured to include a processor for processing image data.

  The image storage unit 22 includes a current image storage unit 24, a differential image storage unit 25, a background image storage unit 26, a difference image storage unit 27, a difference binarized image storage unit 28, a weighted image storage unit 29, and a feature image storage unit 30. Have The image calculation unit 23 includes a differential image generation unit 31, a background image generation unit 32, an inter-image subtraction unit 33, an inter-image logical product calculation unit 34, an image binarization unit 35, a binarized image weighting unit 36, and an inter-image addition. Part 37. The image processing unit 1a includes a background update rate storage unit 38, a background update rate calculation unit 39, a binarization threshold value setting unit 40, and a weight amount setting unit 41.

  The current image storage unit 24 stores current image data input from the image input unit 21. The input image data is a grayscale image with 256 gradations. The differential image creation unit 31 performs a differentiation process on the current image, and the differential image storage unit 25 stores the created differential image data. The background image creation unit 32 creates a background image and a differential background image, and the background image storage unit 26 stores the created background image data and differential background image data. At this time, the background update rate calculation unit 39 calculates and sets the background update rate from the occupancy rate of the vehicle in the image, and the background update rate storage unit 38 stores the background update rate data. The background image creation unit 32 updates the background image at a rate corresponding to the background update rate.

  The inter-image subtracting unit 33 subtracts the current image and the background image, subtracts the differential image and the differential background image, subtracts the current image from the image before ΔT, and the inter-frame subtraction between the image before ΔT and the image before ΔT and 2ΔT before, the current differential image and ΔT Difference processing is performed by performing inter-frame subtraction of the pre-differential image, the ΔT pre-differential image, and the 2ΔT pre-differential image, respectively, to create a differential image. The difference image storage unit 27 stores the image data of the created background difference image, differential background difference image, frame difference image, and differential frame difference image. The inter-image logical product calculation unit 34 performs a logical product operation on the frame difference image and the differential frame difference image between the difference image of the current image and the image before ΔT and the difference image of the image before ΔT and the image before 2ΔT.

  The image binarization unit 35 binarizes each difference image data based on the threshold value set by the binarization threshold value setting unit 40. The difference binarized image storage unit 28 stores the image data of the created background difference binarized image, differential background difference binarized image, frame difference binarized image, and differential frame difference binarized image.

  The binarized image weighting unit 36 creates the background difference binarized image, the differential background difference two based on the weight amount of each difference binarized image set by the weight amount setting unit 41 according to the shooting environment or the like. Weighting is performed on each of the binarized image, the frame difference binarized image, and the differential frame difference binarized image. The weighted image storage unit 29 stores each weighted difference binary image data. The inter-image addition unit 37 adds the weighted background difference binarized image, the differential background difference binarized image, the frame difference binarized image, and the differential frame difference binarized image, respectively, by a plurality of methods. The created difference binary image is synthesized after weighting. The feature image storage unit 30 stores the added and synthesized image data as image data of the feature extraction image. In this way, feature extraction image data is generated in the image processing unit 1a.

  Using this feature extraction image data, image analysis processing such as vehicle body recognition is performed, and vehicle tracking processing, vehicle group speed calculation processing by the traffic volume calculation unit 1b, speed calculation unit 1c, and occupation rate calculation unit 1d from the vehicle detection result, Perform event detection processing.

  Next, the traffic flow state determination process in step S202 in FIG. 2 will be described. FIG. 5 is a flowchart for explaining the processing procedure of the traffic flow state determination according to the embodiment of the present invention.

  The traffic flow state determination unit 2 acquires the traffic volume, speed, and occupation rate, which are information on the traffic volume measured by the traffic volume measuring unit 1 (step S401), and determines whether the traffic volume is equal to or greater than a threshold value. Is determined (step S402). If the traffic volume is equal to or greater than the threshold value (YES in step S402), it is determined whether the speed is equal to or less than the threshold value (step S403). For example, when the vehicle group speed is used for this speed determination, it is possible to accurately measure the speed even when it is difficult to extract the characteristics of the vehicle such as in a traffic jam. It is possible to detect abnormalities in traffic flow with high accuracy.

  If the speed is equal to or lower than the threshold value (YES in step S403), it is determined whether or not the occupation ratio is equal to or higher than the threshold value (step S404). If the occupation ratio is equal to or greater than the threshold value (YES in step S404), it is determined that the traffic flow state is a traffic jam flow (step S405).

  On the other hand, if the traffic volume is less than the threshold value (NO in step S402), the speed is greater than the threshold value (NO in step S403), and the occupation rate is less than the threshold value (NO in step S404), the traffic It is determined that the flow state is a free flow.

  In the above description, the example of determining the traffic flow state by combining all of the traffic volume, the speed, and the occupation ratio as the traffic state amount has been described. However, only one of these or two traffic state amounts are described. May be used to determine the traffic flow state. Moreover, as a traffic state quantity, it is not restricted to traffic volume, speed, and an occupation rate, If a value which shows a traffic state, various state quantities can be applied.

  Moreover, although the example which determines a traffic flow state using one threshold value with respect to each traffic state quantity was demonstrated, you may provide the threshold value for traffic congestion determination and for free flow determination, respectively. . For example, as a speed threshold, it may be determined that the traffic flow is congested if the speed is 20 km / h or less, and free flow if the speed is 40 km / h or more. Furthermore, the threshold value for determining the traffic flow state may be variably set according to the time or the like.

  Next, the abnormality determination condition in step S203 in FIG. 2 will be described. FIG. 6 is an explanatory diagram showing an example of a traffic flow state when a traffic flow abnormality occurs. FIG. 6A shows a case where a sudden event occurs when the traffic volume is large, and FIG. An example of a traffic flow state when an unexpected event occurs when the amount is small is shown.

  As shown in FIGS. 6A and 6B, in order from the upstream side of the road 11, the first camera 12a for monitoring the first monitoring area 11a and the second camera for monitoring the second area 11b. A camera 12b and a third vehicle detector 12c for monitoring the third region 11c are provided. It is assumed that the areas 11a to 11c that can be monitored by the respective cameras 12a to 12c are not continuous, and a portion between these areas cannot be monitored. And the case where a sudden event occurs in the point P between the area | regions 11b and 11c is demonstrated.

  As shown in FIG. 6A, when a sudden event occurs at a point P, a traffic jam occurs at the point P, and the traffic jam is resolved downstream from the point P. Accordingly, the traffic flow abnormality determination condition is set such that the first region 11a is a traffic flow, the second region 11b is a traffic flow, and the third region 11c is a free flow. It can be estimated that a sudden event has occurred with the third region 11c.

  Therefore, the traffic flow abnormality determination unit 3 and the traffic flow abnormality detection unit 4 are configured so that the second region 11b and the third region 11c can be used when the traffic flow state in the regions 11a to 11c satisfies the abnormality determination condition for a predetermined time. It is possible to detect that a traffic flow abnormality has occurred between

  In particular, by determining not only the traffic flow state of the second region 11b downstream of the point P where the sudden event has occurred, but also the traffic flow state of the third region 11c further downstream, Since it is possible to prevent erroneous detection of traffic flow abnormality due to erroneous determination of the traffic flow state in the region 11b, highly accurate traffic flow abnormality detection can be realized.

  Further, as shown in FIG. 6B, when the traffic volume of the vehicle traveling on the road 11 is small, the congestion distance starting from the point P may be short. In such a case, the traffic flow abnormality determination condition is set such that the first region 11a is a free flow, the second region 11b is a congested flow, and the third region 11c is free so that a traffic flow abnormality determination is possible. By setting the flow, it is possible to estimate that a sudden event has occurred between the second region 11b and the third region 11c when the traffic volume is small. Note that this condition may be adopted only when the traffic volume measured in the first region 11a is equal to or less than a predetermined threshold value.

  According to the traffic flow abnormality detection device and the traffic flow abnormality detection method of the embodiment of the present invention, the traffic flow abnormality state is based on the combination of the traffic flow state determined to be the region monitored by the vehicle detector. Therefore, an abnormality in traffic flow can be detected quickly and accurately even outside the measurement range of traffic flow.

  In the embodiment of the present invention, a case where a camera is applied to a vehicle detector has been described. However, the present invention is not limited to this, and an ultrasonic vehicle detector and an electromotive force generated in a loop coil embedded under a road are used. Apply a loop coil type vehicle detector that detects the vehicle, or a tape type vehicle detector that is installed on the road or in the ground and detects the vehicle by connecting the switch when the vehicle passes by its weight May be.

  The traffic flow abnormality detection device and the traffic flow abnormality detection method of the present invention have the effect of being able to detect a traffic flow abnormality quickly and with high accuracy even outside the traffic flow measurement range. Etc. are useful.

The block diagram which shows schematic structure of the traffic flow abnormality detection apparatus which concerns on embodiment of this invention. The flowchart which shows the process sequence of the traffic flow abnormality detection method which concerns on embodiment of this invention. The flowchart which shows the process sequence of the traffic state quantity measurement which concerns on embodiment of this invention. 1 is a block diagram showing a schematic configuration of an image processing unit according to an embodiment of the present invention. The flowchart explaining the processing procedure of the traffic flow state determination which concerns on embodiment of this invention. Explanatory drawing showing an example of traffic flow condition when traffic flow abnormality occurs Explanatory drawing which shows the outline | summary of the road monitoring system containing the traffic flow abnormality detection apparatus which concerns on embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Traffic state quantity measurement part 1a Image processing part 1b Traffic volume calculation part 1c Speed calculation part 1d Occupancy rate calculation part 2 Traffic flow state determination part 3 Traffic flow abnormality determination part 3a Traffic flow abnormal state determination part 3b Traffic flow abnormal state continuation determination Unit 4 traffic flow abnormality detection unit 10 traffic flow abnormality detection device 11 road 12 camera 13 vehicle 21 image input unit 22 image storage unit 23 image calculation unit 24 current image storage unit 25 differential image storage unit 26 background image storage unit 27 differential image storage 27 Unit 28 difference binarized image storage unit 29 weighted image storage unit 30 feature image storage unit 31 differential image creation unit 32 background image creation unit 33 inter-image subtraction unit 34 inter-image logical product computation unit 35 image binarization unit 36 binary Quantized image weighting unit 37 Inter-image addition unit 38 Background update rate storage unit 39 Background update rate calculation unit 40 Binary threshold setting unit 41 Weight amount setting unit

Claims (11)

Traffic state quantity measuring means connected to a plurality of vehicle detectors for monitoring different areas, and measuring traffic state quantities in each of the areas;
Traffic flow state determination means for determining whether the traffic flow in each of the areas is a traffic jam flow or a free flow based on the measured traffic state quantity;
Based on the combination of the area monitored by the vehicle detector and the determined traffic flow state, traffic flow abnormal state determination means for determining whether or not the traffic flow is in an abnormal state;
A traffic flow abnormality detection device comprising: The traffic flow abnormality detection device according to claim 1,
Traffic flow abnormality detection further comprising a traffic flow abnormal state continuation determining unit that determines whether or not the abnormal state has been maintained for a predetermined time when the traffic flow is determined to be abnormal by the traffic flow abnormal state determination unit. apparatus. The traffic flow abnormality detection device according to claim 1 or 2,
The plurality of vehicle detectors are provided in order from the upstream side of the road, respectively, a first vehicle detector for monitoring the first region, a second vehicle detector for monitoring the second region, and a third A third vehicle detector that monitors the area of
The traffic flow abnormal state determination means is abnormal in the traffic flow when it is determined that the first region is a traffic jam flow, the second region is a traffic jam flow, and the third region is a free flow. Traffic flow abnormality detection device that determines that there is. The traffic flow abnormality detection device according to claim 1 or 2,
The plurality of vehicle detectors are provided in order from the upstream side of the road, respectively, a first vehicle detector for monitoring the first region, a second vehicle detector for monitoring the second region, and a third A third vehicle detector that monitors the area of
The traffic flow abnormal state detecting means detects that the traffic flow is abnormal when it is determined that the first region is a free flow, the second region is a traffic jam flow, and the third region is a free flow. Traffic flow abnormality detection device that determines that there is. The traffic flow abnormality detection device according to any one of claims 1 to 4,
The traffic state quantity measuring means measures the traffic volume from the number of vehicles passing through the monitoring area per unit time as the traffic state quantity,
The traffic flow state determining means determines that the traffic flow is a traffic flow when the traffic volume is equal to or greater than a traffic volume congestion flow threshold value, and is a free flow when the traffic volume is equal to or less than the traffic volume free flow threshold value. Anomaly detection device. The traffic flow abnormality detection device according to any one of claims 1 to 5,
The traffic state quantity measuring means measures an average speed of individual vehicles passing through the monitoring area as the traffic state quantity,
The traffic flow state determination means detects a traffic flow abnormality when the average speed is equal to or greater than a speed free flow threshold, and determines that the average speed is a congestion flow when the average speed is equal to or less than a speed jam flow threshold. apparatus. The traffic flow abnormality detection device according to any one of claims 1 to 6,
Each of the vehicle detectors is a traffic flow abnormality detection device including any one of an imaging device, an ultrasonic vehicle detector, a loop coil vehicle detector, and a tape vehicle detector. The traffic flow abnormality detection device according to any one of claims 1 to 6,
The plurality of vehicle detectors includes an imaging device;
The traffic state quantity measuring means is a traffic flow abnormality detecting apparatus that processes an image captured by the imaging device and measures the traffic state quantity. The traffic flow abnormality detection device according to claim 8,
The traffic state quantity measuring means measures the space occupancy rate of the vehicle in the area imaged by the imaging device as the traffic state quantity,
The traffic flow state determination means is a congested flow when the occupation rate is equal to or greater than an occupation rate congestion flow determination threshold, and is a free flow when the traffic volume is equal to or less than the occupation rate free flow determination threshold. A traffic flow abnormality detection device for judging. The traffic flow abnormality detection device according to claim 8 or 9,
The traffic state quantity measuring means measures a vehicle group speed passing through the monitoring area as the traffic state quantity,
The traffic flow state determination means is a free flow when the vehicle group speed is equal to or greater than a speed free flow determination threshold value, and a traffic flow when the vehicle group speed is equal to or less than a speed congestion flow determination threshold value. A traffic flow abnormality detection device for judging. Connected to a plurality of vehicle detectors each monitoring a different area, measuring a traffic state quantity in each of the areas;
Determining whether the traffic flow in each of the areas is a congested flow or a free flow based on the measured traffic state quantity;
Determining whether the traffic flow is abnormal based on a combination of the position of the vehicle detector and the determined traffic flow state;
A traffic flow abnormality detection method comprising:

Images