JP4095411B2 - Traffic flow measuring device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a traffic flow measurement device, and more particularly to a traffic flow measurement image processing device for detecting a state quantity such as a traffic jam in a monitoring range in an automobile traffic flow.
[0002]
[Prior art]
One of the traffic flow measurement methods is to detect the location of an individual vehicle, measure the vehicle speed of the individual vehicle from the amount of movement at a certain time, obtain the average of the individual vehicle speed, and calculate the overall average. By taking this, there was a method of determining the vehicle group speed on the entire road and judging the traffic jam from the vehicle occupancy rate in the lane and the vehicle group speed.
[0003]
However, in this method, it is necessary to recognize the individual vehicle, and there is a problem that the determination accuracy is lowered if the individual vehicle cannot be recognized.
[0004]
In addition, a congestion determination method that does not require recognition of individual vehicles has been proposed (see, for example, Patent Document 1).
However, in this conventional example, since the features in the monitoring image road are extracted using the background image, if a sudden shadow or the like occurs on the road surface, unnecessary feature amounts are detected, which is a major cause of misjudgment. It was.
[0005]
[Patent Document 1]
Japanese Patent Laid-Open No. 10-253649 [0006]
[Problems to be solved by the invention]
Since the conventional traffic congestion judgment method is configured as described above, the speed and the distance between vehicles must be measured from individually recognized vehicles, and the congestion judgment is performed from the traffic density such as the number of vehicles passing per unit time. It is necessary to.
Further, when a plurality of vehicles cannot be recognized and tracked as individual vehicles due to concealment or the like, there is a problem that measurement accuracy is lowered.
And when the method using a background image is used, it has become a cause to the misjudgment of a traffic event by the influence of a shadow.
[0007]
The present invention has been made to solve the above-described problems, and is intended to provide a traffic flow measuring device capable of efficiently measuring a traffic flow even in a situation where an overlap occurs where individual vehicles cannot be recognized. To do.
[0008]
[Means for Solving the Problems]
In the traffic flow measuring apparatus according to the present invention, an image capturing unit that captures an image at a predetermined period, a moving object presence region setting unit that sets a moving object presence region along a moving path of the moving object, and the image capturing unit A moving object existence area image generating means for generating a moving object existence area image from the image captured by the moving object existence area setting means and a moving object existence area preset by the moving object existence area setting means; Road surface luminance change monitoring reference line setting means for determining a road surface luminance change monitoring step line as a road surface luminance change monitoring reference line along a road shape in a moving object existence area set along the moving path of the road surface, and the road surface luminance A road that extracts and outputs a road brightness change on a road brightness change monitoring stepping line as a road brightness change monitoring reference line determined by a change monitoring reference line setting means Brightness change extracting means, and the brightness change in the road brightness change monitoring step as the road brightness change monitoring reference line out of the road brightness change output extracted from the road brightness change extracting means is larger than the other parts in the brightness dispersion Object candidate extraction means for distinguishing and extracting an output of a part whose value is higher than other parts as an object candidate from other parts, and object candidates partially extracted from the road surface luminance change output by the object candidate extraction means Object candidate tracking means for performing a correlation search on a road surface luminance change monitoring step line as a road surface luminance change monitoring reference line is provided .
[0009]
DETAILED DESCRIPTION OF THE INVENTION
Embodiment 1 FIG.
A first embodiment of the present invention will be described with reference to FIGS. FIG. 1 is a block diagram showing the configuration of the traffic flow measuring apparatus according to the first embodiment. FIG. 2 is a plan view showing the moving object existence area set by the moving object existence area setting unit in the first embodiment. FIG. 3 is a plan view showing the road surface luminance change monitoring step line set by the road surface luminance change monitoring step line setting unit according to the first embodiment. FIG. 4 is a curve diagram showing the luminance histogram distribution on the road surface luminance change monitoring step in the first embodiment. FIG. 5 is a flowchart showing a process flow of the object candidate extraction unit in the first embodiment. FIG. 6 is a flowchart showing a process flow of the object candidate tracking unit in the first embodiment. FIG. 7 is a flowchart showing a traffic state determination unit processing flow in the first embodiment.
[0010]
In FIG. 1 showing the configuration of the traffic flow measuring apparatus according to Embodiment 1 of the present invention, an image capturing unit 10 captures an image with a predetermined period by an image sensor such as a monitoring ITV camera, and stores the image as digital data. To do.
The moving object presence area setting unit 11 sets a moving object existence area that requires monitoring on the monitoring road. As shown in FIG. 2, the moving object existence area setting unit 11 sets the moving object existence area (1): MOR and the moving object existence area (2): MOS, and does not change when the camera installation angle is determined. Since this is an area, it is set in advance.
Then, a moving object existence region image generation unit 10A that generates a moving object existence region image from the image picked up by the image pickup unit 10 and the moving object existence region MOR and MOS preset by the moving object existence region setting unit 11 is provided. It is provided on the output side of the image capturing unit 10.
[0011]
The road surface luminance change monitoring step setting unit 12 monitors the road surface luminance change as a reference for monitoring the road surface luminance change in the moving object existing region set by the moving object existing region setting unit 11, that is, along the vehicle movement route in the road lane. Determine the stepping line. As shown in FIG. 3, this step line has a one-pixel width indicated by road surface luminance change monitoring step line (1): BRL and road surface luminance change monitoring step line (2): BRM determined in advance along the lane movement route. It is a line.
[0012]
On the input side of the object candidate extraction unit 13, a road surface luminance change extraction for extracting a luminance histogram distribution as a road surface luminance change on the road surface luminance change monitoring step BRL, BRM set by the road surface luminance change monitoring step line setting unit 12. A portion 13A is provided.
The object candidate extraction unit 13 searches for an object candidate from the luminance histogram distribution on the road surface luminance change monitoring steps BRL and BRM extracted by the road surface luminance change extraction unit 13A.
The object candidate tracking unit 14 searches for the object candidate extracted by the object candidate extracting unit 13 on the road surface for monitoring the luminance change of the road surface using normalized cross-correlation matching, and tracks the object.
The traffic state determination unit 15 excludes road surface structures and shadows from the object candidates tracked by the object candidate tracking unit 14, calculates the object candidate occupation rate and the object average moving speed on the monitored route, and based on the traffic Determine the state.
[0013]
Next, the operation of the object candidate extraction unit 13 will be described with reference to FIGS. 4 and 5.
FIG. 4 shows a luminance histogram distribution on the step lines BRL and BRM set by the road surface luminance change monitoring step line setting unit 12, and FIG. 5 is a processing flow of the object candidate extraction unit 13.
First, a road surface luminance change histogram on the step lines BRL and BRM is generated from the input image by the road surface luminance change extracting unit 13A.
In step S11, the object candidate extraction unit 13 divides the input histogram into several blocks, and calculates a luminance variance value for each block.
In step S12, a block whose block variance value exceeds a certain threshold D is provisionally registered as an object candidate.
In step S13, the presence of an object candidate tracking on the block in the current processing cycle is checked, and if the tracked object is tracking more than two processing cycles, it is excluded from the temporary candidates.
In step S14, the variance value and histogram distribution of the temporarily registered block are stored. The object candidates registered at this time include road surface structures (for example, road surface paint) and shadows.
[0014]
Next, the operation of the object candidate tracking unit 14 will be described with reference to FIG. FIG. 6 is a processing flow of the object candidate tracking unit 14.
In step S21, object candidate information registered in each block is accumulated for the past two processing cycles, and if there are object candidate registrations consecutively in the same block, the variance values are compared, and the block variance value before one processing cycle is determined. If the block distribution value is lower than the current processing cycle, the block one processing cycle before is determined as the tracking block. As a result, it is possible to efficiently register a pattern having a large luminance change in the block.
In step S22, a search is performed using the normalized cross-correlation on the step of the input image using the histogram pattern of the tracking block as a template.
In step S23, a three-dimensional position is calculated from the two-dimensional position of the tracking block.
In step S24, the movement speed of the tracking block is calculated from the movement amount of the three-dimensional position measured in step S23.
[0015]
Next, the operation of the traffic state determination unit 15 will be described with reference to FIG. FIG. 7 is a processing flow of the traffic state determination unit 15.
In step S31, blocks that have not moved the distance of the threshold value L1m in the threshold time T from the tracking initial registration time are excluded from the traffic state determination target as road surface structures or shadow information. When the traffic flow is measured , the stopped object as a measurement target enters a stopped state after passing through a low speed state. Therefore, there is no problem even if an object that does not move from the start of tracking is determined as a road surface structure or a shadow.
In step S32, the block being tracked is classified in lane units, and the average moving speed of the object in the lane is calculated by calculating the block average speed.
In step S33, the blocks being tracked are classified in lane units, and the object candidate occupation ratio on the road surface is calculated from the number of blocks being tracked. For example, if there are 3 steps in one lane and 5 divided blocks per step, the lane is divided into 15 parts, so the occupancy is between 0-100% and about 6.6%. Changes.
In step S34, using the object moving average speed and the object candidate occupancy calculated in steps S32 and S33, if the object moving average speed is lower than the threshold value V1 km / h and the object candidate occupying ratio is larger than O1%, the vehicle is in the lane. Judges that there are many moving objects and that moving objects in the lane are moving slowly, and determines that there is a traffic jam.
[0016]
As described above, according to the first embodiment, since a block having high dispersion is registered and tracked even in a situation where an individual vehicle cannot be specified, a process for specifying the individual vehicle is not required.
In addition, the object tracking is performed including the road surface structure and the shadow. However, since the search method is a correlation process of the one-dimensional direction search of the one-dimensional template, the processing can be performed with a small amount of calculation.
[0017]
Furthermore, in the first embodiment, the number of the step lines BRL, BRM in FIG. 3 is not limited to one in the lane, and the number of the step lines BRL, BRM may be changed as necessary.
In addition, although the steps BRL and BRM in FIG. 3 monitor the change in luminance in units of one pixel width, the widths of the steps BRL and BRM may be increased as long as the processing time is allowed.
Alternatively, the luminance histogram may be created by obtaining the average luminance of the horizontal pixels and projecting it to one pixel width.
[0018]
According to the first embodiment of the present invention, in the traffic flow measuring apparatus that processes an image captured at a predetermined cycle and measures the traffic state of the road, from the image capturing unit 10 that captures the road state at a predetermined cycle. Image capturing means, moving object existence area setting means comprising a moving object existence area setting unit 11 for setting moving object existence areas MOR and MOS along the movement path of the moving object, and image imaging comprising the image imaging part 10 Road surface brightness change monitoring reference comprising road surface brightness change monitoring step lines BRL and BRM for monitoring a change in road surface brightness in an image of the moving object presence area MOR and MOS imaged by the moving object presence area setting unit 11 imaged by the unit Road surface luminance change monitoring reference line setting means comprising a road surface luminance change monitoring step line setting unit 12 for setting a line according to the road shape, and the road surface luminance change An object candidate is extracted by the luminance change in the road surface luminance change monitoring reference line consisting of the road surface luminance change monitoring step lines BRL and BRM set by the road surface luminance change monitoring reference line setting means including the monitoring step line setting unit 12, and this object candidate is extracted. Since the traffic state is determined by tracking the traffic flow, it is possible to provide a traffic flow measuring device that can measure the traffic flow efficiently and accurately even in a situation where overlap occurs where the individual vehicles cannot be recognized.
[0019]
Further, according to the first embodiment of the present invention, in the configuration of the preceding paragraph, the image capturing unit including the image capturing unit 10 that captures an image with a predetermined period, and the moving object existence region MOR along the moving path of the moving object. , A moving object existence area setting means comprising a moving object existence area setting section 11 for setting MOS, an image captured by an image imaging section comprising the image imaging section 10, and a moving object comprising the moving object existence area setting section 11 Moving object existence area image generation means comprising a moving object existence area image generation unit 10A for generating a moving object existence area image from the moving object existence areas MOR and MOS preset by the existence area setting means, and the moving object existence area setting In the moving object existence area MOR, MOS set along the movement path of the moving object by the moving object existence area setting means comprising the unit 11 A road surface luminance change monitoring reference line setting unit including a road surface luminance change monitoring step line setting unit 12 for determining a road surface luminance change monitoring reference line including road surface luminance change monitoring step lines BRL and BRM along the road shape, and the road surface luminance change. Road surface luminance change extraction for extracting the road surface luminance change in the road surface luminance change monitoring reference line consisting of the road surface luminance change monitoring step lines BRL and BRM determined by the road surface luminance change monitoring reference line setting unit consisting of the monitoring step line setting unit 12. Object candidate extraction comprising: a road surface luminance change extracting unit comprising a unit 13A, and extracting a portion having a large luminance change and a high luminance dispersion due to the road surface luminance change extracted from the road surface luminance change extracting unit comprising the road surface luminance change extracting unit 13A Since the object candidate extraction means comprising the unit 14 is provided, even if there is an overlap where the individual vehicles cannot be recognized, It is possible to provide a traffic flow measuring device which can more efficiently accurately measure the flow.
[0020]
Furthermore, according to Embodiment 1 of the present invention, in the configuration of the preceding paragraph, the object candidate extracted by the object candidate extraction unit 13 is correlated with the road surface luminance change monitoring reference line composed of the road surface luminance change monitoring step lines BRL and BRM. Since the object candidate tracking means including the object candidate tracking unit 14 for performing the search is provided, the traffic flow can be measured more efficiently and more accurately even in the situation where the overlap occurs such that the individual vehicles cannot be recognized. A measuring device can be provided.
[0021]
According to the embodiment of the present invention, in the configuration of the preceding paragraph, the traffic condition determination unit that determines the traffic condition within the monitoring range from the output result of the object candidate tracking unit is provided, so that the individual vehicle cannot be recognized. It is possible to provide a traffic flow measuring device that can efficiently measure traffic flow even in a situation where a large amount of overlap occurs and can reliably determine the traffic situation.
[0022]
Embodiment 2. FIG.
A second embodiment of the present invention will be described with reference to FIGS. FIG. 8 is a block diagram showing the configuration of the traffic flow measuring apparatus according to the second embodiment. FIG. 9 is a flowchart showing a processing flow of the stop low speed determination unit in the second embodiment.
In the second embodiment, the configuration other than the specific configuration described here has the same configuration as the configuration in the first embodiment described above, and has the same function. In the drawings, the same reference numerals indicate the same or corresponding parts.
[0023]
FIG. 8 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 2 of the present invention.
In FIG. 8, as in the first embodiment, the image capturing unit 10, the moving object presence area setting unit 11, the road surface luminance change monitoring footline setting unit 12, the object candidate extraction unit 13, the object candidate tracking unit 14, and the traffic state determination A part 15 is provided. And in FIG. 8, the stop low-speed object determination part 16 is provided.
[0024]
Next, the processing flow of the stop low-speed object determination processing 18 will be described with reference to FIG.
In step S41, the block that has been subjected to the tracking process in the object tracking process moves from the tracking start time by a threshold L2m or more, and if the speed is lower than the threshold V2 km / h, it is determined that the object is a low speed moving object.
In step S42, the block that has been tracked in the object tracking process moves beyond the threshold L3m from the start of tracking, and if the speed is less than the threshold V3 km / h, the block is determined to be a stopped object. For example, L2 = 10 m, V2 = 40 km / h, L3 = 10 m, V3 = 5 km / h are set, and a low-speed / stopped object is detected.
In step S44, information on stop in the lane or presence of a low-speed object is set for the lane in which the stop low-speed block exists.
[0025]
As described above, in the second embodiment, the accurate number and position information of the individual vehicles cannot be measured, but it is possible to determine whether or not there is a stopped low-speed object in the lane.
When performing traffic flow measurement, position information of a stopped low-speed object is not important, but information on whether or not a stopped low-speed object exists in the lane is important and necessary. Therefore, it is possible to efficiently determine whether or not there is a stopped low-speed object in the lane with a small amount of calculation.
[0026]
According to the second embodiment of the present invention, in the configuration in the first embodiment, the low-speed moving object and the stop object generated on the road surface luminance change monitoring reference line composed of the road surface luminance change monitoring step lines BRL and BRM are detected. Since the low-speed object determination means comprising the stop low-speed object determination unit 16 is provided, the traffic flow can be measured efficiently and the low-speed object can be detected reliably even in the situation where overlap occurs such that the individual vehicles cannot be recognized. A measuring device can be provided.
[0027]
Embodiment 3 FIG.
A third embodiment of the present invention will be described with reference to FIGS. FIG. 10 is a block diagram showing the configuration of the traffic flow measuring apparatus according to the third embodiment. FIG. 11 is a plan view showing an example of video multiplexing in the third embodiment.
In the third embodiment, the configuration other than the specific configuration described here has the same configuration contents as the configuration in the second embodiment described above, and exhibits the same operation. In the drawings, the same reference numerals indicate the same or corresponding parts.
[0028]
FIG. 10 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 3 of the present invention.
In FIG. 10, as in the second embodiment, the image capturing unit 10, the moving object presence area setting unit 11, the road surface luminance change monitoring footline setting unit 12, the object candidate extraction unit 13, the object candidate tracking unit 14, and traffic state determination Unit 15 and stop low-speed object determination unit 16 are provided. In FIG. 10, a video multiplexing unit 17 that multiplexes videos from a plurality of ITV cameras is provided.
[0029]
Next, the video multiplexing unit 17 will be described with reference to FIG. FIG. 11 shows an example of a video obtained by dividing and multiplexing four videos.
Thereby, the traffic flow measurement of four ITV cameras can be performed with one traffic jam measuring device.
[0030]
As described above, in the third embodiment, traffic flow measurement of a plurality of ITV camera images can be performed simultaneously with one input image, and the traffic flow measurement can be effectively used while reducing costs.
[0031]
Further, since the video multiplexing unit 17 is a screen other division method, the image size becomes 1/4. However, the video multiplexing unit 17 may be a screen time division method instead of the screen multi-division method.
This is, for example, to switch and input images from a plurality of ITV cameras for each processing cycle, and measure the traffic flow of the images from the plurality of ITV cameras with one device.
[0032]
According to the third embodiment of the present invention, in the configuration of the second embodiment, the video screen multiplexing means including the video multiplexing unit 17 is provided, and a plurality of videos are multiplexed and inputted, and a plurality of road traffic videos are simultaneously input. In addition to providing a traffic flow measurement device that can efficiently measure traffic flow and accurately grasp the traffic situation from multiple images even in situations where overlap occurs where individual vehicles cannot be recognized. be able to.
[0033]
Embodiment 4 FIG.
A fourth embodiment of the present invention will be described with reference to FIGS. FIG. 12 is a block diagram showing the configuration of the traffic flow measuring apparatus according to the fourth embodiment. FIG. 13 is a flowchart showing a process flow of the background update speed control unit in the fourth embodiment.
In the fourth embodiment, the configuration other than the specific configuration described here has the same configuration as the configuration in the second embodiment described above, and exhibits the same function. In the drawings, the same reference numerals indicate the same or corresponding parts.
[0034]
FIG. 12 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 4 of the present invention.
In FIG. 12, as in the second embodiment, the image capturing unit 10, the moving object presence area setting unit 11, the road surface luminance change monitoring footline setting unit 12, the object candidate extraction unit 13, the object candidate tracking unit 14, the traffic state determination Unit 15 and stop low-speed object determination unit 16 are provided. And in FIG. 12, the background update speed control part 18 which adjusts the update speed of background update is provided.
[0035]
Next, the processing flow of the background update speed control unit 18 will be described with reference to FIG.
In step S51, a background difference image around the block determined as a road surface structure or a shadow by the traffic state determination unit is generated.
In step S52, from the background difference image generated in step S51, the ratio of the binary silhouette obtained by binarizing the background difference image to the entire image is derived to calculate the binary silhouette occupancy.
In step S53, if the occupancy rate is greater than or equal to the threshold value 02 based on the occupancy rate calculated in step S52, it is determined that the current input image has a large difference from the background, the background update speed parameter is adjusted, and the background is increased at high speed. Control to update. If it is less than the threshold value 02, the background update speed parameter is returned to the original value, and the readjustment is performed so that the background is updated at the normal speed.
[0036]
As described above, in the fourth embodiment, in a method for obtaining a binary silhouette image obtained by binarizing a background difference image using a background difference , a shadow often causes a fatal false detection. By controlling the background update speed in response to the desire to quickly blend into the background , the shadow blends into the background faster than usual, and the shadow generated in the binary silhouette image obtained by binarizing the background difference image Less influence.
Therefore, by adding this function to an apparatus that uses a binary silhouette image obtained by binarizing the background difference image, it is possible to reduce the cause of erroneous detection of shadows.
[0037]
According to the fourth embodiment of the present invention, in the configuration of the second embodiment, the background image update unit of the background image is provided, and the background update of the background image update unit is performed using the extraction result of the extracted object candidate. Since the background update speed control means comprising the background update speed control unit 18 for controlling the speed is provided, traffic flow can be measured efficiently even in the situation where overlap occurs such that individual vehicles cannot be recognized, and errors due to background It is possible to provide a traffic flow measuring device that can accurately eliminate detection.
[0038]
In the embodiment according to the present invention, even in a situation where concealment of vehicles occurs continuously and individual vehicles cannot be recognized, what corresponds to the space occupancy and vehicle group speed is obtained at high speed, and traffic conditions on the road It is an object to provide a traffic event determination method using image processing that automatically and efficiently evaluates and obtains high traffic event determination accuracy without being affected by a shadow.
[0039]
In the embodiment according to the present invention, even in a camera image in which an overlap occurs such that individual vehicles cannot be recognized in traffic flow measurement using an ITV camera, the traffic flow can be efficiently processed only by specifying the feature of the road shape. A traffic flow measuring device capable of measuring is provided.
[0040]
According to the embodiment of the present invention, an image is captured at a predetermined cycle, a brightness distribution histogram along the path of the moving object is created from the captured image, and a block having a high block variance value is normalized using cross-correlation. By tracking and tracking, it is possible to efficiently obtain the object occupancy rate and the object moving average speed in the lane even in the situation where the individual vehicle cannot be recognized, and it is possible to measure traffic events such as stop, low speed and traffic jam.
[0041]
【The invention's effect】
According to the present invention, of the road surface luminance change output extracted from the road surface luminance change extracting means, the luminance change is larger than the other portions in the road surface luminance change monitoring step as the road surface luminance change monitoring reference line, and the luminance dispersion value is other than Overlapping that makes it impossible to recognize individual vehicles by distinguishing and extracting the output of the part higher than the part from other parts as object candidates and performing a correlation search on the road surface brightness change monitoring reference line as the road surface brightness change monitoring reference line It is possible to provide a traffic flow measuring apparatus that can accurately track an object candidate and efficiently measure traffic flow even in a situation where the occurrence of the traffic occurs.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 1 of the present invention.
FIG. 2 is a plan view showing a moving object existence area set by a moving object existence area setting unit according to the first embodiment of the present invention.
FIG. 3 is a plan view showing a road surface luminance change monitoring step line set by a road surface luminance change monitoring step line setting unit according to Embodiment 1 of the present invention;
FIG. 4 is a curve diagram showing a luminance histogram distribution on a road surface luminance change monitoring step according to the first embodiment of the present invention.
FIG. 5 is a flowchart showing a processing flow of an object candidate extraction unit in Embodiment 1 according to the present invention.
FIG. 6 is a flowchart showing a process flow of an object candidate tracking unit in the first embodiment according to the present invention.
FIG. 7 is a flowchart showing a traffic state determination unit processing flow according to the first embodiment of the present invention.
FIG. 8 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 2 of the present invention.
FIG. 9 is a flowchart showing a processing flow of a stop low speed determination unit in Embodiment 2 according to the present invention.
FIG. 10 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 3 of the present invention.
FIG. 11 is a plan view showing an example of video multiplexing in the third embodiment according to the present invention. .
FIG. 12 is a block diagram showing a configuration of a traffic flow measuring apparatus according to Embodiment 4 of the present invention.
FIG. 13 is a flowchart showing a process flow of a background update speed control unit in Embodiment 4 according to the present invention.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 10 Image pick-up part, 11 Moving object presence area setting part, 12 Road surface luminance change monitoring footline setting part, 13 Object candidate extraction part, 14 Object candidate tracking part, 15 Traffic state determination part, 16 Stop low-speed object determination part, 17 Image | video Multiplexer, 18 background update rate controller.

Claims (5)

Image capturing means for capturing an image at a predetermined period, moving object presence area setting means for setting a moving object presence area along a moving path of the moving object, an image captured by the image capturing means, and the presence of the moving object Moving object existence area image generation means for generating a moving object existence area image from a moving object existence area preset by the area setting means, and movement set along the movement path of the moving object by the moving object existence area setting means a road surface brightness change monitor reference line setting means for determining a road surface brightness change monitoring stepping lines as road surface brightness change monitor baseline along the road shape of the object exists in the area, determined by the road surface brightness change monitoring reference line setting means and a road surface brightness change extraction means for extracting output the road surface brightness changes in the road surface brightness change monitoring stepping lines as road surface brightness change monitor reference line, the path The output of the road surface brightness variation road surface brightness change brightness change in the monitoring stepping line is higher large luminance variance values than other portions than the other portions portions as the monitoring reference line of the road surface brightness change output which is extracted from the luminance change extraction means Object candidate extracting means for distinguishing and extracting from the other parts as object candidates, and the road surface brightness as the road brightness change monitoring reference line using the object candidates partially extracted from the road brightness change output by the object candidate extracting means in change monitor stepping line characterized by providing the object candidate tracking means for performing a correlation search transportation flow measuring device. The traffic flow measuring device according to claim 1 , further comprising a traffic state determination unit that determines a traffic state within a monitoring range from an output result of the object candidate tracking unit. According to claim 1 or 2, characterized in that a stop slow object determination means for performing a detection of the low-speed moving object and stationary object generated in the road surface brightness change monitoring stepping line as the road surface brightness change monitor baseline Traffic flow measuring device. The traffic flow measuring device according to any one of claims 1 to 3, further comprising a video screen multiplexing device, wherein a plurality of videos are multiplexed and input, and a plurality of road traffic images are simultaneously measured. . A background update speed control means for controlling a background update speed of the background image update means by using a background image update means for a captured image and using an extraction result of an extracted object candidate is provided. The traffic flow measuring device according to any one of claims 1 to 4 .

Images