JP2001076291A - Traffic measurement system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a traffic measurement system capable of surely obtaining traffic data at an investigation object spot by investigating traffic without requiring manual work and without having time restriction. SOLUTION: The traffic measurement system picks up the image of a prescribed investigation object area 10 by an image pickup means 2, analyzes an image pickup signal outputted from the means 2 by an image analytic means to identify a pedestrian within the area 10, and judges the number of pedestrians 20 by a traffic judging means to automatically investigate and measure the traffic in the area 10 to reliably obtain data on the traffic at a place to be an investigation object without requiring manual work. Thus investigation extending a long period can be executed without regard to a time band and the restriction o investigating spot is reduced, thereby traffic can efficiently be investigated.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention analyzes an image obtained by imaging a specific investigation target area, recognizes a pedestrian in the investigation target area, and measures a traffic volume of the person in the investigation target area. It relates to a quantity measuring system.

[0002]

2. Description of the Related Art Conventionally, when investigating the traffic volume of a person at a certain point, an investigator is placed at or near the point to be inspected, and the number of passers visually observed by the inspector is counted. Investigation methods, such as going, are commonly used.

[0003]

Since the conventional traffic volume survey has been conducted as described above, it is difficult to conduct continuous long-term or long-term surveys, and it is difficult to obtain detailed traffic volume data. There was a problem that there is. Further, it is difficult to increase the number of survey points in terms of costs such as labor costs, and there is also a problem that it is difficult to obtain traffic data at multiple points at the same date and time.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and a traffic amount survey can be performed without human intervention and without any time restrictions, and traffic volume data at a survey target point can be reliably obtained. It is intended to provide a quantity measuring system.

[0005]

According to the present invention, there is provided a traffic amount measuring system which captures an image of a predetermined investigation area and outputs an imaging signal, and an image of the investigation area based on the imaging signal. An image analyzing means for analyzing and identifying an image portion of a passerby passing through the investigation target area from an image of the entire investigation target area; and determining the number of persons from the image portion of the passerby identified by the image analysis means, Traffic amount determining means for accounting as a person. As described above, in the present invention, a predetermined investigation target area is imaged by the imaging means, and an imaging signal output from the imaging means is analyzed by the image analysis means to identify a pedestrian in the investigation target area, and The traffic volume in the surveyed area can be obtained without any human intervention because the traffic volume in the surveyed area can be automatically surveyed and measured by judging the number of In addition, a long-term survey can be conducted regardless of the time zone, and there are few restrictions on survey points, so that an efficient traffic volume survey can be conducted.

In the traffic amount measuring system according to the present invention, the traffic amount determining means may classify the image of the survey target area into a predetermined number and set each of the divided areas as a divided area, if necessary. The reference area for the number of passers is set for each of the divided areas, the area and the center of gravity of the image portion of the passer in the survey target area are obtained, and the reference area of the divided area where the center of gravity is located and the passerby The number of passers is determined by comparing and comparing the area of the image part with the area of the image part of the passer to the reference area. As described above, in the present invention, a predetermined number of divided areas are set for the image of the investigation target area, a reference area for determining the number of passers is set for each divided area, and the area is compared with the area of the image portion of the passerby. By determining the number of passers-by, the difference in the size of passers-by caused by the difference in the distance and angle from the imaging means at each position of the survey target area is reflected in the reference area for each divided area, and Appropriate number of people can be determined, and the number of pedestrians can be accurately grasped with less erroneous determination of the number of people.

Further, in the traffic amount measuring system according to the present invention, the traffic amount determining means may recognize the image every time the traffic amount determining means recognizes that the position of the center of gravity of the image portion of the traffic person is within a predetermined divided area. The area value of the part is acquired as the reference area calculation area data of the predetermined divided area, and the reference area calculation area data acquisition operation is performed for all the divided areas to obtain at least a predetermined number or more of the reference area calculation area data. After performing the above, a predetermined number is extracted from the smaller area among the plurality of reference area calculation area data in each of the divided areas, and an average value of the extracted predetermined number of reference area calculation area data is calculated for each of the divided areas. It is calculated and set as the reference area of each divided area.

As described above, according to the present invention, the area value of the image portion of the passerby is given as the area data for calculating the reference area of the divided region with respect to the divided region having the center of gravity of the image portion of the passerby. , By setting a reference area for each of the divided areas by calculating a predetermined number of average values of the reference area calculation area data provided for each of the divided areas and using the average value as the reference area of each of the divided areas. No work such as calibration or calibration is required, an appropriate reference area can be automatically set as it is after installation, saving labor and providing an accurate reference area for one person in each sectioned area. And the number of passers can be determined more accurately.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A traffic measurement system according to one embodiment of the present invention will be described below with reference to FIGS. FIG. 1 is a block diagram of the traffic measurement system according to the present embodiment, FIG. 2 is an explanatory diagram of a captured image of a survey target area and an explanatory diagram of an imaging state in the traffic measurement system according to the present embodiment, and FIG. Is a reference area determination operation flowchart in the traffic amount measurement system according to the first embodiment, and FIG. 4 is a traffic amount determination operation flowchart in the traffic amount measurement system according to the present embodiment.

In each of the drawings, a traffic amount measuring system 1 according to the present embodiment includes a camera section 2 as an image pickup means for picking up an image of a predetermined investigation target area 10 and outputting an image pickup signal. The image of the target area 10 is analyzed, and the target area 1 is selected from the entire image of the target area 10.
An image analyzing means 3 for identifying an image portion of the passer 20 passing through 0; a traffic amount determining means 4 for judging the number of persons from the image portion of the passer 20 identified by the image analyzing means 3 and counting the number as the number of passers; It is a structure provided with.

As shown in FIG. 2, the camera section 2 is arranged above a vending machine 40 arranged beside the sidewalk 30 so that the imaging direction is directed toward the sidewalk 30.
In the case of (1), a structure is adopted in which the area ahead of the vending machine 40 is set as the investigation target area 10 and the pedestrians 20 passing therethrough are imaged.

The traffic amount judging means 4 divides the image of the survey target area 10 into nine equal parts and sets each of the divided areas as the divided areas 10a to 10i. Judgment condition setting means 4a for setting a reference area for judging the number of passers; image feature calculating means 4b for obtaining the area and the center of gravity of the image portion of a passer in the investigation target area; A number-of-passengers judging means 4c for comparing and comparing the reference area with the area of the image portion of the passerby and judging the number of passers-by from the ratio of the area of the image portion of the passer to the reference area; Means 4d for storing values such as the number of persons and the number of persons passing therethrough, and a traffic amount counting means 4 for calculating the number of persons passing through the survey target area 10 from the number of persons passing each of the stored divided areas. A configuration including and.

Next, a reference area determination operation and a traffic amount determination operation of the traffic amount measuring system according to the present embodiment based on the above configuration will be described with reference to flowcharts shown in FIGS. 3 and 4, respectively. FIG. 3 shows the reference area determination operation.
As shown in the flowchart of FIG. 1, first, the camera unit 2 captures an image of the investigation target area 10 to output an imaging signal.
This imaging signal is input to the image analysis means 3 (Step 101). When a passerby 20 passes through the survey area 10, the passerby 20 is also imaged by the camera unit 2. The image of the investigation target area 10 input as the image pickup signal is analyzed by the image analysis means 3, and an image portion of the passer-by 20 is identified from the entire image (step 102).

Further, based on the identified image portion of the pedestrian 20, the image feature calculating means 4 of the traffic amount determining means 4
In step b, the area of the image portion of the passerby 20 and the position of the center of gravity are calculated (step 103). And the output passerby 2
The determination condition setting unit 4a determines whether the position of the center of gravity of the image portion 0 is present in any of the divided areas of the investigation target area 10 (step 104), and the image of the passer 20 is determined for the predetermined divided area determined here. The area value of the portion is temporarily stored in the storage unit 4d as area data for calculating the reference area of the divided area (step 105).

After this step 105, has a predetermined period of time long enough to acquire and store at least n or more reference area calculating area data in all the divided areas 10a to 10i passed? It is determined whether or not a predetermined time has elapsed (step 106).
Extract n pieces from the smaller area (step 107),
The average value of the extracted n reference area calculation area data is calculated for each of the divided areas, set as the reference area of each of the divided areas, and stored in the storage unit 4d (step 108). After setting and storing the reference areas for all the divided areas 10a to 10i, a series of processing is ended. On the other hand, if the predetermined time has not elapsed in step 106, the process returns to step 101 and repeats the above-described processing for storing the area value of the passerby image portion for each divided area from the imaging (steps 101 to 105). A plurality of reference area calculation area data is acquired and stored in each of the divided areas.

As for the traffic amount determination operation, as shown in the flowchart of FIG. 4, first, the camera unit 2 captures an image of the investigation target area 10 to output an imaging signal. (Step 1
11). When a passerby 20 passes through the survey area 10, the passerby 20 is also imaged by the camera unit 2. The image of the survey target area 10 input as the imaging signal is analyzed by the image analysis means 3 to identify the image portion of the passer-by 20 from the entire image (step 112), and whether or not the passer-by 20 exists. Is determined (step 113). Passengers 20
Is present and the image portion of the passerby 20 is identified, the area of the image portion of the passerby 20 is determined by the image feature calculation means 4b of the traffic amount determination means 4 based on the image portion of the passerby 20. , And the position of the center of gravity are calculated (step 11).
4). On the other hand, if the image portion of the passerby 20 is not identified and the presence of the passerby 20 cannot be confirmed, the survey target area 1
The number of passers within 0 is determined to be 0, and this value is stored as the number of stayers in the investigation target area 10 at the time of the current imaging (step 115).

After step 114, the number-of-parts determining means 4c determines which of the divided areas of the survey area 10 has the calculated center of gravity of the image of the passerby 20 (step 116). The area of the image portion of the passer-by 20 is compared with the reference area of the divided area for the determined predetermined divided area, and the number of persons is determined. Is stored in the storage means 4d (step 117). Even when there are a plurality of image portions of the passerby 20 and each center of gravity is located in each of the plurality of divided areas, the number of passers is similarly determined and stored for each of the divided areas.

After step 117, the total of the number of passing persons stored for all the divided areas 10a to 10i is obtained, and stored in the storage means 4d as the number of persons staying in the survey target area 10 at the time of the current imaging (step 118). The number of persons staying in the investigation area 10 at the time of the current imaging stored in the storage means 4d in the step 118 or the step 115 is compared with the number of persons staying in the investigation area 10 at the time of the previous imaging stored in advance, It is determined whether the number of persons staying in the current area is smaller than the number of persons staying in the previous area (step 119).

If the current number is smaller than the previous number, the difference is obtained and counted as the number of persons who have passed through the survey target area (step 120). Conversely, if the current number of persons is greater than or equal to the previous number, it is determined that there are no passers-by that have passed the investigation target area, and the number of staying persons in the investigation target area 10 at the time of this imaging is newly determined. Step 111 is stored in the storage unit 4d as the last time.
And the above-described processing is repeated (steps 111 to 11).
8).

After counting the number of persons who have passed in the step 120, it is determined whether or not the imaging of the investigation area 10 and the input of the imaging signal are continued (step 1).
21) If it has been continued, the number of staying persons in the investigation target area 10 at the time of the current imaging is set as a new previous time and stored in the storage unit 4d.
Then, the process returns to the step 111 and the above processes are repeated (steps 111 to 120), and if not continued, a series of processes is ended.

As described above, in the traffic measurement system according to the present embodiment, the survey target area 10 is
The image signal output from the camera unit 2 is analyzed by the image analysis means 3 and the pedestrian 2 in the investigation area 10 is
0 is identified, and the number of passers 20 is determined by comparing the area of the image portion of the passers-by 20 with the reference area.
Appropriate number of persons can be determined for each of the divided areas while avoiding the influence of the difference in the distance and angle with the camera unit 2 at each position of the survey target area 10, and the data of the traffic volume can be reliably obtained without human intervention. In addition, efficient traffic volume surveys can be conducted. Further, since a predetermined number of average values are obtained from the plurality of reference area calculation area data previously given to each of the divided areas 10a to 10i and used as the reference area of each of the divided areas, adjustment and calibration of the reference area setting are performed. Work is unnecessary, an appropriate reference area can be automatically set, labor can be saved, and more accurate judgment can be made by reducing errors in the number of persons judgment.

In the traffic volume measuring system according to the above-described embodiment, at the time of the reference area determination operation, a process of obtaining the reference area after a predetermined time has elapsed from the start of the acquisition and storage of the reference area calculation area data. The configuration is not limited to this, and after starting the acquisition and storage of the reference area calculation area data, it is determined whether or not at least n or more reference area calculation area data has been acquired and stored in each of the divided areas 10a to 10i. If at least n or more are stored, the process proceeds to the next step. If not, at least n is obtained and the reference area calculation area data is acquired.
It is also possible to adopt a configuration in which the processing is returned to the first step of each processing to be stored and the processing is repeated, and it is possible to shift from the processing of acquiring and storing the area data for reference area calculation to the next processing of obtaining the reference area in a shorter time, The storage area of the storage means can be further reduced, and the processing can be made more efficient.

In the traffic amount measuring system according to the embodiment, the image of the survey target area 10 is divided into nine equal parts by the judgment condition setting means 4a of the traffic amount judgment means 4, and each of the divided images is divided into nine parts. Division areas 10a-1
Although the configuration is set as 0i, the present invention is not limited to this, and the number of divisions as the divided areas may be another value, and the divided areas do not necessarily have to be the same size.
It is also possible to adopt a configuration in which the size of the region is made different depending on the distance or angle from the camera and in consideration of the setting of the reference area.

[0024]

As described above, according to the present invention, a predetermined investigation target area is imaged by the imaging means, and an imaging signal output from the imaging means is analyzed by the image analysis means, and the traffic in the investigation target area is analyzed. By identifying people and determining the number of passers by the traffic amount judging means, it is possible to automatically investigate and measure the traffic volume in the survey target area. Can be obtained reliably, a long-term survey can be conducted regardless of time zone, and there is little restriction on survey points, so that an effective traffic volume survey can be performed.

Further, according to the present invention, a predetermined number of divided areas are set for the image of the investigation target area, and a reference area for determining the number of passers is set for each of the divided areas so that the area of the image portion of the passerby is reduced. By comparing the number of passers-by, the difference in the size of passers-by caused by the difference in the distance and angle from the imaging means at each position of the survey target area is reflected in the reference area of each divided area, The appropriate number of persons can be determined for each area, and the number of erroneous judgments of the number of persons can be reduced, and the number of passing persons can be accurately grasped.

Further, according to the present invention, the area value of the image portion of the passerby is given as the area data for calculating the reference area of the segmented region with respect to the segmented region having the center of gravity of the image portion of the passerby. , By setting a reference area for each of the divided areas by calculating a predetermined number of average values of the reference area calculation area data provided for each of the divided areas and using the average value as the reference area of each of the divided areas. No work such as calibration or calibration is required, an appropriate reference area can be automatically set as it is after installation, saving labor and providing an accurate reference area for one person in each sectioned area. This has the effect that the number of passing passengers can be determined more accurately by reducing the number of passengers.

[Brief description of the drawings]

FIG. 1 is a block diagram of a traffic measurement system according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram of a captured image of an investigation target area and an explanatory diagram of an imaging state in the traffic amount measurement system according to the embodiment of the present invention.

FIG. 3 is a flowchart of a reference area determination operation in the traffic measurement system according to one embodiment of the present invention.

FIG. 4 is a flowchart of a traffic amount determination operation in the traffic amount measurement system according to the embodiment of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Traffic amount measurement system 2 Camera part 3 Image analysis means 4 Traffic amount determination means 4a Determination condition setting means 4b Image feature calculation means 4c Number of people determination means 4d Storage means 4e Traffic amount counting means 10 Survey area 10a-10i Division area 20 Traffic area Person 30 sidewalk 40 vending machine

Claims (3)

[Claims] An imaging unit configured to image a predetermined investigation target area and output an imaging signal; analyzing an image of the investigation target area based on the imaging signal; Image analyzing means for identifying an image portion of a passerby passing through, and a traffic amount determining means for judging the number of persons from the image portion of the passerby identified by the image analyzing means and accounting as a passer, Traffic volume measurement system. 2. The traffic volume measurement system according to claim 1, wherein the traffic volume determination unit divides the image of the investigation target area into a predetermined number and sets each of the divided areas as a divided area. The reference area for the number of passers is set for each section area, the area and the center of gravity of the image portion of the passer in the survey target area are obtained, and the reference area of the section area where the center of gravity is located and the image of the passer A traffic amount measurement system, wherein the number of passers is determined based on a ratio of an area of an image portion of the passer to the reference area by comparing and contrasting the area of the portion. 3. The traffic amount measuring system according to claim 2, wherein the traffic amount determination means recognizes that the position of the center of gravity of the image portion of the passerby is within a predetermined divided area. Is obtained as reference area calculation area data of the predetermined divided area, and the reference area calculation area data obtaining operation is performed until at least a predetermined number or more of reference area calculation area data is obtained for all the divided areas. After performing, a predetermined number is extracted from a smaller area among a plurality of reference area calculation area data in each of the divided areas, and an average value of the extracted predetermined number of reference area calculation area data is calculated for each of the divided areas. A traffic volume measurement system, wherein each of the divided areas is set as a reference area.