KR20190087276A - System and method for traffic measurement of image based - Google Patents

Abstract

The present invention relates to an image-based traffic amount measurement system capable of correctly measuring a traffic amount regardless of shaking of a camera or a complex traffic environment, and a method thereof. According to the present invention, the image-based traffic amount measurement system comprises: an image acquisition unit acquiring image data of a road; a memory having a traffic amount measurement program using image data embedded therein; and a processor executing the program. The processor sets a plurality of regions in the image data, detects and tracks a moving vehicle to measure a moving traffic amount, sets a partial region for each lane in the image data to estimate a waiting row for each lane.

Description

TECHNICAL FIELD [0001] The present invention relates to an image-

The present invention relates to an image-based real-time traffic intersection traffic measurement system and method.

Conventional image-based traffic volume measurement technology can measure traffic volume assuming that all vehicles move with similar size and flow.

However, since the size and the movement of actual driving vehicles are very diverse, there is a problem in that the accuracy of traffic measurement is deteriorated in an actual traffic situation.

SUMMARY OF THE INVENTION The present invention has been proposed in order to solve the above-mentioned problems, and provides a system and method for measuring traffic volume of an image based on images acquired at a traffic intersection, .

The image-based traffic volume measurement system according to the present invention includes an image acquisition unit for acquiring image data of a road, a memory for storing a traffic volume measurement program using image data, and a processor for executing a program, The moving vehicle is detected and tracked to measure the amount of mobile traffic, and the partial area for each line is set for the image data to estimate the queue for each line.

According to the embodiment of the present invention, it is possible to apply to both unidirectional roads, bidirectional roads, and complex traffic ranges, and it is possible to accurately acquire both traffic volume information by using different measurement algorithms for moving traffic volume and atmospheric traffic volume , It is possible to measure accurate traffic volume even in a camera shake or a complicated traffic environment.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description.

1 is a block diagram illustrating an image-based traffic volume measurement system according to an embodiment of the present invention.
2 is a detailed block diagram of an image-based traffic volume measurement system according to an embodiment of the present invention.
FIG. 3 is an exemplary view showing the measurement of the moving traffic volume according to the embodiment of the present invention.
4 is an exemplary diagram illustrating a queue estimate according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating an example of a result of moving traffic statistics according to an embodiment of the present invention.
6 is a flowchart illustrating an image-based traffic volume measurement method according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, advantages and features of the present invention and methods of achieving them will be apparent from the following detailed description of embodiments thereof taken in conjunction with the accompanying drawings.

The present invention may, however, be embodied in many different forms and should not be construed as being limited to the exemplary embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, And advantages of the present invention are defined by the description of the claims.

It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. &Quot; comprises "and / or" comprising ", as used herein, unless the recited component, step, operation, and / Or added.

Hereinafter, the background of the present invention will be described in order to facilitate the understanding of those skilled in the art, and an embodiment of the present invention will be described.

The real-time traffic measurement system is a system that measures the number of moving vehicles passing through a certain road, range, area, or the number of stalled vehicles staying in real time.

According to the related art, various methods have been proposed to count the number of moving or stopped vehicles. In the past, a traffic measurement technique using infrared rays, a loop sensor, a geomagnetic sensor, or the like has been proposed. However, There is a problem in that the obtained data is simple and it is impossible to confirm whether the data is correct or not.

In recent years, the image sensor performance has been improved and the installation and maintenance cost has become relatively low, so an image based traffic volume measurement system has been proposed.

The image-based traffic volume measurement system according to the related art extracts an area where a lane and a major vehicle flow exist using a canny edge of a vehicle and a lane, calculates a motion history value for a silhouette in the corresponding area, The number of vehicles, the average travel time, and the speed.

However, this method can measure traffic volume on the assumption that all vehicles are of similar size and move in similar flows, but if the vehicle size and movement is very diverse (if there are both very large and slow lorries and fast cars) There is a problem in that it is impossible to estimate an elaborate traffic volume when the vehicles do not keep their own driving lanes correctly or when the traveling direction is various directions.

Further, according to the related art, there is a problem that it is vulnerable to camera shake or a complicated traffic environment due to the use of pixel variation and motion.

In particular, recent traffic measurement systems require not only simple traffic statistics but also violation of traffic laws and traffic accidents within a traffic intersection, and vehicle accidents, it is important to elaborate information about each vehicle.

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-described problems, and it is an object of the present invention to provide a vehicle monitoring system capable of estimating a vehicle queue in an image portion where a distance between vehicles is very narrow, Based traffic volume measurement system and its method that can measure the traffic volume flow based on the traffic volume.

According to the present invention, it is possible to solve the problems of the above-described conventional techniques, such as a low correct rate, difficulty in vehicle type recognition and queue estimation, high cost, and the like, Based on the image analysis, it is possible to measure the stop / move (including direction) traffic volume by traffic type within the traffic range.

1 is a block diagram illustrating an image-based traffic volume measurement system according to an embodiment of the present invention.

The image-based traffic volume measurement system according to the embodiment of the present invention includes an image acquisition unit 100 for acquiring image data of a road, a memory 300 having a traffic volume measurement program using image data, a processor 200 The processor 200 designates a plurality of regions with respect to the image data, measures the amount of mobile traffic by detecting and tracking a moving vehicle, and sets a sub-region for each image data to estimate a line-by-line queue .

The image acquiring unit 100 acquires an image through a camera installed at a higher position than a vehicle passing a traffic intersection and designates a plurality of areas for traffic volume measurement.

At this time, the plurality of areas include a vehicle detection area, a vehicle entry area, a vehicle entry area, and a lane departure partial area for estimating queue-by-lane queue for moving traffic measurement.

The processor 200 measures the amount of moving traffic and acquires the lane, the vehicle type, and the destination direction where the moving vehicle is located.

The processor 200 obtains the vehicle information in the detection area in the rectangular coordinates, and tracks the detected vehicle object in successive frames to detect / track the moving vehicle.

The processor 200 checks whether the vehicle object passes through the vehicle entry area and the vehicle entry area in order, and determines whether the vehicle enters or exits the vehicle.

The processor 200 determines whether or not a vehicle object exists for the predetermined sub-sub-sub-sub-area for estimating the queue-by-sub-queue.

The processor 200 calculates the occupancy rate using the acquired value for the presence or absence of the vehicle object for each sub-region.

FIG. 2 is a detailed block diagram of an image-based traffic volume measurement system according to an embodiment of the present invention, FIG. 3 is an exemplary view illustrating a mobile traffic volume measurement according to an embodiment of the present invention, FIG. Fig.

The direction and number of moving vehicles and the length of vehicle queues are important information for measuring vehicle traffic volume.

2 to 4, an embodiment in which the image-based traffic volume measurement system according to the embodiment of the present invention measures traffic information regarding a moving vehicle and a stationary vehicle in a traffic intersection will be described.

The image acquiring unit 100 includes an image photographing unit 110 and a region designating unit 120.

The image capturing unit 110 acquires a traffic image through a camera installed at a higher position than the vehicle at a traffic intersection and the area designation unit 120 designates a plurality of areas for traffic volume measurement.

Referring to FIG. 3, the area designation unit 120 sets a vehicle detection area 121, a vehicle entry area 122, and a vehicle entry area 123 for measuring the amount of moving traffic.

Referring to FIG. 4, the area designation unit 120 sets a sub-divided sub-area 124 for queue estimation.

The moving traffic measurement unit 210 performs a process of determining a lane, a vehicle type, and a destination direction in which the moving vehicle is located.

The vehicle detecting unit 211 of the moving traffic measuring unit 210 detects the vehicle object based on the image only in the image within the detection area and acquires the detected vehicle object information in the rectangular coordinates.

When the traffic I _{t + 1} corresponding to the second frame ( _{t + 1} ) is acquired, the vehicle tracking unit 212 of the moving traffic measuring unit 210 receives the first frame (I _{t + 1} ) corresponding to the second frame and attempts to detect the image-based vehicle again from the image (I _{t + 1} ) corresponding to the second frame, Combine the two results.

The vehicle classifying unit 213 of the moving traffic measuring unit 210 accumulates the vehicle classification results measured for each frame of the tracked vehicle in the histogram of each vehicle type and transmits the vehicle type results having the most frequent numbers.

The vehicle entry / exit determination unit 214 of the mobile traffic measurement unit 210 determines whether the tracked vehicle object passes first through the vehicle entry area 122 of FIG. 3 and passes through the vehicle entry / exit area 123 of FIG. 3, The end point is checked to determine whether or not the vehicle enters or exits.

Referring to FIG. 3, there is shown a result of vehicle detection, tracking, and determining whether the vehicle is small or large in order to measure moving traffic volume.

Further, it is possible to detect the vehicle flow robust to the noise by judging the vehicle 241 located in the entry area and judging whether the vehicle 241 passes through the entry / exit area (indicated by 242, 243, PASS in FIG. 4) and included in the traffic volume calculation.

The vehicle queue measurement proceeds through a process different from the process performed in the mobile traffic measurement unit 210 described above.

In the case of a moving traffic object, the distance between the vehicle and the vehicle approaches to the camera due to the securing of the safety distance, so that the distance between the vehicles in the image is greatly reduced.

However, when the vehicle is in the waiting state, since the vehicle interval is further awaited, the vehicle interval is narrow, and as shown in the waiting area 301 of FIG. 3, .

Therefore, there is a problem that the vehicle detection does not progress smoothly and the error rate increases and accurate vehicle coefficient is difficult.

According to the embodiment of the present invention, instead of detecting, tracking, and classifying the vehicle for vehicle queue measurement, the queue estimating unit 300 determines whether or not the vehicle presence / ) Of the vehicle.

Referring to FIG. 4, there is shown an example of the partial area setting for each car line, which is indicated by red, orange, blue, and green rectangles sequentially from the first lane to the four lanes.

The line-by-line occupancy calculating unit 222 calculates a occupancy rate by averaging the values for each area by dividing the occupancy by 0 or 1 according to whether or not the vehicle is present in a predetermined discriminating subarea for the queue-by-line queue estimation, The closer the value of the occupancy rate is, the greater the weight is smoothed.

The mobile traffic volume and the queue-specific queue information obtained from the mobile traffic measurement unit 210 and the queue estimation unit 220 are transmitted to the traffic information transmission unit 400. The traffic information transmission unit 400 transmits the traffic information to a necessary place do.

FIG. 5 is a diagram illustrating an example of a result of moving traffic statistics according to an embodiment of the present invention.

FIG. 5 is a view showing a sedan, an SUV, a truck, a compact, a van, and the like of an uphill line UP and a downhill line DOWN according to an embodiment of the present invention. (van), and bus (bus).

6 is a flowchart illustrating an image-based traffic volume measurement method according to an embodiment of the present invention.

The method of measuring an image-based traffic volume according to an exemplary embodiment of the present invention includes a step S610 of obtaining an image of a traffic intersection, a step S620 of measuring a traffic volume by detecting, tracking and classifying a vehicle object S620, And a step S630 of estimating the queue for each line.

In step S610, a traffic image is acquired through a camera installed at a position higher than the vehicle at a traffic intersection, and a plurality of areas for traffic volume measurement are designated.

At this time, the plurality of areas set the vehicle detection area 121, the vehicle entry area 122, and the vehicle entry area 123 as shown in Fig.

Further, as shown in Fig. 4, for the queue estimation, the sub-divided subareas 124 are set.

In step S620, only the image within the vehicle detection area is detected based on the image, and the detected vehicle object information is acquired in rectangular coordinates.

In step S620, when the image I _{t + 1} corresponding to the second frame t + 1 is acquired, the traffic object detected in the first frame t is compared with the image I _{t + 1} ), and an image-based vehicle is detected again at the image (I _{t + 1} ) corresponding to the second frame, the two results are combined, and the traced vehicle is classified to calculate the vehicle result.

In step S620, it is determined whether the tracked vehicle object passes through the vehicle entry area first and then passes through the vehicle entry area.

In step S630, instead of detecting, tracking, and classifying the vehicle as in step S620, it is determined whether or not a vehicle exists in the sub-classified sub-area, and if the vehicle exists in the sub-sub- 0 or 1, and calculate the occupancy rate by averaging the values per area.

Meanwhile, the image-based traffic volume measurement method according to the embodiment of the present invention may be implemented in a computer system or recorded on a recording medium. The computer system may include at least one or more processors, a memory, a user input device, a data communication bus, a user output device, and a storage. Each of the above-described components performs data communication via a data communication bus.

The computer system may further comprise a network interface coupled to the network. A processor may be a central processing unit (CPU), or a semiconductor device that processes instructions stored in memory and / or storage.

Memory and storage may include various forms of volatile or non-volatile storage media. For example, the memory may include ROM and RAM.

Accordingly, the image-based traffic volume measurement method according to an exemplary embodiment of the present invention can be implemented in a computer-executable method. When the image-based traffic volume measurement method according to an embodiment of the present invention is performed in a computer device, computer-readable instructions can perform the measurement method according to the present invention.

Meanwhile, the image-based traffic volume measurement method according to the present invention can be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording media storing data that can be decoded by a computer system. For example, there may be a ROM (Read Only Memory), a RAM (Random Access Memory), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device and the like. The computer-readable recording medium may also be distributed and executed in a computer system connected to a computer network and stored and executed as a code that can be read in a distributed manner.

The embodiments of the present invention have been described above. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

100: image acquiring unit 110:
120: area designation unit 200: processor
210: moving traffic measurement unit 211: vehicle detection unit
212: vehicle tracking unit 213:
214: Vehicle entry / exit determination unit 220:
221: Vehicle presence / absence determination unit for each partial area 222: Vehicle occupancy ratio calculating unit
300: memory 400: traffic information transmission unit

Claims (1)

An image acquiring unit for acquiring image data of a road;
A memory having a traffic volume measurement program using the image data; And
And a processor for executing the program,
Wherein the processor designates a plurality of areas for the image data, measures a moving traffic amount by detecting and tracking a moving vehicle, and sets a sub-area for each of the image data to estimate a queue for each line
Image based traffic volume measurement system.

Images