WO2016145626A1

WO2016145626A1 - Traffic abnormity detection method and device, and image monitoring system

Info

Publication number: WO2016145626A1
Application number: PCT/CN2015/074449
Authority: WO
Inventors: 谭志明; 杨兵兵; 伍健荣
Original assignee: 富士通株式会社; 谭志明; 杨兵兵; 伍健荣
Priority date: 2015-03-18
Filing date: 2015-03-18
Publication date: 2016-09-22
Also published as: CN106796754A

Abstract

A traffic abnormity detection method and device, and an image monitoring system. The traffic abnormity detection method comprises: within a period of time, setting a passing rule for a monitoring region divided into a plurality of sub-regions according to traffic information; detecting and tracking a target object based on an obtained video to obtain a movement track of the target object within the period of time; and determining whether a traffic abnormity occurs to the target object within the period of time according to the passing rule and the movement track. Therefore, the present invention can be applied to more traffic scenes, and aims at more traffic abnormity types, and has a simple implementation algorithm, can be applied to real-time monitoring and has very high detection precision.

Description

Traffic anomaly detection method, device and image monitoring system

Technical field

The present invention relates to the field of video image monitoring technologies, and in particular, to a traffic anomaly detection method and apparatus, and a video monitoring system.

Background technique

With the rapid increase of motor vehicles, some abnormal traffic conditions (such as traffic accidents, traffic jams, traffic violations, etc.) often occur. Anomaly detection techniques are used to detect the abnormal traffic conditions; these abnormal traffic conditions are difficult to detect using conventional traffic equipment (eg, coil detectors, etc.).

Currently, more and more surveillance cameras are being used to monitor traffic conditions.

It should be noted that the above description of the technical background is only for the purpose of facilitating a clear and complete description of the technical solutions of the present invention, and is convenient for understanding by those skilled in the art. The above technical solutions are not considered to be well known to those skilled in the art simply because these aspects are set forth in the background section of the present invention.

Summary of the invention

However, the inventor has found that in the prior art, when the video acquired by the camera is used for anomaly detection, it can only be used for a limited number of scenarios, and has a defect that the application scenario is not extensive enough and the detection precision is not high enough.

Embodiments of the present invention provide a traffic anomaly detection method and apparatus, and a video monitoring system. It is expected to be applicable to all traffic scenarios and to all types of traffic anomalies with high detection accuracy.

According to a first aspect of the embodiments of the present invention, a traffic anomaly detection method is provided, where the traffic anomaly detection method includes:

Setting a pass rule for a monitored area divided into a plurality of sub-areas according to traffic information for a period of time;

Detecting and tracking the target object based on the obtained video, and acquiring a motion trajectory of the target object in the period of time;

And determining, according to the pass rule and the motion trajectory, whether a traffic abnormality occurs in the target object during the period of time.

According to a second aspect of the embodiments of the present invention, a traffic abnormality detecting apparatus is provided, and the traffic abnormality detecting apparatus includes:

The rule setting unit sets a pass rule for the monitoring area divided into the plurality of sub-areas according to the traffic information for a period of time;

a detecting and tracking unit, detecting and tracking the target object based on the obtained video, and acquiring a motion track of the target object in the period of time;

The result determining unit determines whether the target object has a traffic abnormality within the period of time according to the pass rule and the motion trajectory.

According to a third aspect of the embodiments of the present invention, an image monitoring system is provided, including:

a camera that captures a video of the surveillance area;

The traffic anomaly detecting device as described above.

According to still another aspect of an embodiment of the present invention, a computer readable program is provided, wherein when the program is executed in an image monitoring device, the program causes a computer to perform a traffic abnormality as described above in the image monitoring device Detection method.

According to still another aspect of an embodiment of the present invention, a storage medium storing a computer readable program, wherein the computer readable program causes a computer to execute a traffic anomaly detecting method as described above in an image monitoring device.

The beneficial effects of the embodiment of the present invention are: setting a pass rule for a monitoring area divided into a plurality of sub-areas according to traffic information for a period of time; detecting and tracking the target object based on the obtained video, acquiring the target object in the a motion trajectory for a period of time; and determining whether the target object has a traffic anomaly during the period of time according to the pass rule and the motion trajectory. Therefore, it can be applied to more traffic scenarios and to more types of traffic anomalies; in addition, the algorithm is simple, can be used for real-time monitoring and has high detection accuracy.

Specific embodiments of the present invention are disclosed in detail with reference to the following description and the drawings, in which <RTIgt; It should be understood that the embodiments of the invention are not limited in scope. The embodiments of the present invention include many variations, modifications, and equivalents within the scope of the appended claims.

Features described and/or illustrated with respect to one embodiment may be used in one or more other embodiments in the same or similar manner, in combination with, or in place of, features in other embodiments. .

It should be emphasized that the term "comprising" or "comprises" or "comprising" or "comprising" or "comprising" or "comprising" or "comprises"

DRAWINGS

Many aspects of the invention can be better understood with reference to the following drawings. The components in the figures are not drawn to scale, but only to illustrate the principles of the invention. In order to facilitate the illustration and description of some parts of the invention, the corresponding parts in the figures may be enlarged or reduced.

Elements and features described in one of the figures or one embodiment of the invention may be combined with elements and features illustrated in one or more other figures or embodiments. In the accompanying drawings, like reference numerals refer to the

1 is a schematic diagram of a traffic anomaly detection method according to an embodiment of the present invention;

2 is another schematic diagram of a traffic anomaly detection method according to an embodiment of the present invention;

3 is a schematic diagram of a monitoring area corresponding to a camera according to an embodiment of the present invention;

4 is a schematic diagram of attributes of a sub-area according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a monitoring area divided into a plurality of sub-areas according to an embodiment of the present invention; FIG.

6 is a schematic diagram of a plurality of sub-areas defined in an embodiment of the present invention;

7 is a schematic diagram of target object detection according to an embodiment of the present invention;

8 is a schematic diagram of attributes of a target object according to an embodiment of the present invention;

9 is a schematic diagram of a traffic anomaly detecting apparatus according to an embodiment of the present invention;

FIG. 10 is another schematic diagram of a traffic abnormality detecting apparatus according to an embodiment of the present invention; FIG.

FIG. 11 is a schematic diagram showing the structure of an image monitoring apparatus according to an embodiment of the present invention.

detailed description

The foregoing and other features of the present invention will be apparent from the The specific embodiments of the present invention are disclosed in the specification and the drawings, which are illustrated in the embodiment of the invention The invention includes all modifications, variations and equivalents falling within the scope of the appended claims.

Example 1

Embodiments of the present invention provide a traffic anomaly detection method, which is applied to an image monitoring device. 1 is a schematic diagram of a traffic anomaly detection method according to an embodiment of the present invention. As shown in FIG. 1, the method includes:

Step 101: Set a monitoring area divided into a plurality of sub-areas according to traffic information for a period of time Line rule

Step 102: Detecting and tracking a target object based on the obtained video, and acquiring a motion trajectory of the target object in the period of time;

Step 103: Determine, according to the pass rule and the motion track, whether a traffic abnormality occurs in the target object during the period of time.

In this embodiment, the detection of traffic anomalies can be performed based on the video obtained by the camera. The monitoring area may be statically divided into a plurality of sub-areas in advance, for example, may be pre-divided according to traffic signs (such as a left turn mark, a straight line mark, a zebra line, etc.); or the image may be detected by the video according to the video, and then detected according to the detection. The results are divided. The embodiments of the present invention do not limit the specific implementation of the area division.

2 is another schematic diagram of a traffic anomaly detection method according to an embodiment of the present invention. As shown in FIG. 2, the method includes:

Step 201: Divide the monitoring area into multiple sub-areas;

Step 202: Set a pass rule for the monitoring area according to the traffic information for a period of time;

Step 203: Detect and track the target object based on the obtained video;

Step 204: Acquire a motion track of the target object in the period of time;

Step 205, it is determined whether the motion trajectory in the period of time meets the pass rule; if yes, step 206 is performed; if not, step 207 is performed;

Step 206: Determine that the target object has normal traffic during the period of time;

Step 207: Determine that the target object is abnormal in traffic during the period of time.

1 and 2 show traffic anomaly detection performed over a period of time for one target object or a plurality of target objects. For a plurality of time periods, the above steps 102 to 103, or steps 203 to 207 may be repeated.

The embodiments of the present invention are further described below by taking a period of time and a target object as an example.

FIG. 3 is a schematic diagram of a monitoring area corresponding to a camera according to an embodiment of the present invention. As shown in FIG. 3, the camera can be placed at a higher area of the intersection to obtain a larger viewing angle.

For the monitoring area within the coverage of the camera, it may be divided into a plurality of sub-areas in advance. For example, according to traffic signs, it can be divided into a non-motor vehicle area, a motor vehicle area, a left turn lane area, a right turn lane area, a straight lane area, and the like.

That is, each sub-area may have one or more attributes: an identifier of the sub-area, the sub-area is The location in the monitoring area, whether the sub-area is a motor vehicle lane or a non-motor vehicle lane, whether the sub-area is a redirecting lane or a straight lane. In the present embodiment, the attributes of each sub-area may be represented by, for example, 16 bits, that is, each sub-area may have an attribute value from 0x0 to 0xFFFF.

4 is a schematic diagram of sub-area attributes of an embodiment of the present invention. As shown in FIG. 4, the first 4 bits (0-3 bits) may indicate the position of the sub-area in the entire monitoring area (for example, compared with the center point of the monitoring area, if the sub-area is located on the left side, it is represented by 1000). , the upper side is represented by 0100, the right side is represented by 0010, and the lower side is represented by 0001.

As shown in FIG. 4, the next 3 bits (4-6 bits) may indicate the direction change flag of the sub-area (for example, waiting for 100, turning left to 010, turning right to 001); The 3 bits (7-9 bits) can represent the straight line mark of the sub-area (for example, straight line 1 is represented by 100, straight line 2 is represented by 010, and straight line 3 is represented by 001).

As shown in Fig. 4, the next 2 bits (10-11 bits) may indicate the type of area (for example, the area through which the motor vehicle and the non-motor vehicle are allowed to pass is indicated by 00; the area in which the non-motor vehicle is allowed to pass is indicated by 01; The area through which the motor vehicle passes is indicated by 10; the area where the motor vehicle and the non-motor vehicle are allowed to pass, but the passage of pedestrians is prohibited is indicated by 11. For the last 4 bits (12-15 bits) can be used for a variety of other purposes.

Thereby, the monitoring area can be divided into a plurality of sub-areas of different types.

FIG. 5 is a schematic diagram of a monitoring area divided into a plurality of sub-areas according to an embodiment of the present invention. As shown in FIG. 5, the monitoring area may form multiple types of 1 to 9 and A to D. Among them, the areas not marked in Figure 5 can be recorded as NONE, and the corresponding marks of each type are as follows:

1:NONE_POWER;

2: YELLOW_LINE;

3: SIDEWALK;

4: NONE_POWER;

5: STRAIGHT_1;

6: STRAIGHT_2;

7: STRAIGHT_3;

8: TURNLEFT;

9: LEFTWAITING;

A: LEFT_UP_CENTER;

B: LEFT_UP_CENTER;

C:RIGHT_UP_CENTER;

D: RIGHT_DOWN_CENTER.

FIG. 6 is a schematic diagram showing a plurality of sub-areas defined by an embodiment of the present invention, showing an example of a plurality of sub-areas defined. As shown in FIG. 6, each sub-area may have a 16-bit attribute. It is to be noted that FIGS. 4 to 6 only schematically show how to divide the sub-areas and how to define the area attributes; however, the present invention is not limited thereto, and specific definitions may be determined according to actual conditions.

In step 101, the traffic information may refer to traffic light (traffic light) information, or may be information manually directed by the traffic police. The traffic light information can be obtained from other devices; for example, it can be obtained by connecting a traffic light system through a network. The traffic light information or information manually directed by the traffic police can also be obtained from the video obtained by the camera. The present invention will be described below by taking traffic light information as an example.

In this embodiment, the period of time may be one signal period of the traffic light; for example, a red light period or a green light period. During this period of time, a traffic rule may be set for the monitored area divided into a plurality of sub-areas based on the traffic information.

For example, for the lower half of the monitoring area shown in FIG. 5, if the traffic light information is "red light", from the areas 6 to 3 to D are not allowed in the signal period; if the traffic light information For "green light", from area 6 to 3 to D is allowed during this signal period.

Therefore, the traffic area can be set to the traffic rules for a period of time based on the traffic information. These pass rules can be set manually or automatically.

In step 102, the target object can be detected and tracked based on the video obtained by the camera. The target object may be a motor vehicle, such as a bulky truck, a public transportation vehicle, or the like, or a small car, a motorcycle, etc.; the target object may also be a non-motor vehicle, such as a human vehicle such as a bicycle; The object can also be a pedestrian, an animal, or the like. Among them, various target objects have two states: stationary or moving.

In this embodiment, the target object may be detected by subtracting the background image from the current frame.

7 is a schematic diagram of target object detection according to an embodiment of the present invention. As shown in FIG. 7, for example, frame-by-frame detection can detect not only a moving object but also a stationary object; in addition, for a bulky object Or small objects can be detected. For a specific implementation of subtraction using a background image, reference may be made to related art.

Among them, by tracking the same object in a video, the motion track of the target object can be obtained. The motion trajectory of the target object during the period of time may be represented by information of an identifier of one or more sub-regions that the target object passes during the period of time. For example, it can be represented by a vector, and the elements in the vector are the identifiers of one or more sub-regions that pass through.

In this embodiment, the target object may have one or more attributes: an identifier of the target object, a motion trajectory of the target object, a type of the target object, and a state of the target object.

FIG. 8 is a schematic diagram of attributes of a target object according to an embodiment of the present invention. As shown in Figure 8, obj_ID represents the identity of the target object; Vector obj_trajectory represents the motion trajectory of the target object, which can be represented by a vector; obj_type represents the type of the target object, such as a motor vehicle or a non-motor vehicle; obj_status represents the target object The status, for example, is abnormal or normal, and the obj_status can be updated after step 103.

For example, for a certain target object in a certain period of time, the motion trajectory obj_trajectory may adopt the following vector representation {11, 12, 16}; that is, the target object moves from the sub-area 11 to the sub-area 12 during the period of time. Then move to sub-region 16.

In step 103, determining whether a traffic abnormality occurs in the target object during the period of time according to the traffic rule and the motion trajectory, and specifically, the method may include: one of the target objects passing through the time period Or if the plurality of sub-areas meet the pass rule, determining that the target object does not have a traffic anomaly during the period of time; and one or more sub-areas that the target object passes during the period of time does not meet In the case of the pass rule, it is determined that the target object has a traffic anomaly during the period of time.

Still taking the lower half of the monitoring area shown in FIG. 5 as an example, if the traffic rule set in step 101 is: the traffic light information is "red light", the area 7 to 3 to D are not allowed. And, during this time, the trajectory of the target object obtained by step 102 is "7 to 3 to D", then the target object can be determined to be abnormal.

If the pass rule set in step 101 is: the traffic light information is "red light", the area 7 to 3 to 9 are not allowed, and the track of the target object obtained by step 102 during this time is not allowed. If it is "7 to 3 to 9", you can still determine that the target object is abnormal.

If the pass rule set in step 101 is: when the traffic light information is "green light", the area 7 to 3 to D are permitted, and the trajectory of the target object obtained by step 102 during this time is " 7 to 3 to D", it can be determined that the target object is normal.

If the pass rule set in step 101 is: when the traffic light information is "green light", from area 7 to 3 It is allowed to D, and the trajectory of the target object obtained by step 102 during this time is "7", that is, the target object is still or the moving range is small during the period of time, and the target object can be determined to be abnormal. .

It is to be noted that the above only schematically illustrates how to determine the abnormality, but the present invention is not limited thereto. The specific implementation manner can be determined according to the actual scenario.

According to the foregoing embodiment, the monitoring area is divided into multiple sub-areas, and a traffic rule is used to set a traffic rule according to the traffic information; the target object is detected and tracked based on the obtained video, and the target object is obtained. a motion trajectory for a period of time; and determining whether the target object has a traffic anomaly during the period of time according to the pass rule and the motion trajectory. Therefore, it can be applied to more traffic scenarios and to more types of traffic anomalies; in addition, the algorithm is simple, can be used for real-time monitoring and has high detection accuracy.

Example 2

The embodiment of the present invention provides a traffic abnormality detecting device, which corresponds to the traffic abnormality monitoring method of Embodiment 1, and the same content is not described again.

FIG. 9 is a schematic diagram of a traffic abnormality detecting apparatus according to an embodiment of the present invention. As shown in FIG. 9, the traffic abnormality detecting apparatus 900 includes:

The rule setting unit 901 sets a pass rule for the monitoring area divided into the plurality of sub-areas according to the traffic information for a period of time;

The detecting and tracking unit 902 detects and tracks the target object based on the obtained video, and acquires a motion trajectory of the target object in the period of time;

The result determining unit 903 determines whether a traffic abnormality occurs in the target object during the period of time according to the traffic rule and the motion trajectory.

FIG. 10 is another schematic diagram of a traffic abnormality detecting apparatus according to an embodiment of the present invention. As shown in FIG. 10, the traffic abnormality detecting apparatus 1000 includes a rule setting unit 901, a detecting and tracking unit 902, and a result determining unit 903, as described above. Said.

As shown in FIG. 10, the traffic abnormality detecting apparatus 1000 may further include:

The area dividing unit 1001 divides the monitoring area into a plurality of sub-areas.

In this embodiment, each sub-region may have one or more attributes: an identification of the sub-region, a location of the sub-region in the monitoring region, whether the sub-region is a motor vehicle lane or a non-motorized Lane, Whether the sub-area is a redirecting lane or a straight lane.

In this embodiment, the motion trajectory of the target object in the period of time may be represented by an identifier of one or more sub-regions that the target object passes during the period of time.

The result determining unit 903 may be specifically configured to: when the one or more sub-regions that the target object passes in the period of time meets the pass rule, determine that the target object is in the segment No traffic abnormality occurs in the time; if one or more sub-regions that the target object passes during the period of time does not meet the traffic rule, determining that the target object has a traffic abnormality within the certain period of time .

The information acquisition unit 1002 acquires the traffic information from other devices or acquires the traffic information from the video.

The embodiment of the invention further provides an image monitoring device, which includes the traffic

anomaly detecting device

900 or 1000 as described above.

FIG. 11 is a schematic diagram showing the structure of an image monitoring apparatus according to an embodiment of the present invention. As shown in FIG. 11, the image monitoring device 1100 can include a central processing unit (CPU) 1101 and a memory 1102; the memory 1102 is coupled to the central processing unit 1101. The memory 1102 can store various data; and the program is executed under the control of the central processing unit 1101.

In one embodiment, the functions of the traffic

anomaly detection device

900 or 1000 described above may be integrated into the central processor 1101. The central processor 1101 may be configured to implement the traffic anomaly detection method as described in Embodiment 1. That is, the central processing unit 1101 may be configured to perform control for setting a traffic rule for a monitoring area divided into a plurality of sub-areas according to traffic information for a period of time; detecting and tracking the target object based on the obtained video, acquiring the A motion trajectory of the target object during the period of time; determining whether the target object has a traffic anomaly within the period of time according to the pass rule and the motion trajectory.

In another embodiment, the traffic

anomaly detecting device

900 or 1000 may be configured separately from the central processing unit 1101. For example, the traffic

abnormality detecting device

900 or 1000 may be configured as a chip connected to the central processing unit 1101 through a central processing unit. The control of 1101 implements the functions of the traffic

anomaly detecting device

900 or 1000 described above.

In addition, as shown in FIG. 11, the image monitoring apparatus 1100 may further include: an input and output device 1103 and a display The device 1104 and the like; wherein the functions of the above components are similar to those of the prior art, and are not described herein again. It should be noted that the image monitoring device 1100 does not have to include all the components shown in FIG. 11; in addition, the image monitoring device 1100 may further include components not shown in FIG. 11, and reference may be made to the related art.

Example 3

An embodiment of the present invention provides an image monitoring system, where the image monitoring system includes:

a camera that captures a video of the surveillance area;

The traffic anomaly detecting device as described in Embodiment 2.

The embodiment of the present invention further provides a computer readable program, wherein when the program is executed in an image monitoring device, the program causes a computer to execute the traffic abnormality detecting method described in Embodiment 1 in the monitoring device.

The embodiment of the present invention further provides a storage medium storing a computer readable program, wherein the computer readable program causes the computer to execute the traffic abnormality detecting method described in Embodiment 1 in an image monitoring device.

The above apparatus and method of the present invention may be implemented by hardware or by hardware in combination with software. The present invention relates to a computer readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to cause the logic component to implement the various methods described above Or steps. The present invention also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, or the like.

One or more of the functional blocks described in the figures and/or one or more combinations of functional blocks may be implemented as a general purpose processor, digital signal processor (DSP) for performing the functions described herein. An application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any suitable combination thereof. One or more of the functional blocks described with respect to the figures and/or one or more combinations of functional blocks may also be implemented as a combination of computing devices, eg, a combination of a DSP and a microprocessor, multiple microprocessors One or more micro-combinations combined with DSP communication Processor or any other such configuration.

The present invention has been described in connection with the specific embodiments thereof, and it should be understood by those skilled in the art that A person skilled in the art can make various modifications and changes to the present invention within the scope of the present invention.

Claims

A traffic anomaly detection method, the traffic anomaly detection method comprising:

Setting a pass rule for a monitored area divided into a plurality of sub-areas according to traffic information for a period of time;

Detecting and tracking the target object based on the obtained video, and acquiring a motion trajectory of the target object in the period of time;

And determining, according to the pass rule and the motion trajectory, whether a traffic abnormality occurs in the target object during the period of time.
The method of claim 1 wherein the method further comprises:

The monitoring area is divided into a plurality of sub-areas.
The method of claim 2, wherein each sub-area has one or more attributes: an identification of the sub-area, a location of the sub-area in the monitoring area, the sub-area is maneuverable The lane is also a non-motorized lane, and the sub-area is a redirecting lane or a straight lane.
The method of claim 1, wherein the target object has one or more attributes: an identification of the target object, a motion trajectory of the target object, a type of the target object, and a target object status.
The method of claim 1, wherein the motion trajectory of the target object over the period of time is represented by information that the target object is identified by one or more sub-regions that have passed during the period of time.
The method according to claim 5, wherein determining whether the target object has a traffic abnormality during the period of time according to the pass rule and the motion trajectory comprises:

Determining that the target object does not have a traffic abnormality within the period of time if one or more sub-regions that the target object passes within the period of time meets the pass rule;

In a case that one or more sub-regions that the target object passes during the period of time do not conform to the pass rule, it is determined that the target object has a traffic anomaly within the period of time.
The method of claim 1 wherein the method further comprises:

The traffic information is obtained from other devices or obtained from the video.
A traffic anomaly detecting device, the traffic anomaly detecting device comprising:

The rule setting unit sets the monitoring area divided into a plurality of sub-areas according to traffic information for a period of time Customary rules;

a detecting and tracking unit, detecting and tracking the target object based on the obtained video, and acquiring a motion track of the target object in the period of time;

The result determining unit determines whether the target object has a traffic abnormality within the period of time according to the pass rule and the motion trajectory.
The device according to claim 8, wherein the traffic anomaly detecting device further comprises:

The area dividing unit divides the monitoring area into a plurality of sub-areas.
The apparatus of claim 9, wherein each sub-area has one or more attributes: an identification of the sub-area, a location of the sub-area in the monitoring area, the sub-area is maneuverable The lane is also a non-motorized lane, and the sub-area is a redirecting lane or a straight lane.
The apparatus of claim 8, wherein the target object has one or more attributes: an identification of the target object, a motion trajectory of the target object, a type of the target object, and a target object status.
The apparatus of claim 8, wherein the motion trajectory of the target object over the period of time is represented by information that the target object is identified by one or more sub-regions that have passed during the period of time.
The apparatus according to claim 12, wherein the result determining unit is specifically configured to:

Determining that the target object does not have a traffic abnormality within the period of time if one or more sub-regions that the target object passes within the period of time meets the pass rule;

In a case that one or more sub-regions that the target object passes during the period of time do not conform to the pass rule, it is determined that the target object has a traffic anomaly within the period of time.
The apparatus of claim 8 wherein said apparatus further comprises:

The information acquisition unit acquires the traffic information from other devices, or acquires the traffic information from the video.
An image monitoring system comprising:

a camera that captures a video of the surveillance area;

A traffic abnormality detecting device according to claim 8.