Systems and methods for traffic violation detection

Patent metadata

Field	Value
Publication number	US-11790699-B2
Application number	US-202217647976-A
Country	US
Kind code	B2
Filing date	Jan 13, 2022
Priority date	Aug 8, 2019
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

The present disclosure provides a system and method for traffic violation detection. The system may determine a target object which should be given precedence with respect to a vehicle from one or more moving objects by performing an angle correction on the one or more moving objects, wherein the one or more moving objects are objects moving in a predetermined region. When it is determined that a moving direction of the target object is a moving direction towards middle of a road and a target vehicle passing through the predetermined region is not courteous to the target object, the system may mark a state of the target vehicle as a violation state.

First claim

We claim:

1. A system, comprising:
at least one storage device storing executable instructions, and
at least one processor in communication with the at least one storage device, wherein when executing the executable instructions, the at least one processor is directed to cause the system to perform operations including:
identifying one or more candidate objects within a predetermined region associated with a crosswalk at a road from one or more first images of the crosswalk captured by a surveillance equipment mounted near the crosswalk;
for each of the one or more candidate objects, determining a moving direction of the candidate object with respect to the road;
determining one or more target objects from the one or more candidate objects based on one or more moving directions corresponding to the one or more candidate objects;
identifying one or more vehicles within a predetermined range of the crosswalk; and
for each of the one or more vehicles,
obtaining, from the surveillance equipment mounted near the crosswalk, one or more second images including the vehicle at one or more predetermined positions; and
determining whether the vehicle has a traffic violation behavior associated with the one or more target objects based on the one or more second images.

2. The system of claim 1 , wherein for each of the one or more candidate objects, the determining the moving direction of the candidate object with respect to the road includes:
determining an initial position of the candidate object within the predetermined region based on an initial image captured at an initial time point;
determining whether the initial position of the candidate object is in the vicinity of an outer edge of the predetermined region;
in response to a determination that the initial position is in the vicinity of the outer edge of the predetermined region,
determining a plurality of intermediate positions of the candidate object within the predetermined region based on a plurality of sequential images associated with the candidate object, the plurality of sequential images being sequentially captured at a plurality of intermediate time points immediately after the initial time point;
determining a plurality of intermediate moving directions of the candidate object based on a plurality of positions including the initial position and the plurality of intermediate positions, wherein each of the plurality of intermediate moving directions corresponds to two adjacent positions of the plurality of positions; and
determining the moving direction of the candidate object based at least in part on the plurality of intermediate moving directions.

3. The system of claim 2 , wherein the determining the moving direction of the candidate object based at least in part on the plurality of intermediate moving directions includes:
selecting candidate intermediate moving directions satisfying a predetermined condition from the plurality of intermediate moving directions; and
determining the moving direction of the candidate object based on the candidate intermediate moving directions.

4. The system of claim 3 , wherein the selecting the candidate intermediate moving directions satisfying the predetermined condition from the plurality of intermediate moving directions includes:
identifying one or more lane lines associated with the crosswalk;
determining an average angle between the one or more lane lines and a horizontal direction;
for each of the plurality of intermediate moving positions,
determining an angle between the intermediate moving direction and the horizontal direction;
determining a reference angle based on the average angel and the angle between the intermediate moving direction and the horizontal direction;
determining a moving distance connecting the two adjacent positions corresponding to the intermediate moving direction;
determining whether the reference angle is less than a threshold angle and whether the moving distance is larger than a threshold distance; and
in response to a determination that the reference angle is less than the threshold angle and the moving distance is larger than the threshold distance, determining the intermediate moving direction as a candidate intermediate moving direction.

5. The system of claim 3 , wherein the determining the moving direction of the candidate object based on the candidate intermediate moving directions includes:
determining an average moving direction of the candidate intermediate moving directions as the moving direction of the candidate object.

6. The system of claim 1 , wherein the determining the one or more target objects from the one or more candidate objects based the on one or more moving directions corresponding to the one or more candidate objects includes:
for each of the one or more candidate objects,
determining whether the moving direction is a direction away from the road or a direction crossing the road; and
in response to a determination that the moving direction is the direction crossing the road, designating the candidate object as a target object.

7. The system of claim 1 , wherein the determining whether the vehicle has a traffic violation behavior associated with the one or more target objects based on the one or more second images includes:
determining whether the one or more second images are captured within a first predetermined time period; and
in response to a determination that the one or more second images are captured within the first predetermined time period, determining that the vehicle has a traffic violation behavior associated with the one or more target objects.

8. The system of claim 7 , wherein
the one or more predetermined positions include a first line within a first predetermined distance range of a side of a crosswalk area, a second line within the crosswalk area, and a third line within a third predetermined distance range of the other side of the crosswalk area, and
the one or more second images include three images of the vehicle captured at the first line, the second line, and the third line, respectively.

9. The system of claim 1 , wherein the determining whether the vehicle has a traffic violation behavior associated with the one or more target objects based on the one or more second images includes:
determining whether a door of the vehicle is open and whether at least one of the one or more target objects disappears in a second predetermined time period based on the one or more second images; and
in response to a determination that the door of the vehicle is open and the at least one of the one or more target objects disappears, determining that the vehicle does not have a traffic violation behavior associated with the one or more target objects.

10. The system of claim 1 , wherein the at least one processor is configured to cause the system to perform the operations further including:
in response to a determination that the vehicle has a traffic violation behavior associated with the one or more target objects, detecting at least one of a license plate, a speed, a face, or a driving behavior associated with the vehicle.

11. The system of claim 1 , wherein the at least one processor is configured to cause the system to perform the operations further including:
causing a signal device to generate a reminder signal in response to determining the one or more target objects.

12. A method implemented on a computing device including at least one processor and at least one storage medium, and a communication platform connected to a network, the method comprising:
identifying one or more candidate objects within a predetermined region associated with a crosswalk at a

Assignees

• Zhejiang Dahua Technology Co

Inventors

• Lin Jun
• Wang Yayun

Classifications

• G06F18/24765

  Rule-based classification · CPC title

• G06V40/25 Primary

  Recognition of walking or running movements, e.g. gait recognition · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title