Method for stop sign law enforcement using motion vectors in video streams
First Claim
1. A vector-based stop detection method for enforcing traffic signal compliance, the method comprising:
- receiving video data from a surveillance camera;
defining a target area in the received video data;
dividing a current frame into a number of blocks;
computing a displacement for a block between a reference frame and the current frame and describing the displacement of the block as a motion vector;
defining a cluster as a group of one or more connected motion vectors having a length meeting or exceeding a first vector length threshold and classifying a block having a motion vector meeting or exceeding the first vector length as an active motion block;
in response to a number of active motion blocks in the cluster meeting or exceeding a cluster size threshold, classifying the cluster of motion vectors as belonging to a vehicle;
tracking a position of the cluster across two or more video frames;
monitoring the length of motion vectors of the cluster in the two or more video frames and reclassifying any motion vector that no longer exceeds the first vector length threshold as not an active motion block;
in response to the cluster transitioning from having the number of active motion blocks meeting or exceeding the cluster size threshold to having fewer than a second number of active motion blocks, classifying the cluster as being inactive;
in response to the inactivity of the cluster persisting for a predetermined duration, classifying the vehicle as being stationary;
in response to the activity of the cluster persisting in the target area, classifying the vehicle as not being stationary and transmitting a signal and compressed pixel data to a second device.
6 Assignments
0 Petitions
Accused Products
Abstract
A method for enforcing traffic signal compliance includes acquiring a series of temporal related image frames including a target area. Each image frame includes pixel data representative of the target area. The method includes generating one or more motion vectors between two or more of the image frames. The motion vectors are the type produced by compressing the pixel data associated with the two or more image frames. The method includes associating a cluster of motion vectors with a vehicle. The method further includes tracking a position of the vehicle across the two or more image frames. Using the tracking results, the method includes determining whether the vehicle stops in the target area. For the vehicle being determined as not stopping, the method includes signaling an occurrence of noncompliance.
-
Citations
20 Claims
-
1. A vector-based stop detection method for enforcing traffic signal compliance, the method comprising:
-
receiving video data from a surveillance camera; defining a target area in the received video data; dividing a current frame into a number of blocks; computing a displacement for a block between a reference frame and the current frame and describing the displacement of the block as a motion vector; defining a cluster as a group of one or more connected motion vectors having a length meeting or exceeding a first vector length threshold and classifying a block having a motion vector meeting or exceeding the first vector length as an active motion block; in response to a number of active motion blocks in the cluster meeting or exceeding a cluster size threshold, classifying the cluster of motion vectors as belonging to a vehicle; tracking a position of the cluster across two or more video frames; monitoring the length of motion vectors of the cluster in the two or more video frames and reclassifying any motion vector that no longer exceeds the first vector length threshold as not an active motion block; in response to the cluster transitioning from having the number of active motion blocks meeting or exceeding the cluster size threshold to having fewer than a second number of active motion blocks, classifying the cluster as being inactive; in response to the inactivity of the cluster persisting for a predetermined duration, classifying the vehicle as being stationary; in response to the activity of the cluster persisting in the target area, classifying the vehicle as not being stationary and transmitting a signal and compressed pixel data to a second device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A vector-based stop detection system for enforcing traffic signal compliance, the system comprising:
-
a video capture device including; a video capture module configured to acquire a series of temporal related image frames including a target area, each image frame including pixel data representative of the target area; a motion vector extraction module adapted to; divide a current frame into a number of blocks, compute a displacement for a block between a reference frame and the current frame, describe the displacement of the block as a motion vector, define a cluster as a group of one or more connected motion vectors having a length meeting or exceeding a first vector length threshold, in response to a number of blocks in the cluster meeting or exceeding a cluster size threshold, characterize the cluster of motion vectors as belonging to a vehicle; and
,a violation determination module configured to; in response to the cluster transitioning from having the number of active motion blocks meeting or exceeding the cluster size threshold to having fewer than a second number of active motion blocks, classifying the cluster as being inactive; in response to the inactivity of the cluster persisting for a predetermined duration, characterize the vehicle as being stationary; and in response to the vehicle not stopping in the target area, transmit at least one of a signal and the compressed pixel data to a second device. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification