Target tracking method and system in set area based on natural light binocular vision

Abstract

The invention discloses a method and system for tracking a target in a set region based on natural light binocular vision. The method comprises the following steps: obtaining image sequences collectedby two ordinary cameras; determining the constraint conditions of the interest target and the depth-of-field interval set by the user; processing the image sequence, and adopting the binocular visiontracking algorithm and the constraint condition of the interest object to extract the interest object from the processed image, and determining the coordinates of the interest object; based on the mapping relationship between the world coordinate system of two cameras and the two-dimensional coordinates of the object of interest and the depth-of-field interval set by the user, determining the image processing interval; processing the image sequence collected by two ordinary cameras in the image processing section to determine the three-dimensional coordinates of the object of interest in theimage processing section and realize the object tracking. By applying the method or system provided by the invention, the image processing interval can be controlled according to the actual requirements, and the requirements in the privacy protection application scene can be satisfied.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and system for tracking a target in a set area based on natural light binocular vision. Background technique [0002] More than 80% of human perception of external information is obtained through vision. Vision not only refers to the perception of light signals, but also includes the process of acquiring, processing, transmitting, storing and understanding visual information. After the emergence of signal processing theory and computers, people tried to use cameras to obtain environmental images and convert them into digital signals, and used computers to realize the whole process of visual signal processing, thus forming a new subject - computer vision. Computer vision is to obtain images or image sequences through image sensors, and then analyze and understand these images by means of computer image processing, pattern recognition, artificial intelligence and ...

AI Technical Summary

Problems solved by technology

[0006] At present, the images collected by infrared cameras are mainly used as the input of the binocular vision system. Since infrared imaging only has grayscale information, it has the disadvantages of being unable to restore the original phase, high equipment cost, large background noise, and low resolution.

In addition, the current binocular vision system cannot meet the requirements of application scenarios that emphasize privacy protection

Images