Multi-target tracking method and system based on kernel function unsupervised clustering

Abstract

The invention belongs to the image processing field and relates to a multi-target tracking method and a system based on kernel function unsupervised clustering. According to the method, a binocular camera is utilized to acquire left and right sequence images at one same time, and parameters of the binocular camera are utilized for image correction; a parallax error is calculated through extracting image characteristic points and matching characteristics; the acquired parallax error is utilized to calculate the coordinate position of a target characteristic point relative to the camera, namely the coordinate of the camera, ground calibration is accomplished, ground shadow characteristic points can be filtered according to height from the characteristic point to the ground, and ground shadow interference is eliminated; according to the three-dimensional coordinate characteristic point, in combination with the kernel function, unsupervised clustering is carried out for targets with undetermined category quantity, all characteristic points of one target are gathered to form one set, one category corresponds to the position and the direction of one observation value, a present frame of the target can be acquired in combination with the position and the direction of the previous frame target, namely the prediction position value and the prediction direction value, an optimum estimation algorithm is utilized to acquire the position and the direction of the optimum target, and thereby the multi-target fast tracking effect is realized.

Description

technical field [0001] The present invention relates to a multi-target tracking technology and system in the field of image processing technology, in particular to a multi-target tracking technology based on kernel function non-supervised clustering, and a software system for realizing the technology. Background technique [0002] With the development of computer vision and people's increasing awareness of public safety, multi-objective monitoring has played an increasingly important role in production and life. Object detection and object tracking has become an important research content. In the monitoring system, the tracking algorithm can reduce labor costs and save social resources. But because there are many uncertain factors in the tracking environment, the diversity of targets, complex and changeable lighting environment, shadow interference and other problems will bring interference to the tracking algorithm. This also causes many existing systems to be unable to w...

AI Technical Summary

Problems solved by technology

However, the clustering technology uses the height and position of target feature points for clustering, and it also faces the problem of target accuracy matching. When the background is complex, it is difficult to accurately match targets of different shapes.

Images