Multi-target pedestrian detecting and tracking method in monitoring video

Abstract

The invention discloses a multi-target pedestrian detecting and tracking method in monitoring video, comprising the steps that a target detection network based on deep learning is adopted for detecting a first frame of pedestrian image, and an initial rectangular area having one or a plurality of corresponding pedestrian targets can be obtained; based on the initial target area information, the Histogram of oriented gradients feature of a target can be extracted, and kernel function autocorrelation calculating of Fourier expansion domain can be conducted, and the tracking model is initializedbased on the calculating result; based on the target area information of the tracking model, a multi-dimensional construction of a pyramid will be carried out from the second frame of pedestrian image, and the extracting of the Histogram of oriented gradients feature matrix and the kernel function autocorrelation calculating of Fourier expansion domain can be conducted on each scale of the pedestrian rectangular area; the returned check condition is determined, and the identity re-verification and the updating of the tracking model can be conducted on the pedestrian target having returned check. The invention is advantageous in that the problem of drifting models can be resolved; a more accurate pedestrian moving track can be obtained; real-time performance is good.

Description

technical field [0001] The invention relates to the field of image processing of computer vision, in particular to a multi-target pedestrian detection and tracking method in a surveillance video. Background technique [0002] Target detection and tracking based on computer vision is an important topic in the field of machine vision, and has a wide range of application scenarios, such as robot navigation, video surveillance, intelligent transportation, etc. Pedestrian detection and tracking refers to the process of detecting the position information of pedestrians from video sequences, and continuously tracking the moving pedestrian targets to determine their trajectory. [0003] Visual tracking algorithms have been well researched and developed in recent decades. Although many effective visual tracking strategies have been continuously proposed, robust visual tracking is still a great challenge. The problems that need to be solved in target tracking are roughly as follows:...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies in the prior art and provide a multi-target pedestrian detection and tracking method in surveillance video, which effectively solves the problem of low precision, poor robustness, and problems when occlusion or deformation occurs in existing pedestrian detection and tracking. It is easy to track failure issues when

Images