Quick real-time discrimination type tracing method based on multi-local-feature learning

Abstract

The invention relates to a quick real-time discrimination type tracing method based on multi-local-feature learning. The method comprises the following steps of: single-frame decomposition is carried out on a video, a target to be traced is marked in an initial frame through combination with early-stage action identification work or an artificial marking method, then, candidate blocks are obtained in a candidate area through dense sampling, and the local feature of each candidate block is independently calculated; then, on the basis of a circulant matrix and a relevant filter, a classifier is trained in a Fourier domain, a detection formula is used for calculating correlation between each candidate block in a current frame and the target also in the Fourier domain in a position detection stage, and an area with the highest correlation is selected as a prediction position of the target of the current frame; and finally, in the prediction position, a position detection result which has a smallest difference with a previous frame of target is selected as a final tracing result of the current frame, and a new target feature is used for training a new classifier. Except the initial frame, the tracing of other frames is characterized in that position detection is firstly carried out, and then, the training of a new regression function is carried out.

Description

technical field [0001] The invention relates to image processing technology, in particular to a fast real-time discriminative tracking method based on multi-local feature learning. Background technique [0002] Target tracking is one of the hot topics in the field of machine learning. It has a wide range of applications in industry, military and civilian, such as human-computer interaction, assisted driving, video surveillance, biomedical imaging analysis, target behavior analysis, etc. Of course, the target Tracking also faces many challenges, including target deformation, illumination changes, occlusion, motion blur, rotation, scale transformation, etc., which will affect the effect of target tracking. [0003] As one of the core technologies of machine vision, target tracking has always been a hot topic of research by scholars. The current target tracking methods are mainly divided into two types: one is the generative algorithm, which first uses the machine learning algo...

AI Technical Summary

Problems solved by technology

[0002] Target tracking is one of the hot topics in the field of machine learning. It has a wide range of applications in industry, military and civilian, such as human-computer interaction, assisted driving, video surveillance, biomedical imaging analysis, target behavior analysis, etc. Of course, the target Tracking also faces many challenges, including target deformation, illumination changes, occlusion, motion blur, rotation, scale transformation, etc., which will affect the effect of target tracking

Images