Object tracing method based on active scene learning

Abstract

The invention provides an object tracing method based on active scene learning, belonging to the technical field of computer graphics and image mode identification. The difficulty needing to be confronted all together is to not only guarantee the adaption ability of a tracing system to the target change, but also guarantee the learning accuracy to avoid shifting to result in tracing failure. According to the invention, the object tracing is achieved by the steps of online modeling, short-time tracing, overall detection, active scene learning, a constraint method, analysis and extraction of a motion area and the like. By learning a scene online, the background information can be found actively, meanwhile, the motion area analysis and extraction method based on light streams is provided, and the problem of target loss and difficulty in recovering the target, resulting from rapid movement of an objected or severe movement of the scene, can be effectively solved according to the structured constraint. The adaption ability to the target change can be effectively improved, so that the long-time stable rapid object tracing can be achieved, and the object tracing method is mainly applied to various object tracing occasions.

Description

technical field [0001] The invention belongs to the technical field of computer graphic image pattern recognition, in particular to machine learning and computer vision technology. Background technique [0002] Achieving long-term visual tracking in an unconstrained environment is a key issue for numerous computer vision applications, such as video surveillance, human-computer interaction, etc. At present, the tracking method based on machine learning, especially online learning, has become a research hotspot in this field, because in order to obtain long-term stable and reliable tracking performance, the tracking system needs to be able to adapt to the movement changes of the target object. [0003] The purpose of online learning in the tracking process is to discover the unknown data structure, study it, and gradually develop a series of adaptive object tracking methods. Graber, Avidan, Collins, and Lim et al. adopted different self-learning methods to update the object m...

AI Technical Summary

Problems solved by technology

At the same time, a motion region analysis and extraction method based on optical flow analysis is proposed, and according to the above structural constraints, it can effectively solve the problem of insufficient learning due to fast movement of the target or severe movement of the scene, which leads to the loss of the target and is difficult to recover.

Images