Target tracking method based on local feature learning

Abstract

The invention discloses a target tracking method based on local feature learning. A target object and background are resolved into a large number of local units having dimension and shape invariance which serve as training samples of a target and background classification model, and a mode of deep learning is adopted to learn local expression of the target object and background from the training samples. The degree of confidence that each specific area in an image belongs to the target object is judged, thereby realizing accurate positioning of the target object. Since local expression obtained by learning of a large number of samples has a high target identification capability, the tracking method has relatively high adaptability to situations such as target deformation and target occlusion. When an object appearance model is updated, local areas with a relatively high target confidence degree are extracted as training samples of the model, and the model is updated. In the process of target tracking, the method continuously updates the appearance model, learns key characteristics of the target object, and can obtain a relatively good tracking effect under the circumstance that an appearance change is relatively big.

Description

technical field [0001] The present invention relates to the field of computer vision, and more specifically, relates to a target tracking method based on local feature learning. Background technique [0002] As an important research direction in the field of computer vision, object tracking has received extensive attention. This technology has broad application prospects in the fields of security monitoring, unmanned driving and military defense. Although there are already a considerable number of object tracking methods, these methods are often unstable or even invalid under the conditions of illumination changes, object deformation and severe occlusion. Therefore, proposing an effective target tracking algorithm has important application value and practical significance. [0003] At present, many target tracking algorithms have been put into use, and the complete target tracking algorithm can be divided into four main parts: the method of feature extraction, the establis...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the prior art, that is, the features extracted by the target tracking method are weak in expression ability and the update mechanism of the model is poor in adaptability, etc., the present invention proposes a tracking method based on local feature learning. Firstly, the target object and The background is decomposed into a large number of local units with scale and shape invariance, that is, the local area of ​​​​the image, and it is used as the training sample of the target and background classification model, and the target object and the background are learned from the training samples by using deep learning. local expression of

Images