Video target tracking method and device

Abstract

The invention provides a video target tracking method and device. The method comprises the following steps: respectively inputting a tracking target image and a search area image into a first feature extraction module and a second feature extraction module, and carrying out image feature extraction; inputting the tracking target features and the search area features into a feature fusion module based on an interactive attention mechanism for feature fusion; and inputting the fusion features into a classification and regression module, and outputting the image category in the bounding box and the position and size information of the bounding box. According to the invention, image feature extraction is carried out by adopting an attention mechanism, and the region-of-interest features can be obtained to improve the feature extraction efficiency; and an interactive attention mechanism is adopted to carry out feature fusion, so that target features and search area features are fully interacted, and the problem that targets are lost due to illumination, deformation, shielding and the like in the prior art is solved.

Description

technical field [0001] The invention belongs to the technical field of video target tracking, and in particular relates to a video target tracking method and device. Background technique [0002] Video target tracking has been more and more widely used in intelligent monitoring, visual navigation and other fields. Video target tracking generally means that the tracker can accurately find the target and predict its position and size in the subsequent video frame images when the position and size information of the target to be tracked given by the first frame image of the video is known. Since target tracking does not need to know the category information of the target to be tracked, it has strong flexibility in practical applications. The traditional target tracking method is based on the hand-designed feature descriptor of the target to be tracked, but the hand-designed feature descriptor cannot fully consider the influence of the above factors. [0003] In recent years, ...

AI Technical Summary

Problems solved by technology

The existing twin network matching method generally does not consider the complete interaction between the tracking target and the search area, and only processes based on the maximum response, which leads to the loss of the target in scenarios such as different lighting, occlusion, shadows, and deformation of the target to be tracked.

Images