Detecting and tracking method based on visual salient original target

Abstract

The invention discloses a detecting and tracking method based on a visual salient original target. The detecting and tracking method is characterized by comprising the first step of detecting the visual salient original target based on visual salient information, image segmentation and a K-means clustering algorithm, the second step of determining the joint distribution of a target and the visual salient original target based on the Bayesian theory and probability statistics knowledge, thereby obtaining a tracking target model, the third step of optimizing state estimation by use of the Gibbs sampling algorithm and sampling an approximate joint probability based on the spatial position and the salient information of the visual salient original target and an observed value, thereby obtaining the state sequence of the target and the visual salient original target, and the fourth step of obtaining the state information of the target in the current frame based on the MAP (Maximum Posterior Probability) of the Bayesian theory. The detecting and tracking method based on the visual salient original target is high in target tracking anti-disturbance performance, stable in target information description and excellent in robustness.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a video target tracking method, in particular to a detection and tracking method based on a visually significant original target. Background technique [0002] Object tracking is the core technology of video analysis and is widely used in many aspects of computer vision, such as security surveillance, video compression, and robot vision systems. During tracking, the target state information is estimated by the target model. Various interferences in the tracking process, such as background interference, occlusion, target shape and illumination changes, etc., are still technical problems that need to be solved. Especially for non-rigid targets, these disturbance factors may cause changes in the target model, resulting in the failure of the tracking method. [0003] To improve the robustness of tracking, researchers have proposed many different methods. Detection-based trac...

AI Technical Summary

Problems solved by technology

These methods are all based on the target model. When the target changes greatly, it may cause the target to drift or even be lost, and the anti-interference performance is poor.

The literature "Saliency-based Discriminant Tracking" (Saliency-based Discriminant Tracking.IEEE Conference on Computer Vision and Pattern Recognition 2009, pp.1007–1013.), using the low-dimensional feature contrast information based on different regions of the image and the background The disadvantages of the bottom-up saliency map detection method are as follows: first, the description of the target information is unstable, the target and background information cannot be well segmented, and a large amount of prior knowledge of the target is required; the second is the robustness to target occlusion Poor, unstable tracking effect

Images