Target tracking method based on dynamic measurement matrix and target tracking system based on dynamic measurement matrix

Abstract

The invention discloses a target tracking method based on a dynamic measurement matrix and a target tracking system based on the dynamic measurement matrix. The method comprises the following steps of: 1, compressing high-dimension features of samples into low-dimension features, and initializing the dynamic measurement matrix; 2, collecting a plurality of positive sample sets and negative sample sets around a target position to perform classifier updating learning; 3, determining the position of a current frame target; and 4, updating the dynamic measurement matrix, and returning to the second step until the tracking is completed. The dynamic measurement matrix is used for extracting compression features of the target in the tracking process, i.e., in the tracking process, the measurement matrix is updated by utilizing the features of the tracked target and the features of a Naive Bayes classifier; the fixed form of the measurement matrix is improved; and the adaptability of the tracking method is high. Experimental results show that the tracking method has good robustness.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an object tracking method and system based on a dynamic measurement matrix. Background technique [0002] Target tracking based on video or image sequences is one of the hot issues in computer vision, and it is closely related to target detection. The tracking-by-detection method also benefits from the efficiency and accuracy of detection problems. promote. There are many difficulties to be dealt with in the target tracking problem, such as illumination changes, target shape or pose changes, and complex scenes, all of which have a great impact on the tracking effect. [0003] Tracking problems can be roughly divided into two categories. One is the tracking based on the generative model. This method learns the appearance model of the target. When searching for the target position, it looks for the area with the closest distance to the model or the smallest reconstruction error; th...

AI Technical Summary

Problems solved by technology

However, in the CT algorithm, the measurement matrix will not change after initialization, resulting in the solidification of the characteristic mode, resulting in tracking drift in some scenarios

The invention patent with the application number CN201410660331.8 and the name "A Video Target Tracking Method Based on Compressed Sensing" uses the CT algorithm. However, this application always uses this matrix to achieve feature compression throughout the tracking process, that is to say Keeping the sparse matrix unchanged throughout the tracking process leads to the solidification of the characteristic mode, causing tracking drift in some scenarios

Images