Target contour tracking method based on online boosting

Abstract

The present invention provides an online Boosting-based target fine contour tracking method. According to the method, in target fine tracking, super-pixels are adopted to perform block partitioning on an image containing a tracking target, and each super-pixel is regarded as a point, and therefore, computational complexity can be decreased; and an online learning method is adopted to segment the target and background. According to a traditional Online Boosting algorithm, the weights of training samples are the same and do not change with time. However, in the case of target fine tracking, since the moving object changes at all times, as for an online classifier, the longer the time interval between an image frame and a current frame is, the smaller of the weight of the image frame is; in order to realize a weight gradually attenuating effect, an online Boosting classifier which enables the weights of the samples to be decreased progressively with the length of time is designed; and with the increase of the number of video frames, the performance of the classifier is better and better, and therefore, the accurate fine contour of the tracking target can be realized.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to the field of intelligent monitoring. Background technique [0002] The video-based target fine contour tracking technology not only needs to be able to track the position of the target, but also accurately describe the shape of the target. This technology is one of the most basic technologies in the field of computer vision, and can obtain the tracking result of the target contour. The upper-level algorithm further analyzes and processes according to the target contour tracking results to realize the application of scene understanding, target action recognition, and human behavior recognition. The wide application prospect and high research value of this technology have aroused the strong interest of researchers at home and abroad. [0003] The key to fine contour tracking technology based on video lies in the expression of time consistency and space consistency. Temporal consist...

AI Technical Summary

Problems solved by technology

In this way, when the motion estimation is inaccurate, it will affect the accuracy of segmentation. In many videos where the camera itself has motion, it is difficult to obtain a good tracking effect for motion estimation.

In order to solve the situation of camera motion, a method based on graph cut is proposed, which fuses multiple clue functions together. The motion information of the target is usually one of the important clue functions, but the background motion field usually interferes with the target. motion information, making the tracked target outline inaccurate

There are also some semi-automatic segmentation methods, which need to manually mark some target and background areas, which greatly limits their application fields.

Images