Method for rapidly tracking and positioning set targets in grayscale videos

Abstract

The invention relates to a method for rapidly tracking and positioning set targets in grayscale videos. The method comprises the following steps of: carrying out two-dimensional Gaussian kernel cyclicconvolution on a standard target image and an image in a video frame sequence to solve cross-correlation matrixes, and processing positions of targets tracked by the cross-correlation matrixes by using ridge regression method; carrying out weighted average on a detection result of the current frame to serve as a next frame of standard target image; self-convoluting each frame of standard target image and solving a statistic feature of each frame of standard target image, and mapping characterization between two frames as scale change so as to solve scale change, in a moving process, of the target; and deconvolution is carried out on an auto-correlation matrix through discrete Fourier transformation and inverse transformation to update and learn a ridge regression parameter which is used for solving a response matrix in the next frame. The method is high in calculation speed and high in tracking precision, adopts dense sampling, is completely adapted to scale change and can be suitablefor the scenes in which targets are moved from far to near or moved from near to far.

Description

technical field [0001] The invention belongs to a single target tracking and positioning technology in video, and in particular relates to a fast tracking and positioning method for a predetermined target in grayscale video. Background technique [0002] Object tracking is a basic research direction of computer vision, which has a wide range of applications in human-computer interaction, monitoring, augmented reality, machine perception and other scenarios. Currently existing tracking methods are mainly divided into two types: generative model algorithms and discriminative model algorithms. The former uses the method of learning target features, and then performs feature matching in the subsequent frame to track the target, while the latter uses the method of learning to build a classifier, and uses the classifier to distinguish the background and the target, so as to achieve the purpose of identifying the target. [0003] However, none of the existing tracking methods can ...

AI Technical Summary

Problems solved by technology

[0003] However, none of the existing tracking methods can directly adapt to the scene where the target scale changes. The fixed scale makes it not only unable to accurately output the coordinate position of the tracked target in the scene where the target scale changes, but also unable to calibrate the target range.

Existing scale adaptation schemes use some independent methods for scale estimation, which is equivalent to superimposing a set of scale calculation methods independently while tracking, which undoubtedly increases the amount of calculation and complexity, resulting in a complex and slow tracking process

Images