Adaptive ORB object tracking method

Abstract

The invention discloses an adaptive ORB object tracking method. The adaptive ORB object tracking method adds FAST characteristic direction information in order to solve the problem that the FAST characteristic has no direction; a BRIEF characteristic descriptor based on pixel point binary digit comparison is adopted in a characteristic point description portion; the defects that the BRIEF descriptor is sensitive to the image noise and has no rotation invariance are improved; and compared with an SIFT algorithm, the ORB algorithm has the rotation invariance and noise resistance, and the operation speed of the ORB algorithm is higher than that of the SIFT algorithm by two orders of magnitude. The adaptive ORB object tracking method fully utilizes the characteristic of the ORB algorithm, performs further improvement on the PRB algorithm, brings forward the ORB algorithm on the basis of that the improvement, further improves the operation speed and the tracking accuracy, and better meets the demand for the real-time tracking.

Description

technical field [0001] The invention relates to an adaptive ORB target tracking method, which belongs to the field of computer vision. Background technique [0002] With the continuous development of our country's economy and the continuous progress of society, the flow of population is increasing. The huge population flow has brought great challenges to public security. In order to effectively ensure urban security, more and more cities continue to increase the monitoring of public places. Among them, video surveillance is an effective way. For example, in an airport, more than 2,000 cameras are installed. The current monitoring technology mainly collects real-time pictures of the monitored places through cameras, and then displays the collected pictures through display devices. Finally, it is necessary to manually watch the monitoring video to judge whether there is an emergency. This is a passive monitoring method. At the same time, some studies have shown that when peo...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies of the prior art, the present invention provides an adaptive ORB target tracking method, which adds the direction information of the FAST feature to the problem that the FAST feature does not have a direction, and uses pixel-based binary bits in the feature point description part. Compared with the BRIEF feature descriptor, and improved the disadvantages of the BRIEF descriptor being sensitive to image noise and not having rotation invariance, compared with the SIFT algorithm, the ORB algorithm not only has rotation invariance and anti-noise ability, but also operates faster than the SIFT algorithm improved by two orders of magnitude

Images