KFSTRCF-based target tracking architecture

Abstract

The invention relates to a KFSTRCF-based target tracking architecture, which comprises a discrete time Kalman estimator DKE and an STRCF, and the DKE comprises a discrete time system measurement subsystem and a discrete time system copy subsystem; the target tracking result output of the STRCF serves as measured value input of an observation model in discrete time system measurement, a DKE model is updated through a discrete time system copy subsystem, and a state estimation observation updating equation is obtained. According to the method, the Kalman filter and the STRCF are combined to realize visual tracking, so that the problem of instability caused by large-scale application change is solved; and moreover, a step length control method is also introduced to limit the maximum amplitudeof the output state of the proposed framework, so that the problem of target loss caused by sudden acceleration and steering is solved, the KFSTRCF-based target tracking architecture is superior to STRCF in most cases, and particularly, in sports events, the method shows better performance and stronger robustness than competitors.

Description

Technical field: [0001] The present invention relates to the technical field of computer vision target tracking, in particular to a KFSTRCF-based target tracking framework. Background technique: [0002] In recent years, visual tracking technology has been widely used in the field of computer vision, with the help of shared code and datasets, such as OTB-2015 and Temple-Color, we can use various evaluation criteria to understand how this visual tracking method performs, and Identify future research directions in these areas. In many real-world scenarios, as long as the initial state (such as position and size) of the target object in the frame of the image sequence is obtained, the visual tracking algorithm can track the target in the subsequent frames. Although many researchers have been working hard to improve tracking performance for decades, there are still many challenging problems, such as background clutter, occlusion, and out of field of view, etc., so far no algori...

AI Technical Summary

Problems solved by technology

[0007] The invention aims to effectively solve the problem of smoothing and optimizing the target state of the positioning algorithm in large-scale applications due to factors such as background clutter, illumination changes, occlusion, out-of-plane rotation, and out-of-field of view in target tracking, and proposes a KFSTRCF-based target The tracking architecture not only maintains the excellent real-time tracking performance of STRCF, but also overcomes the instability problem caused by large-scale application changes

Images