Abstract
The embedded visual tracking system has higher requirements for real-time performance and system resources, and this is a challenge for visual tracking systems with available hardware resources. The major focus of this study is evaluating the results of hardware optimization methods. These optimization techniques provide efficient utilization based on limited hardware resources. This paper also uses a pragmatic approach to investigate the real-time performance effect by implementing and optimizing a kernel correlation filter (KCF) tracking algorithm based on a vision digital signal processor (vision DSP). We examine and analyze the impact factors of the tracking system, which include DP (data parallelism), IP (instruction parallelism), and the characteristics of parallel processing of the DSP core and iDMA (integrated direct memory access). Moreover, we utilize a time-sharing strategy to increase the system runtime speed. These research results are also applicable to other machine vision algorithms. In addition, we introduced a scale filter to overcome the disadvantages of KCF for scale transformation. The experimental results demonstrate that the use of system resources and real-time tracking speed also satisfies the expected requirements, and the tracking algorithm with a scale filter can realize almost the same accuracy as the DSST (discriminative scale space tracking) algorithm under a vision DSP environment.
Highlights
Moving target tracking is a process of processing and analyzing the video images captured by photoelectric sensors and making full use of the information collected by sensors to track and locate the target
In the sample sample training stage, stage, the target target is selected selected and and is is shifted shifted circularly circularly to to obtain positive and negative samples
This chapter focuses on the experimental evaluation of the real-time performance of the tracking algorithm and the embedded system resources
Summary
Moving target tracking is a process of processing and analyzing the video (sequence) images captured by photoelectric sensors and making full use of the information collected by sensors to track and locate the target. Vision tracking based on correlation filters [5,6,7,8,9,10], such as kernel correlation filters (KCFs) [5,6] and correlation filters with scale estimation (DSST) [7,8], has become a research hotspot due to their advantages in terms of speed and efficiency. KCF is is aa discriminative discriminative tracking tracking algorithm algorithm that that is is divided divided into into two two stages: stages: sample sample training training and target detection. Ridge regression regression is used to train these samples to obtain the target classifier. The correlation is is used used to to train train these these samples samples to to obtain obtain the the target target classifier.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
