Abstract
Single-feature methods are unable to effectively track a target in an underground coal mine video due to the high background noise, low and uneven illumination, and drastic light fluctuation in the video. In this study, we propose an underground coal mine personnel target tracking method using multi-feature joint sparse representation. First, with a particle filter framework, the global and local multiple features of the target template and candidate particles are extracted. Second, each of the candidate particles is sparsely represented by a dictionary template, and reconstruction is achieved after solving the sparse coefficient. Last, the particle with the lowest reconstruction error is deemed the tracking result. To validate the effectiveness of the proposed algorithm, we compare the proposed method with three commonly employed tracking algorithms. The results show that the proposed method is able to reliably track the target in various scenarios, such as occlusion and illumination change, which generates better tracking results and validates the feasibility and effectiveness of the proposed method.
Highlights
Video target tracking has been an important research topic in the field of computer vision
We propose an underground coal mine personnel target tracking method using multi-feature joint sparse representation
We propose a target tracking algorithm that is suitable for an underground coal mine environment in this paper
Summary
Video target tracking has been an important research topic in the field of computer vision. An underground coal mine is a low-lit environment with uneven light distribution; second, the contrast between the underground coal mine target and the background is low; and third, when miners turn their bodies, the lamps on their helmets can cause a drastic change in the surrounding lighting of the target These factors substantially affect the tracking performance of various methods [3]. In the tracker l1 [9], by solving the problem of the minimum l1, each candidate target is described by a sparse linear combination of a set of target templates, in which the corresponding reconstruction error is used to compute the observed probability of a candidate target This method has demonstrated better tracking performance, especially in the case of noise and occlusion, but must find a solution for the minimum l1 problem for each candidate target, which is time-consuming. Experiments with videos from the standard video library validate the advantages of the proposed method in terms of accuracy, stability, real-time performance, and adaptability to the underground coal mine environment [3]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.