Title: Proposed enhancement for vehicle tracking in traffic videos based on computer vision techniques
Authors: Mohamed Maher Ata; Mohamed El-Darieby; Mustafa Abdelnabi; Sameh A. Napoleon
Addresses: Faculty of Engineering, Tanta University, Egypt ' Faculty of Engineering, Regina University, Canada ' Faculty of Engineering, Tanta University, Egypt ' Faculty of Engineering, Tanta University, Egypt
Abstract: In this paper, traffic video enhancement has been approached according to means of computer vision algorithms. We have measured the average number of tracks which assigned correctly in the whole video. These tracks express the correct prediction of vehicles that guarantee the keep track on process of each vehicle from the first frame until the end frame. In addition, some video degradation (i.e., salt and pepper, speckle and Gaussian noise) have been applied in order to measure the effect of these degradations on the tracking efficacy. Some filtering systems have been applied to the degraded traffic video in order to conclude the best filter mask which satisfies the least deviation in the value of assigned tracks. Experimental results shows that both wiener and disk filters are the best mask for salt and pepper video degradation. However, median filter mask is the best choice for both speckle and Gaussian video degradations.
Keywords: video disturbance; prediction; assigned track; GMM; spatial filtering.
DOI: 10.1504/IJAIP.2022.126690
International Journal of Advanced Intelligence Paradigms, 2022 Vol.23 No.3/4, pp.262 - 275
Received: 26 Sep 2017
Accepted: 09 Oct 2017
Published online: 03 Nov 2022 *