A Hybrid Surf-Based Tracking Algorithm with Online Template Generation
Anshul Pareek1, Nidhi Arora2
1Anshul Pareek, ECE Deptt, Maharaja Surajmal Institute Of Technology, Delhi India.
2Dr. Nidhi Arora, CSE Department, G.D. Goenka University, Gurugram, India.
Manuscript received on September 17, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 794-798 | Volume-8 Issue-12, October 2019. | Retrieval Number: L32051081219/2019©BEIESP | DOI: 10.35940/ijitee.L3205.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Visual tracking is the most challenging fields in the computer vision scope. Occlusion full or partial remains to be a big mile stone to achieve .This paper deals with occlusion along with illumination change, pose variation, scaling, and unexpected camera motion. This algorithm is interest point based using SURF as detector descriptor algorithm. SURF based Mean-Shift algorithm is combined with Lukas-Kanade tracker. This solves the problem of generation of online templates. These two trackers over the time rectify each other, avoiding any tracking failure. Also, Unscented Kalman Filter is used to predict the location of target if target comes under the influence of any of the above mentioned challenges. This combination makes the algorithm robust and useful when required for long tenure of tracking. This is proven by the results obtained through experiments conducted on various data sets.
Keywords: Visual Tracking, SURF, Mean-Shift, Lukas Kanade Method, Unscented Kalman Filter Predictor, GrabCut, Online Template Generation and Updation.
Scope of the Article: Algorithm Engineering