Enhancing Occlusion Handling in Real-Time Tracking Systems through Geometric Mapping and 3D Reconstruction Validation
Priya. L1, Poornimathi. K2, P. Kumar3
1Dr. Priya.L, Department of Information Technology, Rajalakshmi Engineering College, Chennai (Tamil Nadu), India.
2Poornimathi.K, Department of Computer Science and Business Systems, Rajalakshmi Engineering College, Chennai (Tamil Nadu), India.
3Dr. P. Kumar, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai (Tamil Nadu), India.
Manuscript received on 20 July 2023 | Revised Manuscript received on 26 July 2023 | Manuscript Accepted on 15 August 2023 | Manuscript published on 30 August 2023 | PP: 7-13 | Volume-12 Issue-6, August 2023 | Retrieval Number: 100.1/ijeat.F42590812623 | DOI: 10.35940/ijeat.F4259.0812623
Open Access | Editorial and Publishing Policies | Cite | Zenodo | 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: Object detection is a classic research problem in the area of Computer Vision. Many smart world applications, like, video surveillance or autonomous navigation systems require a high accuracy in pose detection of objects. One of the main challenges in Object detection is the problem of detecting occluded objects and its respective 3D reconstruction. The focus of this paper is inter-object occlusion where two or more objects being tracked occlude each other. A novel algorithm has been proposed for handling object occlusion by using the technique of geometric matching and its 3D projection obtained. The developed algorithm has been tested using sample data and the results are presented.
Keywords: Computer vision, Image Processing, Object Detection, Occlusion, Reconstruction.
Scope of the Article: Computer vision