A Novel Technique for Moving Object Detection & Tracking with Optical Flow
C.Karthika Pragadeeswari1, G.Yamuna2
1C.Karthika Pragadeeswari, Assistant Professor, Department of ECE, Alagappa Chettiar Government college of Engineering and Technology, Karaikudi, India.
2G.Yamuna, Professor and Head, Department of ECE, Annamalai University, Annamalainagar, India.
Manuscript received on November 12, 2019. | Revised Manuscript received on November 25, 2019. | Manuscript published on 30 November, 2019. | PP: 5182-5188 | Volume-8 Issue-4, November 2019. | Retrieval Number: D7389118419/2019©BEIESP | DOI: 10.35940/ijrte.D7389.118419
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: A novel technique for tracking for tracking of objects in moving state is proposed to done by optical flow analysis which provide accurate results. In this Optical flow analysis, the velocity vectors of the pixels are obtained. As a result, velocity field is analyzed for the frame sequences which are considered and described for short duration of the video. This method doesn’t need to refer the previous frames which reduces the processing time and can be applicable for real time events. This novel algorithm produces better results with repeatability, uniqueness and reliability, compared to previous techniques. This method can be able to perform faster computation and comparison. This can be achieved by performing image convolutions for integral images followed by technical operations in the descriptors and detectors. Finally these methods can be simplified to the needed requirements. This leads to a package of better quality detection followed by description and recognition steps. The paper encircles a brief explanation of the algorithm and the results of simulation are also described in detail.
Keywords: Optical Flow, Frame Conversion, Noise, Velocity Field.
Scope of the Article: Artificial Intelligent Methods, Models, Techniques.