An Efficient Multiple Object Recognition using Gait Feature Extraction based on Gaussian Filter
S. Suchitra1, S. Sangeetha2
1S. Suchitra, Department of Computer Science and Engineering, Hindustan Institute of Technology & Science, Chennai, India.
2S. Sangeetha, Department of Master of Computer Application, Hindustan Institute of Technology & Science, Chennai, India.
Manuscript received on 03 April 2019 | Revised Manuscript received on 07 May 2019 | Manuscript published on 30 May 2019 | PP: 898-904 | Volume-8 Issue-1, May 2019 | Retrieval Number: A9997058119/19©BEIESP
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: Object tracking plays a major role of surveillance in the real time world of robot applications. The object tracking deals with different sizes of objects for better outcomes and the execution relies upon its exactness and its capacity that should track the objects at a high speed. The movement to remove valuable data from the video grouping and monitoring can be characterized toward fragmenting the locale of object tracking. The essential things of video perception, for example, object identification, tracking and recognition using various cameras. Objects are recognized by utilizing the background subtraction of every video frame, and are tracked by a Kalman channel with Gaussian method (KF-GM).To support multiple objects tracking, object recognized algorithm is connected utilizing Gait technique which is utilized with its vigorous execution. Handling of edge is done in MATLAB to get location, tracking and perceived outcomes. It yields promising tracking performance on the challenging videoset01 and videoset02 dataset.
Index Terms: Smart Video Surveillance, Moving Object Identification, Kalman Filter, Gaussian Filter, Multiple Object Tracking, Gait Feature Extraction.
Scope of the Article: Pattern Recognition