Video Summarization: A Review on Local Binary Pattern and Classification Process
Aiswarya. N. R1, Smitha. P. S2
1Aiswarya. N.R, Department of Electronics and Communication Engineering, Sree Chitra Thirunnal College of Engineering, Trivandrum (Kerala), India.
2Smitha.P.S , Department, of Electronics and Communication Engineering , Sree Chitra Thirunnal College of Engineering, Trivandrum (Kerala), India.
Manuscript received on 13 June 2017 | Revised Manuscript received on 20 June 2017 | Manuscript Published on 30 June 2017 | PP: 313-315 | Volume-6 Issue-5, June 2017 | Retrieval Number: E5093066517/17©BEIESP
Open Access | Editorial and Publishing 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: Video summarization system can yield good results if the high level features also called the semantic concepts in video frame are modeled accurately by considering the temporal aspects of the frames. The existing system is context aware surveillance video summarization which is a Domain dependent System. It works only on low level features and correlation between them is extracted and updated using dictionary algorithm in an online fashion. Thus dictionary size increases. In contrast to the existing method, the proposed system is a domain adaptive video summarization framework based on high level features in such a way that the summarized video can capture the key contents by assuring minimum number of frames. One of the high level features extracted is Local binary pattern (LBP).Key frames can be extracted after finding the Euclidean distance between the LBP descriptor in different methods. The key frames are classified using k-means clustering algorithm. The result is compared with several datasets thus showing the effectiveness of the proposed system. The entire work can be simulated using matlab.
Keywords: Euclidean Distance; Feature Extraction; LBP; Video Summarization
Scope of the Article: Classification