An Empirical Study of Pedestrian Detection Techniques with Different Image Resolutions
1Govardhan S.D, Assistant Professor, Department of Electronics and Communication Engineering, Coimbatore Institute of Engineering and Technology, Coimbatore (Tamil Nadu), India.
2Vasuki A, Professor, Department of Mechatronics Engineering CE, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 30 December 2018 | PP: 195-200 | Volume-8 Issue-2S, December 2018 | Retrieval Number: 100.1/ijeat.B10471282S18/18©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: Pedestrians are essential objects in computer vision. In real world images, the art of detecting pedestrians is an essential task for many applications like video surveillance, autonomous driver systems etc., Pedestrian detection is a significant characteristic of the autonomous vehicle driving system because identifying the pedestrians minimizes the accidents between vehicles and pedestrians. In existing techniques, deformable part model was used for identifying the pedestrians in image. However, the detection accuracy of the pedestrians with the existing systems was very low with high time consumption. The objective of our research work is to reduce the pedestrian detection time and space complexity for storing the pedestrian objects. In order to identify the existing pedestrian detection issues, the empirical study is carried out in this paper.
Keywords: Pedestrian, Autonomous Vehicle, Deformable Part Model, Space Complexity, Automatic Driver-Assistance Systems, Video Surveillance.
Scope of the Article: Image Security