Title: A survey of detecting pedestrians from low resolution imagery

Authors: Kyaw Kyaw Htike; Neoh Siew Chin; Zaw Zaw Htike; Choo Wou Onn

Addresses: School of Information Technology, UCSI University, Malaysia ' Faculty of Engineering, UCSI University, Malaysia ' Department of Mechatronic Engineering, International Islamic University, Malaysia ' School of Information Technology, UCSI University, Malaysia

Abstract: Being able to detect pedestrians in image or video has numerous potential benefits in many diverse applications such as image retrieval, elderly monitoring and safety, person counting and driver assistance systems. Although much work have been done for pedestrian detection, recent state-of-the-art research indicate that a lot of improvements still need to be made, especially when it comes to low resolution imagery. Despite a number of review papers on pedestrian detection that have been published, there is a great need for a survey paper that focuses on pedestrian detection for low resolution data. In this paper, we perform an in-depth critical analysis and review of the most representative and relevant papers in this area, including identification and breaking down of the pipeline for low resolution pedestrian detection systems, as well as, discussing and analysing the underlying causes behind low resolution data as well as recommending potential solutions.

Keywords: low resolution; detecting pedestrians; object detection; image analytics; computer vision.

DOI: 10.1504/IJISDC.2017.090877

International Journal of Intelligent Systems Design and Computing, 2017 Vol.1 No.3/4, pp.231 - 261

Received: 05 Oct 2017
Accepted: 05 Nov 2017

Published online: 26 Mar 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article