Seminar by Prof Kar-Ann Toh, Efficient Detection of Human Objects in Images By Pixel Difference Matrix Projection (25 Oct 2022)

Pedestrian detection in the embedded system, such as video surveillance equipment, usually involves low-resolution pedestrian samples and requires a low computational cost. Many pedestrian detectors rely on a large feature pool and suffer in their efficiency and performance for real-time monitoring. In this work, a set of light-weight features is proposed to enhance the pedestrian detection performance when a small-medium scale of training data with low-resolution images is available.

To address this issue, a difference matrix projection (DMP) is developed to compute aggregated multi-oriented pixel differences using global matrix operations. Both the pixel differences and aggregation are computed using global matrix projection to avoid the laborious iterative operations. We tested our method on the INRIA, Daimler Chrysler classification (Daimler-CB), NICTA, and Caltech Pedestrian datasets. The experiments on these benchmark data sets show encouraging results in terms of detection performance, particularly for image datasets with low-resolution pedestrians. Kar-Ann Toh is a Professor in the School of Electrical and Electronic Engineering at Yonsei University, South Korea. He received the PhD degree from Nanyang Technological University (NTU), Singapore in 1999. He worked for two years in the aerospace industry prior to his post-doctoral appointments at research centers in NTU from 1998 to 2002. He was affiliated with the Institute for Infocomm Research in Singapore from 2002 to 2005 prior to his current appointment in Korea. He was a Visiting Professor at National University of Singapore in the year 2020 during his sabbatical leave. His research interests include biometrics, pattern classification, and machine learning. He has served/is serving as an Associate Editor of several international journals including IEEE Transactions on Biometrics, Behavior and Identity Science, IEEE Transactions on Information Forensics and Security, Journal of Franklin Institute, Pattern Recognition Letters, and IET Biometrics.