SYNOPSIS
Pedestrian detection is an essential task in autonomous driving but often is challenged due to partial occlusion, different pose and body articulation of pedestrians, and sensitivity of sensors under ambient lighting conditions. Among different approaches, network fusion has been recently explored as an approach for improving pedestrian detection performance. However, most existing fusion methods suffer from runtime efficiency, modularity, scalability, and maintainability due to the complex structure of the entire fused models, their end-to-end training requirements, and sequential fusion process. Addressing these challenges, here we discuss a novel fusion framework that combines asymmetric inferences from object detectors and semantic segmentation networks for jointly detecting multiple pedestrians. This is achieved by introducing a consensus-based scoring method that fuses pair-wise pixel-relevant information from the object detector and the semantic segmentation network to boost the final confidence scores. The parallel implementation of the object detection and semantic segmentation networks in the fusion framework entails a low runtime overhead. The efficiency and robustness of the fusion framework are extensively evaluated by fusing different state-of-the-art pedestrian detectors and semantic segmentation networks on a public dataset. The generalization of fused models is also examined on new cross pedestrian data collected through an autonomous car. Results show that the fusion method significantly improves detection performance while achieving competitive runtime efficiency.
ABOUT THE SPEAKER
Muhammad Islam received his B.Sc. in Electrical and Electronic Engineering (EEE) from the Bangladesh University of Engineering and Technology (BUET), Bangladesh, in 2009. In 2018, Mr. Islam joined the North Carolina A&T State University to pursue his Ph.D. degree. He is a member of the Autonomous Cooperative Control of Emergent Systems of Systems (ACCESS) Lab in the Department of Electrical and Computer Engineering at North Carolina A&T State University, USA. His current research focuses on computer vision applications, vision-based control, and drive-by-wire control for autonomous vehicles. In particular, his research focuses on developing deep learning-based models for pedestrian detection.