FPGA Implementation of Real-Time Pedestrian Detection Using Normalization-Based Validation of Adaptive Features Clustering

Presently, many researchers and engineers have investigated autonomous driving, which has significantly influenced the revolution of artificial intelligence (AI). One of the critical challenges for autonomous driving is the inadequate precision of autonomous vehicles in detecting pedestrians, which is a major safety hazard to human beings. In this paper, a Field Programmable Gate Array (FPGA) demonstration system with a normalization-based validity index (NbVI) has been proposed for real-time pedestrian detection. The proposed algorithm can accurately detect pedestrians by calculating the Manhattan distance between the target histogram of oriented gradient (HOG) features and real-time pedestrian HOG features. In lieu of sophisticated circuit layout and substantial training burden with neuron computation circuit, the proposed detection system with adaptive features clustering is hardware-friendly and is capable of real-time pedestrian detection using fewer training images with high detection rate (up to 99.2\%). Moreover, the function execution time of pedestrian detection is shortened by 25\% using FPGA acceleration.