A low-cost and high-performance architecture for robust human detection using histogram of edge oriented gradients

Human detection on emerging intelligent transportation systems is a challenging task in hardware implementation. The histogram of oriented gradients (HOG) based human detection is the most successful algorithm due to its superior performance. Unfortunately, more intensive computations and poor performance at a multi-scale and low-contrast makes human detection more difficult and unreliable. To address the above-stated problems, an efficient histogram of edge oriented gradients (HEOG) based human detection is proposed for preserving the edge gradients at low-contrast and to support the multi-scale detection. The proposed algorithm uses approximation methods and adopts pipelined structure that utilizes low-cost and high-speed respectively. Experiments conducted on various challenging human datasets, shows that the outcome of the proposed method provides efficient detection. This algorithm has been synthesized on Xilinx Virtex-5 FPGA board and achieves better hardware utilization compared to other state-of-the-art approaches.