ADAS and Video Surveillance Analytics System Using Deep Learning Algorithms on FPGA

Deep learning algorithms, such as CNN (Convolutional Neural Network), could provide high accuracy for great number of applications including ADAS (Advanced Driver Assistance System) and video surveillance analytics. Considering processing speed and energy efficiency, FPGA is a good hardware to construct customized CNN solution. In this demo session, we want to benefit from hardware technology, and show a fast speed and accurate video analytics system using state-of-the-art deep learning algorithms running on low power FPGA. This system could process 16 channels of continuous input video with the resolution of 1080p. Two functionalities could be easily switched by just clicking a button in this live demo: one ADAS system for vehicle, non-motorized vehicle, and pedestrian detection, tracking, and attributes analytics; and the other video surveillance system for face detection and recognition. The deep learning algorithms used are SSD and densebox for two kinds of objects' detection, which have state-of-the-art accuracy. The FPGA used is Xilinx MPSoC ZU9, and the whole board including this FPGA only cost about 50 Watts with Peak performance at 5.6 TOPS.