Real-Time Vision-Based Stop Sign Detection System on FPGA

Abstract

Many fatal accidents have happened due to drivers failing to stop at stop signs. A stop sign recognition system could be used to reduce the risk of accidents by warning the driver when a vehicle approaches a stop sign at an unexpected speed. In this paper, we describe the implementation of a real-time vision-based stop sign recognition system on a Xilinx Virtex-4 Field Programmable Gate Array (FPGA) device. This system uses a variant of the Histogram of Oriented Gradient (HoG) feature set and the efficient integral map for processing. Simulation and in-vehicle test results show good potential for deploying the system in practice. The FPGA system is able to process 60 frames of 752times480 pixels per second.