Real-time traffic sign detection using SURF features on FPGA

Drivers´ failure to observe traffic signs, especially the stop signs, has led to many serious traffic accidents. Video-based traffic sign detection is an important component of driver-assistance systems. In earlier systems, simple color and shape-based detection methods have been broadly applied. Recently, feature-based traffic sign detection algorithms are proposed to obtain more accurate results, especially when combined with the previous two. The Speeded Up Robust Features (SURF) algorithm is an outstanding feature detector and descriptor with rotation and illumination invariance. Unfortunately, due to its computational complexity, the application of SURF algorithm remains limited in real-time systems. In this paper, we present a real-time SURF-based traffic sign detection system by exploiting parallelism and rich resources in FPGAs. The proposed hardware design is able to accurately process video streams of 800 × 600 resolution at 60 frame per second.