STELLaR - A case-study on SysTEmaticaLLy embedding a Traffic Light Recognition

Jan Micha Borrmann, Frederik Haxel, Dennis Nienhüser, Alexander Viehl, J. Marius Zöllner, Oliver Bringmann, Wolfgang Rosenstiel

Abstract: In this paper we present an embedded implementation of a Traffic Light Recognition (TLR) on a low-cost FPGA device with low memory usage.We follow a systematic approach where we thoroughly investigate computational hot-spots, and systematically partition the system into hardware and software components which we both optimize. Our implementation is evaluated using an actual FPGA board as Hardware-in-the-Loop (HIL). In contrast to other approaches, we are not restricted to filled lights but also detect other types such as arrows, pedestrians or bicycle ones when provided with training data. With an average performance of 45 fps and minimum 12 fps with ~ 5 Watts of power consumption, our system shows real-time behavior even on high-definition video data with high comparable recognition rates while still obeying automotive constraints such as low power. As far as we know, we are the first ones presenting an embedded TLR solution.