Edinburgh Napier University

  An FPGA-based implementation of a pedestrian detection system using thermal infrared imaging is presented. The main feature of the processing platform is its ability to detect pedestrians at frame-rate from an infrared video stream. It is designed as a stand alone processing unit, supporting security systems in low visibility conditions. The processing unit digitizes a video source from a thermal infrared camera and after pre-processing, provides features of the detected pedestrians such as their position, height and width to a host computer where visualization of tracking and statistical operations can be applied to the received data. The data is transmitted to the host PC via a Bluetooth module interfaced to the development board. The wireless communication allows also for remote control of the processing system’s configuration registers. At the present stage of evaluation, the processing unit is limited to detect and transmit the coordinates of one pedestrian in a video frame. The system was implemented using a Xilinx Virtex-II Pro XC2VP30 FPGA chip, no additional memory is required.