FPGA implementation of hot spot detection in Infrared video

This paper describes a Hardware Description Language (HDL) based fully customizable module for real-time Infrared (IR) hot spot detection and feature extraction from a video stream. The aim of the research was to investigate and evaluate possible solutions for object detection using connected component labelling that could be implemented within a streaming video embedded processing platform as a hardware accelerator. The proposed algorithm is based on a single-pass approach; this guarantees real-time processing together with very low resource utilisation. The hardware implementation was verified on a Xilinx XUP V2P (XC2VP30 FPGA) development board with an IR camera module interfaced as a real-time video source. The system was tested with an image resolution of 640 × 480 processing input data at a speed of 30fps which was limited by the bandwidth of the camera.