FPGA Implementation of Infrared Small Target Detection Using the Global Contrast Method

With the continuous development of infrared small target detection technology, the detection accuracy and detection rate in complex backgrounds have significantly improved. However, the performance improvement inevitably leads to increased algorithm complexity, resulting in higher computational load and resource consumption, which poses challenges for applications that require high real-time performance and low power consumption. In response to this challenge, this paper proposes an FPGA-based system for detecting small targets in infrared images. The system adopts a Global Contrast Measurement (GCM) algorithm framework and fully utilizes the parallel computing and pipelining capabilities of the FPGA to achieve hardware-level optimization of the GCM algorithm. Experimental results show that the system's computation delay is 0.863 milliseconds, significantly reducing resource usage and power consumption while meeting the real-time and low-power requirements of practical applications.