In the rapid development of embedded systems, traditional methods are limited by computing resources and real-time performance, making it difficult to meet the needs of complex environments. To address this issue, research focuses on the STM32 embedded motion target tracking and detection method on the foundation of pulse-coupled neural network. The study first identifies the bottleneck of current embedded systems in motion target processing, and then proposes an innovative solution combining pulse-coupled neural network and STM32. Fast and accurate feature extraction and recognition of moving targets can be achieved by embedding the pulse-coupled neural network into the STM32 platform and fully utilizing its parallel processing characteristics. The optimization algorithm and hardware design ensure low-power, real-time, and high-precision target tracking and detection on STM32. The experiment confirms that the proposed algorithm can still maintain an accuracy of 89.1% in the presence of occlusion. It can still maintain success rates of 89.1% and 83.4% in the presence of occlusion, which has the best tracking performance compared to the other four algorithms. The successful application of research will help promote the widespread application of embedded technology in fields such as intelligent monitoring and autonomous driving.