YOLOv5-LF: An Optimized YOLOv5 Algorithm for Real-Time Automatic Tracking

Recent research has concentrated on enhancing robot visual tracking in dynamic settings. To boost real-time tracking capabilities, we introduce an optimized robot visual tracking control system that employs an advanced lightweight YOLOv5 algorithm. This system integrates the LCNet-a lightweight CPU-based Convolutional Neural Network-and a PConv-driven FasterNet module, both of which significantly enhance the detection of object features. Our experimental setup, which uses an industrial camera to acquire target pose data, demonstrates that after implementing the optimized model, the system efficiently detects and tracks moving objects in real-time from video streams. The gimbal's positioning is dynamically adjusted in response to the moving target's image displacement. The YOLOv5-LF network model, quantified with OpenVINO, has demonstrated a detection accuracy of 95.23% and a recognition rate of 90 frames per second (FPS) on Intel's NUC. This not only ensures seamless real-time system management but also enhances the precision of object detection. The refined detection algorithm notably outperforms the original network in terms of visual tracking efficacy on our experimental platform.