Multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm

With the rapid development of smart grid construction in China at present, there is a higher demand for diversified and intelligent video monitoring systems in substations. A multi-target intelligent tracking method for substation video surveillance based on YOLO v8 algorithm was proposed to address the issue of insufficient accuracy in identifying personnel, vehicles, and abnormal intrusions using existing substation video surveillance cameras. Firstly, the YOLO v8 algorithm was used to monitor the substation targets, and the sampling algorithm was used to increase the receptive field and improve the data feature fusion ability. The attention mechanism was used to identify small distant targets. Then, based on Kalman filter and substation camera motion stabilization, the information monitored by YOLO v8 was input into the BoTSORT algorithm to achieve intelligent tracking of substation video monitoring targets in multiple scenes and targets. Finally, experimental verification shows that compared to the YOLO v5 and YOLO v7 algorithms, the average accuracy of target recognition proposed has been improved by 9.73 percent and 5.28 percent, respectively, and the accuracy of target tracking has been improved by 12.34 percent and 8.41 percent, respectively. This has improved the intelligence level of the substation video monitoring system.