Identification Method of Pointer Instrument Based on Improved Yolov8

In view of the shortcomings of traditional methods in complex background and changeable shooting conditions, this paper introduces FasterNet backbone network to achieve model lightweight, and combines BiFormer attention mechanism and Focal-EIoU loss function to optimize the feature extraction and training process. The experimental results demonstrate that the improved YOLOv8 model (BiFaster-YOLOv8) has significantly enhanced the recognition Precision and operational efficiency in the task of pointer instrument recognition. It can effectively meet the instrument recognition requirements in the complex environment of substations, providing reliable technical support for the intelligent and automated inspection of electrical equipment.