Electric power safety clothing and safety helmet detection method and system based on illumination self-adaption

The invention provides an electric power safety clothing and safety helmet detection method and system based on illumination self-adaption, and belongs to the technical field of target detection. According to the method, an initial target detection model is constructed on the basis of a YOLO series algorithm; improving the initial target detection model by adopting an SE attention mechanism and an adaptive weight based on image illumination intensity to obtain an improved target detection model; and training the improved target detection model by using the electric power field images in different environments, and detecting the wearing conditions of the electric power safety clothing and the safety helmet based on the trained target detection model. According to the target detection model, feature representation is enhanced through an SE attention mechanism, then the recognition capability of the model under different illumination conditions is improved by adopting an illumination-based adaptive weight, and t