Application of Object Detection Technology Based on Deep Learning in Safety Protection Equipment

Chemical enterprises develop strict norms, requiring operators to wear safety protective equipment in the production process in accordance with the regulations, the traditional safety supervision method relies on manual, requires a lot of manpower support, low effectiveness, poor real-time, can not carry out dynamic monitoring and early warning. In order to solve this problem, the research is based on deep learning algorithms to detect and identify safety protective equipment worn by chemical workers. In order to improve the performance and efficiency of mask wearing detection algorithm in the practical application of chemical enterprises, this study introduced the attention mechanism based on the YOLOv8 algorithm framework and combined with the characteristics of mask wearing detection task. Through this improvement, the algorithm can focus on the key areas of the image more accurately, thus improving the detection accuracy and speed. In order to further reduce the complexity of the algorithm, a lightweight feature extraction network is also designed. Under the premise of ensuring the detection accuracy, this network significantly reduces the requirement of computing resources, and makes the algorithm more suitable for deployment and operation in practical application scenarios such as chemical enterprises.