Workshop standard behavior monitoring method based on YOLO

Abstract

The invention relates to a YOLO-based workshop standard behavior monitoring method. The method comprises the following steps: (1) constructing a workshop behavior sample data set; (2) an E-YOLO target detection network comprising an encoder, a decoder and a classification regression network is constructed, behavior feature learning is carried out, the encoder is based on a YOLO backbone network, and the decoder constructs an efficient decoding network; and (3) obtaining real-time monitoring image information of the workshop, and performing identification detection on an image to be identified by using the detection model obtained in the step (2.3) to complete monitoring and early warning of non-standard behaviors of the workshop. According to the method, the backbone network, the efficient decoding network and the classification regression network are fused to form the E-YOLO target detection network, the method has higher feature representation capability, high speed can be kept in both training and testing, meanwhile, similar features can be accurately positioned and distinguished, the feature difference between regions is further determined, and the correctness of classification is ensured.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a monitoring method of workshop normative behavior based on YOLO. Background technique [0002] Industrial production workshops, houses used for industrial production, in addition to the fixed workshops used for production and research and development, also include its ancillary buildings, such as power distribution rooms, sewage and equipment storage and other supporting buildings. In industrial production and research and development operations, many The operation of large machines and equipment and the real-time operation of technicians, there are many potential safety hazards, such as the falling of small parts from high altitudes, the loss of motion trajectory during robot debugging, and the abnormal high-speed operation of large equipment on the production line. The technicians in the workshop have caused large and small injuries. In addition to the ex...

Images