Flame smoke detection method based on ODConvBS-YOLOv5s

The invention relates to the technical field of image processing, and discloses a flame smoke detection method based on ODConvBS-YOLOv5s. Comprising the following steps: acquiring a flame smoke image, marking the image through labelligs to make a data set, and preprocessing the data set; according to the improved YOLOv5s flame smoke detection network, an improved YOLOv5s flame smoke detection network is constructed, the YOLOv5s network comprises an input end, a backbone network and a Neck module, the backbone network comprises CBS modules, a CSP1 structure and SPPF spatial pyramid pooling, the Neck module adopts a feature pyramid network FPN, the first two CBS modules in the backbone network of the YOLOv5s network are replaced by ODConvBS modules, and the first two CSP1 structures and the second two ODConvBS modules in the backbone network of the YOLOv5s network are replaced by ODConvBS modules in the backbone network of the YOLOv5s network. The ODConvBS module comprises a full-dimensional dynamic convolution