Research on Garbage Detection Method Based on YOLOv7
With the development of social economy and the continuous improvement of people's living standard,the amount of do-mestic garbage has rapidly increased.In order to effectively deal with the low efficiency and poor accuracy of garbage sorting,a gar-bage detection algorithm based on YOLOv7 network as a base model is proposed.The algorithm made a series of modifications to the YOLOv7 network,firstly,the attention mechanism SimAM was added to the head module,which enhanced the model's perceptual a-bility and adaptive ability so as to improve the detection accuracy;Secondly,non-maximum suppression(soft-NMS)was replaced in the backbone network to remove redundant detection frames;Then,the loss function was improved to be the edge regression loss function SIoU,improving the accuracy and speed of detection;Finally,the C3 module was used to replace the ELAN-W module in the YOLOv7,promoting the network's detection ability for smaller targets.Through experiment on the data-set,the average accuracy of the improved network is 98.93％,which is better than the 96.31％of the original model.Experimental results show that the im-proved algorithm has a more obvious enhancement in detection.
deep learningtarget detectionattention mechanismnon maximum suppressiongarbage classification
万方数据
维普
