Complex backgrounds,large changes in target scales,many small targets,and unbalanced data sets are the main rea-sons for false detection,missed detection,and low detection accuracy of abnormal targets detection on transmission lines.There-fore,an enhanced feature extraction network was proposed,which effectively reduced the information loss during feature extrac-tion and better retained small target feature information.Two directions feature fusion was performed using channel optimization and spatial optimization modules to adapt to the multi-scale changes of the target,and the interference of complex background information was reduced.The balanced sampling with adaptive class suppression loss was used to adaptively balance positive and negative sample gradients to improve the detection accuracy of a few classes and solve the problem of positive and negative sam-ples as well as data imbalance in transmission line data sets.In the transmission line anomaly target detection task,the detection accuracy reaches 90.5％,which shows good detection effects for difficult scenarios.
关键词
输电线路/异常目标/目标检测/特征感知增强/双向特征融合/均衡采样/自适应类抑制损失
Key words
transmission line/anomaly object/object detection/feature-aware enhancement/two directions feature fusion/balanced sampling/adaptive class suppression loss
维普
万方数据