广东工业大学学报2025，Vol.42Issue(5)：86-95,10.DOI:10.12052/gdutxb.250089
面向电力场景图像的动态自适应增量目标检测DA-IOD算法
Dynamic Adaptive Enhancement for Power Scene Images DA-IOD Algorithm for Quantitative Target Detection
摘要
Abstract
Aiming to address the problems of insufficient adaptability to new targets and inability to perform incremental detection in power scenarios using traditional target detection technologies,this paper proposes a Dynamic Adaptive Incremental Object Detection algorithm for power scene images(DA-IOD).Firstly,a Task-Aligned Adaptive Feature Decoupling(TAFD)module is adopted to enhance the feature representation capability.Secondly,an Ultra-lightweight and Effective Dynamic Upsampler(DySample)is introduced to reduce computational burden and latency.Finally,a Complete Intersection over Union(CIoU)regression loss function is designed to modify the loss function of the baseline incremental Efficient-IOD algorithm,which further improves the detection accuracy of the proposed algorithm.In the 3+3 single-step incremental scenario of the Guangdong Power Grid Smart On-site Operation Dataset,out proposed method achieves an improvement of 2.4 percentage points in the mean Average Precision(mAP)when compared with the baseline algorithm.关键词
电网现场作业/输电线路/深度学习/目标检测/增量学习Key words
on-site power grid operation/transmission line/deep learning/object detection/incremental learning分类
信息技术与安全科学引用本文复制引用
陈健华,袁浩亮,陈海淋,许方园..面向电力场景图像的动态自适应增量目标检测DA-IOD算法[J].广东工业大学学报,2025,42(5):86-95,10.基金项目
广东省自然科学基金资助面上项目(2023A1515011041) （2023A1515011041）
南方电网公司科技项目(030100KK52230001) （030100KK52230001）
