@article{Chen2025, 
author = {Jianhua Chen and Haoliang Yuan and Hailin Chen and Fangyuan Xu},
title = {Dynamic Adaptive Enhancement for Power Scene Images DA-IOD Algorithm for Quantitative Target Detection},
year = {2025},
journal = {Journal of Guangdong University of Technology},
volume = {42},
number = {5},
pages = {86-95},
keywords = {on-site power grid operation, transmission line, deep learning, object detection, incremental learning},
url = {https://www.sciopen.com/article/10.12052/gdutxb.250089},
doi = {10.12052/gdutxb.250089},
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.}
}