IViT: An Incremental Learning Method for Object Detection of Hidden Hazards in Transmission Line Corridors

IViT:一种用于输电线路走廊中隐蔽危险目标检测的增量学习方法

阅读:1

Abstract

The inspection of power transmission lines using unmanned aerial vehicles primarily relies on object detection. However, the continuous emergence of new obstacle types necessitates frequent updates to detection models, leading to substantial retraining costs. To address this challenge, we propose a novel framework named IViT, which integrates incremental learning with a hybrid CNN-Transformer architecture for improved identification. We combined knowledge distillation with the elastic response selection distillation strategy to enhance detection performance for old classes and strengthen knowledge retention through star convolutional residual blocks constructed via element-wise multiplication. We designed a separable convolution aggregation block that integrates PConv with an attention mechanism, effectively merging global and local information to improve detection accuracy. Finally, we unified the two modules into a hybrid block. In the static detection task, IViT achieves a mAP of 55.3%, a mAP(50) of 83.6%, and a mAP(75) of 61.0%. For the incremental detection task, it attains a mAP of 57.8%, a mAP(50) of 79.7%, and a mAP(75) of 62.3%. Extensive experiments on the transmission line corridor external damage dataset and the INSPLAD dataset demonstrate that IViT exhibits outstanding detection performance compared to mainstream static object detection models and incremental object detection models.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。