Transmission line detection in aerial images: An instance segmentation approach based on multitask neural networks

文献类型： 外文期刊

第一作者： Li, Bo

作者： Li, Bo;Chen, Cheng;Dong, Shiwen;Qiao, Junfeng

作者机构：

关键词： Transmission line detection; Deep neural networks; Convolutional neural networks

期刊名称：SIGNAL PROCESSING-IMAGE COMMUNICATION （ 影响因子：3.256； 五年影响因子：3.347 ）

ISSN： 0923-5965

年卷期： 2021 年 96 卷

页码：

收录情况： SCI

摘要： Camera-based transmission line detection (TLD) is a fundamental and crucial task for automatically patrolling powerlines by aircraft. Motivated by instance segmentation, a TLD algorithm is proposed in this paper with a novel deep neural network, i.e., CableNet. The network structure is designed based on fully convolutional networks (FCNs) with two major improvements, considering the specific appearance characteristics of trans-mission lines. First, overlaying dilated convolutional layers and spatial convolutional layers are configured to better represent continuous long and thin cable shapes. Second, two branches of outputs are arranged to generate multidimensional feature maps for instance segmentation. Thus, cable pixels can be detected and assigned cable IDs simultaneously. Multiple experiments are conducted on aerial images, and the results show that the proposed algorithm obtains reliable detection performance and is superior to traditional TLD methods. Meanwhile, segmented pixels can be accurately identified as cable instances, contributing to line fitting for further applications.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序