Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition

doi:10.1007/s11063-018-9799-3

	Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition
	Chang, Wenkai1,2 ; Yang, Guodong1 ; Li, En1 ; Liang, Zize1
刊名	NEURAL PROCESSING LETTERS
	2018-12-01
卷号	48 期号:3 页码:1789-1800
关键词	Power line recognition Conditional generative adversarial nets Power line inspection Hybrid robot
ISSN号	1370-4621
DOI	10.1007/s11063-018-9799-3
通讯作者	Chang, Wenkai(changwenkai2013@ia.ac.cn)
英文摘要	In this paper, we propose a learning-based real-time method to recognize and segment an overhead ground wire (OGW) from an image, which is mainly applied to the multi-scale features in a cluttered environment. The recognition and segmentation are implemented under the framework of conditional generative adversarial nets. The generator is an end-to-end convolutional neural network (CNN) with skip connection. The discriminator is a multi-stage CNN and learns the loss function to train the generator. The OGW is recognized and shown in the downsampling visual saliency map. Thus, the location and existence of OGW are verified, which is crucial for the detection in the cluttered environment with structural lines. Detailed experiments and comparisons are performed on real-world images to demonstrate that the proposed method significantly outperforms the traditional method. Additionally, the optimized network achieves approximately 200fps on a graphics card (GTX970) and 30fps on an embedded platform (Jetson TX1).
资助项目	National Natural Science Foundation of China[61403374]
WOS关键词	POWER-LINE DETECTION ; MAINTENANCE
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000451460500031
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/25713]
专题	中国科学院自动化研究所
通讯作者	Chang, Wenkai
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Chang, Wenkai,Yang, Guodong,Li, En,et al. Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition[J]. NEURAL PROCESSING LETTERS,2018,48(3):1789-1800.
APA	Chang, Wenkai,Yang, Guodong,Li, En,&Liang, Zize.(2018).Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition.NEURAL PROCESSING LETTERS,48(3),1789-1800.
MLA	Chang, Wenkai,et al."Toward a Cluttered Environment for Learning-Based Multi-Scale Overhead Ground Wire Recognition".NEURAL PROCESSING LETTERS 48.3(2018):1789-1800.