Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning

doi:10.1007/s11629-016-3950-2

CORC > 成都山地灾害与环境研究所 > 中国科学院水利部成都山地灾害与环境研究所 > Journal of Mountain Science > Journal of Mountain Science-2017 > Vol14 No.4

	Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning
	LU Heng; FU Xiao; LIU Chao; LI Long-guo; HE Yu-xin; LI Nai-wen
刊名	Journal of Mountain Science
	2017-04
卷号	14 期号:4 页码:731-741
关键词	Unmanned Aerial Vehicle Cultivated Land Deep Convolutional Neural Network Transfer Learning Information Extraction
ISSN号	1672-6316
DOI	10.1007/s11629-016-3950-2
通讯作者	LI Nai-wen
文献子类	期刊论文
英文摘要	The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle (UAV) low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning (DTCLE) was proposed. First, linear features (roads and ridges etc.) were excluded based on Deep Convolutional Neural Network (DCNN). Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognition for cultivated land information extraction (ECLE). The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 (of extracting cultivated land) with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 90.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.
语种	英语
内容类型	期刊论文
源URL	[http://ir.imde.ac.cn/handle/131551/18554]
专题	Journal of Mountain Science _Journal of Mountain Science-2017_Vol14 No.4
推荐引用方式 GB/T 7714	LU Heng,FU Xiao,LIU Chao,et al. Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning[J]. Journal of Mountain Science,2017,14(4):731-741.
APA	LU Heng,FU Xiao,LIU Chao,LI Long-guo,HE Yu-xin,&LI Nai-wen.(2017).Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning.Journal of Mountain Science,14(4),731-741.
MLA	LU Heng,et al."Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning".Journal of Mountain Science 14.4(2017):731-741.