干旱区生态环境知识资源中心(Arid): Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery

Arid

DOI	10.1007/s11676-021-01375-z
	Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery
	Zhang, Chong; Zhang, Li; Zhang, Bessie Y. J.; Sun, Jingqian; Dong, Shikui; Wang, Xueyan; Li, Yaxin; Xu, Jian; Chu, Wenkai; Dong, Yanwei; Wang, Pei
通讯作者	Zhang, L (corresponding author), Beijing Forestry Univ, Coll Sci, Beijing 100083, Peoples R China.
来源期刊	JOURNAL OF FORESTRY RESEARCH
ISSN	1007-662X
EISSN	1993-0607
出版年	2021-07
英文摘要	Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer's and user's accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.
英文关键词	UAV images Semantic segmentation LResU-net Land cover classification
类型	Article ; Early Access
语种	英语
开放获取类型	hybrid
收录类别	SCI-E
WOS记录号	WOS:000676068000002
WOS关键词	CARBON STOCKS ; ACCURACY
WOS类目	Forestry
WOS研究方向	Forestry
来源机构	北京林业大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/367541
作者单位	[Zhang, Chong; Zhang, Li; Sun, Jingqian; Wang, Xueyan; Li, Yaxin; Wang, Pei] Beijing Forestry Univ, Coll Sci, Beijing 100083, Peoples R China; [Dong, Shikui] Beijing Forestry Univ, Coll Grassland Sci, Beijing 100083, Peoples R China; [Xu, Jian; Chu, Wenkai; Dong, Yanwei] Xingan League Grassland Workstn, Hinggan League 137400, Inner Mongolia, Peoples R China; [Zhang, Bessie Y. J.] Stanford Univ, Math & Computat Sci Dept, Stanford, CA 94305 USA
推荐引用方式 GB/T 7714	Zhang, Chong,Zhang, Li,Zhang, Bessie Y. J.,et al. Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery[J]. 北京林业大学,2021.
APA	Zhang, Chong.,Zhang, Li.,Zhang, Bessie Y. J..,Sun, Jingqian.,Dong, Shikui.,...&Wang, Pei.(2021).Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery.JOURNAL OF FORESTRY RESEARCH.
MLA	Zhang, Chong,et al."Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery".JOURNAL OF FORESTRY RESEARCH (2021).