Farmland boundary extraction based on the AttMobile-DeeplabV3+network and least squares fitting of straight lines
文献类型： 外文期刊
作者： Lu, Hao 1 ; Wang, Hao 1 ; Ma, Zhifeng 4 ; Ren, Yaxin 5 ; Fu, Weiqiang 1 ; Shan, Yongchao 1 ; Hu, Shupeng 1 ; Zhang, Guangqiang 1 ; Meng, Zhijun 1 ;
作者机构： 1.Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing, Peoples R China
2.State Key Lab Intelligent Agr Power Equipment, Beijing, Peoples R China
3.Natl Engn Res Ctr Intelligent Equipment Agr, Beijing, Peoples R China
4.Beijing Inst Technol, Sch Integrated Circults & Electon, Beijing, Peoples R China
5.Beijing Acad Agr & Forestry Sci, Beijing Res Ctr Informat Technol Agr, Beijing, Peoples R China
关键词： UAV remote sensing; farmland boundary extraction; semantic segmentation; DeeplabV3+; linear fitting
期刊名称：FRONTIERS IN PLANT SCIENCE （ 影响因子：5.6； 五年影响因子：6.8 ）
ISSN： 1664-462X
年卷期： 2023 年 14 卷
页码：
收录情况： SCI
摘要： The rapid extraction of farmland boundaries is key to implementing autonomous operation of agricultural machinery. This study addresses the issue of incomplete farmland boundary segmentation in existing methods, proposing a method for obtaining farmland boundaries based on unmanned aerial vehicle (UAV) remote sensing images. The method is divided into two steps: boundary image acquisition and boundary line fitting. To acquire the boundary image, an improved semantic segmentation network, AttMobile-DeeplabV3+, is designed. Subsequently, a boundary tracing function is used to track the boundaries of the binary image. Lastly, the least squares method is used to obtain the fitted boundary line. The paper validates the method through experiments on both crop-covered and non-crop-covered farmland. Experimental results show that on crop-covered and non-crop-covered farmland, the network's intersection over union (IoU) is 93.25% and 93.14%, respectively; the pixel accuracy (PA) for crop-covered farmland is 96.62%. The average vertical error and average angular error of the extracted boundary line are 0.039 and 1.473 degrees, respectively. This research provides substantial and accurate data support, offering technical assistance for the positioning and path planning of autonomous agricultural machinery.
- 相关文献
作者其他论文 更多>>
-
Influence of speed measurement method on performance of an electric-drive maize precision planter
作者：Ling, Lin;Wu, Guangwei;Wen, Changkai;Xiao, Yuejin;Fu, Weiqiang;Dong, Jianjun;Ding, Jianhong;Meng, Zhijun;Yan, Bingxin;Ling, Lin;Wu, Guangwei;Wen, Changkai;Fu, Weiqiang;Meng, Zhijun
关键词：Speed measurement method; Maize; Electric-drive precision planter; Planting quality; No-tillage field; Tillage field
-
Interactive image segmentation based field boundary perception method and software for autonomous agricultural machinery path planning
作者：Wang, Hao;Ren, Yaxin;Lu, Hao;Shang, Yehua;Hu, Shupeng;Zhang, Guangqiang;Meng, Zhijun;Wen, Changkai;Fu, Weiqiang;Wang, Hao;Shang, Yehua;Hu, Shupeng;Zhang, Guangqiang;Meng, Zhijun;Wen, Changkai;Fu, Weiqiang;Wang, Hao;Shang, Yehua;Hu, Shupeng;Zhang, Guangqiang;Meng, Zhijun;Wen, Changkai;Fu, Weiqiang;Ma, Zhifeng
关键词：Orthoimagery; Instance and semantic segmentation; UAV; Weakly supervised deep learning; Semi-supervised learning
-
Collaborative path planning and task allocation for multiple agricultural machines
作者：Wang, Ning;Yang, Xi;Li, Han;Wang, Tianhai;Xiao, Jianxing;Zhang, Man;Wang, Hao;Wang, Hao
关键词：Multiple agricultural machinery collaborations; Task allocation; Complete coverage path planning; Topological map
-
Structural optimization method of rice precision direct seed-metering device based on multi-index orthogonal experimental
作者：Li, Hanqing;Ling, Lin;Wen, Changkai;Liu, Huaiyu;Wu, Guangwei;An, Xiaofei;Meng, Zhijun;Yan, Bingxin;Li, Hanqing;Wu, Guangwei;An, Xiaofei;Meng, Zhijun;Yan, Bingxin
关键词：rice; precision seed metering device; structural parameters; comprehensive optimization; matrix analysis
-
Method for the automatic recognition of cropland headland images based on deep learning
作者：Qiao, Yujie;Liu, Hui;Ma, Luyao;Qiao, Yujie;Meng, Zhijun;Chen, Jingping;Liu, Hui;Meng, Zhijun
关键词：cropland image; deep learning; image recognition; model compression; MobileNetV2 network
-
Accelerated verification method for the reliability of the motor drive mechanism of the corn precision seed-metering device
作者：Wen, Changkai;Li, Hanqing;Ling, Lin;Meng, Zhijun;Fu, Weiqiang;Yan, Bingxin;Wen, Changkai;Meng, Zhijun;Fu, Weiqiang;Yan, Bingxin;Wen, Changkai;Meng, Zhijun;Fu, Weiqiang;Yan, Bingxin;Zhang, Jing;Zheng, Kan
关键词：Motor drive mechanism; Reliability analysis; Accelerated testing; Field vibration; Corrected acceleration factor
-
Study on influencing factors of hole-filling performance of rice precision direct seed-metering device with hole ejection
作者：Li, Hanqing;Zhao, Chunjiang;Li, Hanqing;Yan, Bingxin;Meng, Zhijun;Ling, Lin;Yin, Yanxin;Zhang, Anqi;Zhao, Chunjiang;Wu, Guangwei;Yan, Bingxin;Meng, Zhijun;Yin, Yanxin;Zhang, Anqi;Wu, Guangwei
关键词：Rice; Precision seeding; Hole ejection; Seed metering device; Hole-filling performance
