数字农科院2.0

Study of convolutional neural network-based semantic segmentation methods on edge intelligence devices for field agricultural robot navigation line extraction

文献类型： 外文期刊

作者： Jiya Yu;Jiye Zhang;Aijing Shu;Yujie Chen;Jianneng Chen;Yongjie Yang;Wei Tang;Yanchao Zhang

作者机构：

关键词： Deep learning;Edge computing;Navigation;Semantic segmentation

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2023 年 209 卷

页码：

收录情况： SCIE（2023版） ; ; EI（2023版）

摘要： Smart agricultural machinery is emerging as the future trend for field robots, and the fully automatic robot has a great application prospect. However, it is a big challenge for robots to navigate in complex farmland environments. In this research, 5 deep learning-based computer vision methods under different field scenes for field navigation line extraction were studied and successfully deployed on an embedded system, which can be integrated into robots for automatic navigation in the future. The field road was segmented by the semantic segmentation algorithm at first, and then the navigation line is extracted from the segmented image by a polygon fitting method. Finally, all the models are transformed through the TensorRT library and deployed on the edge computing device Jetson Nano. In the experiment, five reprehensive semantic segmentation networks namely UNet, Deeplabv3+, BiseNetv1, BiseNetv2, and ENet networks were selected. Among the five networks, Deeplabv3+ is the most accurate. In five scenes, its average segmentation accuracy is 84.87 %, and the navigation line error is 9.59 pixels. Especially in the third scene with shadow and occlusion, it performs best, with only 8.34 pixel error, But the speed of Deeplabv3+ is only 9.7 FPS. ENet, BiseNetv1, and BiseNetv2 are lightweight networks. The speed of ENet is 16.8 FPS, BiseNetv2 is 17 FPS, and BiseNetv1 is 15.8 FPS. In segmentation accuracy and navigation line error, ENet performs better than BiseNet series networks, which are 84.94 % and 10.73 pixels, respectively. In the third scene with shadow and occlusion, it also performs slightly better than BiseNet series networks. In summary, deep learning-based semantic segmentation methods have strong robustness and stability in complex environment compared with previous research. Among all currently available neural networks, ENet has the best performance and good application potential in field navigation.

分类号：

  • 相关文献

[1]Real-Time Object Detection Based on UAV Remote Sensing: A Systematic Literature Review. Zhen Cao,Lammert Kooistra,Wensheng Wang,Leifeng Guo,João Valente. 2023

[2]MRUNet: A two-stage segmentation model for small insect targets in complex environments. Fu kuan WANG,Yi qi HUANG,Zhao cheng HUANG,Hao SHEN,Cong HUANG,Xi QIAO,Wan qiang QIAN. 2023

[3]Maize tassel area dynamic monitoring based on near-ground and UAV RGB images by U-Net model. Xun Yu,Dameng Yin,Chenwei Nie,Bo Ming,Honggen Xu,Yuan Liu,Yi Bai,Mingchao Shao,Minghan Cheng,Yadong Liu,Shuaibing Liu,Zixu Wang,Siyu Wang,Lei Shi,Xiuliang Jin. 2022

[4]High-Precision Tea Plantation Mapping with Multi-Source Remote Sensing and Deep Learning. Yicheng Zhou,Lingbo Yang,Lin Yuan,Xin Li,Yihu Mao,Jiancong Dong,Zhenyu Lin,Xianfeng Zhou. 2024

[5]Global rice multiclass segmentation dataset (RiceSEG): comprehensive and diverse high-resolution RGB-annotated images for the development and benchmarking of rice segmentation algorithms. Junchi Zhou,Haozhou Wang,Yoichiro Kato,Tejasri Nampally,P. Rajalakshmi,M. Balram,Keisuke Katsura,Hao Lu,Yue Mu,Wanneng Yang,Yangmingrui Gao,Feng Xiao,Hongtao Chen,Yuhao Chen,Wenjuan Li,Jingwen Wang,Fenghua Yu,Jian Zhou,Wensheng Wang,Xiaochun Hu,Yuanzhu Yang,Yanfeng Ding,Wei Guo,Shouyang Liu. 2025

[6]Semantic Category Balance-Aware Involved Anti-Interference Network for Remote Sensing Semantic Segmentation. Nie, Jie,Wang, Zhaoxin,Liang, Xinyue,Yang, Chenxue,Zheng, Chengyu,Wei, Zhiqiang. 2023

[7]Design and Experiment of Electric Uncrewed Transport Vehicle for Solanaceous Vegetables in Greenhouse. Chunsong Guan,Weisong Zhao,Binxing Xu,Zhichao Cui,Yating Yang,Yan Gong. 2025

[8]RESEARCH ON THE INTEGRATED NAVIGATION AND POSITIONING SYSTEM FOR POWER CHASSIS IN HILLY AND MOUNTAINOUS AREAS BASED ON PPP-RTK/IMU; 基于 PPP-RTK/IMU 的丘陵山区动力底盘组合导航定位系统研究. Weisong Zhao,Binxing Xu,Chunsong Guan,Jia Deng,Jian Wu,Haiyong Ren,Jinlong Wang,Shen Zhang,Zhifeng Chen. 2025

[9]Speeding at the Edge: An Efficient and Secure Redactable Blockchain for IoT-Based Smart Grid Systems. Youshui Lu,Xiaojun Tang,Lei Liu,F. Richard Yu,Schahram Dustdar. 2023

[10]GVC-YOLO: A Lightweight Real-Time Detection Method for Cotton Aphid-Damaged Leaves Based on Edge Computing. Zhenyu Zhang,Yunfan Yang,Xin Xu,Liangliang Liu,Jibo Yue,Ruifeng Ding,Yanhui Lu,Jie Liu,Hongbo Qiao. 2024

[11]A self-adaptive parallel image stitching algorithm for unmanned aerial vehicles in edge computing environments. Xin Xu,Li Zhang,Jibo Yue,Heming Zhong,Ying Wang,Jie Liu,Yanhui Lu,Hongbo Qiao. 2024

[12]Lightweight model for beef cattle behavior recognition from quadruped robot video in grassland pastures. Wei, Peigang,Sun, Wei,Cao, Shanshan,Kong, Fantao. 2025

[13]QseedNet: A lightweight deep-learning framework for detection of quarantine weed seeds in imported soybean inspection. Jianwei Qiang,Xi Qiao,Yun Yu,Ze Liu,Zhihui Tian,Shuo Zhang. 2025

[14]Multi-Scale Depthwise Separable Convolution for Semantic Segmentation in Street–Road Scenes. Yingpeng Dai,Chenglin Li,Xiaohang Su,Hongxian Liu,Jiehao Li. 2023

[15]TMNet: A Two-Branch Multi-Scale Semantic Segmentation Network for Remote Sensing Images. Yupeng Gao,Shengwei Zhang,Dongshi Zuo,Weihong Yan,Xin Pan. 2023

[16]Improved 3D point cloud segmentation for accurate phenotypic analysis of cabbage plants using deep learning and clustering algorithms. Ruichao Guo,Jilong Xie,Jiaxi Zhu,Ruifeng Cheng,Yi Zhang,Xihai Zhang,Xinjing Gong,Ruwen Zhang,Hao Wang,Fanfeng Meng. 2023

[17]Deriving Agricultural Field Boundaries for Crop Management from Satellite Images Using Semantic Feature Pyramid Network. Yang Xu,Xinyu Xue,Zhu Sun,Wei Gu,Longfei Cui,Yongkui Jin,Yubin Lan. 2023

[18]Attention-optimized DeepLab V3+for automatic estimation of cucumber disease severity. Li, Kaiyu,Zhang, Lingxian,Li, Bo,Li, Shufei,Ma, Juncheng. 2022

[19]Detection and Mapping of Chestnut Using Deep Learning from High-Resolution UAV-Based RGB Imagery. Yifei Sun,Zhenbang Hao,Zhanbao Guo,Zhenhu Liu,Jiaxing Huang. 2023

[20]Lightweight multi-scale feature dense cascade neural network for scene understanding of intelligent autonomous platform. Dai, Yingpeng,Meng, Lingfeng,Sun, Fushan,Wang, Songfeng. 2024

作者其他论文 更多>>