Abstract
The furrow irrigation, which forms a ridge-furrow and grows several crops on the ridge, involves the seeding work using the tractor that follows the path of the ridge. This work requires long hours labor from human, and there is a possibility that the work efficiency may decrease. In this paper, we propose deep learning and stereo image-based algorithms for sowing tasks on ridges via autonomous path-following of the tractor. The collected stereo image is converted into a depth image through a matching algorithm, and the depth image is input to a MobileNetV2-based deep learning network model to obtain a center line of the ridge. In addition, the target value of steering angle control is calculated by waypoint preview control concept. so that the tractor can follow the estimated center line of the ridge. The proposed algorithm is verified by GPS-based path information of autonomous driving and comparing it with human-operated driving path.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
C. Yun et al., Stereovision-based guidance line detection method for auto-guidance system on furrow irrigated fields, IFAC-PapersOnLine, 51 (17) (2018) 157–161.
A. Stentz et al., A system for semi-autonomous tractor operations, Autonomous Robots, 13 (1) (2002) 87–104.
D.-H. Seo et al., Development of steering control system based on CAN for autonomous tractor system, Korean Journal of Agricultural Science, 37 (1) (2010) 123–130.
A. B. McBratney and R. Webster, Detection of ridge and furrow pattern by spectral analysis of crop yield, International Statistical Review/Revue Internationale de Statistique (1981) 45–52.
A. Takagaki et al., Image processing for ridge/furrow discrimination for autonomous agricultural vehicles navigation, IFAC Proceedings Volumes, 46 (18) (2013) 47–51.
S.-J. Lin, W. C. Qi and J.-J. Chen, Ridge-furrow detection in glycine max farm using deep learning, 2020 International Conference on Pervasive Artificial Intelligence (ICPAI), IEEE (2020).
S. Hong et al., A path tracking control algorithm for underwater mining vehicles, Journal of Mechanical Science and Technology, 23 (8) (2009) 2030–2037.
K. He et al., Mask R-CNN, Proceedings of the 2017 IEEE International Conference on Computer Vision, Venezia (2017).
A. Farhadi and R. Joseph, Yolov3: an incremental improvement, arXiv:1804.02767 (2018).
O. Ronneberger, F. Philipp and B. Thomas, U-net: convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham (2015).
M. Sandler et al., Mobilenetv2: inverted residuals and linear bottlenecks, Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City (2018).
M. Tan and L. Quoc, Efficientnet: rethinking model scaling for convolutional neural networks, International Conference on Machine Learning, Long Beach (2019).
K. He et al., Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas (2016).
K. Wada, Labelme: Image Polygonal Annotation with Python, https://doi.org/10.5281/zenodo.5711226 (2022).
A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin and A. A. Kalinin, Albumentations: fast and flexible image augmentations, Information, 11 (2) (2020) 125.
Acknowledgments
This work was supported by Korea Institute for Advancement of Technology (KIAT) grant funded by the Korea government (MOTIE) (P0008473, HRD Program for Industrial Innovation) and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2017R1D1A3B03028104).
Author information
Authors and Affiliations
Corresponding author
Additional information
Hojun Kang is a Master’s student of the Dept. of Mechatronics Engineering, Chungnam National University, Daejeon, Korea. He received his B.S. degree in Mechatronics Engineering from Chungnam National University. His research interests include control and image processing using deep learning for autonomous vehicle.
Dongoh Seo is a Master’s student of the Robotics Program, Korea Advanced Institute of Science and Technology, Daejeon, Korea. He received his B.S. degree in Mechatronics Engineering from Chungnam National University. His research interests include soft robotics. He is focusing on vine robot, a soft growing robot.
Beomjin Lee is a Master’s student of the Dept. of Mechatronics Engineering, Chungnam National University, Daejeon, Korea. He received his B.S. degree in Mechatronics Engineering from Chungnam National University. His research interests include mobility, neural network control.
Jonggyu Han is a Principal Engineering Researcher at the TYMICT, in Gongjucity, Korea. He received his Master’s degree in the Department of Mechatronics Engineering, Chungnam National University in 2000. From 2000 to 2020, he worked with the TYM, a specialized agricultural machinery company. And he has been working at the TYMICT from 2020 to the present. His research interests are in autonomous driving agricultural machinery and telematics systems.
Junhee Jo is an Engeering Reasearcher at the TYMICT, Gongju-city, Korea. He received his Master’s degree from the Department of Mechatronics Engineering, Chungnam National University. He has been working at TYMICT from 2020 to the present. His research interests are in agricultural machinery automation systems.
Mooncheol Won is a Professor at the Department of Mechatronics of Chungnam National University, Daejeon, Korea. He received the B.S. and M.S. degrees in Naval Architecture from Seoul National University, Korea, and the Ph.D. degree in Mechanical Engineering from U.C. Berkeley, USA in 1995. He worked with the the Korea Institute of Machinery & Materials (KIMM), Daejeon, South Korea, from 1987 to 1990. His research interests include control of vehicles and mechatronics systems. He is also focusing on artificial intelligence applications on industrial problems such as self driving of vehicles and robots in regards to computer vision.
Rights and permissions
About this article
Cite this article
Kang, H., Seo, D., Lee, B. et al. Ridge-following control for agricultural tractors using deep learning and stereo camera. J Mech Sci Technol 36, 3667–3675 (2022). https://doi.org/10.1007/s12206-022-0641-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-022-0641-5