Abstract
In agricultural production, periodic monitoring and determination of the state of crops are required. An additional complexity is the multicomponent structure of the analyzed images. For the purpose of intelligent analysis of agricultural fields, RGB image databases were formed and divided into four classes. An analysis of variants of deep neural network (DNN) architectures based on U-net is carried out. DNN has been developed for the segmentation of problem areas in fields. An experimental quality assessment was carried out on the DeepLabV3 architecture in combination with ResNet50. The constructed DNN family based on DeepLabV3 with ResNet50 showed efficiency of distribution and sufficient speed in segmentation of fragments of agricultural fields and determination of the state of crops. It is established that the increase in accuracy of segmentation of agricultural field images according to the “dice coefficient” criterion is limited by the resolution and quality of manual marking of images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Saiz-Rubio V From smart farming towards agriculture 5.0: a review on crop data management. https://www.mdpi.com/2073-4395/10/2/207/htm
Alberto G-G, Sergio O-E, Sergiu O, Victor V-M, Jose G-R A review on deep learning techniques applied to semantic segmentation. https://doi.org/10.48550/arXiv.1704.06857
Badrinarayanan V, Kendall A, Cipolla R SegNet: a deep convolutional encoder-decoder architecture for image segmentation. http://docs.cntd.ru/document/902361843
Xu B et al (2004) Remote sensing monitoring on dynamic status of grassland productivity and animal loading balance in Northern China. In: IGARSS 2004. 2004 IEEE international geoscience and remote sensing symposium, Anchorage, AK, USA, vol 4, pp 2306–2309. https://doi.org/10.1109/IGARSS.2004.1369747
Pelletier C, Valero S, Inglada J, Champion N, Dedieu G (2016) Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas. Rem Sens Environ 187:156–168
Zhang L, Yu W, Li G, Zhang H (2016) An approach for flood inundated duration extraction based on Level Set Method using remote sensing data. In: 2016 IEEE international geoscience and remote sensing symposium (IGARSS), Beijing, China, pp 1820–1822. https://doi.org/10.1109/IGARSS.2016.7729467
Zeng Z-C, Wang Y, Pongetti TJ, Gong F-Y, Newman S, Li Y, Natraj V, Shia R-L, Yung YL, Sander SP (2020) Tracking the atmospheric pulse of a North American megacity from a mountaintop remote sensing observatory. Rem Sens Environ 248:112000
Tokarev KE et al (2015) Crops reclamation management based on hybrid neuro-fuzzy systems. IOP Conf Ser-Earth Environ Sci 421:042015. https://doi.org/10.1088/1755-1315/421/4/042015
Melikhova EV, Rogachev AF (2019) Computer simulation and optimization of parameters of configuration of the contour of moistening under drip irrigation of agricultures. In: Popkova EG (ed) Ubiquitous computing and the internet of things: prerequisites for the development of ICT. Studies in computational intelligence, vol 826, pp 1193–1201. https://doi.org/10.1007/978-3-030-13397-9_122
Soloviev RA, Telpukhov DV, Kustov AG (2017) Automatic segmentation of satellite images based on the modified convolutional neural network UNET. Eng Bull Don (4)
Jeong S, Ko J, Yeom JM (2021) Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea. Sci Total Environ 802(2):149726
Xu J, Yang J, Xiong X et al (2021) Towards interpreting multi-temporal deep learning models in crop mapping. Rem Sens Environ 264:112599. https://doi.org/10.3390/rs13224668
Ofori-Ampofo S, Pelletier C, Lang S (2021) Crop type mapping from optical and radar time series using attention based deep learning. Rem Sens 13:4668
Kussul N, Lavreniuk M, Skakun S et al (2017) Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci Rem Sens Lett (99):1–5
Alekseev AV, Rozaliev VL, Orlova YA, Zaboleeva-Zotova AV (2016) Context-sensitive image analysis for coloring nature images. Adv Intell Syst Comput 451:133–141
He K, Zhang X, Ren X, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the 29th IEEE conference on computer vision and pattern recognition—CVPR, Las Vegas, Nevada, USA, pp 770–778
Fezan Review DeepLabv3 (Semantic Segmentation) (2020). https://medium.com/swlh/review-deeplabv3-semantic-segmentation-52c00ddbf28d
Adrian R Intersection over Union (IoU) for object detection. https://www.pyimagesearch.com/2016/11/07/intersection-over-unioniou-for-object-detection
Seeland M, Mäder P (2021) Multi-view classification with convolutional neural networks. PLoS ONE 16(1):e0245230. https://doi.org/10.1371/journal.pone.0245230
Tsang S-H Review: DeepLabv3. Atrous Convolution (Semantic Segmentation). https://towardsdatascience.com/review-deeplabv3-atrous-convolution-semantic-segmentation-6d818bfd1d74
Rogachev AF, Belousov IS (2022) Neural network identification of problem areas of the state of crops by methods of artificial intelligence. In: Proceedings of the Lower Volga Agro-University Comp, vol 3(67), pp 459–466. https://doi.org/10.32786/2071-9485-2022-03-52
Sozykin AV (2017) Review of deep neural network training methods. Bull SUSU Ser Comput Math Comput Sci 6(3):28–59. https://doi.org/10.14529/cmse170303
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: JMLR workshop and conference proceedings. Proceedings of the 32nd international conference on machine learning, Lille, France, 06–11 July 2015, vol 37, pp 448–456
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–30 June 2016, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Utkin L, Kovalev M, Kasimov E (2021) An explanation method for Siamese neural networks. In: Voinov N, Schreck T, Khan S (eds) Proceedings of international scientific conference on telecommunications, computing and control. Smart innovation, systems and technologies, vol 220. Springer, Singapore. https://doi.org/10.1007/978-981-33-6632-9_19
Sabour S, Fross N, Hinton GE (2017) Dynamic routing between capsules. In: Neural information processing systems (NIPS)
Acknowledgements
The publication has been prepared with the financial support of the RFBR under project No. 20-37-90142.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rogachev, A., Belousov, I., Rogachev, D. (2023). Semantic Image Segmentation of Agricultural Field Problem Areas Using Deep Neural Networks Based on the DeepLabV3 Model. In: Shakya, S., Tavares, J.M.R.S., Fernández-Caballero, A., Papakostas, G. (eds) Fourth International Conference on Image Processing and Capsule Networks. ICIPCN 2023. Lecture Notes in Networks and Systems, vol 798. Springer, Singapore. https://doi.org/10.1007/978-981-99-7093-3_30
Download citation
DOI: https://doi.org/10.1007/978-981-99-7093-3_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7092-6
Online ISBN: 978-981-99-7093-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)