Evaluation of computer vision pipeline for farm-level analytics: A case study in Sugarcane
Authors: 
Sambal Shikhar, Rajiv Ranjan, Aman Sa, Anshika Srivastava, Yash Srivastava, Dinesh Kumar, Shashank Tamaskar, Anupam SobtiAuthors Info & Claims
Sambal Shikhar, Rajiv Ranjan, Aman Sa, Anshika Srivastava, Yash Srivastava, Dinesh Kumar, Shashank Tamaskar, Anupam SobtiAuthors Info & ClaimsPages 238 - 247
Abstract
Analyzing agricultural imagery for farm level insights has been an active area of research in the recent times. For providing the necessary information to stakeholders - be it farmers, financial institutions or governments, various computer vision tasks have to come together. For example, to provide information to a farmer about crop stress in their farm, accurate localization of the farm, identification of the crop type and a monitoring of the field’s micro-climate must be done together. In this work, we set performance benchmarks for three computer vision tasks - farm boundary detection, crop classification and sub-field stress estimation with different modalities of images - Sentinel2, PlanetScope and Drone Imagery. We use public dataset benchmarks for farm boundaries and crop classification and do a controlled field study on a large sugarcane farm in Uttar Pradesh, India for the stress estimation.
Our work benchmarks farm boundary detection for small farms with state of the art deep learning algorithms achieving a dice score of 67%, improves the sugarcane classification accuracy by 10% coming to 98% and demonstrates an accuracy of 72% for water and nitrogen stress estimation.
References
[1]
[n. d.]. Maxar Imagery. https://maxar.com/maxar-intelligence/products/optical-imagery. [Accessed 06-03-2024].
[2]
[n. d.]. Overview | Maps Static API | Google for Developers — developers.google.com. https://developers.google.com/maps/documentation/maps-static/overview. [Accessed 06-03-2024].
[3]
Mohammad Alavi, Mohammad Albaji, Mona Golabi, Abd Ali Naseri, and Saeid Homayouni. 2024. Estimation of sugarcane evapotranspiration from remote sensing and limited meteorological variables using machine learning models. Journal of Hydrology 629 (2024), 130605.
[4]
Han Lin Aung, Burak Uzkent, Marshall Burke, David Lobell, and Stefano Ermon. 2020. Farm parcel delineation using spatio-temporal convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 76–77.
[5]
Bahaa Awad and Isin Erer. 2023. FAUNet: Frequency Attention U-Net for Parcel Boundary Delineation in Satellite Images. Remote Sensing 15, 21 (2023), 5123.
[6]
Jan Behmann, Jörg Steinrücken, and Lutz Plümer. 2014. Detection of early plant stress responses in hyperspectral images. ISPRS Journal of Photogrammetry and Remote Sensing 93 (2014), 98–111.
[7]
Michael Cecil, Fatemeh Kordi, Hanxi (Steve) Li, Sam Khallaghi, and Hamed Alemohammad. 2023. HLS Multi Temporal Crop Classification. https://doi.org/10.57967/hf/0955
[8]
Ranveer Chandra and Stewart Collis. 2021. Digital agriculture for small-scale producers: challenges and opportunities. Commun. ACM 64, 12 (2021), 75–84.
[9]
Somali Chaterji, Nathan DeLay, John Evans, Nathan Mosier, Bernard Engel, Dennis Buckmaster, Michael R Ladisch, and Ranveer Chandra. 2021. Lattice: A vision for machine learning, data engineering, and policy considerations for digital agriculture at scale. IEEE Open Journal of the Computer Society 2 (2021), 227–240.
[10]
Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017).
[11]
Robert Chew, Jay Rineer, Robert Beach, Maggie O’Neil, Noel Ujeneza, Daniel Lapidus, Thomas Miano, Meghan Hegarty-Craver, Jason Polly, and Dorota S Temple. 2020. Deep neural networks and transfer learning for food crop identification in UAV images. Drones 4, 1 (2020), 7.
[12]
Saba Dadsetan, Gisele Rose, Naira Hovakimyan, and Jennifer Hobbs. 2021. Detection and prediction of nutrient deficiency stress using longitudinal aerial imagery. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 14729–14738.
[13]
Raphaël d’Andrimont, Martin Claverie, Pieter Kempeneers, Davide Muraro, Momchil Yordanov, Devis Peressutti, Matej Batič, and François Waldner. 2023. AI4Boundaries: an open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography. Earth System Science Data 15, 1 (2023), 317–329.
[14]
Leonardo Leite de Melo, Verônica Gaspar Martins Leite de Melo, Patrícia Angélica Alves Marques, Jose Antonio Frizzone, Rubens Duarte Coelho, Roseli Aparecida Francelin Romero, and Tim��teo Herculino da Silva Barros. 2022. Deep learning for identification of water deficits in sugarcane based on thermal images. Agricultural Water Management 272 (2022), 107820.
[15]
Matthias Drusch, Umberto Del Bello, Sébastien Carlier, Olivier Colin, Veronica Fernandez, Ferran Gascon, Bianca Hoersch, Claudia Isola, Paolo Laberinti, Philippe Martimort, 2012. Sentinel-2: ESA’s optical high-resolution mission for GMES operational services. Remote sensing of Environment 120 (2012), 25–36.
[16]
Pall Oskar Gislason, Jon Atli Benediktsson, and Johannes R Sveinsson. 2006. Random forests for land cover classification. Pattern recognition letters 27, 4 (2006), 294–300.
[17]
Nataliia Kussul, Mykola Lavreniuk, Sergii Skakun, and Andrii Shelestov. 2017. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters 14, 5 (2017), 778–782.
[18]
Mengmeng Li, Jiang Long, Alfred Stein, and Xiaoqin Wang. 2023. Using a semantic edge-aware multi-task neural network to delineate agricultural parcels from remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing 200 (2023), 24–40.
[19]
Jiang Long, Mengmeng Li, Xiaoqin Wang, and Alfred Stein. 2022. Delineation of agricultural fields using multi-task BsiNet from high-resolution satellite images. International Journal of Applied Earth Observation and Geoinformation 112 (2022), 102871.
[20]
Chang Luo, Shiyao Meng, Xin Hu, Xinyu Wang, and Yanfei Zhong. 2020. Cropnet: Deep Spatial-Temporal-Spectral Feature Learning Network for Crop Classification from Time-Series Multi-Spectral Images. In IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium. 4187–4190. https://doi.org/10.1109/IGARSS39084.2020.9324097
[21]
Alakananda Mitra, Anshuman Singhal, Saraju P Mohanty, Elias Kougianos, and Chittaranjan Ray. 2022. eCrop: a novel framework for automatic crop damage estimation in smart agriculture. SN Computer Science 3, 4 (2022), 319.
[22]
Planet Labs PBC. 2018–. Planet Application Program Interface: In Space for Life on Earth. https://api.planet.com
[23]
Claudio Persello, Jeroen Grift, Xinyan Fan, Claudia Paris, Ronny Hänsch, Mila Koeva, and Andy Nelson. 2023. AI4SmallFarms: A Data Set for Crop Field Delineation in Southeast Asian Smallholder Farms. IEEE Geoscience and Remote Sensing Letters (2023).
[24]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234–241.
[25]
BK Singh, Dulal Chakraborty, Naveen Kalra, and Jaya Singh. 2019. A tool for climate smart crop insurance: Combining farmers’ pictures with dynamic crop modelling for accurate yield estimation prior to harvest. Intl Food Policy Res Inst.
[26]
Alireza Taravat, Matthias P Wagner, Rogerio Bonifacio, and David Petit. 2021. Advanced fully convolutional networks for agricultural field boundary detection. Remote sensing 13, 4 (2021), 722.
[27]
Gabriel Tseng, Ivan Zvonkov, Catherine Lilian Nakalembe, and Hannah Kerner. 2021. Cropharvest: A global dataset for crop-type classification. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).
[28]
Shadman Veysi, Abd Ali Naseri, Saeid Hamzeh, and Harm Bartholomeus. 2017. A satellite based crop water stress index for irrigation scheduling in sugarcane fields. Agricultural water management 189 (2017), 70–86.
[29]
Andrés Viña, Anatoly A Gitelson, Anthony L Nguy-Robertson, and Yi Peng. 2011. Comparison of different vegetation indices for the remote assessment of green leaf area index of crops. Remote sensing of environment 115, 12 (2011), 3468–3478.
[30]
Shyamal S Virnodkar, Vinod K Pachghare, VC Patil, and Sunil Kumar Jha. 2022. CaneSat dataset to leverage convolutional neural networks for sugarcane classification from Sentinel-2. Journal of King Saud University-Computer and Information Sciences 34, 6 (2022), 3343–3355.
[31]
François Waldner, Foivos I Diakogiannis, Kathryn Batchelor, Michael Ciccotosto-Camp, Elizabeth Cooper-Williams, Chris Herrmann, Gonzalo Mata, and Andrew Toovey. 2021. Detect, consolidate, delineate: Scalable mapping of field boundaries using satellite images. Remote sensing 13, 11 (2021), 2197.
[32]
Hengbin Wang, Wanqiu Chang, Yu Yao, Zhiying Yao, Yuanyuan Zhao, Shaoming Li, Zhe Liu, and Xiaodong Zhang. 2023. Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification. Frontiers in plant science 14 (2023), 1130659.
[33]
Sherrie Wang, François Waldner, and David B Lobell. 2022. Unlocking large-scale crop field delineation in smallholder farming systems with transfer learning and weak supervision. Remote Sensing 14, 22 (2022), 5738.
[34]
Giulio Weikmann, Claudia Paris, and Lorenzo Bruzzone. 2021. Multi-year crop type mapping using pre-trained deep long-short term memory and Sentinel 2 image time series. In Image and Signal Processing for Remote Sensing XXVII, Vol. 11862. SPIE, 171–181.
[35]
Giulio Weikmann, Claudia Paris, and Lorenzo Bruzzone. 2021. Timesen2crop: A million labeled samples dataset of sentinel 2 image time series for crop-type classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 (2021), 4699–4708.
[36]
Xiaochun Zhang, Qinxue Xiong, Liping Di, Junmei Tang, Jin Yang, Huayi Wu, Yan Qin, Rongrui Su, and Wei Zhou. 2018. Phenological metrics-based crop classification using HJ-1 CCD images and Landsat 8 imagery. International Journal of Digital Earth 11, 12 (2018), 1219–1240.
[37]
Zindi. [n. d.]. Zindi — zindi.africa. https://zindi.africa/competitions/agrifieldnet-india-challenge. [Accessed 28-02-2024].
Index Terms
- Evaluation of computer vision pipeline for farm-level analytics: A case study in Sugarcane
Recommendations
The Study of Discrimination of Remotely Sensed Data for Designing the Separation Technique between Cassava and Sugarcane Farmland
GISTAM 2019: Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and ManagementCassava and sugarcane are the most important agricultural crops in Thailand. The cultivations of those are similarly in crop season, natural resources, and climate. For decades, the farmers usually switch their plant depending on unit price and ...
Assessing the fidelity of Landsat-based fAPAR models in two diverse sugarcane growing regions
Highlights- Linear SWIR-based NDMI and AFRI models predicted fAPAR for irrigated and rainfed sugarcane most accurately.
AbstractSugarcane is a globally important crop used for producing sugar and for generating renewable energy. Timely and accurate forecasts of sugarcane yield and production are needed to optimize supply chain operations. Crop growth models (...
Measuring and modelling CO2 effects on sugarcane
In order to fully capture the benefits of rising CO2 in adapting agriculture to climate change, we first need to understand how CO2 affects crop growth. Several recent studies reported unexpected increases in sugarcane (C4) yields under elevated CO2, ...
Comments
Information & Contributors
Information
Published In
July 2024
354 pages
ISBN:9798400710483
DOI:10.1145/3674829
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 August 2024
Check for updates
Author Tags
Qualifiers
- Short-paper
- Research
- Refereed limited
Conference
COMPASS '24: ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies
July 8 - 11, 2024
New Delhi, India
Acceptance Rates
Overall Acceptance Rate 25 of 50 submissions, 50%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 77Total Downloads
- Downloads (Last 12 months)77
- Downloads (Last 6 weeks)34
Reflects downloads up to 22 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format