(47-3) 14 * << * >> * Russian * English * Content * All Issues

Low-parameter method for delineation of agricultural fields in satellite images based on multi-temporal MSAVI2 data
M.A. Pavlova 1, V.A. Timofeev 1, D.A. Bocharov 1, D.S. Sidorchuk 1, A.L. Nurmukhametov 1, A.V. Nikonorov 2,3, M.S. Yarykina 1, I.A. Kunina 1, A.A. Smagina 1, M.A. Zagarev 1

1 Institute for Information Transmission Problems, RAS, 127051, Moscow, Russia, Bolshoy Karetny per. 19, build. 1;
2 IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS,
443001, Samara, Russia, Molodogvardeyskaya 151;
3 Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34

 PDF, 4771 kB

DOI: 10.18287/-6179-CO-1235

Pages: 451-463.

Full text of article: Russian language.

Abstract:
This paper considers an issue of delineating agricultural fields in satellite images. In this task we follow a multi-temporal data approach. We show that on such data, good quality can be achieved using a simple low-parameter method. The method consists of a combination of a field detector and an edge detector. The field detection is based on an Otsu thresholding technique and for the edge detection we use a Canny detector. Facing a lack of available datasets and aiming to estimate the proposed algorithm, we prepared and published our dataset consisting of 18,859 expertly annotated fields using Sentinel-2 data. We implement one of the state-of-the-art deep-learning approaches and compare it with the proposed method on our dataset. The experiment shows the proposed simple multi-temporal algorithm to outperform the state-of-the-art instant data approach. This result confirms the importance of using multi-temporal data and for the first time demonstrates that the delineation problem can be solved at a lower cost without loss of quality. Our approach requires a significantly less amount of training data when compared with the NN-based one. The dataset of agricultural fields used in the work and the proposed algorithm implementation in Python are published in open access.

Keywords:
low-parameter algorithm, computer vision, fields delineation, remote sensing, multi-temporal data, open dataset.

Citation:
Pavlova MA, Timofeev VA, Bocharov DA, Sidorchuk DS, Nurmukhametov AL, Nikonorov AV, Yarykina MS, Kunina IA, Smagina AA, Zagarev MA. Low-parameter method for delineation of agricultural fields in satellite images based on multi-temporal MSAVI2 data. Computer Optics 2023; 47(3): 451-463. DOI: 10.18287/-6179-CO-1235.

Acknowledgements:
This work was supported by the Russian Science Foundation (Project No. 20-61-47089).

References:
  1. Garcia-Pedrero A, et al. The outlining of agricultural plots based on spatiotemporal consensus segmentation. Remote Sens 2018; 10: 1991. DOI: 10.3390/rs10121991.
  2. Steven MD, Clark JA, eds. Applications of remote sensing in agriculture. Elsevier; 2013.
  3. Rokhmana CA. The potential of UAV-based remote sensing for supporting precision agriculture in Indonesia. Procedia Environ Sci 2015; 24: 245-253. DOI: 10.1016/j.proenv.2015.03.032.
  4. Campbell JB, Wynne RH. Introduction to remote sensing. Guilford Press; 2011.
  5. Cracknell AP. Introduction to remote sensing. CRC press; 2007.
  6. Davis SM, et al. Remote sensing: the quantitative approach. McGraw-Hill College; 1978.
  7. Elachi C, Van Zyl JJ. Introduction to the physics and techniques of remote sensing. John Wiley & Sons; 2021.
  8. Camps-Valls G, et al. Remote sensing image processing. Morgan & Claypool Publishers; 2011. DOI: 10.2200/S00392ED1V01Y201107IVM012.
  9. Schowengerdt RA. Remote sensing: models and methods for image processing. Academic Press; 2006.
  10. Michishita R, et al. Empirical comparison of noise reduction techniques for NDVI time-series based on a new measure. ISPRS J Photogramm Remote Sens 2014; 91: 17-28. DOI: 10.1016/j.isprsjprs.2014.01.003.
  11. Martins VS, et al. Assessment of atmospheric correction methods for Sentinel-2 MSI images applied to Amazon Floodplain Lakes. Remote Sens 2017; 9: 322. DOI: 10.3390/rs9040322.
  12. Lantzanakis G, Mitraka Z, Chrysoulakis N. Comparison of physically and image based atmospheric correction methods for Sentinel-2 satellite imagery. In Book: Karacostas T, Bais A, Nastos PT, eds. Perspectives on atmospheric sciences. Springer International Publishing Switzerland; 2017: 255-261. ISBN: 978-3-319-35095-0.
  13. Sola I, et al. Assessment of atmospheric correction methods for Sentinel-2 images in Mediterranean landscapes. Int J Appl Earth Obs Geoinf 2018; 73: 63-76. DOI: 10.1016/j.jag.2018.05.020.
  14. Silva GF, et al. Near real-time shadow detection and removal in aerial motion imagery application. ISPRS J Photogramm Remote Sens 2018; 140: 104-121. DOI: 10.1016/j.isprsjprs.2017.11.005.
  15. Guo R, Dai Q, Hoiem D. Paired regions for shadow detection and removal. IEEE Trans Pattern Anal Mach Intell 2013; 35: 2956-2967. DOI: 10.1109/TPAMI.2012.214.
  16. Bocharov DA, et al. Cloud shadows detection and compensation algorithm on multispectral satellite images for agriculture regions. J Commun Technol Electron 2022; 67: 728-739. DOI: 10.1134/S1064226922060171.
  17. Deshpande AM, Patale SR, Roy S. Removal of line striping and shot noise from remote sensing imagery using a deep neural network with post-processing for improved restoration quality. Int J Remote Sens 2021; 42: 7357-7380. DOI: 10.1080/01431161.2021.1957512.
  18. Crommelinck S, et al. Review of automatic feature extraction from high-resolution optical sensor data for UAV-based cadastral mapping. Remote Sens 2016; 8: 689. DOI: 10.3390/rs8080689.
  19. Torre M, Radeva P. Agricultural-field extraction on aerial images by region competition algorithm. Proc 15th Int Conf on Pattern Recognition (ICPR-2000) 2000; 1: 313-316. DOI: 10.1109/ICPR.2000.905337.
  20. Wagner MP, Oppelt N. Extracting agricultural fields from remote sensing imagery using graph-based growing contours. Remote Sens 2020; 12: 1205. DOI: 10.3390/rs12071205.
  21. Joel D. Semi-automatic detection of field boundaries from highresolution satellite imagery. PhD Thesis, Wageningen University 2015. DOI: 10.13140/RG.2.1.4931.8804.
  22. Garcia-Pedrero A, et al. Deep learning for automatic outlining agricultural parcels: Exploiting the land parcel identification system. IEEE Access 2019; 7: 158223-158236. DOI: 10.1109/ACCESS.2019.2950371.
  23. Ji CY. Delineating agricultural field boundaries from TM imagery using dyadic wavelet transforms. ISPRS J Photogramm Remote Sens 1996; 51(6): 268-283. DOI: 10.1016/0924-2716(95)00017-8.
  24. Watkins B, Van Niekerk A. A comparison of object-based image analysis approaches for field boundary delineation using multi-temporal Sentinel-2 imagery. Comput Electron Agric 2019; 158: 294-302. DOI: 10.1016/j.compag.2019.02.009.
  25. Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986; PAMI-8: 679-698. DOI: 10.1109/TPAMI.1986.4767851.
  26. Waldner F, Diakogiannis FI. Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sens Environ 2020; 245: 111741. DOI: 10.1016/j.rse.2020.111741.
  27. García-Pedrero A, Gonzalo-Martín C, Lillo-Saavedra M. A machine learning approach for agricultural parcel delineation through agglomerative segmentation. Int J Remote Sens 2017; 38: 1809-1819. DOI: 10.1080/01431161.2016.1278312.
  28. Aung HL, et al. Farm parcel delineation using spatio-temporal convolutional networks. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops (CVPRW-2020) 2020: 340-349. DOI: 10.1109/CVPRW50498.2020.00046.
  29. Belgiu M, Csillik O. Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sens Environ 2018; 204: 509-523. DOI: 10.1016/j.rse.2017.10.005.
  30. Watkins B, Van Niekerk A. Automating field boundary delineation with multi-temporal Sentinel-2 imagery. Comput Electron Agric 2019; 167: 105078. DOI: 10.1016/j.compag.2019.105078.
  31. North HC, Pairman D, Belliss SE. Boundary delineation of agricultural fields in multitemporal satellite imagery. IEEE J Sel Top Appl Earth Obs Remote Sens 2019; 12: 237-251. DOI: 10.1109/JSTARS.2018.2884513.
  32. Yan L, Roy DP. Automated crop field extraction from multi-temporal Web Enabled Landsat Data. Remote Sens Environ 2014; 144: 42-64. DOI: 10.1016/j.rse.2014.01.006.
  33. Singh S, Suresh M, Jain K. Land Information Extraction with Boundary Preservation for High Resolution Satellite Image. International Journal of Computer Applications 2015; 120: 39-43. DOI: 10.5120/21243-4014.
  34. Persello C, et al. Delineation of agricultural fields in smallholder farms from satellite images using fully convolutional networks and combinatorial grouping. Remote Sens Environ 2019; 231: 111253. DOI: 10.1016/j.rse.2019.111253.
  35. Wagner MP, Oppelt N. Deep learning and adaptive graph-based growing contours for agricultural field extraction. Remote Sens 2020; 12: 1990. DOI: 10.3390/rs12121990.
  36. Zhang H, et al. Automated delineation of agricultural field boundaries from Sentinel-2 images using recurrent residual U-Net. Int J Appl Earth Obs Geoinf 2021; 105: 102557. DOI: 10.1016/j.jag.2021.102557.
  37. Yerlygin LA, Teplyakov LM. Improvement of a line segment detector based on a neural network by adding engineering features [In Russian]. Sensory systems 2021; 35: 50-54. DOI: 10.31857/S0235009221010042.
  38. Teplyakov L, et al. Line detection via a lightweight CNN with a Hough layer. Proc SPIE 2020; 11605, 116051B. DOI: 10.1117/12.2587167.
  39. North HC, Pairman D, Belliss SE. Paddock segmentation using multi-temporal satellite imagery. Proc IEEE Geoscience and Remote Sensing Symposium 2014: 1596-1599. DOI: 10.1109/IGARSS.2014.6945951.
  40. Qi J, et al. A modified soil adjusted vegetation index. Remote Sens Environ 1994; 48: 119-126. DOI: 10.1016/0034-4257(94)90134-1.
  41. Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern Syst 1979; 9: 62-66.
  42. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In Book: Medical image computing and computer-assisted intervention – MICCAI 2015. Cham, Switzerland: Springer; 2015: 234-241. DOI: 10.1007/978-3-319-24574-4_28.
  43. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale-image recognition. arXiv Preprint. 2014. Sorce: https://arxiv.org/abs/1409.1556. DOI: 0.48550/arXiv.1409.1556.
  44. Rakhlin A, Davydow A, Nikolenko S. Land cover classification from satellite imagery with U-net and lovász-Softmax loss. Proc CVPR Workshops 2018: 262-266.
  45. Masoud KM, Persello C, Tolpekin VA. Delineation of agricultural field boundaries from Sentinel-2 images using a novel super-resolution contour detector based on fully convolutional networks. Remote sens 2019; 12(1): 59. DOI: 10.3390/rs12010059.
  46. Yao J, et al. The classification method study of crops remote sensing with deep learning, machine learning, and Google Earth engine. Remote Sens 2022; 14(12): 2758. DOI: 10.3390/rs14122758.
  47. Zhang Z, et al. Cloudformer V2: Set prior prediction and binary mask weighted network for cloud detection. Mathematics 2022; 10(15): 2710.1.
  48. Kuang B, et al. Rock segmentation in the navigation vision of the planetary rovers. Mathematics 2021; 9(23): 3048. DOI: 10.3390/math9233048.
  49. Zhang Z, et al. HA-RoadFormer: Hybrid attention transformer with multi-branch for large-scale high-resolution dense road segmentation. Mathematics 2022; 10(11): 1915. DOI: 10.3390/math10111915.
  50. Clinton N, et al. Accuracy assessment measures for object-based image segmentation goodness. Photogramm Eng Remote Sens 2010; 76(3): 289-299.
  51. Long J, et al. Delineation of agricultural fields using multi-task BsiNet from high-resolution satellite images. Int J Appl Earth Obs Geoinf 2022; 112: 102871. DOI: 10.1016/j.jag.2022.102871.
  52. Tetteh GO, Gocht A, Conrad C. Optimal parameters for delineating agricultural parcels from satellite images based on supervised Bayesian optimization. Comput Electron Agric 2020; 178: 105696. DOI: 10.1016/j.compag.2020.105696.
  53. Zhan Q, et al. Quality assessment for geo-spatial objects derived from remotely sensed data. Int J Remote Sens 2005; 26(14): 2953-2974. DOI: 10.1080/01431160500057764.
  54. Lucieer A, Stein A. Existential uncertainty of spatial objects segmented from satellite sensor imagery. IEEE Trans Geosci Remote Sens 2002; 40(11): 2518-2521. DOI: 10.1109/TGRS.2002.805072.
  55. Ershov EI, et al. A generalization of Otsu method for linear separation of two unbalanced classes in document image binarization. Computer Optics 2021; 45(1): 66-76. DOI: 10.18287/2412-6179-CO-752.
  56. Panfilova E, Shipitko OS, Kunina I. Fast Hough transform-based road markings detection for autonomous vehicle. Proc SPIE 2020; 11605: 116052B. DOI: 10.1117/12.2587615.
  57. Panfilova EI, Kunina IA. Using window hough transform for detecting elongated boundaries in an image [In Russian]. Sensory systems 2020; 34: 340-353. DOI: 10.31857/S0235009220030075.
  58. Sidorchuk DS, Volkov VV, Nikonorov AV. Comparison of the nonlinear contrast-preserving visualization method for multispectral images with well-known decolorization algorithms [In Russian]. Information Processes 2020; 20: 41-54.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20