Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Recursive classification of satellite imaging time-series: An application to land cover mapping (2301.01796v4)

Published 4 Jan 2023 in eess.IV

Abstract: Despite the extensive body of literature focused on remote sensing applications for land cover mapping and the availability of high-resolution satellite imagery, methods for continuously updating classification maps in real-time remain limited, especially when training data is scarce. This paper introduces the Recursive Bayesian Classifier (RBC), which converts any instantaneous classifier into a robust online method through a probabilistic framework that is resilient to non-informative image variations. Three experiments are conducted using Sentinel-2 data: water mapping of the Oroville Dam in California and the Charles River basin in Massachusetts, and deforestation detection in the Amazon. RBC is applied to a Gaussian Mixture Model (GMM), Logistic Regression (LR), and our proposed Spectral Index Classifier (SIC). Results show that RBC significantly enhances classifier robustness in multitemporal settings under challenging conditions, such as cloud cover and cyanobacterial blooms. Specifically, balanced classification accuracy improves by up to 26.95% for SIC, 12.4% for GMM, and 13.81% for LR in water mapping, and by 15.25%, 14.17%, and 14.7% in deforestation detection. Moreover, without additional training data, RBC improves the performance of the state-of-the-art DeepWaterMap and WatNet algorithms by up to 9.62% and 11.03%. These benefits are provided by RBC while requiring minimal supervision and maintaining a low computational cost that remains constant for each time step regardless of the time-series length.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (95)
  1. Evaluation of Water Indices for Surface Water Extraction in a Landsat 8 Scene of Nepal. Sensors 18, 2580. doi:10.3390/s18082580.
  2. A land use and land cover classification system for use with remote sensor data. volume 964. US Government Printing Office.
  3. Bayesian Reasoning and Machine Learning. 04-2011 ed., Cambridge University Press. URL: http://www.cs.ucl.ac.uk/staff/d.barber/brml. in press.
  4. Fast Unmixing and Change Detection in Multitemporal Hyperspectral Data. IEEE Transactions on Computational Imaging 7, 975–988.
  5. Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review. IEEE Geoscience and Remote Sensing Magazine 9, 223–270.
  6. Kalman filtering and expectation maximization for multitemporal spectral unmixing. IEEE Geoscience and Remote Sensing Letters 19, 1–5.
  7. Sentinel-2 Images from Oroville Dam and Charles River. URL: https://doi.org/10.5281/zenodo.7391412, doi:10.5281/zenodo.7391412.
  8. Recursive classification of satellite imaging time-series: An application to land cover mapping. arXiv preprints URL: https://arxiv.org/abs/2301.01796.
  9. Online variational filtering and parameter learning, in: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (Eds.), Advances in Neural Information Processing Systems. URL: https://openreview.net/forum?id=et2st4Jqhc.
  10. Multiearth 2023 – multimodal learning for earth and environment workshop and challenge. arXiv:2306.04738.
  11. Joint Super-Resolution and Image Restoration for PLÉIADES NEO Imagery. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 43B1, 9–15. doi:10.5194/isprs-archives-XLIII-B1-2022-9-2022.
  12. A bayesian approach to multipath mitigation in gnss receivers. IEEE Journal of Selected Topics in Signal Processing 3, 695–706. doi:10.1109/JSTSP.2009.2023831.
  13. Noise estimation by minima controlled recursive averaging for robust speech enhancement. Signal Processing Letters, IEEE 9, 12 – 15. doi:10.1109/97.988717.
  14. Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series. IEEE Transactions on Geoscience and Remote Sensing 60. doi:10.1109/TGRS.2021.3076667.
  15. Classification of time series of multispectral images with limited training data. IEEE Transactions on Image Processing 22, 3219–3233.
  16. Cubature kalman filter based training of hybrid differential equation recurrent neural network physiological dynamic models, in: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE. pp. 763–766.
  17. Land use/land cover classification using time series Landsat 8 images in a heavily urbanized area. Advances in Space Research 63. doi:10.1016/j.asr.2018.12.005.
  18. Coastline Change Assessment at the Aegean Sea Coasts in Turkey Using Multitemporal Landsat Imagery. Journal of Coastal Research - J COASTAL RES 23, 691–698. doi:10.2112/04-0398.1.
  19. Predicting flood susceptibility using LSTM neural networks. Journal of Hydrology 594. doi:10.1016/j.jhydrol.2020.125734.
  20. Flood monitoring by integration of Remote Sensing technique and Multi-Criteria Decision Making method. Computers and Geosciences 160, 105045. URL: https://www.sciencedirect.com/science/article/pii/S0098300422000127, doi:https://doi.org/10.1016/j.cageo.2022.105045.
  21. Water Body Detection and Delineation with Landsat TM Data. Photogrammetric Engineering and Remote Sensing 66, 1461–1467.
  22. F assessment of landuse/landcover (LULC) change of Tbilisi and surrounding area using remote sensing (RS) and GIS. Annals of Agrarian Science 16, 163–169. URL: https://www.sciencedirect.com/science/article/pii/S1512188718300824, doi:https://doi.org/10.1016/j.aasci.2018.02.005.
  23. An effective modified water extraction method for Landsat-8 OLI imagery of mountainous plateau regions. IOP Conference Series: Earth and Environmental Science 34, 012010. doi:10.1088/1755-1315/34/1/012010.
  24. Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of Photogrammetry and Remote Sensing 116, 55–72.
  25. Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping. Remote sensing of environment 220, 135–151.
  26. Classifying pedestrian actions in advance using predicted video of urban driving scenes, in: 2019 International Conference on Robotics and Automation (ICRA), pp. 2097–2103. doi:10.1109/ICRA.2019.8794278.
  27. Reconstructing semi-arid wetland surface water dynamics through spectral mixture analysis of a time series of Landsat satellite images (1984–2011). Remote Sensing of Environment 177, 171–183. URL: https://www.sciencedirect.com/science/article/pii/S0034425716300682, doi:https://doi.org/10.1016/j.rse.2016.02.040.
  28. Coastline Extraction Using Support Vector Machine from Remote Sensing Image. Journal of Multimedia 8. doi:10.4304/jmm.8.2.175-182.
  29. A New Cascade Model for the Hierarchical Joint Classification of Multitemporal and Multiresolution Remote Sensing Data . IEEE Transactions on Geoscience and Remote Sensing 54, 6333 – 6348. URL: https://hal.inria.fr/hal-01308039.
  30. Conditional Random Fields for Multitemporal and Multiscale Classification of Optical Satellite Imagery. IEEE Transactions on Geoscience and Remote Sensing 53, 659–673. doi:10.1109/TGRS.2014.2326886.
  31. Characterization of Planetscope-0 Planetscope-1 surface reflectance and normalized difference vegetation index continuity. Science of Remote Sensing 3, 100014. doi:10.1016/j.srs.2021.100014.
  32. Enhancing particle filtering using gaussian processes, in: 2020 IEEE 23rd International Conference on Information Fusion (FUSION), IEEE. pp. 1–7.
  33. Hybrid neural network augmented physics-based models for nonlinear filtering, in: 2022 25th International Conference on Information Fusion (FUSION), IEEE. pp. 1–6.
  34. Surface Water Mapping by Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10, 4909–4918. doi:10.1109/JSTARS.2017.2735443.
  35. Mapping with skysat images. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B1-2022, 99–106. doi:10.5194/isprs-archives-XLIII-B1-2022-99-2022.
  36. Information theory and statistical mechanics. Phys. Rev. 106, 620–630. URL: https://link.aps.org/doi/10.1103/PhysRev.106.620, doi:10.1103/PhysRev.106.620.
  37. Land cover classification based on NDVI using LANDSAT8 time series: A case study Tirupati region, in: 2016 International Conference on Communication and Signal Processing (ICCSP), IEEE. pp. 1332–1335.
  38. Recursive bayesian inference and learning for target tracking with unknown maneuvers. International Journal of Adaptive Control and Signal Processing 36, 1032 – 1044.
  39. 3D convolutional neural networks for crop classification with multi-temporal remote sensing images. Remote Sensing 10, 75.
  40. Remote estimation of chlorophyll a concentrations over a wide range of optical conditions based on water classification from VIIRS observations. Remote Sensing of Environment 241, 111735. URL: https://www.sciencedirect.com/science/article/pii/S003442572030105X, doi:https://doi.org/10.1016/j.rse.2020.111735.
  41. Integrating OpenStreetMap crowdsourced data and Landsat time-series imagery for rapid land use/land cover (LULC) mapping: Case study of the Laguna de Bay area of the Philippines. Applied Geography 67, 140–149. URL: https://www.sciencedirect.com/science/article/pii/S0143622815300321, doi:https://doi.org/10.1016/j.apgeog.2015.12.006.
  42. A comparison of different land-use classification techniques for accurate monitoring of degraded coal-mining areas. Environmental Earth Sciences 77. doi:10.1007/s12665-018-7893-5.
  43. Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images. IEEE Transactions on Geoscience and Remote Sensing 55, 4638–4654. doi:10.1109/TGRS.2017.2695326.
  44. Spectral unmixing. IEEE Signal Processing Magazine 19, 44–57.
  45. Evaluating spectral indices for water bodies extraction in Western Tibetan Plateau. The Egyptian Journal of Remote Sensing and Space Science 24, 619–634. URL: https://www.sciencedirect.com/science/article/pii/S1110982321000703, doi:https://doi.org/10.1016/j.ejrs.2021.09.003.
  46. Comparing four machine learning algorithms for land cover classification in gold mining: A case study of kyaukpahto gold mine, northern myanmar. Sustainability 14, 10754. doi:10.3390/su141710754.
  47. Evaluation of Global Water Resources Reanalysis Products in the Upper Blue Nile River Basin. Journal of Hydrometeorology 21, 935 – 952. URL: https://journals.ametsoc.org/view/journals/hydr/21/5/jhm-d-19-0233.1.xml, doi:10.1175/JHM-D-19-0233.1.
  48. Remote sensing time series revealing land surface dynamics: Status quo and the pathway ahead, in: Remote Sensing Time Series. Springer, pp. 1–24.
  49. Simulation of the regional climatic impact of Amazon deforestation. Nature 342, 411–413. doi:10.1038/342411a0.
  50. Online multi-resolution fusion of space-borne multispectral images, in: 2022 IEEE Aerospace Conference (AERO), IEEE. pp. 1–12.
  51. High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform. Remote sensing of environment 209, 227–239.
  52. An applicable and automatic method for earth surface water mapping based on multispectral images. International Journal of Applied Earth Observation and Geoinformation 103, 102472.
  53. Intelligent Information and Database Systems: Recent Developments. Springer International Publishing. URL: http://dx.doi.org/10.1007/978-3-030-14132-5, doi:10.1007/978-3-030-14132-5.
  54. Improving the accuracy of land use and land cover classification of landsat data using post-classification enhancement. Remote Sensing 1, 330–344. doi:10.3390/rs1030330.
  55. Online multichannel speech enhancement based on recursive em and dnn-based speech presence estimation. IEEE/ACM Transactions on Audio, Speech, and Language Processing 28, 3080–3094. doi:10.1109/TASLP.2020.3036776.
  56. On the recursive joint position and attitude determination in multi-antenna gnss platforms. Remote Sensing 12. URL: https://www.mdpi.com/2072-4292/12/12/1955, doi:10.3390/rs12121955.
  57. Sub-pixel mapping : a comparison of techniques, in: In: 25th EARSeL Symposium Global Developments in Environmental Earth Observation from Space, Oporto, Portugal.
  58. Harvesting the Landsat archive for land cover land use classification using deep neural networks: Comparison with traditional classifiers and multi-sensor benefits. ISPRS Journal of Photogrammetry and Remote Sensing 200, 106–119. doi:10.1016/j.isprsjprs.2023.05.005.
  59. Water Observations from Space: Mapping Surface Water from 25 Years of Landsat Imagery Across Australia. Remote Sensing of Environment 174. doi:10.1016/j.rse.2015.11.003.
  60. Biodiversity monitoring in changing tropical forests: A review of approaches and new opportunities. Remote. Sens. 9, 1059. URL: https://api.semanticscholar.org/CorpusID:41555272.
  61. Automatic extraction of shorelines from Landsat TM and ETM multi-temporal images with subpixel precision. Remote Sensing of Environment 123, 1–11. doi:10.1016/j.rse.2012.02.024.
  62. Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas. Remote Sensing of Environment 187, 156–168. doi:10.1016/j.rse.2016.10.010.
  63. Effect of training class label noise on classification performances for land cover mapping with satellite image time series. Remote Sensing 9. doi:10.3390/rs9020173.
  64. Temporal convolutional neural network for the classification of satellite image time series. Remote Sensing 11. doi:10.3390/rs11050523, arXiv:1811.10166.
  65. Rapid response flood detection using the MSG geostationary satellite. Int. J. Applied Earth Observation and Geoinformation 13, 536–544. doi:10.1016/j.jag.2011.02.002.
  66. Local climate zone-based urban land cover classification from multi-seasonal Sentinel-2 images with a recurrent residual network. ISPRS Journal of Photogrammetry and Remote Sensing 154, 151–162. URL: https://www.sciencedirect.com/science/article/pii/S0924271619301261, doi:https://doi.org/10.1016/j.isprsjprs.2019.05.004.
  67. Spectral unmixing. International Journal of Remote Sensing 33, 5307–5340. URL: https://doi.org/10.1080/01431161.2012.661095, doi:10.1080/01431161.2012.661095, arXiv:https://doi.org/10.1080/01431161.2012.661095.
  68. Sensor-based detection of algal blooms for public health advisories and long-term monitoring. Science of The Total Environment 767, 144984.
  69. Temporal Vegetation Modelling Using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-spectral Satellite Images, in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society. pp. 1496–1504. doi:10.1109/CVPRW.2017.193.
  70. Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences 8, 611.
  71. Land Use/Cover Classification Techniques Using Optical Remotely Sensed Data in Landscape Planning. INTECH. pp. 21–54. doi:10.5772/2761.
  72. Pedestrian path prediction with recursive bayesian filters: A comparative study, pp. 174 – 183. doi:10.1007/978-3-642-40602-7_18.
  73. Land cover classification from multi-temporal, multi-spectral remotely sensed imagery using patch-based recurrent neural networks. Neural Networks 105, 346–355.
  74. Amazon deforestation and climate change. Science 247, 1322–1325. URL: https://www.science.org/doi/abs/10.1126/science.247.4948.1322, doi:10.1126/science.247.4948.1322, arXiv:https://www.science.org/doi/pdf/10.1126/science.247.4948.1322.
  75. A Neural Network Approach to Flood Mapping Using Satellite Imagery. Computing and Informatics 29, 1013–1024.
  76. Water Quality Properties Derived from VIIRS Measurements in the Great Lakes. Remote Sensing 12, 1605. doi:10.3390/rs12101605.
  77. Selection of classification techniques for land use/land cover change investigation. Advances in Space Research 50, 1250–1265. URL: https://www.sciencedirect.com/science/article/pii/S0273117712004218, doi:https://doi.org/10.1016/j.asr.2012.06.032.
  78. The use of prior probabilities in maximum likelihood classification of remotely sensed data. Remote Sensing of Environment 10, 135–163. URL: https://www.sciencedirect.com/science/article/pii/0034425780900115, doi:https://doi.org/10.1016/0034-4257(80)90011-5.
  79. Classification mapping of salt marsh vegetation by flexible monthly NDVI time-series using Landsat imagery. Estuarine, Coastal and Shelf Science 213, 61–80.
  80. Bayesian Classification in a Time-varying Environment. Technical Report. Purdue University.
  81. Assessing land use and land cover change detection using remote sensing in the Lake Tana basin, Northwest Ethiopia. Cogent Environmental Science 6, 1778998. URL: https://doi.org/10.1080/23311843.2020.1778998, doi:10.1080/23311843.2020.1778998, arXiv:https://doi.org/10.1080/23311843.2020.1778998.
  82. Spectral variability of remotely sensed target materials: Causes, models, and strategies for mitigation and robust exploitation. IEEE Geoscience and Remote Sensing Magazine 7, 8–30.
  83. Quantitative monitoring of inland water using remote sensing of the upper reaches of the Huangpu River, China. International Journal of Remote Sensing 31, 2471–2492. URL: https://doi.org/10.1080/01431160902994440, doi:10.1080/01431160902994440, arXiv:https://doi.org/10.1080/01431160902994440.
  84. A recursive bayesian approach to describe retinal vasculature geometry. Pattern Recognition 87, 157–169. URL: https://www.sciencedirect.com/science/article/pii/S0031320318303625, doi:https://doi.org/10.1016/j.patcog.2018.10.017.
  85. MultiSenGE: A multimodal and multitemporal benchmark dataset for land use/land cover remote sensing applications. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-3-2022, 635–640. doi:10.5194/isprs-annals-V-3-2022-635-2022.
  86. Wifi fingerprinting and tracking using neural networks, in: Proceedings of the 32nd International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2019), pp. 2314–2324.
  87. Automated Subpixel Surface Water Mapping from Heterogeneous Urban Environments Using Landsat 8 OLI Imagery. Remote Sensing 8, 584. URL: http://dx.doi.org/10.3390/rs8070584, doi:10.3390/rs8070584.
  88. Urban surface water body detection with suppressed built-up noise based on water indices from Sentinel-2 MSI imagery. Remote sensing of environment 219, 259–270.
  89. ESA WorldCover 10 m 2020 v100.
  90. Cloud/shadow detection framework based on spectral indices for multi/hyperspectral optical remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing 144, 235 – 253. doi:10.1016/j.isprsjprs.2018.07.006.
  91. Extraction of Coastline in Aquaculture Coast from Multispectral Remote Sensing Images: Object-Based Region Growing Integrating Edge Detection. Remote Sensing 5, 4470–4487. URL: https://www.mdpi.com/2072-4292/5/9/4470, doi:10.3390/rs5094470.
  92. Potential Bands of Sentinel-2A Satellite for Classification Problems in Precision Agriculture. International Journal of Automation and Computing 16, 16. URL: https://www.mi-research.net/en/article/doi/10.1007/s11633-018-1143-x, doi:10.1007/s11633-018-1143-x.
  93. Spatiotemporal fusion of multisource remote sensing data: Literature survey, taxonomy, principles, applications, and future directions. Remote Sensing 10, 527.
  94. An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions. Remote Sensing of Environment 114, 2610–2623.
  95. Remote sensing of land change: A multifaceted perspective. Remote Sensing of Environment 282, 113266. doi:10.1016/j.rse.2022.113266.

Summary

We haven't generated a summary for this paper yet.