sapiСистемный анализ и прикладная информатика«System analysis and applied information science»2309-49232414-0481Belarusian National Technical University10.21122/2309-4923-2023-4-20-28sapi-642Research ArticleСистемный анализSystem analysisКлассификация методов сегментации снимков земной поверхностиClassification of earth surface image segmentation methodsКуприяноваД. B.KypriyanavaD. V.

Старший преподаватель, аспирант, кафедра электронных вычислительных машин

г. Минск

Kypriyanava Dziana V., Senior Lecturer, PhD Student, Electronic Computing Machines Department

Minsk

kupriuanova@bsuir.byПерцевД. Ю.PertsauD. Y.

Кандидат технических наук, доцент, доцент кафедры электронных вычислительных машин

г. Минск

 

Pertsau Dmitry Y., Associate Professor, Associate Professor of Electronic Computing Machines Department 

Minsk

pertsev@bsuir.byТатурМ. М.TaturM. M.

Доктор технических наук, профессор, профессор кафедры электронных вычислительных машин

г. Минск

Tatur Mikhail M., Doctor of Science, Professor, Professor of Electronic Computing Machines Department

Minsk

tatur@bsuir.byБелорусский государственный университет информатики и радиоэлектроникиБеларусьBelarusian State University of Informatics and RadioelectronicsBelarus202311012024042028Copyright © Куприянова Д.B., Перцев Д.Ю., Татур М.М., 20242024Куприянова Д.B., Перцев Д.Ю., Татур М.М.Kypriyanava D.V., Pertsau D.Y., Tatur M.M.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://sapi.bntu.by/jour/article/view/642

В данной работе представлена классификация методов сегментации снимков земной поверхности. Рассмотрены такие подходы как сравнение с шаблоном, машинное обучение и глубокие нейронные сети, а также применение знаний об анализируемых объектах. Рассмотрены особенности применения вегетационных индексов для сегментации данных по спутниковым снимкам. Отмечены преимущества и недостатки. Систематизированы результаты, полученные авторами методик, появившихся за последние 10 лет, что позволит заинтересованным быстрее сориентироваться, сформировать идеи для последующих исследований.

The classification of methods for land surface image segmentation is presented in the paper. Such approaches as template matching, machine learning and deep neural networks, as well as application of knowledge about analyzed objects are considered. Peculiarities of vegetation indices application for satellite images data segmentation are considered. Advantages and disadvantages are noted. The results obtained by the authors of the methods that have appeared over the last 10 years are systematized, which will allow those interested to get oriented faster and form ideas for further research.

дистанционное зондированиеглубокое обучениемашинное обучениесегментацияremote sensingmachine learningsemantic segmentationvegetation indicesReferencesCopernicus Sentinel Data Access: Annual Report, 2022 [Electronic resource]. Access mode: https://scihub.copernicus.eu/twiki/pub/SciHubWebPortal/AnnualReport2022/COPE-SERCO-RP-23-1493_SentinelDataAccessAnnual_Report_2022.pdf. Accessed: 19.11.2023.Copernicus Sentinel Data Access: Annual Report, 2022 [Electronic resource]. Access mode: https://scihub.copernicus.eu/twiki/pub/SciHubWebPortal/AnnualReport2022/COPE-SERCO-RP-23-1493_SentinelDataAccessAnnual_Report_2022.pdf. Accessed: 19.11.2023.Cheng G., Han Junwei.Asurvey on object detection in optical remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing. 2016. Vol. 117. Pр. 11-28. doi: 10.1016/j.isprsjprs.2016.03.014Cheng G., Han Junwei.Asurvey on object detection in optical remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing. 2016. Vol. 117. Pр. 11-28. doi: 10.1016/j.isprsjprs.2016.03.014Stankov K., He Dong-Chen. Detection of Buildings in Multispectral Very High Spatial Resolution Images Using the Percentage Occupancy Hit-or-Miss Transform. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2014. Vol. 7. Issue 10. Pp. 4069-4080. doi: 10.1109/JSTARS.2014.2308301Stankov K., He Dong-Chen. Detection of Buildings in Multispectral Very High Spatial Resolution Images Using the Percentage Occupancy Hit-or-Miss Transform. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2014. Vol. 7. Issue 10. Pp. 4069-4080. doi: 10.1109/JSTARS.2014.2308301Weber J., Lefèvreb S. Spatial and spectral morphological template matching. Image and Vision Computing. 2012. Vol. 30. Issue 12. Pp. 934-945. doi: 10.1016/j.imavis.2012.07.002Weber J., Lefèvreb S. Spatial and spectral morphological template matching. Image and Vision Computing. 2012. Vol. 30. Issue 12. Pp. 934-945. doi: 10.1016/j.imavis.2012.07.002Chaudhuri D., Kushwaha N., Samal A. Semi-Automated Road Detection From High Resolution Satellite Images by Directional Morphological Enhancement and Segmentation Techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2012. Vol. 5. Issue 5. Pp. 1538-1544. doi: 10.1109/JSTARS.2012.2199085Chaudhuri D., Kushwaha N., Samal A. Semi-Automated Road Detection From High Resolution Satellite Images by Directional Morphological Enhancement and Segmentation Techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2012. Vol. 5. Issue 5. Pp. 1538-1544. doi: 10.1109/JSTARS.2012.2199085Lin Y., He H., Yin Z., Chen F. Rotation-invariant object detection in remote sensing images based on radial-gradient angle. IEEE Geoscience and Remote Sensing Letters. 2015. Vol. 12. Issue 4. Pp. 746-750. doi: 10.1109/LGRS.2014.2360887Lin Y., He H., Yin Z., Chen F. Rotation-invariant object detection in remote sensing images based on radial-gradient angle. IEEE Geoscience and Remote Sensing Letters. 2015. Vol. 12. Issue 4. Pp. 746-750. doi: 10.1109/LGRS.2014.2360887Liu G., Sun X., Fu K., Wang H. Interactive geospatial object extraction in high resolution remote sensing images using shape-based global minimization active contour model. Pattern Recognition Letters. 2013. Vol. 34. Issue 10. Pp. 1186-1195. doi: 10.1016/j.patrec.2013.03.031Liu G., Sun X., Fu K., Wang H. Interactive geospatial object extraction in high resolution remote sensing images using shape-based global minimization active contour model. Pattern Recognition Letters. 2013. Vol. 34. Issue 10. Pp. 1186-1195. doi: 10.1016/j.patrec.2013.03.031Tao C., Tan Y., Cai H., Tian J. Airport detection from large IKONOS images using clustered SIFT keypoints and region information. IEEE Geoscience and Remote Sensing Letters. 2011. Vol. 8. Issue 1. Pp. 128-132. doi: 10.1109/LGRS.2010.2051792Tao C., Tan Y., Cai H., Tian J. Airport detection from large IKONOS images using clustered SIFT keypoints and region information. IEEE Geoscience and Remote Sensing Letters. 2011. Vol. 8. Issue 1. Pp. 128-132. doi: 10.1109/LGRS.2010.2051792Leninisha S., Vani K. Water flow based geometric active deformable model for road network. ISPRS Journal of Photogrammetry and Remote Sensing. 2015. Vol. 102. Pp. 140-147. doi: 10.1016/j.isprsjprs.2015.01.013Leninisha S., Vani K. Water flow based geometric active deformable model for road network. ISPRS Journal of Photogrammetry and Remote Sensing. 2015. Vol. 102. Pp. 140-147. doi: 10.1016/j.isprsjprs.2015.01.013Weidner U., Förstner W. Towards automatic building extraction from high-resolution digital elevation models. ISPRS Journal of Photogrammetry and Remote Sensing. 1995. Vol. 50. Issue 4. Pp. 38-49. doi: 10.1016/0924–2716(95)98236–SWeidner U., Förstner W. Towards automatic building extraction from high-resolution digital elevation models. ISPRS Journal of Photogrammetry and Remote Sensing. 1995. Vol. 50. Issue 4. Pp. 38-49. doi: 10.1016/0924–2716(95)98236–SOk A.O., Senaras C., Yuksel B. Automated detection of arbitrarily shaped buildings in complex environments from monocular VHR optical satellite imagery. IEEE Transactions on Geoscience and Remote Sensing. 2013. Vol. 51. Issue 3. Pp. 17011717. doi: 10.1109/TGRS.2012.2207123Ok A.O., Senaras C., Yuksel B. Automated detection of arbitrarily shaped buildings in complex environments from monocular VHR optical satellite imagery. IEEE Transactions on Geoscience and Remote Sensing. 2013. Vol. 51. Issue 3. Pp. 17011717. doi: 10.1109/TGRS.2012.2207123Akçay H.G., Aksoy S. Building detection using directional spatial constraints. IEEE International Geoscience and Remote Sensing Symposium. 2010. Pp. 1932-1935. doi: 10.1109/IGARSS.2010.5652842Akçay H.G., Aksoy S. Building detection using directional spatial constraints. IEEE International Geoscience and Remote Sensing Symposium. 2010. Pp. 1932-1935. doi: 10.1109/IGARSS.2010.5652842Rouse J.W. [et al.] Monitoring vegetation systems in the Great Plains with ERTS. Third Earth Resources Technology Satellite–1 Symposium. Vol. 1: Technical Presentations, section A. 1973. NASA. Pp. 309-317.Rouse J.W. [et al.] Monitoring vegetation systems in the Great Plains with ERTS. Third Earth Resources Technology Satellite–1 Symposium. Vol. 1: Technical Presentations, section A. 1973. NASA. Pp. 309-317.Huete A. [et al.] Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment. 2002. Vol. 83. Issue 1-2. Pp. 195-213. doi: 10.1016/S0034–4257(02)00096–2Huete A. [et al.] Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment. 2002. Vol. 83. Issue 1-2. Pp. 195-213. doi: 10.1016/S0034–4257(02)00096–2Riggs G., Hall D., Salomonson V. A Snow Index for the Landsat Thematic Mapper and Moderate Resolution Imaging Spectrometer. Proceedings of IGARSS'94 – 1994 IEEE International Geoscience and Remote Sensing Symposium. 1994. Pasadena, CA, USA. Pp. 1942-1944. doi: 10.1109/IGARSS.1994.399618Riggs G., Hall D., Salomonson V. A Snow Index for the Landsat Thematic Mapper and Moderate Resolution Imaging Spectrometer. Proceedings of IGARSS'94 – 1994 IEEE International Geoscience and Remote Sensing Symposium. 1994. Pasadena, CA, USA. Pp. 1942-1944. doi: 10.1109/IGARSS.1994.399618McFeeters S. The Use of Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features. International Journal of Remote Sensing. 1996. Vol. 17. Pp. 1425-1432. doi: 10.1080/01431169608948714McFeeters S. The Use of Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features. International Journal of Remote Sensing. 1996. Vol. 17. Pp. 1425-1432. doi: 10.1080/01431169608948714Gitelson A., Kaufman Y., Merzlyak M. Use of a green channel in remote sensing of global vegetation from EOSMODIS. Remote Sensing of Environment. 1996. Vol. 58. Issue 3. Pp. 289-298. doi: 10.1016/S0034–4257(96)00072–7Gitelson A., Kaufman Y., Merzlyak M. Use of a green channel in remote sensing of global vegetation from EOSMODIS. Remote Sensing of Environment. 1996. Vol. 58. Issue 3. Pp. 289-298. doi: 10.1016/S0034–4257(96)00072–7Penuelas J., Baret F., Filella I. Semi–Empirical Indices to Assess Carotenoids/Chlorophyll-a Ratio from Leaf Spectral Reflectance. Photosynthetica. 1995. Vol. 31. Pp. 221-230.Penuelas J., Baret F., Filella I. Semi–Empirical Indices to Assess Carotenoids/Chlorophyll-a Ratio from Leaf Spectral Reflectance. Photosynthetica. 1995. Vol. 31. Pp. 221-230.Key C., Benson N. Landscape Assessment: Remote Sensing of Severity, the Normalized Burn Ratio; and Ground Measure of Severity, the Composite Burn Index. FIREMON: Fire Effects Monitoring and Inventory System, RMRS-GTR, Ogden, UT: USDA Forest Service. 2005.Key C., Benson N. Landscape Assessment: Remote Sensing of Severity, the Normalized Burn Ratio; and Ground Measure of Severity, the Composite Burn Index. FIREMON: Fire Effects Monitoring and Inventory System, RMRS-GTR, Ogden, UT: USDA Forest Service. 2005.Huang S. [et al.] A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forestry Research. 2021. Vol. 32. doi: 10.1007/s11676–020–01155–1Huang S. [et al.] A commentary review on the use of normalized difference vegetation index (NDVI) in the era of popular remote sensing. Journal of Forestry Research. 2021. Vol. 32. doi: 10.1007/s11676–020–01155–1Miura T. [et al.] An error and sensitivity analysis of atmospheric resistant vegetation indices derived from dark target-based atmospheric correction. Remote Sensing of Environment. 2001. Vol. 78. Issue 3. Pp. 284-298. doi: 10.1016/S0034–4257(01)00223–1Miura T. [et al.] An error and sensitivity analysis of atmospheric resistant vegetation indices derived from dark target-based atmospheric correction. Remote Sensing of Environment. 2001. Vol. 78. Issue 3. Pp. 284-298. doi: 10.1016/S0034–4257(01)00223–1Matsushita B. [et al.] Sensitivity of the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) to Topographic Effects: A Case Study in High-density Cypress Forest. Sensors. 2007. Vol. 7. Pp. 2636-2651. doi: 10.3390/s7112636Matsushita B. [et al.] Sensitivity of the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) to Topographic Effects: A Case Study in High-density Cypress Forest. Sensors. 2007. Vol. 7. Pp. 2636-2651. doi: 10.3390/s7112636Liu L., Shi Z. Airplane detection based on rotation invariant and sparse coding in remote sensing images. Optik. 2014. Vol. 125. Issue 18. Pp. 5327-5333. doi: 10.1016/j.ijleo.2014.06.062Liu L., Shi Z. Airplane detection based on rotation invariant and sparse coding in remote sensing images. Optik. 2014. Vol. 125. Issue 18. Pp. 5327-5333. doi: 10.1016/j.ijleo.2014.06.062Li E. [et al.] Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF. IEEE Transactions on Geoscience and Remote Sensing. 2015. Vol. 53. Issue 8. Pp. 4483-4495. doi: 10.1109/TGRS.2015.2400462Li E. [et al.] Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF. IEEE Transactions on Geoscience and Remote Sensing. 2015. Vol. 53. Issue 8. Pp. 4483-4495. doi: 10.1109/TGRS.2015.2400462Yao X. [et al.] A coarse-to-fine model for airport detection from remote sensing images using target–oriented visual saliency and CRF. Neurocomputing. 2015. Vol. 164. Pp. 162-172. doi: 10.1016/j.neucom.2015.02.073Yao X. [et al.] A coarse-to-fine model for airport detection from remote sensing images using target–oriented visual saliency and CRF. Neurocomputing. 2015. Vol. 164. Pp. 162-172. doi: 10.1016/j.neucom.2015.02.073Zhang W. [et al.] A generic discriminative part-based model for geospatial object detection in optical remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing. 2015. Vol. 99. Pp. 30-44. doi: 10.1016/j.isprsjprs.2014.10.007Zhang W. [et al.] A generic discriminative part-based model for geospatial object detection in optical remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing. 2015. Vol. 99. Pp. 30-44. doi: 10.1016/j.isprsjprs.2014.10.007Long J. [et al.] Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017. Vol. 39. Issue 4. Pp. 640-651. doi: 10.1109/TPAMI.2016.2572683Long J. [et al.] Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017. Vol. 39. Issue 4. Pp. 640-651. doi: 10.1109/TPAMI.2016.2572683Chen G. [et al.] SDFCNv2: an improved FCN framework for remote sensing images semantic segmentation. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13234902Chen G. [et al.] SDFCNv2: an improved FCN framework for remote sensing images semantic segmentation. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13234902Chen L. [et al.] EFCNet: ensemble full convolutional network for semantic segmentation of high–resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters. Vol. 19. doi: 10.1109/LGRS.2021.3076093Chen L. [et al.] EFCNet: ensemble full convolutional network for semantic segmentation of high–resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters. Vol. 19. doi: 10.1109/LGRS.2021.3076093Foivos I. [et al.] ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. Vol. 162. Pp. 94-114. doi: 10.1016/j.isprsjprs.2020.01.013Foivos I. [et al.] ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. Vol. 162. Pp. 94-114. doi: 10.1016/j.isprsjprs.2020.01.013Yue K. [et al.] TreeUNet: adaptive tree convolutional neural networks for subdecimeter aerial image segmentation. ISPRS Journal of Photogrammetry and Remote Sensing. 2019. Vol. 156. Pp. 1-13. doi: 10.1016/j.isprsjprs.2019.07.007Yue K. [et al.] TreeUNet: adaptive tree convolutional neural networks for subdecimeter aerial image segmentation. ISPRS Journal of Photogrammetry and Remote Sensing. 2019. Vol. 156. Pp. 1-13. doi: 10.1016/j.isprsjprs.2019.07.007Bai H. [et al.] HCANet: a hierarchical context aggregation network for semantic segmentation of high-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters. 2021. Vol. 19. doi: 10.1109/LGRS.2021.3063799Bai H. [et al.] HCANet: a hierarchical context aggregation network for semantic segmentation of high-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters. 2021. Vol. 19. doi: 10.1109/LGRS.2021.3063799Weng L. [et al.] Water areas segmentation from remote sensing images using a separable residual segnet network. ISPRS International Journal of Geo-Information. 2020. Vol. 9. doi: 10.3390/ijgi9040256Weng L. [et al.] Water areas segmentation from remote sensing images using a separable residual segnet network. ISPRS International Journal of Geo-Information. 2020. Vol. 9. doi: 10.3390/ijgi9040256Mi L., Chen Z. Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. Vol. 159. Pp. 140-152. doi: 10.1016/j.isprsjprs.2019.11.006Mi L., Chen Z. Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. Vol. 159. Pp. 140-152. doi: 10.1016/j.isprsjprs.2019.11.006Zhao D. [et al.] Semantic segmentation of remote sensing image based on regional selfattention mechanism. IEEE Geoscience and Remote Sensing Letters. Vol. 19. doi: 10.1109/LGRS.2021.3071624Zhao D. [et al.] Semantic segmentation of remote sensing image based on regional selfattention mechanism. IEEE Geoscience and Remote Sensing Letters. Vol. 19. doi: 10.1109/LGRS.2021.3071624Liu K.-H., Lin B.-Y. MSCSA-Net: Multi-Scale Channel Spatial Attention Network for Semantic Segmentation of Remote Sensing Images. Applied Sciences. 2023. Vol. 13. Issue 17. doi: 10.3390/app13179491Liu K.-H., Lin B.-Y. MSCSA-Net: Multi-Scale Channel Spatial Attention Network for Semantic Segmentation of Remote Sensing Images. Applied Sciences. 2023. Vol. 13. Issue 17. doi: 10.3390/app13179491Li R., Duan C.X. ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fineresolution remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing. 2021. Vol. 181. Pp. 84-98. doi: 10.1016/j.isprsjprs.2021.09.005Li R., Duan C.X. ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fineresolution remotely sensed imagery. ISPRS Journal of Photogrammetry and Remote Sensing. 2021. Vol. 181. Pp. 84-98. doi: 10.1016/j.isprsjprs.2021.09.005Luo H. [et al.] High-resolution aerial images semantic segmentation using deep fully convolutional network with channel attention mechanism. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2019. Vol. 12. Issue 9. Pp. 3492-3507. doi: 10.1109/JSTARS.2019.2930724Luo H. [et al.] High-resolution aerial images semantic segmentation using deep fully convolutional network with channel attention mechanism. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2019. Vol. 12. Issue 9. Pp. 3492-3507. doi: 10.1109/JSTARS.2019.2930724Liu Y. [et al.] RoadNet: learning to comprehensively analyze road networks in complex urban scenes from highresolution remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing. 2019. Vol. 57. Issue 4. Pp. 2043-2056. doi: 10.1109/TGRS.2018.2870871Liu Y. [et al.] RoadNet: learning to comprehensively analyze road networks in complex urban scenes from highresolution remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing. 2019. Vol. 57. Issue 4. Pp. 2043-2056. doi: 10.1109/TGRS.2018.2870871Li X. [et al.] Encoding contextual information by interlacing Transformer and convolution for remote sensing imagery semantic segmentation. Remote Sensing. 2022. Vol. 14. doi: 10.3390/rs14164065Li X. [et al.] Encoding contextual information by interlacing Transformer and convolution for remote sensing imagery semantic segmentation. Remote Sensing. 2022. Vol. 14. doi: 10.3390/rs14164065Zhao X. [et al.] Memory-augmented Transformer for remote sensing image semantic segmentation. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13224518Zhao X. [et al.] Memory-augmented Transformer for remote sensing image semantic segmentation. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13224518Sun S. [et al.] Semantic segmentation for buildings of large intra-class variation in remote sensing images with O-GAN. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13030475Sun S. [et al.] Semantic segmentation for buildings of large intra-class variation in remote sensing images with O-GAN. Remote Sensing. 2021. Vol. 13. doi: 10.3390/rs13030475

The authors declare that there are no conflicts of interest present.