Abstract
The increasing common use of incidental unrectified satellite images have many applications for mapping of earth for coastal and ocean applications. Hazard assessment and natural resource management can also be done via this process. Remote sensing is being used extensively due to the increase in the number of satellites in space. It is also the future of optimization of GPS systems and the internet. To demonstrate the semantic segmentation process, this study presents proposed solutions along with their evaluation metrics adapted from fully connected neural networks such as UNet and PSPNet. UNet architecture based deep learning model has outperformed PSPNet based architecture with overall Mean-IOU score of 0.51 on the test set in the semantic segmentation. The overall accuracy of the model can further be improved by providing homogeneous features to train the model, balance classes and by incorporating more data set for semantic segmentation. The developed model can be useful to the authorities for smart city planning and landuse mapping.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bosch M, Foster K, Christie G, Wang S, Hager GD, Brown M (2019) Semantic stereo for incidental satellite images, in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 1524-1532
Cao Y, Vassantachart A, Ye J, Yu C, Ruan D, Sheng K., ... & Zada G (2020). Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric UNet architecture. Physics in Medicine & Biology
Deng L, Yu D (2014) Deep learning: methods and applications, Foundations and Trends® in Signal Processing 7, 197–387
Dey V, Zhang Y, Zhong M (2010) A review on image segmentation techniques with remote sensing perspective
https://www.diva-gis.org/datadown. Accessed Jan 1 2021.
Kavzoglu T, Tonbul H, Erdemir MY, Colkesen I (2018) Dimensionality reduction and classification of hyperspectral images using object-based image analysis. Journal of the Indian Society of Remote Sensing 46:1297–1306
Le Saux B, Yokoya N, Hänsch R, Brown M (2019) Data Fusion Contest 2019 (DFC2019), IEEE Dataport, doi: https://doi.org/10.21227/c6tm-vw12.
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436
Li Y, Wang S, Tian Q, Ding X (2015) Feature representation for statistical-learning-based object detection: A review. Pattern Recogn 48(11):3542–3559
Li P, Li J, Huang Z, Li T, Gao C-Z, Yiu S-M, Chen K (2017) Multi-key privacy-preserving deep learning in cloud computing. Futur Gener Comput Syst 74:76–85
Li Y, Tao J, Schuller BR, Shan S, Jiang D, Jia J (2017) Mec 2017: Multimodal emotion recognition challenge, in 2018 First Asian Conference on Affective Computing and Intelligent Interaction (ACII Asia), 1-5
Liu AK, Peng CY, Chang S-S (1997) Wavelet analysis of satellite images for coastal watch. IEEE J Oceanic Eng 22:9–17
Lu H, Li Y, Chen M, Kim H, Serikawa S (2018) Brain intelligence: go beyond artificial intelligence. Mobile Networks and Applications 23:368–375
Marcus G (2018) Deep learning: A critical appraisal, arXiv preprint
Matiz S, Barner KE (2019) Inductive conformal predictor for convolutional neural networks: Applications to active learning for image classification. Pattern Recogn 90:172–182
Paoletti ME, Haut JM, Fernandez-Beltran R, Plaza J, Plaza AJ, Pla F (2018) Deep pyramidal residual networks for spectral–spatial hyperspectral image classification. IEEE Trans Geosci Remote Sens 57:740–754
Paul S, Kumar DN (2018) Spectral-spatial classification of hyperspectral data with mutual information based segmented stacked autoencoder approach. ISPRS J Photogramm Remote Sens 138:265–280
Ringeval F, Schuller BR, Valstar M, Cowie R, Kaya H, Schmitt M, Amiriparian S, Cummins N, Lalanne D, Michaud A (2018) AVEC 2018 workshop and challenge: Bipolar disorder and cross-cultural affect recognition, in Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop, 3–13
Schmidhuber JR (2015) Deep learning in neural networks: An overview. Neural networks 61:85–117
Schölkopf B, Smola A, Müller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5):1299–1319
Sharma S (2017). Activation functions in neural networks. Towards Data Science 6
Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY (2019) Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 103:167–175
Vapnik V, Guyon I, Hastie T (1995) Support vector machines. Mach Learn 20(3):273–297
Wei Y, Zhao Z, Song J (2004) Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection, in IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium, 2008-2010
Yang X, Zeng Z, Teo SG, Wang L, Chandrasekhar V, Hoi S (2018) Deep Learning for Practical Image Recognition: Case Study on Kaggle Competitions, in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 923–931
Yue J, Zhao W, Mao S, Liu H (2015) Spectral–spatial classification of hyperspectral images using deep convolutional neural networks. Remote Sensing Letters 6:468–477
Zhang Q, Yang LT, Chen Z, Li P, Bu F (2018a) An adaptive dropout deep computation model for industrial IoT big data learning with crowdsourcing to cloud computing. IEEE Trans Industr Inf 15:2330–2337
Zhang C, Pan X, Li H, Gardiner A, Sargent I, Hare J, Atkinson PM (2018b) A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification. ISPRS J Photogramm Remote Sens 140:133–144
Zou Q, Ni L, Zhang T, Wang Q (2015) Deep learning based feature selection for remote sensing scene classification. IEEE Geosci Remote Sens Lett 12:2321–2325
Acknowledgements
The authors are grateful to the IEEE GRSS IADF committee chairs – Bertrand Le Saux, Ronny Hänsch, and Naoto Yokoya – for their collaboration in leveraging this work to enable public research and for important recommendations to improve the challenge tracks. This work was made possible by the advocacy and support from Bennett University, Greater Noida. Commercial satellite imagery was provided courtesy of DigitalGlobe. U. S. Cities lidar and vector data were made publicly available by the Homeland Security Infrastructure Program.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: H. Babaie
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chaurasia, K., Nandy, R., Pawar, O. et al. Semantic segmentation of high-resolution satellite images using deep learning. Earth Sci Inform 14, 2161–2170 (2021). https://doi.org/10.1007/s12145-021-00674-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-021-00674-7