Abstract
During the last decade, huge advancements took place in remote sensing affecting speed and quality of data acquisition, processing and mapping. This rapid progress became possible especially due to shifts in software development involving cloud technologies as well as success of deep neural networks (DNN) in processing tremendous amount of data. In particular tasks such as image processing, DNNs achieve remarkable results considering accuracy and precision of pattern recognition. In order to achieve human-level performance solving image processing problem, Deep Learning (DL) solutions must be appropriately trained using powerful hardware worth of thousands of dollars which is often suboptimal to handle using on-premises servers. Current work suggests infrastructure-as-a-service (IaaS) solution for landing remote sensing (RS) data stream processing algorithm involving the latest advancements in image processing using DL solutions and cloud technologies optimized for work with the suggested algorithm such as Kubernetes and Apache Airflow hosted on Google Computing Platform (GCP). The suggested algorithm is represented as a directed acyclic graph (DAG) within IaaS-application. The mentioned cloud technologies are used for better representation of the workflow which implements a complex system for paralleling compute-heavy tasks of very high resolution (VHR) satellite imagery processing to provide the visualized segmentation results for urban development maps in a fast and efficient way.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baret, F., Buis, S.: Estimating canopy characteristics from remote sensing observations: review of methods and associated problems. Adv. Land Remote Sens. pp. 173–201 (2008). https://doi.org/10.1007/978-1-4020-6450-0_7
Bisong, E.: Containers and google kubernetes engine. In: Building Machine Learning and Deep Learning Models on Google Cloud Platform, pp. 655–670. Apress, Berkeley, CA (2019). https://doi.org/10.1007/978-1-4842-4470-8_45
Bruzzone, L., Demir, B.: A review of modern approaches to classification of remote sensing data. In: Manakos, I., Braun, M. (eds.) Land Use and Land Cover Mapping in Europe. RSDIP, vol. 18, pp. 127–143. Springer, Dordrecht (2014). https://doi.org/10.1007/978-94-007-7969-3_9
BUBER, E., DIRI, B.: Performance analysis and CPU vs GPU comparison for deep learning. In: 2018 6th International Conference on Control Engineering Information Technology (CEIT), pp. 1–6 (2018). https://doi.org/10.1109/CEIT.2018.8751930
Frogner, C., Zhang, C., Mobahi, H., et al.: Learning with a Wasserstein loss. In: Advances in Neural Information Processing Systems, vol. 28 (2015). https://doi.org/10.48550/arXiv.1506.05439
Fu, Y., Guo, H., Li, M., et al.: Cpt: efficient deep neural network training via cyclic precision. arXiv preprint arXiv:2101.09868 (2021). https://doi.org/10.48550/arXiv.2101.09868
Ghanbari, H., Mahdianpari, M., Homayouni, S., Mohammadimanesh, F.: A meta-analysis of convolutional neural networks for remote sensing applications. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 3602–3613 (2021). https://doi.org/10.1109/JSTARS.2021.3065569
Hnatushenko, V., Hnatushenko, V., Kavats, O., et al.: Pansharpening technology of high resolution multispectral and panchromatic satellite images. Sci. Bull. Nat. Min. Univ. 4, 91–98 (2015)
Hnatushenko, V., Zhernovyi, V.: Complex Approach of High-Resolution Multispectral Data Engineering for Deep Neural Network Processing. In: Lytvynenko, V., Babichev, S., Wójcik, W., Vynokurova, O., Vyshemyrskaya, S., Radetskaya, S. (eds.) ISDMCI 2019. AISC, vol. 1020, pp. 659–672. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-26474-1_46
Hnatushenko, V., Zhernovyi, V.: Method of improving instance segmentation for very high resolution remote sensing imagery using deep learning. In: Babichev, S., Peleshko, D., Vynokurova, O. (eds.) DSMP 2020. CCIS, vol. 1158, pp. 323–333. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61656-4_21
Hnatushenko, V., Zhernovyi, V., Udovyk, I., Shevtsova, O.: Intelligent system for building separation on a semantically segmented map. In: CEUR Workshop Proceedings, pp. 1–11 (2021)
Hong, S., Roh, B., Kim, K.H., et al.: PvaNet: lightweight deep neural networks for real-time object detection. arXiv preprint arXiv:1611.08588 (2016). https://doi.org/10.48550/arXiv.1611.08588
Hordiiuk, D., Hnatushenko, V.: Neural network and local laplace filter methods applied to very high resolution remote sensing imagery in urban damage detection. In: 2017 IEEE International Young Scientists Forum on Applied Physics and Engineering (YSF), pp. 363–366 (2017). https://doi.org/10.1109/YSF.2017.8126648
Hutchinson, M., Antono, E., Gibbons, B., et al.: Overcoming data scarcity with transfer learning. arXiv preprint arXiv:1711.05099 (2017). https://doi.org/10.48550/arXiv.1711.05099
Jain, P., Mo, X., Jain, A., Subbaraj, H., et al.: Dynamic space-time scheduling for GPU inference. arXiv preprint arXiv:1901.00041 (2018). https://doi.org/10.48550/arXiv.1901.00041
Kaab, A.: Remote sensing of permafrost-related problems and hazards. Permafrost Periglac. Process. 19(2), 107–136 (2008). https://doi.org/10.1002/ppp.619
Kimmel, J., Mcdole, A., Abdelsalam, M., Gupta, M., Sandhu, R.: Recurrent neural networks based online behavioural malware detection techniques for cloud infrastructure. IEEE Access 9, 68066–68080 (2021). https://doi.org/10.1109/ACCESS.2021.3077498
Madiajagan, M., Raj, S.: Parallel computing, graphics processing unit (GPU) and new hardware for deep learning in computational intelligence research. In: Deep Learning and Parallel Computing Environment for Bioengineering Systems, pp. 1–15. Elsevier (2019). https://doi.org/10.1016/B978-0-12-816718-2.00008-7
Mueller, P.: Cryptocurrency mining: asymmetric response to price movement. Available at SSRN 3733026 (2020). https://doi.org/10.2139/ssrn.3733026
Natarajan, A., Ganesan, D., Marlin, B.: Hierarchical active learning for model personalization in the presence of label scarcity. In: 2019 IEEE 16th International Conference on Wearable and Implantable Body Sensor Networks (BSN), pp. 1–4. IEEE (2019). https://doi.org/10.1109/BSN.2019.8771081
Ranjit, M.P., Ganapathy, G., Sridhar, K., Arumugham, V.: Efficient deep learning hyperparameter tuning using cloud infrastructure: Intelligent distributed hyperparameter tuning with Bayesian optimization in the cloud. In: 2019 IEEE 12th International Conference on Cloud Computing (CLOUD), pp. 520–522 (2019). https://doi.org/10.1109/CLOUD.2019.00097
Sethi, K., Kumar, R., Prajapati, N., Bera, P.: Deep reinforcement learning based intrusion detection system for cloud infrastructure. In: 2020 International Conference on Communication Systems Networks (COMSNETS), pp. 1–6 (2020). https://doi.org/10.1109/COMSNETS48256.2020.9027452
Sovrano, F., Palmirani, M., Vitali, F.: Combining shallow and deep learning approaches against data scarcity in legal domains. Gov. Inf. Quart. 39(3), 101715 (2022). https://doi.org/10.1016/j.giq.2022.101715
Strom, N.: Scalable distributed DNN training using commodity GPU cloud computing. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)
Sze, V., Chen, Y.H., Yang, T.J., Emer, J.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017). https://doi.org/10.1109/JPROC.2017.2761740
Sze, V., Chen, Y.H., Yang, T.J., Emer, J.: Efficient processing of deep neural networks. Synth. Lect. Comput. Archit. 15(2), 1–341 (2020). https://doi.org/10.2200/S01004ED1V01Y202004CAC050
Teerapittayanon, S., McDanel, B., Kung, H.T.: Distributed deep neural networks over the cloud, the edge and end devices. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), pp. 328–339. IEEE (2017). https://doi.org/10.1109/ICDCS.2017.226
Walter-Tscharf, V.: Implementation and evaluation of a MLaaS for document classification with continuous deep learning models. In: Architecture, Engineering, and Technology (AET), p.55
Wiedemann, S., Mehari, T., Kepp, K., Samek, W.: Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 720–721 (2020). https://doi.org/10.48550/arXiv.2004.04729
Yao, Y., Deng, J., Chen, X., et al.: Deep discriminative CNN with temporal ensembling for ambiguously-labeled image classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12669–12676 (2020). https://doi.org/10.1609/aaai.v34i07.6959
You, Y., Zhang, Z., Hsieh, C.J., Demmel, J., Keutzer, K.: Fast deep neural network training on distributed systems and cloud tpus. IEEE Trans. Parallel Distrib. Syst. 30(11), 2449–2462 (2019). https://doi.org/10.1109/TPDS.2019.2913833
Yu, Z., Fu, Y., Wu, S., et al.: Ldp: learnable dynamic precision for efficient deep neural network training and inference. arXiv preprint arXiv:2203.07713 (2022). https://doi.org/10.48550/arXiv.2203.07713
Zheng, H., Xu, F., Chen, L., Zhou, Z., Liu, F.: Cynthia: Cost-efficient cloud resource provisioning for predictable distributed deep neural network training. In: Proceedings of the 48th International Conference on Parallel Processing, pp. 1–11 (2019). https://doi.org/10.1145/3337821.3337873
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhernovyi, V., Hnatushenko, V., Shevtsova, O. (2023). IaaS-Application Development for Paralleled Remote Sensing Data Stream Processing. In: Babichev, S., Lytvynenko, V. (eds) Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making. ISDMCI 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 149. Springer, Cham. https://doi.org/10.1007/978-3-031-16203-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-16203-9_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16202-2
Online ISBN: 978-3-031-16203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)