A Novel Approach for Satellite Image Classification using Optimized Deep Convolutional Neural Network

A Novel Approach for Satellite Image Classification using Optimized Deep Convolutional Neural Network

© 2022 by IJETT Journal
Volume-70 Issue-6
Year of Publication : 2022
Authors : Bindhu J S, Pramod K V
DOI : 10.14445/22315381/IJETT-V70I6P236

How to Cite?

Bindhu J S, Pramod K V, "A Novel Approach for Satellite Image Classification using Optimized Deep Convolutional Neural Network," International Journal of Engineering Trends and Technology, vol. 70, no. 6, pp. 349-365, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I6P236

Recently, remote sensing images have been extensively used in different scene classification. Satellite image classification is used for different applications like land use classification, crop monitoring, forest cover mapping, and natural disaster detection. Accurate classification of scenes in satellite images is very challenging due to the complex, rich details in the images. This work presents a deep learning framework for accurately classifying scene types through improved learning. The proposed approach pre-processes the input image with an adaptive bilateral filtering approach. Then, the pre-processed input image is given as an input to the proposed Optimized Deep Convolutional Neural Network (ODCNN) for improved feature learning and classification. Here, the ODCNN framework is utilized to classify different scenes in the satellite images accurately.
Moreover, the modified beetle swarm optimization (MBSO) algorithm is utilized for weights optimization in the ODCNN classifier. This process improves the learning of the ODCNN classifier by accurately detecting the scene in remote sensing images. The results of the presented approach are compared with various existing schemes using different performance measures. It is proved that the examined presented approach outperforms the various existing schemes in accuracy (99.75%), precision (99.16%), recall (99.523%), and F-measure (99.34%), kappa measure (0.99), and processing time (10.67 seconds).

Filtering, Feature learning, Optimization, Deep learning, Classification.

[1] Lv, Y.; Zhang, X.; Xiong, W.; Cui, Y.; Cai, M. An End-to-End Local-Global-Fusion Feature Extraction Network for Remote Sensing Image Scene Classification. Remote Sens. 11 (2019) 3006. Https://Doi.Org/10.3390/Rs11243006
[2] Bechtel, B.; Alexander, P.J.; Böhner, J.; Ching, J.; Conrad, O.; Feddema, J.; Mills, G.; See, L.; Stewart, I. Mapping Local Climate Zones for a Worldwide Database of the Form and Function of Cities. ISPRS Int. Jgeo-Inf, 4 (2015) 199-219. Https://Doi.Org/10.3390/Ijgi4010199
[3] Lu Cui, Yonghua Zhao, Jianchao Liu, Huanyuan Wang, Ling Han, Juan Li, Zenghui Sun, Vegetation Coverage Prediction for the Qinling Mountains Using the CA–Markov Model, ISPRS International Journal of Geo-Information, 10.3390/Ijgi10100679. 10 (679) (2021).
[4] Zou, F., Xiao, W., Ji, W., He, K., Yang, Z., Song, J., .& Li, K. Arbitrary-Oriented Object Detection Via Dense Feature Fusion and Attention Model for Remote Sensing Super-Resolution Image. Neural Computing and Applications, 32(18) (2020) 14549-14562.
[5] Long, Y., Xia, G. S., Li, S., Yang, W., Yang, M. Y., Zhu, X. X., & Li, D., Dirs: on Creating Benchmark Datasets for Remote Sensing Image Interpretation, (2020). Arxiv Preprint Arxiv:2006.12485.
[6] Georgiosovakoglou, Thomas K. Alexandridis, Jan G.P.W Clevers, Ioannis Z. Gitas., Downscaling of MODIS Leaf Area Index Using Landsat Vegetation Index. Geocarto International 0:0, (2020) 1-24.
[7] Lanfa Liu, Ana-Maria Olteanu-Raimond, Laurence Jolivet, Arnaud-Le Bris, Linda See., A Data Fusion- Based Framework to Integrate Multi-Source VGI in an Authoritative Land Use Database. International Journal of Digital Earth, 14(4) (2021) 480-509.
[8] El-Hamid, H.T.A., Caiyong, W. &Yongting, Z. Geospatial Analysis of Land Use Driving Force in Coal Mining Area: Case Study in Ningdong, China. Geojournal, 86 (2021) 605–620. Https://Doi.Org/10.1007/S10708-019-10078-2
[9] Liu, J., Kuang, W., Zhang, Z. Et Al. Spatiotemporal Characteristics, Patterns, and Causes of Land-Use Changes in China Since the Late 1980s. J. Geogr. Sci, 24 (2014) 195–210. Https://Doi.Org/10.1007/S11442-014-1082-6
[10] Bey, A.; Sánchez-Pausdíaz, A.; Maniatis, D.; Marchi, G.; Mollicone, D.; Ricci, S.; Bastin, J.-F.; Moore, R.; Federici, S.; Rezende, M.; Patriarca, C.; Turia, R.; Gamoga, G.; Abe, H.; Kaidong, E.; Miceli, G. Collect Earth: Land Use and Land Cover Assessment Through Augmented Visual Interpretation. Remote Sens, 8 (2016) 807. Https://Doi.Org/10.3390/Rs8100807
[11] Thoman, P., Dichev, K., Heller, T. Et Al. A Taxonomy of Task-Based Parallel Programming Technologies for High-Performance Computing. J Supercomput, 74 (2018) 1422–1434. Https://Doi.Org/10.1007/S11227-018-2238-4
[12] Hossam, M.A., Ebied, H.M., Abdel-Aziz, M.H. Et Al. Accelerated Hyperspectral Image Recursive Hierarchical Segmentation Using Gpus, Multicore Cpus, and Hybrid CPU/GPU Cluster. J Real-Time Image Proc , 14 (2018) 413–432. Https://Doi.Org/10.1007/S11554-014-0464-4
[13] Chen, Y., Chen, Q., & Jing, C., Multi-Resolution Segmentation Parameters Optimization and Evaluation for VHR Remote Sensing Image Based on Mean NSQI and Discrepancy Measure. Journal of Spatial Science, 66(2) (2021)253-278.
[14] Chen, C., Gong, W., Chen, Y., & Li, W., Object Detection in Remote Sensing Images Based on A Scene-Contextual Feature Pyramid Network. Remote Sensing, 11(3) (2019) 339.
[15] Wang, L., Yan, J., Mu, L., & Huang, L., Knowledge Discovery From Remote Sensing Images: A Review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(5) (2020) E1371.
[16] Zahra Assarkhaniki, Soheilsabri, Abbas Rajabifard., Using Open Data to Detect the Structure and Pattern of Informal Settlements: an Outset to Support Inclusive Sdgs’ Achievement. Big Earth Data, 5(4) (2021) 497-526.
[17] Shah, K., Patel, H., Sanghvi, D. Et Al. A Comparative Analysis of Logistic Regression, Random Forest and KNN Models for the Text Classification. Augment Hum Res, 5 (2020) 12. Https://Doi.Org/10.1007/S41133-020- 00032-0
[18] Hu, Y.; Zhang, Q.; Zhang, Y.; Yan, H. A Deep Convolution Neural Network Method for Land Cover Mapping: A Case Study of Qinhuangdao, China. Remote Sens, 10 (2018) 2053. Https://Doi.Org/10.3390/Rs10122053
[19] Zahraassarkhaniki, Soheilsabri, Abbasrajabifard., Using Open Data to Detect the Structure and Pattern of Informal Settlements: an Outset to Support Inclusive Sdgs’ Achievement. Big Earth Data, 5(4) (2021) 497-526.
[20] Sebastiãorogério Da Silva Neto, Thomástabosa Oliveira, Igor Vitorteixeira, Samuel Benjamin Aguiar De Oliveira, Vanderson Souza Sampaio, Theo Lynn, Patricia Takako Endo and Rhoel Ramos Dinglasan Machine Learning and Deep Learning Techniques to Support Clinical Diagnosis of Arboviral Diseases: A Systematic Review, Journal: PLOS Neglected Tropical Diseases, 16(1) (2022) E0010061. DOI: 10.1371/Journal.Pntd.0010061.
[21] Avenash, R., & Viswanath, P., Semantic Segmentation of Satellite Images Using A Modified CNN with Hard-Swish Activation Function. in VISIGRAPP (4: VISAPP), (2019) 413-420.
[22] Neupane, B., Horanont, T., & Aryal, J., Deep Learning-Based Semantic Segmentation of Urban Features in Satellite Images: A Review and Meta-Analysis. Remote Sensing, 13(4) (2021) 808.
[23] Khamparia, A., Gupta, D., De Albuquerque, V.H.C., Et Al. Internet of Health Things-Driven Deep Learning System for Detection and Classification of Cervical Cells Using Transfer Learning. J Supercomput, 76 (2020) 8590–8608. Https://Doi.Org/10.1007/S11227-020-03159-4
[24] Yu, X., Tang, L., Wu, X. Et Al. Nondestructive Freshness Discriminating of Shrimp Using Visible/Near-Infrared Hyperspectral Imaging Technique and Deep Learning Algorithm. Food Anal. Methods, 11 (2018) 768–780. Https://Doi.Org/10.1007/S12161-017-1050-8
[25] Chen, Y., Ming, D. &Lv, X. Superpixel Based Land Cover Classification of VHR Satellite Image Combining Multi-Scale CNN and Scale Parameter Estimation. Earth Sci Inform, 12 (2019) 341–363.Https://Doi.Org/10.1007/S12145-019-00383-2.
[26] Shabbir, Amsa, Nouman Ali, Jameel Ahmed, Bushra Zafar, Aqsa Rasheed, Muhammad Sajid, Afzal Ahmed, and Saadathanif Dar, Satellite and Scene Image Classification Based on Transfer Learning and Fine-Tuning of Resnet50, Mathematical Problems in Engineering, 2021 (2021).
[27] Robinson, Y. Harold, Et Al. Tree-Based Convolutional Neural Networks for Object Classification in Segmented Satellite Images, the International Journal of High-Performance Computing Applications, (2020) 1094342020945026.
[28] Zhang, W.; Tang, P.; Zhao, L. Remote Sensing Image Scene Classification Using CNN-Capsnet. Remote Sens, 11 (2019) 494. Https://Doi.Org/10.3390/Rs11050494
[29] Xiaoweixu, Yinrong Chen, Junfeng Zhang, Yu Chen, Prathik Anandhan&Adhiyaman Manickam., A Novel Approach for Scene Classification From Remote Sensing Images Using Deep Learning Methods, European Journal of Remote Sensing, 54(2) (2021) 383-395. DOI: 10.1080/22797254.2020.1790995
[30] G. Cheng, X. Xie, J. Han, L. Guo, and G.-S. Xia, Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13 (2020) 3735–3756.
[31] Anwer, R.M., Khan, F.S. &Laaksonen, J. Compact Deep Color Features for Remote Sensing Scene Classification. Neural Process Lett, 53 (2021) 1523–1544. Https://Doi.Org/10.1007/S11063-021-10463-4
[32] Yin, Liancheng, Peiyi Yang, Keming Mao, and Qian Liu, Remote Sensing Image Scene Classification Based on Fusion Method, Journal of Sensors, 2021 (2021).
[33] Yuegao, Jun Shi, Jun Li &Ruoyu Wang ., Remote Sensing Scene Classification Based on High-Order Graph Convolutional Network, European Journal of Remote Sensing, 54 (2021) 141-155. DOI: 10.1080/22797254.2020.1868273
[34] Shabbir, A., Ali, N., Ahmed, J., Zafar, B., Rasheed, A., Sajid, M., & Dar, S. H., Satellite and Scene Image Classification Based on Transfer Learning and Fine Tuning Ofresnet 50. Mathematical Problems in Engineering, (2021). Https://Doi.Org/10.1155/2021/5843816
[35] Robinson, Y. H., Vimal, S., Khari, M., Hernández, F. C. L., & Crespo, R. G., Tree-Based Convolutional Neural Networks for Object Classification in Segmented Satellite Images. The International Journal of High Performancecomputingapplications, (2020).
[36] Vinothini, Vengateshkumar., Design of KNN Classified Segmentation of Hyper Spectral Imaging, IJETT International Journal of Electronics and Communication Engineering (IJETT-IJECE), (2019) 67-74.
[37] Keerti Maithil , Tasneem Bano Rehman., Urban Remote Sensing Image Segmentation Using Dense U-Net+. IJETT International Journal of Computer Science and Engineering, 9(3) (2022) 21-28.