Deep Learning-Based Hybrid Multivariate Improved ResNet and U-Net Scheme for Satellite Image Classification to Detect Targeted Region
DOI:
https://doi.org/10.13052/2024.ACES.J.400801Keywords:
Hybrid multivariate improved residual neural network and U-Net, multi-heuristic tuna swarm optimization, remote sensing, satellite image, YOLO v3 segmentationAbstract
In the field of remote sensing, the process of segmentation and classification of satellite images is a challenging task attributable to different types of target detection. There are problems in recognizing a target and clutter region. Then, there is a necessity to consider these problems regarding the classification of satellite image using an effectual approach. In this approach, a deep learning dependent automated segmentation, detection, and classification of satellite images is carried with artificial intelligence methods. Initially, the input image is preprocessed, segmented using Edge-ROI and YOLO v3 based segmentation in which the parameter is tuned by means of multi-heuristic tuna swarm optimization (MH-TSO) approach and is classified using hybrid multivariate improved residual network (ResNet) and U-Net classifier approach. The stage of Edge-ROI segmentation and YOLO v3 based segmentation is employed to extract regions. The preprocessing is carried using median average filtering along with adaptive histogram equalization. A scheme of deep learning-based multivariate improved residual neural network for classification of satellite images is proposed effectively. The proposed technique performance is estimated for three kinds of dataset, namely Salinas, Pavia University, and Indian Pines satellite image datasets, and the results obtained are shown, which proves the efficiency of the suggested mechanism.
Downloads
References
X. Zhang and J. Xiang, “Moving object detection in video satellite image based on deep learning,” in Proc. SPIE LIDAR Imaging Detection and Target Recognition, Xi’an, China, vol. 10605, p. 106054H, 2017.
F. A. Mianji, Y. Gu, Y. Zhang, and J. Zhang, “Enhanced self-training superresolution mapping technique for hyperspectral imagery,” IEEE Geoscience and Remote Sensing Letters, vol. 8, no. 4, pp. 671-675, 2011.
M. J. Khan, H. S. Khan, A. Yousaf, K. Khurshid, and A. J. I. A. Abbas, “Modern trends in hyperspectral image analysis: A review,” IEEE Access, vol. 6, pp. 14118-14129, 2018.
J. Chen and A. Zipf, “Deep learning with satellite images and volunteered geographic information,” in Geospatial Data Science Techniques and Applications, J. Chen and A. Zipf, Eds. Boca Raton, FL: CRC Press, p. 63, 2017.
C. Avolio, M. Á. M. Armenta, A. J. Lucena, M. J. F. Suarez, P. V. Martin-Mateo, and F. L. González, “Automatic recognition of targets on very high resolution SAR images,” in 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 2271-2274, 2017.
R. J. Soldin, “SAR target recognition with deep learning,” in 2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA, pp. 1-8, 2018.
Y. E. García-Vera, A. Polochè-Arango, C. A. Mendivelso-Fajardo, and F. J. Gutiérrez-Bernal, “Hyperspectral image analysis and machine learning techniques for crop disease detection and identification: A review,” Sustainability, vol. 16, no. 14, p. 6064, 2024.
P. Ilamathi and S. Chidambaram, “Integration of hyperspectral imaging and deep learning for sustainable mangrove management and sustainable development goals assessment,” Wetlands, vol. 45, no. 9, 2025.
N. Dahiya, G. Singh, S. Singh, and V. Sood, “Crop land assessment with deep neural network using hyperspectral satellite dataset,” in Hyperautomation in Precision Agriculture. Cambridge, MA, USA: Academic Press, pp. 159-167,2025.
P. Sevugan, V. Rudhrakoti, T. H. Kim, M. Gunasekaran, S. Purushotham, and R. Chinthaginjala, “Class-aware feature attention-based semantic segmentation on hyperspectral images,” PLoS One, vol. 20, no. 2, p. e0309997, 2025.
R. Luo, P. Lu, P. Chen, H. Wang, X. Zhang, and S. Yang, “Hyperspectral classification of ancient cultural remains using machine learning,” Remote Sensing Applications: Society and Environment, vol. 37, p. 101457, 2025.
Q. Zhe, W. Gao, C. Zhang, G. Du, Y. Li, and D. Chen, “A hyperspectral classification method based on deep learning and dimension reduction for ground environmental monitoring,” IEEE Access, 2025.
S. Chen, H. Wang, F. Xu, and Y.-Q. Jin, “Target classification using the deep convolutional networks for SAR images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 8, pp. 4806-4817, 2016.
Z. Lin, K. Ji, M. Kang, X. Leng, and H. Zou, “Deep convolutional highway unit network for SAR target classification with limited labeled training data,” IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 7, pp. 1091-1095, 2017.
J. H. Cho and C. G. Park, “Multiple feature aggregation using convolutional neural networks for SAR image-based automatic target recognition,” IEEE Geoscience and Remote Sensing Letters, vol. 15, no. 12, pp. 1882-1886, 2018.
I. Fedorchenko, A. Oliinyk, A. Stepanenko, T. Zaiko, S. Shylo, and A. Svyrydenko, “Development of the modified methods to train a neural network to solve the task on recognition of road users,” Eastern-European Journal of Enterprise Technologies, vol. 2, no. 9, pp. 46-55, 2019.
H. He, S. Wang, D. Yang, and S. Wang, “SAR target recognition and unsupervised detection based on convolutional neural network,” in Proc. 2017 Chinese Automation Congress (CAC), pp. 435-438, 2017.
I. M. Gorovyi and D. S. Sharapov, “Comparative analysis of convolutional neural networks and support vector machines for automatic target recognition,” in Proc. 2017 IEEE Microwaves, Radar and Remote Sensing Symposium (MRRS), pp. 63-66, 2017.
Y. Kwak, W.-J. Song, and S.-E. Kim, “Speckle-noise-invariant convolutional neural network for SAR target recognition,” IEEE Geoscience and Remote Sensing Letters, vol. 16, no. 4, pp. 549-553, 2018.
B. Sehgal, H. S. Shekhawat, and S. K. Jana, “Automatic target recognition using recurrent neural networks,” in Proc. 2019 Int. Conf. on Range Technology (ICORT), Chandipur, India, pp. 1-5, 2019.
H. Shen, Y. Lin, Q. Tian, K. Xu, and J. Jiao, “A comparison of multiple classifier combinations using different voting-weights for remote sensing image classification,” International Journal of Remote Sensing, vol. 39, no. 11, pp. 3705-3722, 2018.
D. Ye, Y. Li, C. Tao, X. Xie, and X. Wang, “Multiple feature hashing learning for large-scale remote sensing image retrieval,” ISPRS International Journal of Geo-Information, vol. 6, no. 11, p. 364, 2017.
M. Häberle, M. Werner, and X. X. Zhu, “Geo-spatial text-mining from Twitter: A feature space analysis with a view toward building classification in urban regions,” European Journal of Remote Sensing, vol. 52, no. 2, pp. 2-11, 2019.
M. Al Mufti, E. Al Hadhrami, B. Taha, and N. Werghi, “SAR automatic target recognition using transfer learning approach,” in Proc. 2018 Int. Conf. on Intelligent Autonomous Systems (ICoIAS), Singapore, pp. 1-4, 2018.
M. Al Mufti, E. Al Hadhrami, B. Taha, and N. Werghi, “Using transfer learning technique for SAR automatic target recognition,” in Proc. SPIE Future Sensing Technologies, Tokyo, Japan, vol. 11197, p. 111970A, 2019.
A. Khan, A. Sohail, U. Zahoora, and A. Qureshi, “A survey of the recent architectures of deep convolutional neural networks,” Artificial Intelligence Review, vol. 53, pp. 5455-5516, 2020.
W. NanLan and Z. Xiaoyong, “Hyperspectral data classification algorithm considering spatial texture features,” Mathematical Problems in Engineering, vol. 2022, p. 901234, 2022.
X. Hu, T. Zhou, and Y. Peng, “Semisupervised deep learning using consistency regularization and pseudolabels for hyperspectral image classification,” Journal of Applied Remote Sensing, vol. 16, no. 2, p. 026513, 2022.
H. Chen, T. Wang, T. Chen, and W. Deng, “Hyperspectral image classification based on fusing S3-PCA, 2D-SSA and random patch network,” Remote Sensing, vol. 15, no. 13, p. 3402, 2023.
U. A. Bhatti, M. Huang, H. Neira-Molina, S. Marjan, M. Baryalai, and H. Tang, “MFFCG: Multi feature fusion for hyperspectral image classification using graph attention network,” Expert Systems with Applications, vol. 229, p. 120496,2023.
