Small Object Detection in Remote Sensing Imagery Using Optimized Faster R-CNN
Keywords:
Small Object Detection;Remote Sensing Images; Fully Convolutional Networks (FCN); Dingo Optimization and Tunicate Swarm (DOTSA); Optimized Faster R-CNN.Abstract
Small object detection in remote sensing images is the procedure of recognising and integrating small, particular objects within an image taken by a remote sensing device, including satellite or aerial drone.An innovative hybrid deep learning based small object detectionmodel is introduced in this research work. The proposed model is divided into five main phases: (a) Pre-Processing (b) Segmentation (c) Feature Extraction (d) Feature Fusion (e) deep learning based small object detection. Initially, the collected raw image is pre-processed via gaussian filtering (for noise removal) and adaptive histogram equalization approach (for contrast enhancement). From the pre-processed image,the Region of Intertest (ROI) is identified viathe Fully Convolutional Networks (FCN). Then, from the identified ROI areas, the features like scale invariant feature transform, local binary patterns and Haar like features are extracted. The extracted features are fused using the score level fusion. From the fused features, the optimal features are selected using the new Dingo Optimization and Tunicate Swarm (DOTSA) algorithm, which is the conceptual amalgamation of the standard Tunicate Swarm optimizer (TSA) and standard Dingo Optimizer (DO), respectively. The small object detection is accomplished via the new optimized faster R-CNN, whose weight functions are optimized via the new Dingo Optimization and Tunicate Swarm (DOTSA) algorithm. The proposed model is implemented using the MATLAB platform.The findings are evaluated in terms of accuracy, sensitivity, precision, FPR, FNR, etc. using the present models. The proposed model has recorded the highest detection accuracyas 98%.
Downloads
References
Wang, P., Sun, X., Diao, W. and Fu, K., 2019. FMSSD: Feature-merged single-shot detection for multi scale objects in large-scale remote sensing imagery. IEEE Transactions on Geo science and Remote Sensing, 58(5), pp.3377-3390.
Lu, H., Li, H., Chen, L., Cheng, Y., Zhu, D., Li, Y., Lv, R., Chen, G., Su, X., Lang, L. and Li, Q., 2021. A ship detection and tracking algorithm for an airborne passive interferometric microwave sensor (PIMS). IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, pp.3519-3532.
Sun, J., Zhang, Y., Wu, Z., Zhu, Y., Yin, X., Ding, Z., Wei, Z., Plaza, J. and Plaza, A., 2019. An efficient and scalable framework for processing remotely sensed big data in cloud computing environments. IEEE Transactions on Geoscience and Remote Sensing, 57(7), pp.4294-4308.
Sun, X., Wang, B., Wang, Z., Li, H., Li, H. and Fu, K., 2021. Research progress on few-shot learning for remote sensing image interpretation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, pp.2387-2402.
Du, W., Addepalli, S. and Zhao, Y., 2019. The spatial resolution enhancement for a thermogram enabled by controlled subpixel movements. IEEE Transactions on Instrumentation and Measurement,69(6), pp.3566-3575.
Huang, Z., Yang, S., Zhou, M., Li, Z., Gong, Z. and Chen, Y., 2022. Feature map distillation of thin nets for low-resolution object recognition. IEEE Transactions on Image Processing, 31, pp.1364-1379.
Lei, J., Luo, X., Fang, L., Wang, M. and Gu, Y., 2020. Region-enhanced convolutional neural network for object detection in remote sensing images. IEEE Transactions on Geo science and Remote Sensing, 58(8), pp.5693-5702.
Chen, J., Wan, L., Zhu, J., Xu, G. and Deng, M., 2019. Multi-scale spatial and channel-wise attention for improving object detection in remote sensing imagery. IEEE Geo science and Remote Sensing Letters, 17(4), pp.681-685.
Pang, J., Li, C., Shi, J., Xu, Z. and Feng, H., 2019. $mathcal {R}^ 2$-CNN: fast Tiny object detection in large-scale remote sensing images. IEEE Transactions on Geo science and Remote Sensing, 57(8), pp.5512-5524.
Dong, Z., Wang, M., Wang, Y., Zhu, Y. and Zhang, Z., 2019. Object detection in high resolution remote sensing imagery based on convolutional neural networks with suitable object scale features. IEEE Transactions on Geo science and Remote Sensing, 58(3), pp.2104-2114.
Lu, X., Ji, J., Xing, Z. and Miao, Q., 2021. Attention and feature fusion SSD for remote sensing object detection. IEEE Transactions on Instrumentation and Measurement, 70, pp.1-9.
Dataset1 and Dataset2 collected from: “https://github.com/chaozhong2010/VHR-10_dataset_coco”, 2023-01-20.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
