深度學習技術的迅速發展使得影像辨識的能力顯著提升，尤其在物件偵測領域。其中執行自然景象的物件偵測，大型物件在圖像中多以側視圖的方式呈現並占據了圖片的主要視覺，如汽車、飛機。隨著遙測技術的成熟，現今透過衛星與無人機遙測技術可以拍出清晰的環境影像，而較特別的是遙測影像是由地理景象與物體的俯視圖組成，為物件偵測提出新的挑戰。因此本研究綜整自然景色、衛星遙測與無人機遙測的影像資料集，介紹三者之間的差異性。接著透過Web of Science進行文獻搜索，獲得近五年共4,492篇遙測物件偵測研究之文章，進行文獻宏觀了解此領域發展趨勢，並透過搜尋結果進行關鍵字萃取以建構遙測物件偵測本體論，提供研究者此領域的基本訊息。本研究提出遙測軍事物件圖像智能分類方法，用於識別遙測圖像中的各種目標物，包括飛機、無人機、船舶和車輛等。遙測物件偵測可用於防禦和進攻的國防安全應用，以識別潛在的威脅，近一步採取適當的行動。此研究數據集由多個遙測資料集收集而成，使用 6,393 張遙測影像，其中影像亦加入天氣擴增以模擬真實情境。方法第一階段採用先進的YOLOv7模型進行圖像之載具即時偵測與分類，將載具快速進行陸海空三大分類，透過實驗設計優化模型參數，達到平均精度87.3%。第二階段則細分各類的載具分為軍用、民用、其他特殊用途，共包含八個細項類別。第二階段使用多種分類模型進行比較，包含VGG、ResNet、DenseNet 和 EfficientNet。其中分類表現測試集最為優異是使用YOLOv7與 EfficientNet b7之模型精準度達到80.35%的mAP。

The development of deep learning technology has improved the ability of object detection. When performing object detection on natural scenery images, large objects often appear in a side view and dominate the main visual aspect. Nowadays, remote sensing (RS) technology can capture higher-resolution images. The RS images consist of geographical scenes and bird's-eye views of objects, which pose new challenges for computer vision tasks. Thus, this research first conducts a comprehensive overview of natural scenery, satellite-captured, and UAV-captured RS datasets and inroduces the difference between three types of datasets. Next, 4,492 RS object detection articles over the past five years are retrieved from Web of Science to conduct bibliometric analysis. Furthermore, an ontology is constructed using keyterm extraction to provide essential information in this field. This research proposes an intelligent classification of RS military object images aiming to detect objects including aircrafts, UAVs, ships, and vehicles. The proposed methodology can be utilized for defense and offense purposes to identify potential threats and further actions can be taken. The research collects 6,393 RS images, including simulated weather conditions, to replicate real-world conditions. The first stage of the approach employs the advanced YOLOv7 model for real-time detection, which primarily categorizes objects into land, sea, and air categories. YOLOv7 model parameters are optimized through the design of experiments, leading to mAP of 87.3%. In the second stage, the detected objects are further subclassified into eight specific categories. Several classification models, including VGG, ResNet, DenseNet, and EfficientNet, are compared. With the combination of YOLOv7 and EfficientNet b7 models achieve the best classification performance of mAP 80.35%.

摘要 I
Abstract II
Table of Contents III
List of Figures V
List of Tables VI
1. Introduction 1
1.1 Research background 1
1.2 Research purpose 3
1.3 Research limitations 5
1.4 Research framework 5
2. Literature review 8
2.1 Overview of public datasets 8
2.2 UAV and military vehicle image datasets 14
2.3 Object detection models 15
2.4 Hierarchical classification models 21
2.5 Bibliometric analysis of RS image object detection research 22
3. Intelligent classification of RS military object images 29
3.1 Methodology structure 29
3.2 Dataset preparation and preprocessing 31
3.3 Object localization and classification model 39
3.4 Sub-category classification models 42
4. Experiment for verification 45
4.1 Experimental evaluation metrics 45
4.2 Object localization and classification model testing 47
4.3 Intelligent classification of RS military object images testing 49
4.4 Nine experiment results 53
5. Conclusions and future research 55
References 57
Appendix 64
A.1. RS images for YOLOv7 model training (localization and main category) 64
A.2. RS images for CNN models training (sub-category classification) 68

1. Benedek, C., Descombes, X., & Zerubia, J. (2011). Building development monitoring in multitemporal remotely sensed image pairs with stochastic birth-death dynamics. IEEE transactions on pattern analysis and machine intelligence, 34(1), 33-50.
2. Bo, L., Xiaoyang, X., Xingxing, W., & Wenting, T. (2021). Ship detection and classification from optical remote sensing images: A survey. Chinese Journal of Aeronautics, 34(3), 145-163.
3. Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
4. Bouguettaya, A., Zarzour, H., Kechida, A., & Taberkit, A. M. (2021). Vehicle detection from UAV imagery with deep learning: a review. IEEE transactions on neural networks and learning systems.
5. Chen, K., Fu, K., Yan, M., Gao, X., Sun, X., & Wei, X. (2018). Semantic segmentation of aerial images with shuffling convolutional neural networks. IEEE geoscience and remote sensing letters, 15(2), 173-177.
6. Cheng, G., & Han, J. (2016). A survey on object detection in optical remote sensing images. ISPRS journal of photogrammetry and remote sensing, 117, 11-28.
7. Cheng, G., Han, J., & Lu, X. (2017). Remote sensing image scene classification: Benchmark and state of the art. Proceedings of the IEEE, 105(10), 1865-1883.
8. Cheng, G., Han, J., Zhou, P., & Guo, L. (2014). Multi-class geospatial object detection and geographic image classification based on collection of part detectors. ISPRS journal of photogrammetry and remote sensing, 98, 119-132.
9. Cheng, G., Zhou, P., & Han, J. (2016). Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 54(12), 7405-7415.
10. Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248-255.
11. Di, Y., Jiang, Z., & Zhang, H. (2021). A public dataset for fine-grained ship classification in optical remote sensing images. Remote Sensing, 13(4), 747.
12. Diakogiannis, F. I., Waldner, F., Caccetta, P., & Wu, C. (2020). ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS journal of photogrammetry and remote sensing, 162, 94-114.
13. Ding, J., Xue, N., Xia, G.-S., Bai, X., Yang, W., Yang, M. Y., Belongie, S., Luo, J., Datcu, M., & Pelillo, M. (2021). Object detection in aerial images: A large-scale benchmark and challenges. IEEE transactions on pattern analysis and machine intelligence, 44(11), 7778-7796.
14. Dong, R., Jiao, L., Zhang, Y., Zhao, J., & Shen, W. (2021). A multi-scale spatial attention region proposal network for high-resolution optical remote sensing imagery. Remote Sensing, 13(17), 3362.
15. Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., & Tian, Q. (2018). The unmanned aerial vehicle benchmark: Object detection and tracking. Proceedings of the European conference on computer vision (ECCV),
16. Erdoğan, İ. C. (2020). War Tank Images Dataset. https://www.kaggle.com/datasets/icanerdogan/war-tank-images-dataset
17. Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2), 303-338.
18. Everingham, M. a. V. G., L. and Williams, C. K. I. and Winn, J. and Zisserman, A. (2012). The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results.
19. Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, 1440-1448.
20. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition,
21. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., & Cai, J. (2018). Recent advances in convolutional neural networks. Pattern recognition, 77, 354-377.
22. Gupta, P. P., Bhavya; Singal, Gaurav; Rao, D Vijay. (2021). Military and Civilian Vehicles Classification. https://doi.org/10.17632/njdjkbxdpn.1
23. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2961-2969.
24. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 37(9), 1904-1916.
25. Hossain, M., Hossain, M. A., & Sunny, F. A. (2019, December). A UAV-based traffic monitoring system for smart cities. In 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), 1-6.
26. Hou, L., Xue, J., Lu, K., Hao, L., & Rahman, M. M. (2019, December). A single-stage multi-class object detection method for remote sensing images. In 2019 IEEE Visual Communications and Image Processing (VCIP), 1-4.
27. Hsieh, M. R., Lin, Y. L., & Hsu, W. H. (2017). Drone-based object counting by spatially regularized regional proposal network. In Proceedings of the IEEE international conference on computer vision, 4145-4153.
28. Jaderberg, M., Simonyan, K., & Zisserman, A. (2015). Spatial transformer networks. Advances in neural information processing systems, 28.
29. Jana, A. (2021). Military Tanks Dataset. https://www.kaggle.com/datasets/antoreepjana/military-tanks-dataset-images
30. Jiao, L., Sun, W., Yang, G., Ren, G., & Liu, Y. (2019). A hierarchical classification framework of satellite multispectral/hyperspectral images for mapping coastal wetlands. Remote Sensing, 11(19), 2238.
31. Ju, M., Luo, J., Zhang, P., He, M., & Luo, H. (2019). A simple and efficient network for small target detection. IEEE Access, 7, 85771-85781.
32. Jung, A. B. (2020). imgaug. Retrieved Mar 9, 2023 from https://github.com/aleju/imgaug
33. Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4401-4410.
34. Lechner, A. M., Foody, G. M., & Boyd, D. S. (2020). Applications in remote sensing to forest ecology and management. One Earth, 2(5), 405-412.
35. Lee, D., La, W. G., & Kim, H. (2018, October). Drone detection and identification system using artificial intelligence. In 2018 International Conference on Information and Communication Technology Convergence (ICTC), 1131-1133.
36. Li, K., Cheng, G., Bu, S., & You, X. (2017). Rotation-insensitive and context-augmented object detection in remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 56(4), 2337-2348.
37. Li, Y., Fu, K., Sun, H., & Sun, X. (2018). An aircraft detection framework based on reinforcement learning and convolutional neural networks in remote sensing images. Remote Sensing, 10(2), 243.
38. Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2117-2125.
39. Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, 2980-2988.
40. Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 740-755. Springer International Publishing.
41. Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 8759-8768.
42. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 21-37. Springer International Publishing.
43. Liu, Y., Fan, B., Wang, L., Bai, J., Xiang, S., & Pan, C. (2018). Semantic labeling in very high resolution images via a self-cascaded convolutional neural network. ISPRS journal of photogrammetry and remote sensing, 145, 78-95.
44. Liu, Z., Wang, H., Weng, L., & Yang, Y. (2016). Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds. IEEE geoscience and remote sensing letters, 13(8), 1074-1078.
45. Lu, X., Ji, J., Xing, Z., & Miao, Q. (2021). Attention and feature fusion SSD for remote sensing object detection. IEEE Transactions on Instrumentation and Measurement, 70, 1-9.
46. Ma, A., Wan, Y., Zhong, Y., Wang, J., & Zhang, L. (2021). SceneNet: Remote sensing scene classification deep learning network using multi-objective neural evolution architecture search. ISPRS journal of photogrammetry and remote sensing, 172, 171-188.
47. Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019). Deep learning in remote sensing applications: A meta-analysis and review. ISPRS journal of photogrammetry and remote sensing, 152, 166-177.
48. Özel, M. (2022). Drone-dataset. Retrieved Nov 1, 2022 from https://github.com/dasmehdix/drone-dataset
49. Özyurt, F. (2020). Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures. The Journal of Supercomputing, 76(11), 8413-8431.
50. Parag, T., & Wang, H. (2020). Multilayer Dense Connections for Hierarchical Concept Classification. arXiv preprint arXiv:2003.09015.
51. Patel, K., Bhatt, C., & Mazzeo, P. L. (2022). Improved Ship Detection Algorithm from Satellite Images Using YOLOv7 and Graph Neural Network. Algorithms, 15(12), 473.
52. Razakarivony, S., & Jurie, F. (2016). Vehicle detection in aerial imagery: A small target detection benchmark. Journal of Visual Communication and Image Representation, 34, 187-203.
53. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 779-788.
54. Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271).
55. Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
56. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.
57. Rozantsev, A., Lepetit, V., & Fua, P. (2016). Detecting flying objects using a single moving camera. IEEE transactions on pattern analysis and machine intelligence, 39(5), 879-892.
58. Shanmugapriya, P., Rathika, S., Ramesh, T., & Janaki, P. (2019). Applications of remote sensing in agriculture-A Review. International Journal of Current Microbiology and Applied Sciences, 8(1), 2270-2283.
59. Shao, Z., Sumari, N. S., Portnov, A., Ujoh, F., Musakwa, W., & Mandela, P. J. (2021). Urban sprawl and its impact on sustainable urban development: a combination of remote sensing and social media data. Geo-spatial Information Science, 24(2), 241-255.
60. Shermeyer, J., Hossler, T., Van Etten, A., Hogan, D., Lewis, R., & Kim, D. (2021). Rareplanes: Synthetic data takes flight. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 207-217.
61. Shin, S.-J., Kim, S., Kim, Y., & Kim, S. (2020). Hierarchical multi-label object detection framework for remote sensing images. Remote Sensing, 12(17), 2734.
62. Singha, S., & Aydin, B. (2021). Automated Drone Detection Using YOLOv4. Drones, 5(3), 95.
63. Sishodia, R. P., Ray, R. L., & Singh, S. K. (2020). Applications of remote sensing in precision agriculture: A review. Remote Sensing, 12(19), 3136.
64. Uijlings, J. R., Van De Sande, K. E., Gevers, T., & Smeulders, A. W. (2013). Selective search for object recognition. International journal of computer vision, 104(2), 154-171.
65. Union of Concerned Scientists. (2022). UCS Satellite Database. Retrieved Oct 27, from https://www.ucsusa.org/resources/satellite-database
66. United States Geological Survey. (2022). What Is Remote Sensing and What Is It Used For? Retrieved Oct 27, 2022, from https://www.usgs.gov/faqs/what-remote-sensing-and-what-it-used
67. Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696.
68. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., ... & Tang, X. (2017). Residual attention network for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3156-3164.
69. Wu, W., Liu, H., Li, L., Long, Y., Wang, X., Wang, Z., Li, J., & Chang, Y. (2021). Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image. PloS one, 16(10), e0259283.
70. Wu, Z.-Z., Wan, S.-H., Wang, X.-F., Tan, M., Zou, L., Li, X.-L., & Chen, Y. (2020). A benchmark data set for aircraft type recognition from remote sensing images. Applied Soft Computing, 89, 106132.
71. Yang, X., Sun, H., Fu, K., Yang, J., Sun, X., Yan, M., & Guo, Z. (2018). Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sensing, 10(1), 132.
72. Yang, Y., & Newsam, S. (2010, November). Bag-of-visual-words and spatial extensions for land-use classification. In Proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems, 270-279.
73. Yu, Y., Si, X., Hu, C., & Zhang, J. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 31(7), 1235-1270.
74. Zhang, C., Liu, J., Yu, F., Wan, S., Han, Y., Wang, J., & Wang, G. (2018). Segmentation model based on convolutional neural networks for extracting vegetation from Gaofen-2 images. Journal of Applied Remote Sensing, 12(4), 042804-042804.
75. Zhang, T., Wang, G., Zhuang, Y., Chen, H., Shi, H., & Chen, L. (2020, September). Feature Enhanced Centernet for Object Detection in Remote Sensing Images. In IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, 1639-1642.
76. Zhao, Z.-Q., Zheng, P., Xu, S.-t., & Wu, X. (2019). Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems, 30(11), 3212-3232.
77. Zhu, P., Wen, L., Bian, X., Ling, H., & Hu, Q. (2018). Vision meets drones: A challenge. arXiv preprint arXiv:1804.07437.
78. Zhu, X., & Bain, M. (2017). B-CNN: branch convolutional neural network for hierarchical classification. arXiv preprint arXiv:1709.09890.