請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95216完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 韓仁毓 | zh_TW |
| dc.contributor.advisor | Jen-Yu Han | en |
| dc.contributor.author | 林育銓 | zh_TW |
| dc.contributor.author | Yu-Chuan Lin | en |
| dc.date.accessioned | 2024-09-03T16:09:42Z | - |
| dc.date.available | 2024-09-04 | - |
| dc.date.copyright | 2024-09-03 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-14 | - |
| dc.identifier.citation | Akar, Ö. (2018). The rotation forest algorithm and object-based classification method for land use mapping through uav images. Geocarto international, 33(5):538–553.
AlpacaTechJP (2017, july 16). selective search python implementation. https://github.com/alpacatechjp/selectivesearch. Chen, P.-C., Chiang, Y.-C., and Weng, P.-Y. (2020). Imaging using unmanned aerial vehicles for agriculture land use classification. Agriculture, 10(9):416. Cheng, G., Yuan, X., Yao, X., Yan, K., Zeng, Q., Xie, X., and Han, J. (2023). Towards large-scale small object detection: Survey and benchmarks. IEEE Transactions on Pattern Analysis and Machine Intelligence. Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., and Zhang, L. (2021). Dynamic head: Unifying object detection heads with attentions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7373–7382. Delavarpour, N., Koparan, C., Nowatzki, J., Bajwa, S., and Sun, X. (2021). A technical study on uav characteristics for precision agriculture applications and associated practical challenges. Remote Sensing, 13(6):1204. Deng, S., Li, S., Xie, K., Song, W., Liao, X., Hao, A., and Qin, H. (2020). A global-local self-adaptive network for drone-view object detection. IEEE Transactions on Image Processing, 30:1556–1569. Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y., et al. (2019). Visdrone-det2019: The vision meets drone object detection in image challenge results. In Proceedings of the IEEE/CVF international conference on computer vision workshops, pages 0–0. Felzenszwalb, P. F. and Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International journal of computer vision, 59:167–181. Gao, Y., Liu, Y., Zhang, H., Li, Z., Zhu, Y., Lin, H., and Yang, M. (2020). Estimating gpu memory consumption of deep learning models. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pages 1342–1352. Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018). Recent advances in convolutional neural networks. Pattern recognition, 77:354–377. Iizuka, K., Itoh, M., Shiodera, S., Matsubara, T., Dohar, M., and Watanabe, K. (2018). Advantages of unmanned aerial vehicle (uav) photogrammetry for landscape analysis compared with satellite data: A case study of postmining sites in indonesia. Cogent Geoscience, 4(1):1498180. Kandel, I. and Castelli, M. (2020). The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT express, 6(4):312–315. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25. Lattanzi, D. and Miller, G. (2017). Review of robotic infrastructure inspection systems. Journal of Infrastructure Systems, 23(3):04017004. Li, C., Yang, T., Zhu, S., Chen, C., and Guan, S. (2020). Density map guided object detection in aerial images. In proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 190–191. Li, Z., Liu, F., Yang, W., Peng, S., and Zhou, J. (2021a). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems, 33(12):6999–7019. Li, Z., Liu, X., Zhao, Y., Liu, B., Huang, Z., and Hong, R. (2021b). A lightweight multiscale aggregated model for detecting aerial images captured by uavs. Journal of Visual Communication and Image Representation, 77:103058. Lin, R. (2022). Analysis on the selection of the appropriate batch size in cnn neural network. In 2022 International Conference on Machine Learning and Knowledge Engineering (MLKE), pages 106–109. IEEE. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and 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, pages 740–755. Springer. Liu, M., Wang, X., Zhou, A., Fu, X., Ma, Y., and Piao, C. (2020). Uav-yolo: Small object detection on unmanned aerial vehicle perspective. Sensors, 20(8):2238. Micheal, A. A., Vani, K., Sanjeevi, S., and Lin, C.-H. (2021). Object detection and tracking with uav data using deep learning. Journal of the Indian Society of Remote Sensing, 49:463–469. Osco, L. P., de Arruda, M. d. S., Gonçalves, D. N., Dias, A., Batistoti, J., de Souza, M., Gomes, F. D. G., Ramos, A. P. M., de Castro Jorge, L. A., Liesenberg, V., et al. (2021). A cnn approach to simultaneously count plants and detect plantation-rows from uav imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 174:1–17. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28. Silvagni, M., Tonoli, A., Zenerino, E., and Chiaberge, M. (2017). Multipurpose uav for search and rescue operations in mountain avalanche events. Geomatics, Natural Hazards and Risk, 8(1):18–33. Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Tijtgat, N., Van Ranst, W., Goedeme, T., Volckaert, B., and De Turck, F. (2017). Embedded real-time object detection for a uav warning system. In Proceedings of the IEEE international conference on computer vision workshops, pages 2110–2118. Uijlings, J. R., Van De Sande, K. E., Gevers, T., and Smeulders, A. W. (2013). Selective search for object recognition. International journal of computer vision, 104:154–171. Ultralytics (2023, july). Yo5lov8 Documentation. https://github.com/ultralytics/ultralytics/tree/main?tab=readme-ov-file. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y. M. (2023). Yolov7: Trainable bag-offreebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7464–7475. Xu, Y., Yu, G., Wang, Y., Wu, X., and Ma, Y. (2017). Car detection from low-altitude uav imagery with the faster r-cnn. Journal of Advanced Transportation, 2017(1):2823617. Yamashita, R., Nishio, M., Do, R. K. G., and Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9:611–629. Yang, F., Fan, H., Chu, P., Blasch, E., and Ling, H. (2019). Clustered object detection in aerial images. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8311–8320. Yu, X., Gong, Y., Jiang, N., Ye, Q., and Han, Z. (2020). Scale match for tiny person detection. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 1257–1265. Zhai, X., Huang, Z., Li, T., Liu, H., and Wang, S. (2023). Yolo-drone: an optimized yolov8 network for tiny uav object detection. Electronics, 12(17):3664. 周巧盈, 巫思揚, and 陳琦玲(2020). 無人飛行載具之航拍影像應用於水稻倒伏災損 判釋. 台灣農業研究, 69(1):25–45. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95216 | - |
| dc.description.abstract | 無人機作為遙測的新興工具，若能結合深度學習進行自動化物件偵測，將能使人們對於無人機的應用範疇有更深的拓展與運用。然而無人機影像與普遍影像不同，其具備高解析度與目標物相對尺寸較小的特性，在應用卷積神經網路技術時，會面臨到高解析度導致的GPU記憶體容量不足的限制。過往研究在解決這項限制時多以降低影像解析度的方式來減少GPU記憶體的需求，但這樣的做法會使目標物的特徵變模糊且稀缺，導致小物件偵測的困境。本研究提出一依照Focus-and-Detect概念的優化辦法，先對影像進行子區域提出，後再針對子區域進行偵測。在沒有降低解析度的情況下減少模型輸入影像的尺寸，減少GPU記憶體需求的同時維持無人機具備的高解析度，進而在相對尺度較小的目標物也能有足夠清晰的特徵，避免了小物件偵測的困境。在子區域提出的部分，本研究發展一子區域提出演算法Modified Selective Search。演算法所提出的候選區域能具備理想子區域的特性，大小適當且包含多個目標物。本研究透過子區域提出方法所訓練的yolov8模型，在VisDrone無人機影像資料集中的高解析度影像上，達到比透過降低影像解析度方式所訓練的yolov8模型更好的表現結果。在測試資料的評估上增加了12%的mAP表現，並且在特徵相似的物件中有更好的區分效果。然子區域提出的方法會需要更多的訓練時間與儲存空間來儲存子區域影像，總結來說是一以時間換取表現以及資源的方法。 | zh_TW |
| dc.description.abstract | Drones, as an emerging tool in remote sensing, already possess extensive application potential in the field of civil engineering. The integration of deep learning for automated object detection could further expand the applications of drones and enhance their utility. However, drone imagery differs from conventional computer vision images, characterized by high resolution and relatively small object sizes. When applying convolution neural networks, this leads to constraints due to GPU memory limitations caused by high resolutions. Previous studies often addressed this limitation by reducing image resolution, which blurs and sparsifies the features of small objects, thus complicating small object detection. This study proposes an optimization approach based on the Focus-and-Detect concept, which involves segmenting the image into sub-regions before processing object detection. This method reduces the need for GPU memory without sacrificing image resolution. Furthermore, the high-resolution capability of drones ensures that even relatively small objects possess sufficient feature content, making the sub-region proposal method particularly suited to drone imagery. In this study, we modify the Selective Search algorithm to propose an optimized sub-region proposal method, Modified Selective Search. The proposed candidate regions by this algorithm have the ideal characteristics of sub-regions, being appropriately sized and containing multiple objects. The yolov8 model trained using this sub-region proposal method achieved superior performance on the high-resolution VisDrone drone imagery dataset compared to models trained with reduced-resolution images, improving the mAP by 12% in test data evaluations and exhibiting enhanced differentiation among vehicles, trucks, and vans, which have similar features. While the sub-region proposal method requires additional training time and storage space, it essentially trades time for improved performance and lower GPU memory requirement. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-03T16:09:42Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-03T16:09:42Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
誌謝 ii 中文摘要 iii Abstract iv 目次 v 圖次 vi 表次 vii 第一章緒論 1 1.1 研究背景. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 研究動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3 研究目的. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 第二章研究方法設計11 2.1 子區域提出的方法. . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.1.1 Selective Search 的介紹. . . . . . . . . . . . . . . . . . . . . . . 12 2.1.2 針對研究目標所調整的修改版Selective Search . . . . . . . . . . 14 2.2 子區域的篩選方法. . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.2.1 篩選掉尺寸過小的候選區域. . . . . . . . . . . . . . . . . . . . 17 2.2.2 篩選掉第一階段產生就已超過希望尺寸的候選區域. . . . . . . 18 2.2.3 篩選掉高重複的候選區域. . . . . . . . . . . . . . . . . . . . . . 19 2.3 子區域提出方法的評估指標. . . . . . . . . . . . . . . . . . . . . . 20 2.3.1 平均地真資料的涵蓋率. . . . . . . . . . . . . . . . . . . . . . . 20 2.3.2 量化子區域的理想程度. . . . . . . . . . . . . . . . . . . . . . . 21 第三章實驗結果與討論 23 3.1 VisDrone 資料集中的高解析度影像. . . . . . . . . . . . . . . . . . 23 3.2 訓練階段的專注偵測. . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.2.1 子區域對應的標註資料. . . . . . . . . . . . . . . . . . . . . . . 25 3.2.2 修改版Selective Search 的參數設定. . . . . . . . . . . . . . . . 25 3.2.3 修改版Selective Search 的子區域提出結果. . . . . . . . . . . . 29 3.3 評估階段的專注偵測. . . . . . . . . . . . . . . . . . . . . . . . . . 31 3.4 物件偵測模型的訓練與測試資料的評估結果. . . . . . . . . . . . . 32 3.4.1 四種實驗使用的資料集. . . . . . . . . . . . . . . . . . . . . . . 32 3.4.2 四種實驗訓練所需時間與GPU 記憶體使用量. . . . . . . . . . 34 3.4.3 四種實驗在測試資料的評估結果. . . . . . . . . . . . . . . . . . 35 第四章結論與未來展望 41 4.1 成果討論. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 4.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 4.2.1 研究方法的改進. . . . . . . . . . . . . . . . . . . . . . . . . . . 42 4.2.2 研究方法的延伸應用. . . . . . . . . . . . . . . . . . . . . . . . 43 參考文獻 45 | - |
| dc.language.iso | zh_TW | - |
| dc.title | 卷積網路應用於高畫質無人機影像中小物件偵測的優化辦法 | zh_TW |
| dc.title | An Advanced Technique for Enhancing the Performance of Convolutional Neural Networks in Small Object Detection with High Resolution UAV Image | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 吳日騰;甯方璽;莊子毅 | zh_TW |
| dc.contributor.oralexamcommittee | Rih-Teng Wu;Fang-Shii Ning;Tzu-Yi Chuang | en |
| dc.subject.keyword | 無人機影像,深度學習,卷積神經網路,小物件偵測,區域提出, | zh_TW |
| dc.subject.keyword | UAV imagery,deep learning,CNN,small object detection,regional proposal, | en |
| dc.relation.page | 49 | - |
| dc.identifier.doi | 10.6342/NTU202404011 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-08-14 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 此日期後於網路公開 2025-08-09 | 32.84 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。