請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96160完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張恆華 | zh_TW |
| dc.contributor.advisor | Herng-Hua Chang | en |
| dc.contributor.author | 王盈玄 | zh_TW |
| dc.contributor.author | Ying-Hsuan Wang | en |
| dc.date.accessioned | 2024-11-18T16:07:22Z | - |
| dc.date.available | 2024-11-19 | - |
| dc.date.copyright | 2024-11-18 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-10-12 | - |
| dc.identifier.citation | [1] Z. Liu, Y. Zhang, X. Yu, and C. Yuan, “Unmanned Surface Vehicles: An Overview of Developments and Challenges,” Annual Reviews in Control, vol. 41, pp. 71–93, 2016.
[2] S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz, and D. Terzopoulos, “Image Segmentation Using Deep Learning: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, pp. 3523–3542, 2022. [3] T. Belabed, M. G. F. Coutinho, M. A. C. Fernandes, C. V. Sakuyama, and C. Souani, “User Driven FPGA-Based Design Automated Framework of Deep Neural Networks for Low-Power Low-Cost Edge Computing,” IEEE Access, vol. 9, pp. 89162–89180, 2021. [4] A. Kirillov, K. He, R. Girshick, C. Rother, and P. Dollár, “Panoptic Segmentation,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9396–9405, 2019. [5] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. [6] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems (F. Pereira, C. Burges, L. Bottou, and K. Weinberger, eds.), vol. 25, Curran Associates, Inc., 2012. [7] B. Xu, N. Wang, T. Chen, and M. Li, “Empirical Evaluation of Rectified Activations in Convolutional Network,” arXiv preprint arXiv:1505.00853, 2015. [8] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning Representations by Back-Propagating Errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986. [9] J. Long, E. Shelhamer, and T. Darrell, “Fully Convolutional Networks for Semantic Segmentation,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440, 2015. [10] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for LargeScale Image Recognition,” 2015. [11] H. Noh, S. Hong, and B. Han, “Learning Deconvolution Network for Semantic Segmentation,” in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1520–1528, 2015. [12] V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481–2495, 2017. [13] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Medical Image Computing and ComputerAssisted Intervention – MICCAI 2015 (N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, eds.), (Cham), pp. 234–241, Springer International Publishing, 2015. [14] L. Yao, D. Kanoulas, Z. Ji, and Y. Liu, “ShorelineNet: An Efficient Deep Learning Approach for Shoreline Semantic Segmentation for Unmanned Surface Vehicles,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5403–5409, 2021. [15] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, 2018. [16] B. Bovcon and M. Kristan, “WaSR—A Water Segmentation and Refinement Maritime Obstacle Detection Network,” IEEE Transactions on Cybernetics, vol. 52, no. 12, pp. 12661–12674, 2022. [17] M. Teršek, L. Žust, and M. Kristan, “eWaSR – an Embedded-Compute-Ready Maritime Obstacle Detection Network,” 2023. [18] Advanced Micro Devices, Inc., “Zynq UltraScale+ MPSoC Data Sheet: Overview (DS891) v1.10.” Online PDF, 2022. [Online]. Available: https://docs.amd.com/v/u/en-US/ds891-zynq-ultrascale-plus-overview. [19] Advanced Micro Devices, Inc., “Vivado 2022.1.” [20] P. Plagwitz, F. Hannig, M. Ströbel, C. Strohmeyer, and J. Teich, “A Safari through FPGA-based Neural Network Compilation and Design Automation Flows,” in 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 10–19, 2021. [21] F. Hamanaka, T. Odan, K. Kise, and T. V. Chu, “An Exploration of State-of-theArt Automation Frameworks for FPGA-Based DNN Acceleration,” IEEE Access, vol. 11, pp. 5701–5713, 2023. [22] FastML Team, “fastmachinelearning/ hls4ml,” 2023. https://github.com/fastmachinelearning/hls4ml. [23] T. Aarrestad et al., “Fast convolutional neural networks on FPGAs with hls4ml,” Mach. Learn. Sci. Tech., vol. 2, no. 4, p. 045015, 2021. [24] FastML Team, “hls4ml 0.8.1 documentation.” https://fastmachinelearning.org/hls4ml/. [25] Y. Umuroglu, N. J. Fraser, G. Gambardella, M. Blott, P. Leong, M. Jahre, and K. Vissers, “FINN: A Framework for Fast, Scalable Binarized Neural Network Inference,” in Proceedings of the 2017 ACM/SIGDA International Symposium on FieldProgrammable Gate Arrays, FPGA ’17, pp. 65–74, ACM, 2017. [26] M. Blott, T. B. Preußer, N. J. Fraser, G. Gambardella, K. O＇brien, Y. Umuroglu, M. Leeser, and K. Vissers, “FINN-R: An end-to-end deep-learning framework for fast exploration of quantized neural networks,” ACM Transactions on Reconfigurable Technology and Systems (TRETS), vol. 11, no. 3, pp. 1–23, 2018. [27] Advanced Micro Devices, Inc., “Vitis AI User Guide (UG1414) v2.5.” Online PDF, 2022. [Online]. Available: https://docs.amd.com/r/2.5-English/ug1414-vitis-ai/Vitis-AI-Overview. [28] A. Pappalardo, “Xilinx/brevitas,” 2023. [29] Advanced Micro Devices, Inc., “Zynq DPU Product Guide (PG338) v3.3.” Online PDF, 2021. [Online]. Available: https://docs.amd.com/r/3.3-English/pg338-dpu. [30] F. Jentzsch, Y. Umuroglu, A. Pappalardo, M. Blott, and M. Platzner, “RadioML Meets FINN: Enabling Future RF Applications With FPGA Streaming Architectures,” IEEE Micro, vol. 42, no. 6, pp. 125–133, 2022. [31] J. Wang and S. Gu, “FPGA Implementation of Object Detection Accelerator Based on Vitis-AI,” in 2021 11th International Conference on Information Science and Technology (ICIST), pp. 571–577, 2021. [32] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 2018. [33] R. A. Amin, M. Hasan, V. Wiese, and R. Obermaisser, “FPGA-Based Real-Time Object Detection and Classification System Using YOLO for Edge Computing,” IEEE Access, vol. 12, pp. 73268–73278, 2024. [34] J. C. Njuguna, A. T. Çelebi, and A. Çelebi, “Implementation and Optimization of LeNet-5 Model for Handwritten Digits Recognition on FPGAs using Brevitas and FINN,” in 2023 Innovations in Intelligent Systems and Applications Conference (ASYU), pp. 1–5, 2023. [35] K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016. [36] B. Bovcon, J. Muhovič, J. Perš, and M. Kristan, “The MaSTr1325 Dataset for Training Deep USV Obstacle Detection Models,” in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3431–3438, 2019. [37] Advanced Micro Devices, Inc., “Kria KV260 Vision AI Starter Kit..” https://www.amd.com/zh-tw/products/system-on-modules/kria/k26/kv260-vision-starter-kit.html. [Accessed 15-08-2024]. [38] Advanced Micro Devices, Inc., “Kria KV260 Vision AI Starter Kit Data Sheet (DS986) v1.2.” Online PDF, 2024. [Online]. Available: https://docs.amd.com/r/en-US/ds986-kv260-starter-kit. [39] Advanced Micro Devices, Inc., “Kria K26 SOM Data Sheet (DS987) v1.5.” Online PDF, 2024. [Online]. Available: https://docs.amd.com/r/en-US/ds987-k26-som. [40] I. Hubara, Y. Nahshan, Y. Hanani, R. Banner, and D. Soudry, “Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming,” 2020. [41] Advanced Micro Devices, Inc., “Vitis High-Level Synthesis User Guide (UG1399) v2022.1.” Online PDF, 2021. [Online]. Available: https://docs.amd.com/r/en-US/ug1399-vitis-hls. [42] Advanced Micro Devices, Inc., “Vitis Vision Library.” https://xilinx.github.io/Vitis_Libraries/vision/2022.1/index.html. [43] Advanced Micro Devices, Inc., “https://www.pynq.io/.” https://www.pynq.io/. [44] B. Bovcon, J. Muhovič, D. Vranac, D. Mozetič, J. Perš, and M. Kristan, “MODS—A USV-Oriented Object Detection and Obstacle Segmentation Benchmark,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 13403–13418, 2022. [45] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” 2017. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96160 | - |
| dc.description.abstract | 於無人水面載具技術發展中，自動導航扮演了重要的角色。為了利用電腦視覺技術實現無人水面載具的自動導航，視覺系統必須具有分辨障礙物的能力。影像分割是種將像素點進行分類的影像處理技巧，於無人水面載具應用中，可透過影像分割將輸入影像分割為水體、天空、障礙物，藉以供導航使用。在無人水面載具的應用場景，視覺系統必須符合即時性、精準性、低功耗、低成本的需求。本研究利用FPGA作為硬體平台，開發適用於無人水面載具的即時影像分割系統。利用包含1325張真實水域影像的MasTr1325資料集，訓練了用於水域影像分割的卷積神經網路，並利用Vitis-AI架構佈署至FPGA，實現神經網路的硬體加速。而為了改善系統效能，我們透過可程式化邏輯對影像前處理運算進行硬體加速，並使用多執行緒設計應用程式。實驗結果顯示，本研究提出之系統吞吐量可達25 FPS，而在包含8175張影像之MODS測試資料集上，達到超過85%的F1分數，可以滿足無人水面載具導航之需求。 | zh_TW |
| dc.description.abstract | In the development of unmanned surface vehicle (USV) technology, autonomous navigation plays a critical role. To achieve autonomous navigation using computer vision technology, the visual system of the vehicle must be capable of distinguishing obstacles. Image segmentation is an image processing technique that classifies pixels into meaningful regions. In the application of autonomous ship, the input image can be segmented input into water, sky, and obstacle for navigation. During USV navigation, the visual system must meet the requirements of real-time performance, precision, low power consumption, and low cost. This thesis used field programmable gate array (FPGA) as the hardware platform to develop a real-time image segmentation system suitable for USV application. We trained a convolutional neural network (CNN) with the MasTr1325 dataset for maritime image segmentation and deployed it to FPGA using the Vitis-AI framework to achieve hardware acceleration. To further improve system performance, we accelerated the image preprocessing step through programmable logic and used multithreading in the application design. Experimental results showed that the proposed system achieved a throughput of 25 FPS, and the segmentation results reached an F1 score over 85% on MODS dataset containing 8175 images, meeting the requirements of USV navigation. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-11-18T16:07:22Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-11-18T16:07:22Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii 英文摘要 iii 目次 v 圖次 ix 表次 xi 縮寫列表 xii 第一章 緒論 1 1.1 研究背景 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 研究動機 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.3 研究目的 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.4 研究貢獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.5 論文架構 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 第二章 背景介紹及文獻回顧 4 2.1 類神經網路應用於水域影像分割 . . . . . . . . . . . . . . . . . . . . 4 2.1.1 影像分割 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.1.2 神經網路簡介 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.2.1 基本概念、神經元、激勵函數 . . . . . . . . . . . . 5 2.1.2.2 卷積神經網路 . . . . . . . . . . . . . . . . . . . . . . 6 2.1.3 影像分割模型架構 . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.3.1 全卷積網路 . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.3.2 編碼器-解碼器架構 . . . . . . . . . . . . . . . . . . . 8 2.1.4 水域影像分割文獻回顧 . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 部署神經網路至 FPGA . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.1 FPGA 簡介 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.2 架構分類 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2.3 常見架構介紹 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.2.4 文獻回顧 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 第三章 影像分割模型架構 18 3.1 模型架構 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.2 模型訓練 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.2.1 訓練資料集 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.2.2 資料擴增 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 第四章 FPGA 系統設計 23 4.1 硬體平台 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.2 開發流程概述 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.3 Vitis-AI 開發流程 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.1 架構選擇 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.2 開發流程 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3.2.1 模型檢查 . . . . . . . . . . . . . . . . . . . . . . . . 27 4.3.2.2 模型量化 . . . . . . . . . . . . . . . . . . . . . . . . 28 4.3.2.3 輸出編譯結果 . . . . . . . . . . . . . . . . . . . . . . 28 4.4 系統開發 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.4.1 PS-PL 分工 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.4.2 PL：前處理 IP . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.4.3 PL：Overlay 設計 . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.4.3.1 PS-PL 傳輸 . . . . . . . . . . . . . . . . . . . . . . . 32 4.4.3.2 IP 與 PS 介面設定 . . . . . . . . . . . . . . . . . . . 32 4.4.3.3 建立區塊設計 . . . . . . . . . . . . . . . . . . . . . . 33 4.4.3.4 Vitis 流程 . . . . . . . . . . . . . . . . . . . . . . . . 33 4.4.4 PS 應用開發 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 第五章 實驗結果與討論 36 5.1 實驗環境配置 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 5.2 評估指標 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.2.1 分割結果評估 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 5.2.2 系統效能評估 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.3 模型架構消融實驗 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 5.3.1 實驗設置 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 5.3.2 未量化模型之評估結果 . . . . . . . . . . . . . . . . . . . . . . . 42 5.3.3 量化後之評估結果 . . . . . . . . . . . . . . . . . . . . . . . . . . 44 5.3.4 分割結果呈現 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 5.4 系統架構評估 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 5.5 提出系統之參數與性能 . . . . . . . . . . . . . . . . . . . . . . . . . 56 第六章 結論與未來展望 57 6.1 結論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 6.2 未來展望 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 參考文獻 59 | - |
| dc.language.iso | zh_TW | - |
| dc.title | 基於FPGA之無人水面載具影像分割系統 | zh_TW |
| dc.title | An FPGA-based Image Segmentation System for Unmanned Surface Vehicles | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳昭宏;陳彥廷;郭庭榕 | zh_TW |
| dc.contributor.oralexamcommittee | Jau-Horng Chen;Yen-Ting Chen;Ting-Jung Kuo | en |
| dc.subject.keyword | 無人水面載具,影像分割,FPGA,類神經網路,深度學習, | zh_TW |
| dc.subject.keyword | USV,image segmentation,FPGA,artificial neural network,deep learning, | en |
| dc.relation.page | 64 | - |
| dc.identifier.doi | 10.6342/NTU202404468 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-10-13 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 工程科學及海洋工程學系 | - |
| 顯示於系所單位： | 工程科學及海洋工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 目前未授權公開取用 | 16.37 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。