跳到主要內容

臺灣博碩士論文加值系統

(44.220.44.148) 您好!臺灣時間:2024/06/14 10:56
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:蕭宇展
研究生(外文):Hsiao, Yu-Chan
論文名稱:應用於光達點雲的可適性去霧演算法
論文名稱(外文):Adaptively De-Fog Algorithm for LiDAR Point Clouds
指導教授:桑梓賢
指導教授(外文):Sang, Tzu-Hsien
口試委員:桑梓賢蔡嘉明張添烜
口試委員(外文):Sang, Tzu-HsienTsai, Chia-MingChang, Tian-Sheuan
口試日期:2022-12-12
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:電子研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:111
語文別:中文
論文頁數:57
中文關鍵詞:光達直方圖多重回波偵測三維點雲除霧
外文關鍵詞:fog removal3D point cloudmulti-echo detectionLiDARhistogram
相關次數:
  • 被引用被引用:0
  • 點閱點閱:103
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
光學雷達系統的一個優勢在於能夠在白天、夜晚快速生成高精度的圖像,然而,當它們運作在有雪、濃霧…等惡劣天候狀況的時候,成像品質便會大幅降低,其中尤以霧(Fog)的影響最為嚴重。因此,許多研究人員正在積極克服這些限制,雖然近年已經有一些針對光達系統的去噪研究發表,但由於速度和精度性能的限制,結果仍然不足以應用於自動駕駛汽車,並且,基於光達點雲的去霧研究則鮮少被發表。
在本篇論文中首先分析了在均勻霧中的光達所蒐集到的均勻霧點雲特性,並提出一種基於點雲的距離及強度的通用可適性霧濾波器,也和一般的首回波濾波(First Echo Removal filter) 法進行比較。此外也在模擬資料以及人造霧環境中進行驗證。
我們在人造的非均勻霧環境下的實驗結果顯示,可以同時獲得大於90%的召回率(Recall)和精度(Precision),並且能達到實時運作。
One of the advantages of LiDAR systems is that it can quickly generate high-precision images during the day and night. However, when LiDAR operate in severe weather conditions such as snow, dense fog, etc., the image quality will be greatly reduced, especially fog was the most serious. Therefore, many researchers are actively overcoming these limitations, although there are some denoising studies on LiDAR systems have been published in recent years, the results are still insufficient for application in autonomous vehicles due to speed and accuracy performance limitations, even more, the study of fog removal filter based on LiDAR point cloud is rarely published.
In this thesis, the properties of point clouds collected by LiDAR under the uniform fog are firstly analyzed, and a general adaptive fog removal filter based on the distance and intensity of point clouds is proposed. We also compared proposed method with the general first echo removal filter. In addition, it is verified on both simulated data and real-world LiDAR point clouds with artificial fog environment.
Our experimental results in an artificial non-uniform fog environment show that a recall rate (Recall) and a precision (Precision) greater than 90% can be obtained at the same time, and can achieve real-time operation.
摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章 緒論 1
1.1研究目的 1
1.2論文架構 2
第二章 近年相關研究 2
2.1 光學雷達原理 2
2.1.1. 接收端與發射端 3
2.1.2. 時間數位轉換器(TDC) 4
2.1.3. 三維光達 5
2.1.4. 多重回波和 CFAR 介紹 6
2.2 點雲去噪相關研究 9
2.3.1. 基於統計的噪聲點雲過濾法 9
2.3.2. 基於光子強度的噪聲點雲過濾法 11
2.3.3. 基於深度學習的噪聲點雲過濾法 11
2.3.4. 結論 11
第三章 除霧算法 13
3.1 均勻霧點雲的位置 13
3.2 判斷是否需要除霧 18
3.3 均勻霧 19
3.4 非均勻霧 24
3.5 首回波濾波法 26
第四章 模擬及實驗結果 27
4.1 模擬結果 27
4.2 實驗結果I 31
4.3 實驗結果II 37
4.4 結論 43
第五章 總結 45
1、統計模擬資料後歸納出霧點雲的分布位置及範圍 45
2. 以點雲的光子強度及位置為基礎開發通用除霧演算法 46
3. 以模擬、實驗資料驗證除霧算法有效性 48
4. 應用建議 53
參考文獻 55
[1] T. -P. Yu, “Aerosols removal algorithm based on deep learning,” master degree thesis, 2020.
[2] C. -I. Lin, “Performance of LiDAR in Foggy Environments based on AI edge computing platform,” master degree thesis, 2021.
[3] Stanislas, L., Nubert, J., Dugas, D., Nitsch, J., Sünderhauf, N., Siegwart, R., Cadena, C., & Peynot, T. (2021). Airborne particle classification in lidar point clouds using deep learning. Field and Service Robotics, 395–410.
[4] Heinzler, R., Piewak, F., Schindler, P., & Stork, W. (2020). Cnn-based lidar point cloud de-noising in adverse weather. IEEE Robotics and Automation Letters, 5(2), 2514–2521.
[5] Kurup, A., & Bos, J. (2021). Dsor: A scalable statistical filter for removing falling snow from lidar point clouds in severe winter weather. ArXiv Preprint ArXiv:2109.07078.
[6] Park, J.-I., Park, J., & Kim, K.-S. (2020). Fast and accurate desnowing algorithm for LiDAR point clouds. IEEE Access, 8, 160202–160212.
[7] Charron, N., Phillips, S., & Waslander, S. L. (2018). De-noising of lidar point clouds corrupted by snowfall. 2018 15th Conference on Computer and Robot Vision (CRV), 254–261.
[8] LMS1000 - Sick. https://cdn.sick.com/media/docs/1/21/121/Product_information_LMS1000_2D_LiDAR_sensors_en_IM0080121.PDF.
[9] McManamon, P. F. (2019). Lidar technologies and Systems.
[10] Niclass, C., Soga, M., Matsubara, H., Ogawa, M., & Kagami, M. (2013). A 0.18µm CMOS SoC for a 100m-range 10fps 200×96-pixel time-of-flight depth sensor. 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers, 488–489. https://doi.org/10.1109/ISSCC.2013.6487827
[11] Kumagai, O., Ohmachi, J., Matsumura, M., Yagi, S., Tayu, K., Amagawa, K., Matsukawa, T., Ozawa, O., Hirono, D., Shinozuka, Y., Homma, R., Mahara, K., Ohyama, T., Morita, Y., Shimada, S., Ueno, T., Matsumoto, A., Otake, Y., Wakano, T., & Izawa, T. (2021). 7.3 A 189×600 Back-Illuminated Stacked SPAD Direct Time-of-Flight Depth Sensor for Automotive LiDAR Systems. 2021 IEEE International Solid- State Circuits Conference (ISSCC), 64, 110–112. https://doi.org/10.1109/ISSCC42613.2021.9365961
[12] Technote TCSPC. (n.d.). Retrieved November 30, 2022, from https://www.picoquant.com/images/uploads/page/files/7253/technote_tcspc.pdf
[13] Yoo, H. W., Druml, N., Brunner, D., Schwarzl, C., Thurner, T., Hennecke, M., & Schitter, G. (2018). MEMS-based lidar for autonomous driving. E & i Elektrotechnik Und Informationstechnik, 135(6), 408–415.
[14] T. -P. Yu, “Aerosols removal algorithm based on deep learning,” master degree thesis, 2020.
[15] Phillips, T. G., Guenther, N., & McAree, P. R. (2017). When the dust settles: The four behaviors of lidar in the presence of fine airborne particulates. Journal of Field Robotics, 34(5), 985–1009.
[16] Hahner, M., Sakaridis, C., Dai, D., & Van Gool, L. (2021). Fog simulation on real LiDAR point clouds for 3D object detection in adverse weather. Proceedings of the IEEE/CVF International Conference on Computer Vision, 15283–15292.
[17] Rohling, H. (1983). Radar CFAR thresholding in clutter and multiple target situations. IEEE Transactions on Aerospace and Electronic Systems, 4, 608–621.
[18] Rohling, H. (2011). Ordered statistic CFAR technique-an overview. 2011 12th International Radar Symposium (IRS), 631–638.
[19] Rohling, H., & Mende, R. (1996). OS CFAR performance in a 77 GHz radar sensor for car application. Proceedings of International Radar Conference, 109–114.
[20] Ogawa, T., & Wanielik, G. (2016). TOF-LIDAR signal processing using the CFAR detector. Advances in Radio Science, 14(F.), 161–167.
[21] Rusu, R. B., & Cousins, S. (2011). 3d is here: Point cloud library (pcl). 2011 IEEE International Conference on Robotics and Automation, 1–4.
[23] Duan, Y., Yang, C., Chen, H., Yan, W., & Li, H. (2021). Low-complexity point cloud denoising for LiDAR by PCA-based dimension reduction. Optics Communications, 482, 126567.
[24] Roriz, R., Campos, A., Pinto, S., & Gomes, T. (2021). DIOR: A Hardware-assisted Weather Denoising Solution for LiDAR Point Clouds. IEEE Sensors Journal, 22(2), 1621–1628.
[25] Piewak, F., Pinggera, P., Schafer, M., Peter, D., Schwarz, B., Schneider, N., Enzweiler, M., Pfeiffer, D., & Zollner, M. (2018). Boosting lidar-based semantic labeling by cross-modal training data generation. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 0–0.
[26] S. Y.Tsai, “Countermeasures and Performance of LiDAR in Foggy Environments”, National Chiao Tung University master degree thesis, 2019
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊