簡易檢索 / 詳目顯示

回結果列表
研究生： 吳明哲
Wu, Ming-Che
論文名稱： 基於類神經網路架構早期偵測空停車格
Neural Network Approaches for Early Detecting Vacant Parking Space
指導教授： 葉梅珍
Yeh, Mei-Chen
學位類別： 碩士
Master
系所名稱： 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2018
畢業學年度： 106
語文別： 中文
論文頁數： 43
中文關鍵詞： 停車格偵測 、行車紀錄器 、卷積神經網路 、長短期記憶網路
英文關鍵詞： Parking Space Detection, Dash Cam, Convolutional Neural Network, Long Short-Term Memory
DOI URL： http://doi.org/10.6345/THE.NTNU.DCSIE.021.2018.B02
論文種類： 學術論文
相關次數： 點閱：136  下載：8 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本論文解決駕駛人耗費不必要的時間在尋找停車地點之問題。提早偵測停車格的智慧系統是重要的，駕駛可能因為分神在找尋停車格，而導致交通意外發生，且在大城市中經常發生停車格嚴重不足的問題。在本研究中，我們使用行車紀錄器蒐集共5,800部的影片資料集(駕駛人的視角)，藉由深度學習的技術，建置可以偵測前方是否有空停車位的類神經網路模型。為了增進偵測效能，我們提出了一個新的損失函數以優化時序資料，最後開發出一個可以早期偵測空停車格的駕駛輔助系統。在本研究中，我們也建立了一個提早偵測空停車格的評比實驗 (Benchmark)，可以讓後續相關領域的研究者評估其實驗結果。

    This thesis addresses the problem of spending unnecessary time on searching for a place to park. Early detection of vacant parking space is important because traffic accidents often happen due to the distraction of a driver when the driver is looking for vacant parking space. Furthermore, according to the statistic from Department of Transportation, Taipei City Government, there is about sixty thousand registrations difference between cars and parking spaces, indicating the serious problem of shortage of parking space in a big city. In this study, we collect a dataset that contains 5,800 dash-cam videos. We train neural network models through the deep learning technique to detect whether or not there is a vacant parking space ahead. In order to improve the detection performance, we propose a new loss function to optimize the sequence problem. We develop a driving assistance system for early detecting vacant parking space which aims to reduce the danger when driving. Finally, we also establish a benchmark for this task, which can be used to evaluate future related experiments and systems.

    附表目錄 iv 附圖目錄 v 第一章 簡介 1 1.1 研究背景與動機 1 1.2 研究目的 1 1.3 研究貢獻 3 1.4 論文架構 3 第二章 文獻探討 5 2.1 高空式停車位偵測 5 2.1.1攝影機視角 5 2.1.2空拍機視角 7 2.2 雷達裝置停車位偵測 8 2.3 行車視角停車位偵測 9 第三章 資料集 12 第四章 實驗方法 17 4.1 損失函數 17 4.2 模型架構 19 4.2.1 3D CNN 19 4.2.2 3D CNN-LSTM 20 第五章 實驗結果與分析 23 5.1 實驗設置 23 5.2 實驗一(3D CNN with MSE/Confidence Loss) 24 5.3 實驗二(3D CNN-LSTM with MSE/Confidence Loss) 28 5.4 提早偵測 33 5.5 影片範例 34 5.6 實驗三(3D CNN/3D CNN-LSTM with Cross Entropy/Confidence Loss) 36 第六章 總結與未來展望 40 參考文獻 41

    [1] N. True. " Vacant Parking Space Detection in Static Images. " Projects in Vision &
    Learning, University of California, 2007 [Online]. Available:
    http://www.cs.ucsd.edu/classes/wi07/cse190-a/reports /ntrue.pdf.
    [2] G. Amato, F. Carrara, F. Falchi, C. Gennaro and C. Vairo. " Car Parking Occupancy Detection using Smart Camera Networks and Deep Learning." Proc. IEEE ISCC, pp. 1212–1217Messina, Italy, 27–30 June 2016.
    [3] Q. Wu, C. C. Huang, S. Y. Wang, W. C. Chiu and T. H. Chen. " Robust Parking Space Detection Considering Inter-space Correlation. " Proc. IEEE ICME, pp. 659-662, July 2007.
    [4] M.-R. Hsieh, Y.-L. Lin, and W. H. Hsu. " Drone-based Object Counting by Spatially Regularized Regional Proposal Networks. " Proc. IEEE ICCV, 2017.
    [5] M. R. Schmid, S. Ates, J. Dickmann, F. Hundelshausen and H. J. Wuensche.
    " Parking Space Detection with Hierarchical Dynamic Occupancy Grids. " Proc. IEEE IV, pp. 254-259, June 2011.
    [6] S. Ji, W. Xu, M. Yang, and K. Yu. " 3D Convolutional Neural Networks for Human Action Recognition. " PAMI, 35(1):221– 231, 2013.
    [7] L. Wang, Y. Qiao, and X. Tang. " Action Recognition with Trajectory-pooled Deep-convolutional Descriptors. " Proc. CVPR, 2015.
    [8] Christoph Feichtenhofer, Axel Pinz, and Andrew Zisserman. " Convolutional Two-stream Network Fusion for Video Action Recognition. " Proc. CVPR, 2016.
    [9] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. " Gradient-based Learning Applied to Document Recognition. " Proc. IEEE, 1998.
    [10] M.-R. Hsieh, Y.-L. Lin, and W. H. Hsu. " Drone-based Object Counting by Spatially Regularized Regional Proposal Networks. " Proc. IEEE ICCV, 2017
    [11] R. Fusek, K. Mozdren, M. Surkala and E. Sojka. "Adaboost for Parking Lot Occupation Detection. " Proc. CORES, 2013, pp. 681–690.
    [12] W. Niu, J. Long, D. Han and Y. Wang. " Human Activity Detection and Recognition for Video Surveillance. " Proc. IEEE ICME, Taipei, Taiwan, 27–30 June 2004; Volume 1, pp. 719–722.
    [13] K. He, X. Zhang, S. Ren, and J. Sun. " Deep Residual Learning for Image Recognition. " Proc. IEEE CVPR, pages 770–778, 2016.
    [14] Gao Huang, Zhuang Liu, and Kilian Q. Weinberger. " Densely Connected Convolutional Networks. " arXiv:1608.06993, 2016.
    [15] P. R. de Almeida, L. S. Oliveira, A. S. B., E. J. S. and A. L. Koerich. " Pklot - A
    Robust Dataset for Parking Lot Classification ", Expert Systems with Applications, vol. 42, no. 11, pp. 4937-4949, 2015.
    [16] Jie-Qi, Huang. " A Study of Video Recorder Based Active Outdoor Parking Space. Detection System ", M.S. Thesis, National Cheng Kung University, 2012.
    [17] M.Y. I. Idris, E.M. Tamil, Z. Razak, N.M. Noor and L.W. Kin. " Smart Parking System using Image Processing Techniques in Wireless Sensor Network Environment. " Information Technology Journal, vol. 8, pp. 114-127, 2009.
    [18] A. Krizhevsky, I. Sutskever, and G. Hinton. " ImageNet Classification with Deep Convolutional Neural Networks. " Proc. NIPS, 2012.
    [19] S. Hochreiter and J. Schmidhuber. " Long Short-Term Memory." Neural Computation , vol. 9, no. 8, pp. 1735-1780, 1997.
    [20] A. Graves, A.-R. Mohamed, and G. Hinton. " Speech recognition with deep recurrent neural networks. " Proc. ICASSP, pp. 6645–6649, 2013.

    下載圖示
    QR CODE