臺灣博碩士論文加值系統

本研究中，我們提出了一多階層之停車空位偵測的語意推理架構。由低階語意至高階語意，這個架構共包含了影像特徵層、子影像區域分類層、區域結構結合層、以及停車場狀態推論層。首先，我們使用長方體來模擬三維空間中的每一停車格，此長方體可拆解為六個面;接著，我們將此三維空間中的六個面投影到停車場影像中以進一步進行停車狀態語意推理分析。在影像特徵層中，我們針對每一投影面所涵蓋之區域進行正規化，並根據該區域的影像資訊擷取抗光影變化的特徵。由於停車場上的車輛有規律地停放，我們發現每個投影面所能觀察到的影像資訊會呈現特定形式的遮蔽型態。藉由分類出遮蔽型態，系統能從中推論出停車格狀態。因此，在子影像區域分類層，我們設計並訓練出能辨認不同遮蔽型態的弱分類器，而分類器的輸出則含有遮蔽型態與停車狀態之間的資訊。在我們的系統中，我們進一步將分類器的輸出當成中階語意特徵，並當成資訊輸入區域結構結合層。在結合層中，我們利用辨識提升演算法(Boosting method)來整合不同分類器的遮蔽型態分類資訊，並推論出一個以三格停車空位為單位的區域停車狀態。在停車場狀態層中，我們把這些區域狀態視為高等特徵並利用馬可夫隨機場來推斷最終的停車狀態。我們的實驗結果展現出此多階層語意推理架構可以克服車輛併停所產生的相互遮蔽並且在不同的天候條件下達到更好的停車空位偵測結果

In this research, we proposed a novel semantic inference framework with multiple layers for vacant parking space detection. The framework consists of an image layer, a patch layer, a space layer, and a lot layer. In the image layer, image patches are selected based on the 3-D parking lot structure. We found the occlusion pattern within each patch reveals partial cues of parking status. Thus, our system extracted lighting-invariant features of patches and trained weak classifiers to recognize the occlusion pattern in the patch layer. The outputs of the classifiers, presenting the types of inter-object occlusion, were treated as the mid-level features and inputted to the space layer. Next, a boosted space classifier was trained to recognize the mid-level features and output the status of a 3-space unit in a probability fashion. In the lot layer, we regarded these local status decisions as high-level evidences and proposed a Markov Random Field to infer the final status of the parking lot. Our results show that the proposed framework can overcome the inter-object occlusion and achieve better space detection in different weather conditions.

CHINESE ABSTRACT i
ENGLISH ABSTRACT ii
ACKNOWLEDGEMENT iii
TABLE OF CONTENT iv
LIST OF TABLES vi
LIST OF FIGURES vii
CHAPTER 1 INTRODUCTION 1
1.1. Research Background and Motive 1
1.2. Research Objective 4
1.3. Structure of the Thesis 5
CHAPTER 2 LITERATURE REVIEW 6
2.1. Discriminative Framework 6
2.2. Generative Framework 9
CHAPTER 3 RESEARCH METHODOLOGY 13
3.1. The Image Layer 14
3.2. The Patch Layer 16
3.3. The Space Layer 18
3.4. The Lot Layer 21
CHAPTER 4 EXPERIMENTAL RESULTS 25
4.1. Experiment Environment and Testing Data 25
4.2. Different Weather Conditions Performance Evaluation 26
4.3. Different Views and Heights Performance Evaluation 28
4.4. Evaluation of Patch Classification and Boosting Ability 28
4.5. Error Propagation Problem 30
4.6. Comparison of System Performance 30
4.7. System Complexity 33
CHAPTER 5 CONCLUSIONS AND FUTURE PROSPECTS 34
5.1. Discussion and Future Works 34
5.2. Conclusion 36
REFERENCE 37
APPENDIX 41

[1]Jatuporn Chinrungrueng, Udomporn Sunantachaikul, Satien Triamlumlerd, “Smart Parking: an Application of optical Wireless Sensor Network,” International Symposium on Applications and the Internet Workshops, pp. 66, 2007.
[2]Jatuporn Chinrungrueng, Songphon Dumnin, and Ronachai Pongthornseri, “iParking: a Parking Management Framework,” 11th International Conference on ITS Telecommunications, pp. 63-68, 2011.
[3]V.W.S. Tang, Y. Zheng, J. Cao, “An Intelligent Car Park Management System Based On Wireless Sensor Networks,” 1st International Symposium On Pervasive Computing And Applications, pp.65-70, 3-5 Aug, 2006.
[4]A.S.G. Prasad, U. Sharath, B. Amith, B.R. Supritha, S. Asokan, and G.M. Hegde, “Fiber Bragg Grating Sensor Instrumentation for Parking Space Occupancy Management,” International Conference on Optical Engineering, pp. 1-4, July 2012.
[5]Zusheng Zhang, Ming Tao, and Huaqiang Yuan, “A Parking Occupancy Detection Algorithm Based on AMR Sensor,” IEEE Sensors Journal, vol. 15, no. 2, pp. 1261-1269, February 2015.
[6]I. Masaki, “Machine-Vision Systems for Intelligent Transportation Systems,” IEEE International Conference on Intelligent Transportation System, Vol.13, Issue 3, pp.24-31, 1998.
[7]S. Funck, N. Mohler and W. Oertel, “Determining Car-Park Occupancy from Single Images,” IEEE Intelligent Vehicles Symposium, 2004.
[8]T. Horparasert, D. Harwood, L. A. Davis, “A Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection,” IEEE International Conference on Computer Vision, pp. 1-19, 1999.
[9]Chris Stauffer, W. E. L Grimson, “Adaptive Background Mixture Models for Real-time Tracking,” IEEE International Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 246-252, 1999.
[10]P. Power and J. Schoonees, “Understanding Background Mixture Model for Foreground Segmentation,” Proceeding of Image and Vision Computing New Zealand, pp. 267-271, Nov. 2002.
[11]Luo-Wei Tsai, Jun-Wei Hsieh, Kao-Chin Fan, “Vehicle Detection Using Normalized Color and Edge Map,” IEEE Transactions on Image Processing, Vol. 16, Issue 3, pp.850-864, March 2007.
[12]N.True, “Vacant parking space detection in static image,” Projects in Vision & Learning, University of California, 2007.
[13]Wand Lixia and Jiang Dalin, “A method of Parking space detection based on image segmentation and LBP,” International Conference on Multimedia Information Networking and Security, pp. 229-232, Nov. 2012.
[14]Paulo Almeida, Luiz S. Oliveira, Eunelson Silva Jr., Alceu Britto Jr., and Alessandro Koerich, “Parking Space Detection using Textural Descriptors,” in IEEE International Conference on Systems, Man, and Cybernetics, 2013.
[15]Harish Bhaskar, Naoufel Werghi, and Saeed AL-Mansoori, “Rectangular Empty Parking Space Detection using SIFT based Classification,” in Proceedings of the Sixth International Conference on Computer Vision Theory and Applications, 5-7 March, 2011.
[16]H. Ichihashi, T. Katada, M. Fujiyoshi, A. Notsu, and K. Honda, “Improvement in the performance of camera based vehicle detector for parking lot,” in Proc. IEEE Int. Conf. Fuzzy Syst., pp. 1950–1956, 2010.
[17]R.J. López-Sastre, P. Gil Jimenez, F.J. Acevedo, and S. Maldonado Bascon, “Computer Algebra Algorithms Applied to Computer Vision in a Parking Management System,” IEEE International Symposium on Industrial Electronics, 2007.
[18]Q. Wu, C. C. Huang, S. Y. Wang, W. C. Chiu, and T. H. Chen, “Robust Parking Space Detection Considering Inter-Space Correlation,” IEEE International Conference on Multimedia and Expo, pp. 659-662, 2007.
[19]Y. Boykov, O. Veksler and R. Zabih, “Efficient Approximate Energy Minimization via Graph Cuts,” IEEE Transactions on PAMI, Vol. 3, pp.1222-1239, 2001.
[20]C.C. Huang, S. J. Wang, Y. J. Chang, and T. Chen, “A Bayesian Hierarchical Detection Framework for Parking Space Detection,” IEEE International Conference on Acoustics, Speech and Signal Processing, Apr. 2008.
[21]C.C. Huang, S. J. Wang, “A Hierarchical Bayesian Generation Framework for Vacant Parking Space Detection,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 20, Issue 12, pp. 1770-1785, Dec. 2010.
[22]C.C. Huang, Y.S. Tai, and S.J. Wang, “Vacant Parking Space Detection Based On Plane-Based Bayesian Hierarchical Framework,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 23, Issue 9, pp. 1598–1610, Sept. 2013.
[23]Diana Delibaltov, Wencheng Wu, Robert P. Loce, and Edgar A. Bernal , “Parking Lot Occupancy Determination from Lamp-post Camera Images,” in Proceedings of the 16th International IEEE Annual Conference on Intelligent Transportation Systems, 6-9 October, 2013.
[24]T. Ahnonen, A. Hadid, M. Pietikainen, “Face description with local binary patterns: Application to face recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037–2041, 2006.
[25]Jamie Shotton, John Winn, Carsten Rother, Antonio Criminisi, “Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context,” Int. J. Comput. Vision, 2007.
[26]Andrew Y. Ng and Michael I. Jordan, “On Discriminative vs. Generative Classifiers: A Comparison of Logistic Regression and Naive Bayes,” Neural Information Processing Systems 14, 2001.
[27]Michael A. Nielsen. (2015). Neural Networks and Deep Learning. [Online]. Available: http://neuralnetworksanddeeplearning.com
[28]N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, June 2005.
[29]Aleix M. Martínez, Avinash C. Kak, “PCA versus LDA”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, Issue 2, pp.228–233, Feb. 2001.
[30]C. M. Bishop, Pattern Recognition and Machine Learning Springer, 2006.
[31]Mark Schmidt. (2014). UGM: Matlab code for undirected graphical models. [Online]. Available at: http://www.cs.ubc.ca/~schmidtm/Software/UGM.html.
[32]C. C. Huang. (2015). Huang’s Projects. [Online]. Available at http://acm.ee.ccu.edu.tw:5500/ParkingLotSystemDemo.html.