臺灣博碩士論文加值系統

隨著物聯網技術的發展，車聯網的技術已經漸趨成熟。然而，這樣的系統只注重於個別車輛駕駛的狀況，經常忽略周邊車輛，如此更突顯車聯網技術的關鍵性。本論文提出了兩個系統來獲得移動車輛的大數據分析，並通過車聯網來構建一個安全和智慧的道路系統。
首先提出的系統利用攝影機擷取車輛車牌的最佳位置的演算法。本系統不僅滿足即時偵測的目標，且可在連續影像中獲得一張具有最佳車輛車牌的觸發影像，本演算法無需額外架設特別的硬體裝置，可以精確擷取具有最佳車輛車牌的觸發影像，並提供給車牌辨識系統進行車牌辨識。與傳統的偵測方法相比，可大量省下硬體的成本及維護費用。實驗結果顯示本演算法是穩定且正確的演算法。
本論文另外提出一個是利用兩個低成本的小型互補式金屬氧化物半導體（CMOS）相機作為視覺感測器，運用有效的即時偵測演算法來偵測前方車輛和測量距離。這種低成本視覺感測器屬於非同步的視覺系統，因為客製化的雙鏡頭是經由擷取卡來依序擷取成對的影像，且左和右影像具有輕微的時間差。本論文提出的偵測演算法包含四個模組，分別為影像預處理、車輛偵測、追踪已偵測的車輛及距離測量。利用所提出的偵測演算法解決低價的非同步拍攝影像視覺偵測的問題，使得立體視覺的偵測可以不受到同步拍攝系統的限制。利用此偵測演算法針對高速公路、城市和鄉村道路進行長期性能測試的結果，證實該系統成功地偵測前方車輛距離，通過本論文提出的兩系統演算法，得到大數據的分析可以提供車聯網資訊，並構建一個安全和智慧的道路系統。
 

With the development for “Internet of Things (IoT)” technology, Internet of Vehicle technology has become mature. Such systems, nevertheless, focus only on individual vehicle’s driving conditions and often ignore that of the surrounding vehicles, thus making “Internet of Vehicle (IoV)” technology significantly crucial. This paper proposes two systems to obtain the big data analytics of moving vehicles, and to construct a safety and wisdom road system by IoV.
The first proposed system utilizes the location of the vehicle to trigger the camera to capture an image of the vehicle. This not only achieves the goal of detecting an image in real time, but as well obtains the best image with the license plate as a triggering image. The proposed algorithm does not require additional hardware, facilitating the precise retrieval of an image that both contains a vehicle and represents the best image from a series of images for recognizing the characters on license plates.
This paper proposes another effective real-time detection algorithm that uses two low-cost compact Complementary Metal-Oxide Semiconductor (CMOS) cameras as vision sensors to detect front vehicles and measure distances. This low-cost vision sensor is an asynchronous vision system since a custom-made binocular is used to capture pairs of images via a low-cost grabber card and the left and right images have a slight time difference. Nevertheless, the proposed detection algorithm, which comprises four modules—namely, image preprocessing, vehicle detection, detected vehicle tracking, and distance measurement—is unrestrained by the limitations of the epipolar constraints for synchronous vision systems, and also enables the system to overcome the asynchronous detection problem affecting conventional low-cost vision systems. The results of long-term performance tests conducted on highways and urban and country roads confirm that the proposed system can successfully detect the distance of the front vehicle.
The proposed algorithms significantly reduce the cost of hardware and are much easier and cheaper to maintain than the traditional detection methods. An extensive vehicle-detection test demonstrates that the proposed algorithm is reliable and accurate. The analysis of the big data obtained by the proposed algorithms can provide the information of IoV and construct a safety and wisdom road system.

摘要 i
Abstract iii
Acknowledgements v
Table of Contents vi
List of Figures viii
List of Tables xi
Chapter 1. Introduction 1
1.1 Vehicle Detection Algorithm for Applications Pertaining to License Plate Recognition ………………………………………………………………………………3
1.2 A Vision Sensor System for Intelligent Vehicles 7
1.3 Contribution 10
1.4 Organization 11
Chapter 2. Method of Vehicle Detection Algorithm for Applications Pertaining to License Plate Recognition 13
2.1 Dynamic vehicle detection 14
2.2 Vehicle detection and background renewal 17
2.3 Vehicle location analysis 21
Chapter 3. Method of A Vision Sensor System for Intelligent Vehicles 24
3.1 Stereo vision from asynchronous cameras 24
3.2 The stereo vision vehicle detection algorithm 28
3.3 Image preprocessing 29
3.4 Vehicle detection 30
3.5 Detected vehicle tracking 32
3.6 Distance measurement 34
Chapter 4. RESULTS and DISCUSSION of Vehicle Detection Algorithm for Applications Pertaining to License Plate Recognition 36
Chapter 5. RESULTS and DISCUSSION of A Vision Sensor System for Intelligent Vehicles 43
5.1 System overview 43
5.2 System reliability analysis on highways 44
5.3 Experimental Results Obtained under Various Weather/Illumination Conditions ……………………………………………………………………………..50
Chapter 6. Technique of IOT 52
6.1 Cloud servo system 54
6.2 Combination Tests on Freeway ETC 55
6.3 Integration with the Police Authorities Systems 58
6.3.1 General road stolen vehicles license plate recognition system 58
6.3.2 Vehicle-mounted license plate recognition system 65
6.4 Parking Lots Management System 80
6.5 Weighbridge Management system 84
Chapter 7. Conclusion 88
7.1 Conclusion of Vehicle Detection Algorithm for Applications Pertaining to Licesnse Plate Recognition 88
7.2 Conclusion of a Vision Sensor System for Intelligent Vehicles 89
7.3 Future works 90
References 91
CURRICULUM VITAE 94

REFERENCES
[1] Gao, Y., Lee, H.J. Local tiled deep networks for recognition of vehicle make and model. Sensors, 2016, 16, 226.
[2] Zheng, D., Zhao, Y., Wang, J. An efficient method of license plate location. Pattern Recognition letters, 2005, 26, 2431–2438.
[3] Li, Q. A geometric framework for rectangular shape detection. IEEE Trans. Image Process. 2014, 23, 4139–4149.
[4] Wijnhoven, R.G.J., With, P.H.N. Identity verification using computer vision for automatic garage door opening, IEEE trans. Consum. Electron., 2011, 57, 906–914.
[5] Ashtari, A.H., Nordin, M.J., Fathy, M. An Iranian license plate recognition system based on color features. IEEE Trans. Intell. Transp. Syst., 2014, 15, 1690–1704.
[6] Thooyamani, K.P., Khanaa, V., Udayakumar, R., Middle-East Journal of Science Research. 2013, 18, 1768-1774.
[7] Chang, S.-L., Chen, L.-S., Chung, Y.-C., Chen, S.-W. Automatic license plate recognition. IEEE Trans. Intell. Transp. Syst., 2004, 15, 42–53.
[8] Hsu, G.-S., Chen, J.-C., Chung Y.Z. Application-Oriented License Plate Recognition, IEEE Transactions on Vehicular Technology, 2013, 62(2), 552-561.
[9] Li, B., Tian, B., Li, Y., Wen, D. Component-based license plate detection using conditional random field model. IEEE Trans. Intell. Transp. Syst., 2013, 14, 1690–1699.
[10] Deb, K., Jo, K. Segmenting the license plate region using a color model. Pattern recognition, Yin, P.; Publisher: InTech, Rijeka, Croatia, 2009; pp. 401–418.
[11] Comelli, P., Ferragina, P., Granieri, M. N., Stabile, F. Optical recognition of motor vehicle license plates. IEEE Trans. Veh. Technol., 1995, 44, 790–799.
[12] Wu, P.-F., Lin, S.-P., Chiu, C.-C. Extracting characters from real vehicle license plates out-of-doors. IET Comput. Vis., 2007, 1, 2–10.
[13] Nakanishi, T.; Ishii, K. Automatic Vehicle Image Extraction Based on Spatio-Temporal Image Analysis. IAPR International Conference on Computer Vision and Applications, 1992, 1, 500–504.
[14] Li, C.; Ikeuchi, K.; Sakauchi, M. Acquisition of Traffic Information Using A Video Camera with 2D Spatio-Temporal Image Transformation Technique. IEEE Int. Conf. on Intell. Transp. Syst., 1995, 634–638.
[15] Lipton, A. J.; Fujiyoshi, H.; Patil, R. S. Moving Target Classification and Tracking from Real-Time Video. IEEE Workshop on Appl. of Comput. Vis., 1998, 8–14.
[16] Chiu, C. C.; Ku, M. Y.; Liang, L. W. A Robust Object Segmentation System Using a Probability-Based Background Extraction Algorithm. IEEE Trans. Circuits Syst. Video Technol., 2010, 20, 518–528.
[17] Wu, B. F.; Juang, J. H. Adptive Vehicle Detector Approach for Complex Environments. IEEE Int. Conf. on Intell. Transp. Syst., 2012, 817–827.
[18] Nashashibi A., Sarabandi K., De R. R., Frantzis P., and Ulaby F., “An ultrafast wide-band millimeter-wave (MMW) polarimetric radar for remote sensing applications,” IEEE Trans Geosci. Remote Sens., vol. 40, no. 8, pp. 1777-1786, 2002.
[19] Shiu HT, Hall PS, Hoare EG, and Clarke NJ, “Advance path measurement for automotive radar applications,” IEEE Trans. Intell. Transp. Syst., vol. 7, no. 3, pp. 273-281, 2006.
[20] Jung HG., Cho YH., Yoon PJ., and Kim J., “Scanning laser-radar-based target position designation for parking aid system,” IEEE Trans Intell. Transp. Syst., vol. 9 no. 3, pp. 406-424, 2008.
[21] Trivedi MM., Gandhi T., and McCall J. “Looking-in and looking-out of a vehicle Computer-vision-based enhanced vehicle safety,” IEEE Trans. Consum. Electron., vol. 8, no. 1, pp. 108 - 120, 2007.
[22] Broggi A., Bertozzi M., Fascioli A., Bianco CGL, and Piazzi A., “Visual perception of obstacles and vehicles for platooning,” IEEE Trans Intell. Transp. Syst., vol. 1, no. 3, pp. 164-172, 2000.
[23] Suzuki T., and Kanade T., “A Measurement of vehicle motion and orientation using optical flow,” Proc. IEEE ITSC, Tokyo, pp. 346-349, 1999.
[24] Stein GP., Mano O., and Shashua A., “A robust method for computing vehicle ego-motion,” Proc. IEEE IV, Dearborn, pp. 362-368-397, 2000.
[25] Srinivasa N., “Vision-based vehicle detection and tracking method for forward collision warning in automobiles,” Proc. IEEE IV, New York, pp. 626-631, 2002.
[26] Shashua A, Gdalyahu Y, and Hayun G., “Pedestrian detection for driving assistance systems: Single-frame classification and system level performance,” Proc. IEEE IV, Parma, pp.1-6, 2004.
[27] Forsyth DA, “Computer Vision: A Modern Approach,” New Jersey, Prentice Hall, 2000
[28] Ma Y, Soatto S, Kosecka J, Sastry SS., “An invitation to 3-D vision,” Springer, 2000.
[29] Bensrhair A., Bertozzi M., Broggi A., Fascioli A., Mousset S., and Toulminet G., “Stereo vision-based feature extraction for vehicle detection,” Proc. IEEE IV, New York, pp. 465-470, 2002.
[30] Toulminet G., Bertozzi M., Mousset S., Bensrhair A., and Broggi, A., “Vehicle detection by means of stereo vision-based obstacles features extraction and monocular pattern analysis,” IEEE Trans. on image processing., vol. 15 no. 8, pp. 2364-2375, 2006.
[31] Ito T., and Yamada K., “Preceding vehicle and road lanes recognition methods for RCAS using vision system,” IEEE IV, Paris, pp. 85-90, 1994.
[32] Suzuki K., Horiba I., and Sugie N., “Fast connected-component labeling based on sequential local operations in the course of forward raster scan followed by backward raster scan.,” Pattern Recognition, pp. 434-437, 2000.