臺灣博碩士論文加值系統

駕駛在開車時需要一個安全及便利的開車環境。現代的車載安全系統已經有快速的進步也引起大眾的關注。而本研究提出的系統是從後置式的魚眼相機接收到實時的影像並且可以幫助駕駛避免許多危險的事件。研究顯示當駕駛開車時切換車道而發生的意外時常發生。因此本研究開發出用於預測車輛軌跡的系統提高駕駛的安全性。當事件或者是有風險時系統會提醒駕駛危險性。Adaboost及Kalman filter被當成是系統主要的技術。他是可以預測接近盲點的車輛以防止駕駛切換車道時後方車輛碰撞的情況。

Drivers require a safe and convenient driving environment when they are driving. Contemporary vehicle safety systems have rapidly improved and gained public attention. The proposed system receives real-time images from a rear-mounted fisheye camera and assists drivers in avoiding many dangerous conditions. Research indicates that driving accidents often occur when drivers are switching lanes. Therefore, to improve driving safety, this study developed a system for predicting vehicle trajectory. When accidents are likely and risks are present, the system alerts the driver. An AdaBoost algorithm was employed for vehicle detection, and a Kalman filter was selected as the main component of the proposed system; it is an effective means for predicting the trajectories of approaching vehicles in the blind spots to prevent collisions from behind during lane switching.

Abstract
Contents
1 Introduction
1.1 Motivation
1.2 Objective
1.2.1 Detecting the blind spots in the rear-view mirror
1.2.2 Predicting the timing of the approaching and vehicle its trajectory in
the rear area
2 Related Works
2.1 Point of driver's eyes
2.2 Indirect vision of vehicle
2.2.1 Rear-view mirror inside the vehicle
2.2.2 Rear-view mirror outside the vehicle
2.3 Blind spot area
2.4 Stopping distance
2.4.1 Idling distance
2.4.2 Braking distance
2.5 AdaBoost Algorithm
2.6 Kalman Filter
3 Collision Prediction System
3.1 System Architecture
3.2 Vehicle Detection with Adaboost Algorithm
3.2.1 Integral Image
3.2.2 The Features
3.2.3 Cascade Classier
3.2.4 The Training Data Set
3.2.5 The Result of Vehicle Detection
3.3 Vehicle Motion Trajectory Prediction
3.3.1 Underlying Dynamic System Model
3.3.2 The Result of Motion Trajectory Prediction
3.4 Collision Prediction System
4 Experimental Results
4.1 Experiment Setup
4.2 Results
5 Conclusion and Future Work
5.1 Conclusion
5.2 Future Work

[1] Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: International Conference on Computer Vision and Pattern Recognition. Volume 1., IEEE (2001) 511 - 518.
[2] R. P. Mahapatra, K. Vimal Kumar, G.K., Mahajan, R.: Ultra sonic sensor based blind spot accident prevention system. In: International Conference on Advanced Computer Theory and Engineering, IEEE (Dec. 2008) 992 - 995.
[3] Chang, J., Cho, C.: Vision-based front vehicle detection and its distance estimation. In: International Conference on Systems, Man and Cybernetics. Volume 3., IEEE (Oct. 2006) 2063 - 2068.
[4] C. H. Chen, T. Y. Chen, D.Y.H., Feng, K.W.: Front vehicle detection and distance estimation using single-lens video camera. In: International Conference on Robot, Vision and Signal Processing, IEEE (2015) 14 - 17.
[5] Hsiao, P., Yeh, C.: A portable real-time lane departure warning system based on embedded calculating technique. In: 63rd Vehicular Technology Conference. Volume 6., IEEE (May. 2006) 2982 - 2986.
[6] W.B Horng, C.Y Chen, Y.C., Fan, C.: Driver fatigue detection based on eye tracking and dynamk, template matching. In: International Conference on Networking, Sensing and Control. Volume 1., IEEE (Mar. 2004) 7 - 12.
[7] Chang, J.Y., Cho, C.W.: Vision-based front vehicle detection and its distance estimation. In: International Conference on Systems, Man and Cybernetics, IEEE (2006) 2063 - 2068.
[8] D. V. Thombre, J.H.N., Lekha, D.: Human detection and tracking using image segmentation and kalman filter. In: International Conference on Intelligent Agent and Multi-Agent Systems, IAMA (2009) 1 - 5.
[9] et al., B.F.L.: Integrating appearance and edge features for sedan vehicle detection in the blind-spot area. In: International Conference on Intelligent Transportation Systems. Volume 13., IAMA (2012) 737 - 747.
[10] Seunghwan Baek, H.K., Boo, K.: Robust vehicle detection and tracking method for blind spot detection system by using vision sensors. In: World Conference on Complex Systems, WCCS (2014) 729 - 735.
[11] Chen, C.T., Chen, Y.S.: Real-time approaching vehicle detection in blind-spot area. In: International IEEE Conference on Intelligent Transportation Systems, IEEE (2009) 1 - 6.
[12] Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: Journal of Computer and System Sciences. Volume 55., science direct (Aug. 1997) 119 139.
[13] Ma, Y., Ding, X.: Robust real-time face detection based on cost-sensitive adaboost method. In: International Conference on Multimedia and Expo. Volume 2., IEEE (July 2003) II - 465 - 8.
[14] J. M. Guo, C. C. Lin, C.H.C., Liu, Y.F.: Face gender recognition with half toning-based adaboost classifiers. In: International Conference on Circuits and Systems, IEEE (May 2013) 2497 - 2500.
[15] Viola, P., Jones, M.J.: Robust real-time face detection. In: International Journal on Computer Vision. Volume 57., IEEE (May. 2004) 137 - 154.
[16] Dai, S., Zhang, Y.: Adaboost in region-based image retrieval. In: International Conference on Acoustics, Speech, and Signal Processing. Volume 3., IEEE (May 2014) III - 429-32.
[17] C. Huang, B. Wu, H.A., Lao, S.: Omni-directional face detection based on real adaboost. In: International Conference on Image Processing. Volume 1., IEEE (Oct. 2004) 593 596.
[18] S. Yousefi, X.W.C., Champagne, B.: Mobile localization in non-line-of-sight using constrained square-root unscented kalman filter. In: International Conference on Vehicular Technology. Volume 64., IEEE (May 2015) 2071 - 2083.
[19] Chris van Hinsbergen, T.S.: Localized extended kalman filter for scalable real-time traffic state estimation. In: International Conference on Computer Vision and Pattern Recognition. Volume 13., IEEE (2012) 385 - 394.
[20] C. Luo, S. I. McClean, G.P., Teacy, L.: Uav position estimation and collision avoidance using the extended kalman filter. In: International Conference on Computer Vision and Pattern Recognition. Volume 62., IEEE (July 2013) 2749 - 2749.
[21] C.Antoniou, M.B.A., Koutsopoulos, H.N.: Nonlinear kalman filtering algorithms for on-line calibration of dynamic traffic assignment models. In: International Conference on Transactions on Intelligent Transportation Systems. Volume 8., IEEE (Dec. 2007) 661 - 670.
[22] Gustafsson, F., Hendeby, G.: Some relations between extended and unscented kalman filters. In: International Conference on Transactions on Signal Processing. Volume 60., IEEE (Feb. 2012) 545 - 555.
[23] Y. Hao, Z. Xiong, F.S., Wang, X.: Comparison of unscented kalman filters. In: International Conference on Mechatronics and Automation, IEEE (2007) 895 - 899.
[24] S. Hong, C. Lee, F.B., Hedrick, J.K.: A novel approach for vehicle inertial parameter identification using a dual kalman filter. In: International Conference on Intelligent Transportation Systems. Volume 16., IEEE (Feb. 2015) 151 - 161.
[25] R. Aguilar-Ponce, J. L. Tecpanecatl-Xihuitl, A.K., Bayoumi, M.: Pixel-level image fusion scheme based on linear algebra. In: International Conference on Circuits and Systems, IEEE (May 2007) 2658 - 2661.
[26] W. van der Mark, D. Fontijne, L.D., Groen, F.C.A.: Vehicle ego-motion estimation with geometric algebra. In: IEEE Transactions on Intelligent Vehicle Symposium. Volume 1., IEEE (2002) 58 - 63.
[27] J. C. Nascimento, M.A.T.F., Marques, J.S.: Trajectory classification using switched dynamical hidden markov models. In: IEEE Transactions on Image Processing. Volume 19., IEEE (May 2010) 1338 - 1348.
[28] Pruteanu-Malinici, I., Carin, L.: Infinite hidden Markov models for unusual-event detection in video. In: IEEE Transactions on Image Processing. Volume 17., IEEE (May 2008) 811 - 822.
[29] Ichir, M.M., Mohammad-Djafari, A.: Hidden Markov models for wavelet-based blind source separation. In: IEEE Transactions on Image Processing. Volume 15., IEEE (July 2006) 1887 - 1899.
[30] F. Destrempes, M.M., Angers, J.F.: A stochastic method for Bayesian estimation of hidden markov random field models with application to a color model. In: IEEE Transactions on Image Processing. Volume 14., IEEE (Aug. 2005) 1096 - 1108.
[31] Chris van Hinsbergen, T.S.: An introduction to hidden Markov models. In: IEEE ASSP Magazine. Volume 3., IEEE (1986) 4 - 16.
[32] Barnich, O., Droogenbroeck, M.V.: Vibe: A universal background subtraction algorithm for video sequences. In: IEEE Transactions on Signal Processing Society. Volume 20., IEEE (June 2011) 1709 - 1724.
[33] Tsai, D.M., Lai, S.C.: Independent component analysis-based background subtraction for indoor surveillance. In: IEEE Transactions on Image Processing. Volume 18., IEEE (Jan. 2009) 158 - 167.
[34] Intachak, T., Kaewapichai, W.: Real-time illumination feedback system for adaptive background subtraction working in traffic video monitoring. In: IEEE Transactions on Intelligent Signal Processing and Communications Systems, IEEE (2011) 1 - 5.
[35] Zhang, J., Ma, D.: Nonlinear prediction for Gaussian mixture image models. In: IEEE Transactions on Image Processing. Volume 13., IEEE (June 2004) 836 - 847.
[36] Hammond, D.K., Simoncelli, E.P.: Image modeling and denoising with
orientation-adapted Gaussian scale mixtures. In: IEEE Transactions on Image
Processing. Volume 17., IEEE (Nov. 2008) 2089 – 2101.
[37] D. Mukherjee, Q.M.J.W., Nguyen, T.M.: Multiresolution based Gaussian mixture model for background suppression. In: IEEE Transactions on Image Processing. Volume 22., IEEE (Dev. 2013) 5022 - 5035.
[38] Lee, D., Kim, J.: Object detection using directional integral image. In: Ubiquitous Robots and Ambient Intelligence, 2013 10th International Conference on, URAI (2013) 285 - 286.
[39] Y. D. Hoseini, S.M.S., Sadri, S.: A novel cmos image sensor for high speed parallel integral image computation. In: 2013 21st Iranian Conference on Electrical Engineering. Volume 1., ICEE (2013) 1 - 6.
[40] Cheng, W.C., Jhan, D.M.: A cascade classifier using adaboost algorithm and support vector machine for pedestrian detection. In: IEEE Transactions on Systems, Man, and Cybernetics, IEEE (2011) 1430 - 1435.
[41] Z. Zhang, B. Zhang, K.Z., Yang, W.: A network shaped cascade classifier based on potential functions for pedestrian detection. In: IEEE Transactions on Guidance, Navigation and Control Conference, IEEE (2014) 2321 - 2325.
[42] L. Yang, P. Luo, C.C.L., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: International Conference on Computer Vision and Pattern Recogntion, CVPR (2015) 3973 - 3981.
[43] C. Luo, S. I. McClean, G.P., Teacy, L.: Uav position estimation and collision avoidance using the extended kalman filter. In: International Conference on Computer Vision and Pattern Recognition. Volume 62., IEEE (July 2013) 2749 - 2749.