臺灣博碩士論文加值系統

本篇論文針對行人辨識提出一個多特徵智慧型行人辨識系統，以達到提高行人辨識率的目的。此系統可主動在串列影像中找出移動中的物體，接著擷取物體的多種特徵，包刮梯度直方圖、Haar-like特徵、全域平均值、梯度影像，最後判斷此物體是否為行人。在本篇論文中採用雙層的類神經網路，包刮初級層與次級層，其中初級層類神經網路先針對單一特徵進行訓練，接著再將初級層匯集至次級層進行多特徵的統合訓練，此雙層架構的設計除了可提高行人辨識率外，亦嘗試減少訓練資料的使用，由實驗結果可知此雙層架構確實可提高行人辨識率，並且在較少的訓練資料下得到相近的準確率。

The thesis proposes an intelligent pedestrian recognition system to find out pedestrians from a sequence of images based on multi-features, including Histogram of Gradient, Haar-like feature, Global average and Gradient image. A two-staged neural network is adopted for the recognition system, which executes the training of single feature in the primary stage and then the training of multi-features in the secondary stage. The use of the two-staged neural network is not only to increase the accuracy rate but also to reduce the training data. From the experiment results, the two-staged neural network indeed improves the recognition performance and most importantly, it is workable in the case that a smaller amount of training data is used.

Contents
Chinese Abstract.......................................................................................i
English Abstract....................................................................................ii
Acknowledgement iii
Contents iv
List of Figures vi
List of Tables ix

Chapter 1 Introduction 1
1.1 Preliminary and thesis organization 1
1.2 System overview 2
Chapter 2 Related Work 5
2.1 Foreground segmentation 5
2.2 shadow removal 6
2.3 Morphology operation 6
2.4 Neural network 8
2.4.1 Intorduction to ANNs 8
2.4.2 Back-Propagation Network 11
Chapter 3 Pre-process and detect algorithm of pedestrian detection 15
3.1 Foreground segmentation 15
3.2 Shadow removal 17
3.3 Morphology operation 18
3.4 Histogram projection 21
3.5 Feature extraction 23
3.6 Detect Algorithm 28
Chapter 4 Experimental Results 39
4.1 Moving object detection 39
4.2 Pedestrian recognition 42
Chapter 5 Conclusions and Future Works 51
Reference 54

[1] L. Zhao and C. Thorpe. “Stereo- and neural network-based pedestrian detection.” IEEE Trans. on ITS, 1(3), 2000.
[2] Y.-T. Chen and C.-S. Chen. “Fast human detection using a novel boosted cascading structure with meta stages.” IEEE TIP, 17(8):1452–1464, 2008.
[3] J. Wang et al. “An Adjacent Multiple Pedestrians Detection BASED on ART2 Neural Network.” ISNN 2006, LNCS 3972, pp. 244-252, 2006
[4] D. Duque, H. Santos, and P. Cortez. “Moving Object Detection Unaffected by Cast Shadows, Highlights and Ghosts.” IEEE International Conference image processing, 2005
[5] Li-Qun Xu, Jose Luis Landabaso, Montse Pardas, “Shadow Removal with Blob-based Morphological Reconstruction for Error Correction” IEEE ICASSP. vol. 4, No. 5, 2005.
[6] Heikkila, J. and O. Silven, “A real-time system for monitoring of cyclists and pedestrians,” IEEE Workshop on Visual Surveillance, Fort Collins, CO, Jun.26, 1999, pp.74-81.
[7] Cedras, C. and M. Shah, “Motion-based recognition: a survey,” Image and Vision Computing, vol.13, No.2, pp.129-155, March 1995.
[8] A. Neri, S. Colonnese, G. Russo, and P. Talone, “Automatic moving object and background separation,” Signal Process. 66, 219-232(1998).
[9] S. Chien, Y. Huang, and L. Chen, “Predictive watershed: a fast watershed algorithm for video segmentation,” IEEE Trans. Circuits Syst. Video Technol. 13(5), 453-461 (2003)
[10] S. Chien, S. Ma, and L. Chen, “Efficient moving object segmentation algorithm using background registration technique,” IEEE Trans. Circuits Syst. Video Trchnol. 12(7), 577-586 (2002).
[11] Collins, R. T., A. J. Lipton, and T. Kanade, “A System for Video Surveillance and Monitoring”, Technical Report, CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University, May 2000.
[12] Kim et al., “Real-time disparity estimation using foreground segmentation for stereo sequences.” Optical Engineering 45(3), 037402 (2006)
[13] R.Cucchiara, C. Grana, M. Piccardi, A. Prati, and S.Sirotti, “Improving shadow suppression in moving object detection with HSV color information.” IEEE Int’l Conference on Intelligent Transportation Systems, Aug. 2001,pp.334-339.
[14] P. Kumar, K. Sengupta, and S. Ranganath, ”Real time detection and recognition of human profiles using inexpensive desktop cameras.” in Proc. ICPR’00, pp. 1096-1099, IEEE Computer Soc., (2000).
[15] A. Shashua, Y. Gdalyahu, and G. Hayun, “Pedestrian detection for driving assistance systems: Single-frame classification and system level performance.” in Proc. IEEE Intell. Vehicles Symp. Jun. 2004, pp. 1-6.
[16] N. Dalal and B. Triggs. “Histograms of oriented gradients for human detection.” IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn., 2005.
[17] Q. Zhu, C. Yeh, T. Cheng, and S. Avidan, “Fast human detection using a cascade of histograms of oriented gradients,” IEEE Conf. Comput. Vis. Pattern Recog., Jun. 2006, pp. 1491-1498
[18] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” IEEE Proc. Int. Conf. Computer Vision and Pattern Recognition, 2001, vol. 1, pp. 511-518.
[19] A. Khashman., “Intelligent Face Recognition: Local Versus Global Pattern Averaging.” Berlin Springer, 2006.
[20] S. Munder, D.M. Gavrila: An experimental study on pedestrian classification. IEEE Trans. Pattern Anal. Mach. Intell. 28(11), 1863-1868 (2006)
[21] http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/
[22] D.J. Hand, R.J. Till. “A simple generalization of the area under the ROC curve to multiple class classification problems.” Machine Learning, 45, 171-186. (2001).