( 您好!臺灣時間:2021/03/07 01:52
字體大小: 字級放大   字級縮小   預設字形  


研究生(外文):Han-Hsuan Chen
論文名稱(外文):Integrating Appearance and Edge Features for on-road Bicycle and Motorcycle Detection in the Nighttime
外文關鍵詞:On-road Bicycle and Motorcycle DetectionCyclist DetectionFeature IntegrationSpatial RelationshipNighttime
  • 被引用被引用:0
  • 點閱點閱:100
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0

It is critical to detect bicycles and motorcycles on the road because collision of autos with those light vehicles becomes major cause of on-road accidents nowadays especially in the nighttime. Therefore, a vision-based nighttime on-road bicycle and motorcycle detection method relying on use of a camera and near-infrared lighting mounted on an auto vehicle is proposed in this paper. Generally, the objects will reflect near-infrared lighting. However, some components of the bicycles and the motorcycles absorb most infrared lighting and thus make the bicycles and motorcycles hardly recognizable. To cope with this problem, the aforementioned detection method is part-based, which combines the two kinds of features related to the characteristics of bicycles and motorcycles. Also, the information about the geometric relation among all the parts and the object centroid is learned off-line. Due to high computation load, selection of effective parts with better geometric information is imperative for detection.
On the other hand, cyclist is also an important object to detect. We adopt a two-fold strategies, where one detects the cyclist by a holistic-based detector, and second is to establish a spatial relationship model between the cyclist and his/her riding vehicle off line. In particular, the second strategy filters out the wrong detection. The performance of spatial relationship validation depends on the tightness of bounding box. Hence, we propose a bounding box refinement to refine the detection results. To validate the proposed results, several experiments are conducted to show that the developed system is reliable in detecting bicycles and motorcycles on the road in the nighttime.

口試委員會審定書 #
誌謝 i
中文摘要 ii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Challenges 3
1.3 Related Work 6
1.4 Contributions 9
1.5 Thesis Organization 10
Chapter 2 Preliminaries 12
2.1 Histogram of Oriented Gradient (HOG) 12
2.1.1 HOG Descriptor 12
2.1.2 HOG Feature Encoding 14
2.2 Support Vector Machine (SVM) 14
2.2.1 Objective of SVM 15
2.2.2 Linear SVM 16
2.2.3 Soft Margin 18
2.3 System Overview 20
Chapter 3 Near-Infrared Part-based Classifier Construction 22
3.1 Part Extraction 23
3.1.1 Edge-based Feature Part Extraction 23
3.1.2 Appearance-based Feature Part Extraction 24
3.2 Part Clustering 26
3.2.1 Similarity Measure for Edge-Based Feature 26
3.2.2 Similarity Measure for Appearance-Based Feature 27
3.3 Exploiting Relationship among Parts and Object Centroid 30
3.3.1 Position Relation Model Construction 30
3.3.2 Centroid Information Clustering 32
3.4 Part Selection 33
Chapter 4 Near-Infrared based Nighttime Bicycle and Motorcycle Detection 36
4.1 Overview of Detection System 37
4.2 Preprocessing 38
4.3 Bicycle and Motorcycle Detection 40
4.3.1 Part Detection and Centroid Voting 40
4.3.2 Centroid Finding by Analyzing the Voting Space 41
4.4 Bounding Box Refinement 42
4.4.1 Bounding Box Extending 42
4.4.2 Bounding Box Mixing 43
4.5 Cyclist Detection with Spatial Relationship Model 44
4.5.1 The observation of Cyclist and Vehicle 44
4.5.2 Spatial Relationship Model 45
4.5.3 Cyclist Detection Refinement with Spatial Relationship Model 48
Chapter 5 Experiments 49
5.1 Environment Setting and Performance Measurement 49
5.1.1 Environment Setting 49
5.1.2 Performance Measurement 50
5.2 Training Dataset 52
5.3 Experiment Results of Caltech Motorbike Dataset 53
5.4 Comparison of the Part-based Feature Integrating 55
5.5 Experiment Results of nighttime on-road Bicycle/Motorcycle and Cyclist Detection 58
5.5.1 Performance of nighttime on-road Bicycle/Motorcycle Detection 58
5.5.2 Performance of nighttime Cyclist Detection 60
Chapter 6 Conclusion 63
References 65

[1]歷年道路交通事故件數,民國 92年-101年. Available: http://talas-pub.iot.gov.tw/TBfiles/Download/101_A_table1.pdf
[2]歷年道路交通事故死亡人數、受傷人數、死亡率及受傷率(依人口數、領有駕駛執照人數、機動車輛登記數、延車公里計算),民國92年-101年. Available: http://talas-pub.iot.gov.tw/TBfiles/Download/101_A_table2.pdf
[3]102年 道路交通事故(A1+A2類)─車種別. Available: http://www.npa.gov.tw/NPAGip/wSite/ct?xItem=69474&;ctNode=12595&;mp=1
[4]N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in International IEEE Conference on Computer Vision and Pattern Recognition, 2005, pp. 886-893.
[5]Q. Zhu, M.-C. Yeh, K.-T. Cheng, and S. Avidan, "Fast human detection using a cascade of histograms of oriented gradients," in International IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, pp. 1491-1498.
[6]P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, "Object detection with discriminatively trained part-based models," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 1627-1645, 2010.
[7]B. Leibe, A. Leonardis, and B. Schiele, "Robust object detection with interleaved categorization and segmentation," International journal of computer vision, vol. 77, pp. 259-289, 2008.
[8]A. Opelt, A. Pinz, and A. Zisserman, "Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection," International Journal of Computer Vision, vol. 80, pp. 16-44, 2008.
[9]L. Bourdev and J. Malik, "Poselets: Body part detectors trained using 3d human pose annotations," in International IEEE Conference on Computer Vision, 2009, pp. 1365-1372.
[10]L. Bourdev, S. Maji, T. Brox, and J. Malik, "Detecting people using mutually consistent poselet activations," presented at the European Conference on Computer Vision, 2010.
[11]G. Gkioxari, B. Hariharan, R. Girshick, and J. Malik, "Using k-poselets for detecting people and localizing their keypoints," presented at the International IEEE Conference on Computer Vision and Pattern Recognition 2014.
[12]Y. Fujimoto and J.-i. Hayashi, "A method for bicycle detection using ellipse approximation," in Korea-Japan Joint Workshop on Frontiers of Computer Vision, 2013, pp. 254-257.
[13]T. Ardeshiri, F. Larsson, F. Gustafsson, T. B. Schon, and M. Felsberg, "Bicycle tracking using ellipse extraction," in International IEEE Conference on Information Fusion, 2011, pp. 1-8.
[14]S. Messelodi, C. M. Modena, and G. Cattoni, "Vision-based bicycle/motorcycle classification," Pattern Recognition Letters, vol. 28, pp. 1719-1726, 2007.
[15]C.-C. Chiu, M.-Y. Ku, and H.-T. Chen, "Motorcycle detection and tracking system with occlusion segmentation," in IEEE Eighth International Workshop on Image Analysis for Multimedia Interactive Services, 2007, pp. 32-32.
[16]J. Yan, Q. Ling, Y. Zhang, F. Li, and F. Zhao, "An Adaptive Bicycle Detection Algorithm Based on Multi-Gaussian Models," Journal of Computational Information Systems, vol. 9, pp. 10075-10083, 2013.
[17]H. Cho, P. E. Rybski, and W. Zhang, "Vision-based bicycle detection and tracking using a deformable part model and an EKF algorithm," in International IEEE Conference on Intelligent Transportation Systems, 2010, pp. 1875-1880.
[18]T. Li, X. Cao, and Y. Xu, "An effective crossing cyclist detection on a moving vehicle," in the 8th World Congress on Intelligent Control and Automation, 2010, pp. 368-372.
[19]H. Jung, J. K. Tan, S. Ishikawa, and T. Morie, "Applying HOG feature to the detection and tracking of a human on a bicycle," in International IEEE Conference on Control, Automation and Systems, 2011, pp. 1740-1743.
[20]H. Jung, Y. Ehara, J. K. Tan, H. Kim, and S. Ishikawa, "Applying MSC-HOG Feature to the Detection of a Human on a Bicycle," in International IEEE Conference on Control, Automation and Systems, 2012, pp. 514-517.
[21]C.-E. Wu, Y.-M. Chan, L.-C. Fu, P.-Y. Hsiao, S.-S. Huang, H.-H. Chen, et al., "Combining Multiple Complementary Features for Pedestrian and Motorbike," presented at the International IEEE Conference on Intelligent Transportation Systems, 2013.
[22]K. Takahashi, Y. Kuriya, and T. Morie, "Bicycle detection using pedaling movement by spatiotemporal Gabor filtering," International Journal of Innovative Computing, Information and Control, vol. 8, 2012.
[23]G. Duan, H. Ai, and S. Lao, "A structural filter approach to human detection," in European Conference on Computer Vision, ed: Springer, 2010, pp. 238-251.
[24]D. G. Lowe, "Object recognition from local scale-invariant features," in The proceedings of the seventh IEEE international conference on Computer vision, 1999, pp. 1150-1157.
[25]V. Vapnik, The nature of statistical learning theory: Springer-Verlag, 1995.
[26]C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, pp. 273-297, 1995.
[27]J. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 679-698, 1986.
[28]G. Borgefors, "Hierarchical chamfer matching: A parametric edge matching algorithm," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, pp. 849-865, 1988.
[29]Y.-S. Lee, Y.-M. Chan, L.-C. Fu, P.-Y. Hsiao, L.-A. Chuang, Y.-H. Chen, et al., "Nighttime pedestrian detection by selecting strong near-infrared parts and enhanced spatially local model," in International IEEE Conference on Intelligent Transportation Systems, 2012, pp. 1765-1770.

第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔