(3.236.214.19) 您好!臺灣時間:2021/05/09 21:33
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:蘇及第
研究生(外文):SU, JI-DI
論文名稱:基於PHF與MHOG混合特徵於行人檢測
論文名稱(外文):Pedestrian Detection Based on PHF and MHOG Mixed Feature.
指導教授:許巍嚴
指導教授(外文):Hsu, Wei-Yen
口試委員:劉建財劉偉名
口試委員(外文):LIU, CHIEN-TSAILIU, WEI-MIN
口試日期:2017-06-28
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊管理系研究所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:中文
論文頁數:44
中文關鍵詞:行人檢測特徵萃取MHOGSVM部件遮蔽問題
外文關鍵詞:pedestrian detectionfeature extractionMHOGSVMpartial occlusion problem
相關次數:
  • 被引用被引用:0
  • 點閱點閱:190
  • 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:5
  • 收藏至我的研究室書目清單書目收藏:0
本研究提出一改進方法來解決單張影像行人檢測中,人潮擁擠或行人部分被遮蔽的情況。首先我們選用了兩種特徵萃取方法分別地使用於行人不同的部位,一是基於Gabor濾波前處理的MHOG特徵,此特徵萃取方法是延伸行人檢測的經典方法HOG,可有效增加此特徵對於行人上半身的描述;另一個是基於把原有的Haar-like特徵修改成適合行人部件使用的PHF特徵,因行走中的手臂與腿時常處於歪斜的狀態。兩種特徵萃取方法皆有使用積分圖加速法有效地加速運算。
得到行人特徵後,藉由兩層的SVM分類器來處理行人部分被遮蔽的情況,第一層SVM用來判斷各個部件是否被遮蔽,接著使用未遮蔽的部件所得到的機率分數作為對應的第二層SVM分類器的特徵值,即可判斷該檢測窗口是否有行人。最後使用ROC曲線及混淆矩陣兩個評估方式進行實驗,結果證明本研究提出之方法能有效處理人潮擁擠或行人部分被遮蔽的情況,並可以在不同的場景中成功地實現行人檢測。

Pedestrian detection is a considerable practical interest. The study proposes an improved methodology to solve crowded scenes or partial occlusion problem in pedestrian detection. First, the study used two feature extraction methods in different parts of pedestrians. One feature descriptors is MHOG based on Gabor filter and the other is PHF. They modified from HOG and Haar-like features descriptors and are adaptive for the shape of human upper body and human limbs, respectively. Both feature extraction methods use the integral image to effectively speed up the step. Second, the two-layer SVM classifier is used to deal with the partial occlusion problem. The first layer SVM can be used to determine that which human part is occluded, and then let the probability scores that obtained by the unoccluded parts as the feature value of the second SVM classifier. Through this processing, we can determine whether the detection window contains pedestrians. The experiment was tested by the ROC curve and the confusion matrix and the experiment result demonstrate that the method for pedestrian detection can effectively solve crowded crowd or partial occlusion problem, and it can be achieved in different outdoor environments.
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與研究問題 4
1.3 論文貢獻 6
1.4 論文架構 6
第二章 文獻探討 7
2.1 基層特徵 8
2.2 基於學習後得到之影像特徵 9
2.3 混合特徵 10
第三章 材料與研究方法 14
3.1 實驗材料及樣本擷取 14
3.2 方法流程圖 15
3.3 Gabor濾波前處理及基於多尺度區塊的方向梯度直方圖 16
3.3.1 影像前處理-Gamma校正法與Gabor濾波 17
3.3.2 計算影像的梯度值 18
3.3.3 設定網格及區塊 19
3.3.4 積分圖加速法與MHOG改進之步驟 20
3.3.5 局部的L2-norm正規化 21
3.4 基於Haar-Like的平行四邊形特徵 22
3.4.1 影像前處理 22
3.4.2 PHF主要想法及積分圖加速法 22
3.4.3 模板設定與應用積分圖計算特徵值之方法 24
3.5 主成份分析 26
3.6 利用兩層的支持向量機及組合部件模型處理遮蔽問題 27
3.7 評估指標 30
第四章 實驗結果與討論 32
4.1 實驗環境 32
4.2 Gabor濾波前處理評估 32
4.3 第一層SVM分類器評估 33
4.4 實驗結果 34
第五章 結論與未來展望 38
5.1 本研究之結論 38
5.2 未來展望 38
參考文獻 39


英文文獻
Agarwal, S., Awan, A., & Roth, D. (2004). Learning to detect objects in images via a sparse, part-based representation. IEEE transactions on pattern analysis and machine intelligence, 26(11), 1475-1490.
Andriluka, M., Schnitzspan, P., Meyer, J., Kohlbrecher, S., Petersen, K., Von Stryk, O & Schiele, B. (2010, October). Vision based victim detection from unmanned aerial vehicles. In Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on (pp. 1740-1747). IEEE.
Ahmadipour, Z., Afrasiabi, M., & Khotanlou, H. (2016, September). Multiple human detection in images based on differential evolution and HOG-LBP. In Information and Knowledge Technology (IKT), 2016 Eighth International Conference on (pp. 61-65). IEEE.
Chao, W. L. (2010). Gabor wavelet transform and its application. R98942073 (TFA&WT final project).
Curio, C., Edelbrunner, J., Kalinke, T., Tzomakas, C., & Von Seelen, W. (2000). Walking pedestrian recognition. IEEE Transactions on intelligent transportation systems, 1(3), 155-163.
Conde, C., Moctezuma, D., De Diego, I. M., & Cabello, E. (2013). HoGG: Gabor and HoG-based human detection for surveillance in non-controlled environments. Neurocomputing, 100, 19-30.
Dalal, N., & Triggs, B. (2005, June). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Vol. 1, pp. 886-893). IEEE.
Dalal, N., Triggs, B., & Schmid, C. (2006, May). Human detection using oriented histograms of flow and appearance. In European conference on computer vision (pp. 428-441). Springer Berlin Heidelberg.
Dollár, P., Tu, Z., Perona, P., & Belongie, S. (2009). Integral channel features.
Dollár, P., Wojek, C., Schiele, B., & Perona, P. (2009, June). Pedestrian detection: A benchmark. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 304-311). IEEE.
Dollar, P., Wojek, C., Schiele, B., & Perona, P. (2012). Pedestrian detection: An evaluation of the state of the art. IEEE transactions on pattern analysis and machine intelligence, 34(4), 743-761.
Gao, W., Ai, H., & Lao, S. (2009, June). Adaptive contour features in oriented granular space for human detection and segmentation. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 1786-1793). IEEE.
Gavrila, D. M., Giebel, J., & Munder, S. (2004, June). Vision-based pedestrian detection: The protector system. In Intelligent Vehicles Symposium, 2004 IEEE(pp. 13-18). IEEE.
Geronimo, D., Lopez, A. M., Sappa, A. D., & Graf, T. (2010). Survey of pedestrian detection for advanced driver assistance systems. IEEE transactions on pattern analysis and machine intelligence, 32(7), 1239-1258.
Hoang, V. D., Le, M. H., & Jo, K. H. (2014). Hybrid cascade boosting machine using variant scale blocks based HOG features for pedestrian detection. Neurocomputing, 135, 357-366.
Hoang, V. D., & Jo, K. H. (2016). Joint components based pedestrian detection in crowded scenes using extended feature descriptors. Neurocomputing, 188, 139-150.
Liu, Y., Shan, S., Zhang, W., Chen, X., & Gao, W. (2009, June). Granularity-tunable gradients partition (GGP) descriptors for human detection. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 1255-1262). IEEE.
Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 815-823).
Schwartz, W. R., Kembhavi, A., Harwood, D., & Davis, L. S. (2009, September). Human detection using partial least squares analysis. In Computer vision, 2009 IEEE 12th international conference on (pp. 24-31). IEEE.
Tuzel, O., Porikli, F., & Meer, P. (2008). Pedestrian detection via classification on riemannian manifolds. IEEE transactions on pattern analysis and machine intelligence, 30(10), 1713-1727.
Viola, P., & Jones, M. J. (2004). Robust real-time face detection. International journal of computer vision, 57(2), 137-154.
Viola, P., Jones, M. J., & Snow, D. (2003, October). Detecting pedestrians using patterns of motion and appearance. In null (p. 734). IEEE.
Walk, S., Majer, N., Schindler, K., & Schiele, B. (2010, June). New features and insights for pedestrian detection. In Computer vision and pattern recognition (CVPR), 2010 IEEE conference on (pp. 1030-1037). IEEE.
Wang, X., Han, T. X., & Yan, S. (2009, September). An HOG-LBP human detector with partial occlusion handling. In Computer Vision, 2009 IEEE 12th International Conference on (pp. 32-39). IEEE.
Watanabe, T., Ito, S., & Yokoi, K. (2009). Co-occurrence histograms of oriented gradients for pedestrian detection. Advances in Image and Video Technology, 37-47.
Wojek, C., & Schiele, B. (2008). A performance evaluation of single and multi-feature people detection. Pattern Recognition, 82-91.
Wu, B., & Nevatia, R. (2005, October). Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on(Vol. 1, pp. 90-97). IEEE.
Wu, B., & Nevatia, R. (2007). Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. International Journal of Computer Vision, 75(2), 247-266.
Wu, J., & Rehg, J. M. (2011). CENTRIST: A visual descriptor for scene categorization. IEEE transactions on pattern analysis and machine intelligence, 33(8), 1489-1501.
Wu, J., Geyer, C., & Rehg, J. M. (2011, May). Real-time human detection using contour cues. In Robotics and Automation (ICRA), 2011 IEEE International Conference on (pp. 860-867). IEEE.
Wojek, C., Walk, S., & Schiele, B. (2009, June). Multi-cue onboard pedestrian detection. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on (pp. 794-801). IEEE.
Xia, L., Chen, C. C., & Aggarwal, J. K. (2011, June). Human detection using depth information by kinect. In Computer Vision and Pattern Recognition Workshops (CVPRW), 2011 IEEE Computer Society Conference on (pp. 15-22). IEEE.
Yuan, J., Liu, Z., & Wu, Y. (2011). Discriminative video pattern search for efficient action detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(9), 1728-1743.
Zhu, Q., Yeh, M. C., Cheng, K. T., & Avidan, S. (2006). Fast human detection using a cascade of histograms of oriented gradients. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on (Vol. 2, pp. 1491-1498). IEEE.

中文文獻
黃亞勤,民100。基於視線跟踪技術的眼控鼠標研究與實現[D]。西華大學博士論文。
賈慧星、章毓晉,民96。車輛輔助駕駛系統中基於計算機視覺的行人檢測研究綜述。自動化學報,33(1),84-90。

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
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