跳到主要內容

臺灣博碩士論文加值系統

(44.200.86.95) 您好!臺灣時間:2024/05/20 07:36
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

我願授權國圖
: 
twitterline
研究生:蕭文淵
研究生(外文):Hsiao, Wen-Yuan
論文名稱:整合高速雲台之自動入侵物偵測技術研究整合高速雲台之自動入侵物偵測技術研究整合高速雲台之自動入侵物偵測技術
指導教授:蘇英俊瞿忠正瞿忠正引用關係
指導教授(外文):Su, Ing-JiunnQu, Zhong-Zheng
學位類別:碩士
校院名稱:國防大學理工學院
系所名稱:電子工程碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2008
畢業學年度:97
語文別:中文
外文關鍵詞:accident detectionhigh resolution imageintelligent surveillance system
相關次數:
  • 被引用被引用:1
  • 點閱點閱:263
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
近年來在現行的道路、重要路口架設監控錄影系統已非常普及,固定式攝影機將可在同時間拍攝與追蹤多個物件,但由於固定式攝影機不具有放大與追蹤的功能,所以將無法針對特定目標物進行追蹤與取得高解析的影像。因此便突顯出PTZ(Pan, Tilt, Zoom)攝影機在影像監控系統中的重要性。
有鑑於此,本研究中提出了一套結合固定式攝影機和PTZ攝影機的新式智慧型監控系統,固定式攝影機將被用做長時的監控,以確保交通參數資訊不會遺失,不過固定式攝影機卻無法提供移動物件的高解析影像,為了彌補這個缺點,我們利用了PTZ攝影機去做追蹤與放大目標物,以提供更多詳細的資訊,改善固定式攝影機的無法取得高解析影像的缺點。
本研究在智慧型即時影像物件偵測與切割技術下,將可藉由固定式攝影機所拍攝到的影像做移動物件的切割,並將針對所切割出的移動物件做偵測與辨識取得交通資訊,然後再利用PTZ攝影機對此移動物件拍攝高解析的影像。
在智慧型運輸系統應用中,本研究提出了四種事件的偵測,分別為行進中車輛的掉落物偵測、車輛違規逆向行駛、車輛違規路邊停車和事故車輛偵測,當系統針對移動物體偵測到事件產生時,系統將發出警示,並把物件的座標轉換成PTZ攝影機的座標,立即驅動旋轉雲台帶動攝影機,拍攝較近距離的放大清晰影像,以便做後續的交通事件舉發。
Over the past few years, fixed video surveillance systems set on the road sides or intersections are very popular. Although the fixed video cameras can capture and track many targets at the same time. However, without the function of enlargement and rotation, they can not immediately focus and track specified targets in a video field. Thus, PTZ(Pan, Tilt, Zoom) camera become a very important solution for video surveillance systems.
In this study, we propose a new intelligent surveillance system which integrates with a fixed video camera and a PTZ camera. Using the fixed video camera, the proposed system can continually detect traffic information during a long time tracking. In order to compensate the shortcomings of the fixed video camera and to provide high resolution images and more detailed traffic information, a PTZ camera is utilized to track and magnify the specified targets.
This study applies a real-time object detection and a robust image segmentation algorithm to segment the moving objects. After the moving object segmentation, we can detect and identify the moving objects in real time. While the moving objects are segmented by the fixed camera, the parameters of moving objects including the coordinate and speed are estimated for advanced studies. Then, the high resolution image can be obtained by the PTZ camera driven by the coordinate of the moving objects.
For the applications of intelligent transportation systems, the study also proposes accident detections including falling objects detection, vehicles reversion travel, vehicles illegal parking and vehicles accident detection . After the abnormal event detection, the system will send out a warning signal and transmit the object’s coordinate to the PTZ camera. The PTZ camera will be driven to magnify the object image and to provide more detailed traffic information.
誌謝 ii
摘要 iii
ABSTRACT iv
目錄 v
表目錄 viii
圖目錄 ix
1、 緒論 1
1.1 研究動機 1
1.2 論文回顧 2
1.2.1 事件偵測 2
1.2.2 PTZ 5
1.3 論文架構 8
2、 硬體架構 9
2.1 硬體架構 9
2.1.1 攝影機與旋轉雲台 11
2.1.2 RS-232/RS-485轉換器 16
2.1.3 影像擷取卡 17
2.2 系統硬體架設 18
2.3 軟體架構 20
3、 研究方法 21
3.1 背景擷取 22
3.1.1 漸進式背景分類擷取法 22
3.1.2 機率值的調整 25
3.2 入侵物切割法 27
3.2.1 顏色切割 28
3.2.2 連通物件 29
3.2.3 邊緣切割 29
3.2.4 移動物體的重建 30
3.3 背景更新 30
3.4 物件追蹤 31
3.4.1 追蹤參考點 31
3.4.2 車輛顏色資訊 32
3.4.3 車輛外型資訊 32
3.5 事故偵測 33
4、 異常事件偵測 34
4.1 異常事件偵測功能概述 34
4.2 異常事件偵測流程 34
4.2.1 行進中車輛的掉落物偵測 34
4.2.2 車輛違規逆向行駛 37
4.2.3 車輛違規路邊停車 39
4.2.4 事故車輛 41
5、 攝影機校正參數 43
5.1 固定式攝影機參數 43
5.1.1 內部參數 44
5.1.2 外部參數 46
5.1.3 雙攝影座標轉換 48
5.2 可變焦攝影機參數 49
6、 實驗結果 52
6.1 實驗環境 52
6.2 實驗室事件模擬 55
6.2.1 行進中車輛的掉落物偵測 55
6.2.2 車輛違規逆向行駛 59
6.2.3 車輛違規路邊停放 62
6.2.4 事故車輛 67
6.3 台北市運研所實際事件偵測 69
6.3.1 行進中車輛的掉落物偵測 69
6.3.2 車輛違規逆向行駛 71
6.3.3 車輛違規路邊停放 72
7、 結論與未來展望 75
參考文獻 76
自傳 79
[1]Scotti, G., Marcenaro, L., Selvaggi, F., and Regazzoni, C. S., “Dual camera intelligent sensor for high definition 360 degrees surveillance,” IEE Proceedings on Image and Signal Processing, Vol. 152, No. 2, pp. 250-257, April, 2005.
[2]Robert, C., “A System for Video Surveillance and Monitoring,” The Robotics Institiute on Technical Report, CMU-RI-TR-00-12, May, 2000.
[3]Hong, L., Wenkai, P., Hongbin, Z., “Motion detection for multiple moving targets by using an omnidirectional camera,” Vol. 1, pp. 422-426, Oct, 2003.
[4]Chiu, C. C., Wang, C. Y., Ku, M. Y., and Lu, Y. B., “Real Time Recognition and Tracking System of Multiple Vehicles,” Proceedings of IEEE Intelligent Vehicles Symposium (IV2006), Tokyo, Japan, pp. 478-483, June, 2006.
[5]梁立偉,“智慧型即時影像之入侵物件偵測與切割技術”,碩士論文,國防大學中正理工學院資訊科學所,桃園,2007。
[6]洪順煌,“即時影像之交通資訊偵測系統研究”,碩士論文,國防大學中正理工學院電子所,桃園,2007。
[7]楊智壬,“攝影機自動白平衡影響下之入侵物偵測方法”,碩士論文,國防大學理工學院電子所,桃園,2008。
[8]Wren, C. R., Azarbayejani, A., Darrell, T., and Pentland, A. P., “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 780–785, July, 1997.
[9]Haritaoglu, I., Harwood, D., and Davis, L. S., “W4: Real-Time Surveillance of People and Their Activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 8, pp. 809–830, August, 2000.
[10]Ji, X., Wei, Z., and Feng, Y., “Effective Vehicle Detection Technique for Traffic Surveillance Systems,” Visual Communication and Image Representation, Vol. 17, No. 3, pp. 647–658, June, 2006.
[11]Cai, Q. and Aggarwal, J. K., “Tracking Human Motion in Structured Environments Using a Distributed-Camera System,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 12, pp. 1241-1247, November, 1999.
[12]Cucchiara, R., Piccardi, M., and Mello, P., “Image Analysis and Rule-Based Reasoning for A Traffic Monitoring System,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, No. 2, pp. 119-130, June, 2000.
[13]Lai, A. H. S. and Yung, N. H. C., “Vehicle-Type Identification Through Automated Virtual Loop Assignment and Block-Based Direction-Biased Motion Estimation,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, pp. 86-97, June, 2000.
[14]Foresti, G. L., “Object Recognition and Tracking for Remote Video Surveillance,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 7, pp. 1045-1062, October, 1999.
[15]Kamijo, S., Matsushita, Y., Ikeuchi, K., and Sakauchi, M., “Traffic Monitoring and Accident Detection at Intersections,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, No. 2, pp. 108-118, June, 2000.
[16]Kanhere, N. K., Birchfield, S. T., “Real-Time Incremental Segmentation and Tracking of Vehicles at Low Camera Angels Using Stable Feature,” IEEE Transactions on Intelligent Transportation Systems, Vol. 9, No. 1, pp. 148-160, March, 2008.
[17]Lim, D. W., Choi, S. H., Jun, J. S., “Automated detection of all kinds of violations at a street intersection using real time individual vehicle tracking,” IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 126-129, April, 2002.
[18]郭守正,“停車場自動監視系統”,碩士論文,中華大學,新竹,2003。
[19]Chung, Y. C., “Integration of Omnidirectional and Movable Cameras for Indoor Surveillance,” IPPR Conference on Computer Vision, Graphics and Image Processing (CVGIP), pp. 1-7, August, 2004.
[20]Li, T. Y., Wang, C. M., Hung, Y. I., Fan, K. C., “A Visual Monitoring System Using Wide-Angle Cameras and Pan-Tilt Camera,” IPPR Conference on Computer Vision, Graphics and Image Processing (CVGIP), August, 2004.
[21]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,” International Conference on Pattern Recognition, Vol. 2, Barcelona, pp. 434 – 437, September, 2000.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top