(3.236.222.124) 您好!臺灣時間:2021/05/14 16:25
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:謝一鳴
研究生(外文):Yi-ming Hsieh
論文名稱:一個運用視訊中時間與空間資訊之攝影機關係建立方法的研究
論文名稱(外文):A Study of Camera Relationship Establishment Method Based on Temporal and Spatial Information in Video Clips
指導教授:廖珗洲廖珗洲引用關係
指導教授(外文):Hsien-Chou Liao
學位類別:碩士
校院名稱:朝陽科技大學
系所名稱:資訊工程系碩士班
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:96
語文別:中文
論文頁數:45
中文關鍵詞:多攝影機環境監視系統移動物體偵測
外文關鍵詞:surveillance systemmulti-cameramoving object detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:164
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:2
近年來攝影機普遍應用於日常生活做為監視錄影的設備,透過即時影像
的分析,可以針對移動物體進行偵測、分類或辨識等功能。除了單一攝影
機的分析之外,多攝影機的協調運作也是近年來許多研究的重點,藉此提
供更多的智慧型服務。多攝影機的協調運作必須事先定義攝影機在空間位
置上的關係,如此當某個移動物體離開某一台攝影機的監視範圍時,透過
關係就可以預測下一個可能出現該物體的攝影機。為了簡化攝影機空間關
係上的建立,在本論文中提出一個能夠依據錄製影像的內容來自動化建立
攝影機關係的方法,此方法主要以影像上移動物體的資訊為主,透過統計
分析來建立正確的空間關係。而實際針對一個具有13 台攝影機之社區監視
系統的錄製影像進行實驗分析,其結果顯示所提出方法確實能夠自動地建
立出攝影機的空間關係。
With video surveillance cameras being widely used in daily life as the
equipment for surveillance recording in recent years, analyzing real-time video
clip offers the function of detecting, sorting or identifying moving objects,
which encompasses more than analyzing a single surveillance camera, but
coordinating the operations of multiple cameras has become a focal point in
many recent studies, through which to offer more intelligent services.
Synchronizing the operations of multiple surveillance cameras requires defining
the cameras’ spatial relationship first, which, when a moving object leaves the
filming range of a certain camera, can be used to predict which camera that the
moving object is likely to appear. To simplify establishing the camera spatial
relationship, our method primarily operates on the information of moving
objects in the image to establish accurate spatial relationship using statistical
relationship, and moves to analyze the recorded image of an actual community
surveillance system comparing of 13 surveillance cameras, where the
experiment findings reveal that the method can indeed establish camera spatial
relationship effectively.
中文摘要 ...............................I
Abstract...............................II
誌謝..................................III
第一章 簡介.............................1
第二章 相關研究.........................7
第三章 方法............................14
3.1 移動物體的偵測.................... 15
3.2 攝影機二元關係的建立.............. 20
3.3 攝影機三元關係的建立.............. 26
3.4 關係結合.......................... 27
第四章 實驗............................31
第五章 結論和未來研究..................42
參考文獻...............................44

表目錄
表1:物體移動方向的判斷結果...................................................................... 21
表2:時間間隔1 到5 秒所得到Binary Camera Relationship 的範例.......... 24
表3:時間間隔1 到5 秒所得到camera pair 的統計結果............................. 25
表4:一個Binary Camera Relationship 所記錄的資訊的範例...................... 25
表5:每台攝影機的前後關係統計表.............................................................. 26
表6:三元關係的範例...................................................................................... 27
表7:初步組合的結果...................................................................................... 28
表8:組合後的關係.......................................................................................... 30
表9:方向標記的格式...................................................................................... 30
表10:最後的結果............................................................................................ 30
表11:尖峰時段下相鄰攝影機的時間差距.................................................... 40
表12:離峰時段下相鄰攝影機的時間差距.................................................... 40

圖目錄
圖1:交通意外預測的(a)背景相減與(b) activity patterns................................ 1
圖2:車輛分類的(a)建立車道分隔線與(b)實驗結果....................................... 2
圖3:道路監視與車流量分析的(a)背景相減與(b) Region growing................ 2
圖4:物體追蹤的(a)物體空間分佈圖與(b)實驗畫面....................................... 3
圖5:一個攝影機的空間關係範例.................................................................... 5
圖6:一個監視系統的範例................................................................................ 6
圖7:不同角度下的攝影機所拍攝到的畫面.................................................... 8
圖8:兩個不同視角之間的協調........................................................................ 8
圖9:視角協調的實驗結果................................................................................ 9
圖10:攝影機之間FOV line (Field Of View) 的協調................................... 10
圖11:Knight 系統架構圖................................................................................ 11
圖12:Knight 系統中的物體移動路徑預測與追蹤........................................ 12
圖13:雙目鏡頭移動人物偵測的(a)流程圖(b)辨識重疊的階層.................. 12
圖14:方法的運作流程.................................................................................... 15
圖15:Video Clip 的切割與分群示意圖......................................................... 16
圖16:移動物體偵測的步驟截圖.................................................................... 18
圖17:移動物體偵測的範例............................................................................ 19
圖18:用來記錄視訊檔案以及移動物體資訊的XML 檔案範例................. 20
圖19:兩台攝影機空間上的監視區域............................................................ 23
圖20:社區監視系統的攝影機架設位置圖.................................................... 32
圖21:社區監視系統的硬體與軟體................................................................ 32
圖22:關係建立工具的執行畫面.................................................................... 34
圖23:關係建立工具的操作步驟.................................................................... 35
圖24:有岔路情形下尖峰時段中各時間點的(a)正確率與(b)錯誤率.......... 37
圖25:有岔路情形下離峰時段中各時間點的(a)正確率與(b)錯誤率.......... 38
圖26:無岔路情形下尖峰時段中各時間點的(a)正確率與(b)錯誤率. ......... 39
圖27:無岔路情形下離峰時段中各時間點的(a)正確率與(b)錯誤率. ......... 39
[1] W. M. Hu, X. J. Xiao, D. Xie, and T. N. Tan, “Traffic Accident Prediction
Using Vehicle Tracking and Trajectory Analysis,” in Intelligent
Transportation Systems, Vol.1, 2003, pp.220-225.
[2] J. W. Hsieh, S. H. Yu, Y. S. Chen, and W. F. Hu, “Automatic Traffic
Surveillance System for Vehicle Tracking and Classification,” in Intelligent
Transportation Systems, Vol.7, June 2006, pp.175-187.
[3] Z. Jinglei and L. Zhengguang, “A Vision-Based Road Surveillance System
Using Improved Background Subtraction and Region Growing Approach,”
in Eighth ACIS International Conference on Software Engineering,
Artificial Intelligence, Networking, and Parallel/Distributed Computing, Vol.
3, August 2007, pp.819-822.
[4] J. X. Wang, G. Bebis, and R. Miller, “Robust Video-Based Surveillance by
Integrating Target Detection with Tracking,” in Proceedings of the 2006
Conference on Computer Vision and Pattern Recognition Workshop, June
2006, pp.137.
[5] J. Black and T. Ellis, “Multi camera image tracking,” in Image and Vision
Computing, June 2005, pp. 1256-1267.
[6] O. Javed, Z. Rasheed, O. Alatas, and M. Shah, “KNIGHT: A Real Time
Surveillance System For Multiple Overlapping And Non-Overlapping
Cameras,” in ICME 2003, 2003, pp.649-652.
45
[7] M. Shah, O. Javed, and K. Shafique, “Automated Visual Surveillance in
Realistic Scenarios,” in Multimedia, IEEE, Vol. 14, Jan.-March 2007,
pp.30-39.
[8] Y. Ran and Q.Zheng, “Multi Moving People Detection From Binocular
Sequences,” in ICME 2003, July 2003, pp. 297-300.
[9] G. Jing, D. Rajin and C.E. Siong, “Motion Detection with Adaptive
Background And Dynamic Thresholds,” in Information, Communications
and Signal Processing, Dec. 2005, pp. 41 -45.
[10] A. Colombari, A. Fusiello, and V. Murino, “Segmentation and Tracking of
Multiple Video Objects”, Pattern Recognition, Vol 40, Issue 4, Apr. 2007,
pp. 1307-1317.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top