跳到主要內容

臺灣博碩士論文加值系統

(3.231.230.177) 您好!臺灣時間:2021/07/28 22:12
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:簡宏恩
研究生(外文):Hung-En Chien
論文名稱:以軟/硬體共設計方式實現即時監控系統
論文名稱(外文):Hardware/Software Co_design For Real-Time Surveillance System
指導教授:許明華許明華引用關係
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電子與資訊工程研究所碩士班
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:2004
畢業學年度:92
語文別:中文
論文頁數:78
中文關鍵詞:物件追蹤監控系統
外文關鍵詞:ARMSOCsurveillance systemobject tracking
相關次數:
  • 被引用被引用:12
  • 點閱點閱:243
  • 評分評分:
  • 下載下載:60
  • 收藏至我的研究室書目清單書目收藏:0
隨著犯罪率的提高,影像監控系統已普遍應用於各種場合,因此,本文提出了一套更具監控效果的即時影像監控系統。
本論文所提出的影像監控系統可分為兩大部分:(1)物件偵測(2)物件追蹤。
在物件偵測部分,我們使用背景相減、低通濾波器(LPF)及連接物標籤化(Labeling)來完成移動物體的偵測。在物體追蹤部分,為了減小搜索面積與時間,我們提出快速演算法來計算搜索範圍(Search Region),同時我們亦設計一信賴值 D 來提升比對移動物體的速度,此信賴值 D 包含了物體移動方向、物體移動位置及物體面積大小這三個變數。為了達到即時監控的效果,我們將整個影像監控系統劃分為硬體與軟體兩部分並實現於SOC發展平台上,經由分析上述演算法之執行時間,我們發現移動物件偵測部分是最花時間的,因此我們將移動物件偵測部分以硬體實現,並且針對低通濾波器(LPF)及連接物標籤化(Labeling)這兩個運算分別提出新的硬體架構。而物件追蹤的部分則交由軟體(ARM)來計算。
最後將所設計的硬體電路經由AHB匯流排與ARM做溝通,並使用ARM公司生產的發展平台Integrator來驗證整個影像監控系統。
In order to reduce the crime rate, image surveillance system has been generally applied to various kinds of occasions. In the thesis, we study a powerful real-time image surveillance system.
The proposed image surveillance system includes two major parts : (1) object detection (2)object tracking. In the object detection part, we adopt these ways of background subtraction、low pass filter and connected component labeling to complete detection of moving object. In the object tracking part, we propose an efficient algorithm that can calculate the search region rapidly and reduce the searching area and time greatly . At the same time, we also present a dependent value “D” to increase the speed of searching for moving object . The dependent value “D” includes three parameters of moving direction、moving position and object area . In order to achieve the real-time surveillance system, we partition the whole image surveillance system into hardware and software parts, and implement it on SOC development platform. According to analyzing the computation of our approach, we find out that the most time consuming is object detection. So we propose two hardware architectures for low pass filter and connected component labeling respectively. Then, these two architectures are implemented by FPGA. The object tracking part is realized by software(ARM code).
Finally, we make the communication between the FPGA hardware and ARM processor via AHB bus, and use ARM-development-platform integrator to verify the whole real-time surveillance system.
中文摘要------------------------------------------------------------i
英文摘要-----------------------------------------------------------ii
誌謝--------------------------------------------------------------iii
目錄---------------------------------------------------------------iv
表目錄-------------------------------------------------------------vi
圖目錄------------------------------------------------------------vii

第一章、緒論---------------------------------------------------------1
1.1研究動機與背景--------------------------------------------- 1
1.2各章節摘要------------------------------------------------- 2

第二章、相關背景----------------------------------------------------3
2.1 空間濾波器(Spatial Filter)---------------------------------3
2.2影像二值化------------------------------------------------- 4
2.3型態學(Morphology)----------------------------------------- 5
2.3.1膨脹(Dilation)及侵蝕(Erosion)------------------------ 5
2.3.2斷開(Opening)及閉合(Closing)------------------------- 6
2.3.3 型態濾波---------------------------------------------8
2.4 連接物標籤化(Connected-Component Labeling)-----------------8

第三章、監控系統---------------------------------------------------10
3.1系統流程圖------------------------------------------------ 11
3.2物體的偵測------------------------------------------------ 12
3.3物體追蹤-------------------------------------------------- 13
3.4模擬驗證結果---------------------------------------------- 22

第四章、系統單晶片設計與發展平台-----------------------------------23
4.1系統單晶片設計-------------------------------------------- 23
4.2軟硬體共設計及驗證---------------------------------------- 24
4.3發展平台硬體架構------------------------------------------ 26
4.4 ARM發展平台設計流程---------------------------------------28
4.5以記憶體為基礎的介面整合---------------------------------- 29
4.6系統晶片匯流排AMBA----------------------------------------33
4.6.1 AHB系統特色-----------------------------------------34
4.6.2 系統描述--------------------------------------------34
4.6.3 匯流排訊號說明--------------------------------------35
第五章、在ARM Integrator發展平台上實現監控系統--------------------37
5.1監控系統架構---------------------------------------------- 37
5.1.1 影像輸入--------------------------------------------37
5.1.2 影像輸出--------------------------------------------38
5.2軟/硬體分割----------------------------------------------- 38
5.3低通濾波器硬體實現---------------------------------------- 39
5.4影像物件標籤化方法與硬體架構設計-------------------------- 41
5.4.1 3X4 Window物件標籤化方法----------------------------42
5.4.2 Label-Assigning------------------------------------- 45
5.4.3 P1處理單元------------------------------------------46
5.4.4 P2處理單元------------------------------------------48
5.4.5 3X4 Window 硬體架構----------------------------------50
5.4.6 Pair-Processing------------------------------------- 52
5.4.7 Class Register Array硬體邏輯電路--------------------54
5.4.8 Combine電路-----------------------------------------54
5.4.9 3X4 Window物件標籤化系統架構圖----------------------56
5.5 硬體執行結果----------------------------------------------58
5.6 監控系統軟/硬體共驗證結果---------------------------------59

第六章、結論與未來展望---------------------------------------------63

參考文獻-----------------------------------------------------------64
[1] Haritaoglu, I.; Harwood, D.; Davis, L.S., “W4: real-time surveillance of people and their activities,” Pattern Analysis and Machine Intelligence, IEEE Transactions on , Volume: 22 Issue: 8 , Aug. 2000
[2] E. Stringa and C. S. Regazzoni, “Real-time video-shot detection for scene surveillance applications,” IEEE Trans. Image Processing,vol. 9, pp. 69–79, Jan. 2000.
[3] C. Sacchi and C. S. Regazzoni, “A distributed surveillance system for detection of abandoned objects in unmanned railway environments,” IEEE Trans. Veh. Technol., vol. 49, pp. 2013–2026, Sept. 2000.
[4] X. Gao, T. E. Boult, F. Coetzee, and V. Ramesh, “Error analysis of background adaptation,” in Proc. 2000 IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, Hilton Head Island, SC, June 2000, pp. 503–510.
[5] Pavlidis, I.; Morellas, V.; Tsiamyrtzis, P.; Harp, S., “Urban surveillance systems: from the laboratory to the commercial world,” Proceedings of the IEEE, Vol.89, No.10, Oct. 2001. pp.478 -497.
[6] Roberts, G.; Darney, I., “Novel rapid deployment surveillance system,” Computing & Control Engineering Journal, Vol.13, No.1 , Feb. 2002, pp.21 -25.
[7] Bartolini, F.; Tefas, A.; Barni, M.; Pitas, I. , “Image authentication techniques for surveillance applications,” Proceedings of the IEEE , Vol.89. No.10, Oct. 2001, pp.1403 -1418.
[8] Tancharoen, D.; Jitapunkul, S.; Triamlumlerd, S.; Kittipanya-ngam, P.; Chompun, “Object segmentation based on multiple features for low bit rate video coding,” WCCC-ICSP 2000, 5th International Conference Proceedings o. Signal Processing, Vol. 2, pp.975 -978.
[9] Vsam home page [Online]. Available: www.cs.cmu.edu/vsam/vsamhome.html.
[10] R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsim, D.Tolliver, N. Enomoto, O. Hasegawa, P. Burt, and L.Wixson, “A system for video surveillance and monitoring: Vsam final report,” Robotics Institute, Carnegie Mellon Univ., Pittsburgh , PA , Tech. Rep. CMU-RI-TR-00–12, 2000.
[11] I. J. Cox and S. L. Hingorani, “An efficient implementation of reid’s multiple hypothesis tracking algorithm and its evaluation for the purpose of visual tracking,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 18, pp. 138–150, Feb. 1996.
[12] Makarov, A. Sep 1996 “Comparison of background extraction based intrusion
detection algorithms”Image Processing, 1996. Proceedings., International Conference on Volume.1 pp. 521-524.

[13]Durucan, E.; Ebrahimi, T.; Oct 2001 “Change detection and background extraction by linear algebra” Proceedings of the IEEE Volume. 89, Issue.10, pp.1368-1381.
[14] Nicol, C.J.;” A systolic architecture for labeling the connected components of multi-valued images in real time,” Computer Vision and Pattern Recognition, 1993. Proceedings CVPR ''93., 1993 IEEE Computer Society Conference on , 15-17 June 1993 pp. 136 -141.
[15] Ranganathan, N.; Mehrotra, R.; Subramanian, S.;” A high speed systolic architecture for labeling connected components in an image,” Systems, Man and Cybernetics, IEEE Transactions on , Volume: 25 Issue: 3 , March 1995 pp. 415 -423.
[16] Shuenn-Der Jean; Chi-Min Liu; Chih-Chi Chang; Zen Chen;” A new algorithm and its VLSI architecture design for connected component labeling,” Circuits and Systems, 1994. ISCAS ''94., 1994 IEEE International Symposium on , Volume: 2 , 30 May-2 June 1994 pp.565 -568.
[17] Suzuki, K.; Horiba, I.; Sugie, N.;” Fast connected-component labeling based on sequential local operations in the course of forward raster scan followed by backward raster scan,” Pattern Recognition, 2000. Proceedings. 15th International Conference on , Volume: 2 , 3-7 Sept 2000 , pp.434 -437.
[18] Shao-Yi Chien; Yu-Wen Huang; Bing-Yu Hsieh; Liang-Gee Chen.“Single chip video segmentation system with a programmable PE array.” ASIC, 2002. Proceedings. 2002 IEEE Asia-Pacific Conference on , 6-8 Aug. 2002.
[19] Shao-Yi Chien; Yu -Wen Huang; Shyh -Yih Ma; Liang-Gee Chen. “A hybrid
morphology processing units architecture for real-time video segmentation systems.” Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE
International Symposium on , Volume: 5 , 6-9 May 2001.
[20]“ARM Integrator/CM7TDMI User Guide”,ARM Inc.1999.
[21]“ARM Developer Suite Getting Started Guide”,ARMInc.1999.
[22] Di Stefano, L.; Bulgarelli, A. ” A simple and efficient connected components
labeling algorithm.” Image Analysis and Processing, 1999. Proceedings.
International Conference on , 27-29 Sept. 1999.
[23] Khanna, V.; Gupta, P.; Hwang, C.J.,” Finding connected components in digital images.” Information Technology: Coding and Computing, 2001. Proceedings. International Conference on , 2-4 April 2001.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top