跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.87) 您好!臺灣時間:2025/02/13 04:57
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:廖奕霖
研究生(外文):Yi-Lin Liao
論文名稱:以FPGA實現紅外光即時移動物件追蹤
論文名稱(外文):Appling FPGA to Implement Real-Time Infrared Tracking of Moving Objects
指導教授:謝振榆謝振榆引用關係
指導教授(外文):Jen-Yu Shieh
學位類別:碩士
校院名稱:國立虎尾科技大學
系所名稱:光電與材料科技研究所
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:2012
畢業學年度:100
語文別:中文
論文頁數:65
中文關鍵詞:FPGA中值濾波器背景相減法影像標籤化物件追蹤
外文關鍵詞:FPGAMedian FilterBackground SubtractionImage LabelingObject Tracking
相關次數:
  • 被引用被引用:0
  • 點閱點閱:571
  • 評分評分:
  • 下載下載:10
  • 收藏至我的研究室書目清單書目收藏:1
在紅外線監控系統中,有別於一般可見光影像的特性,能夠發展出不同於可見光影像分析的應用。但紅外線影像品質不佳,低對比度、少特徵點等等缺點,所以先利用中值濾波器進行影像復原與重建,來提升紅外光影像的品質,此濾波器是基於排序統計理論的一種,能有效地去除雜訊,是一種非線性信號處理的技術,運算簡單、速度快。前置處理後,先建立參考背景影像,儲存在SDRAM,同時擷取連續影像與參考背景影像進行相減動作,計算出影像差異值。背景相減法後會因光源變化或移動快慢等因素造成雜訊及物件破碎的問題,以形態學處理之閉合運算來修補破碎不完整的區塊,斷開運算來去除不必要的雜訊或小區塊。為了達到移動物件追蹤,先將不同移動物件進行影像分割,採取方法為影像標籤化,並利用重心法分別求出重心坐標與邊界座標,最後將移動物件提取出來。

大多數監控系統多以PC作為平台,不僅效率低且佔據空間。本論文以Altera Cyclone II FPGA DE2-70為系統核心,紅外線攝影機透過ADV7180類比轉數位,ITU-R 656解碼電路,影像透過SDRAM當作資料緩衝並同時進行交錯式掃描,再經由許多模組進行影像演算法運算,接著把YCbCr訊號轉換為RGB色彩空間,最後將處理後的結果顯示於LCD上。系統皆以Verilog硬體電路完成,所以能快速地運算演算法,達到即時物件追蹤的功能。


Unlike optical image analysis characteristics, various applications can be developed for infrared monitoring systems. Because infrared images are characterized by poor quality, low contrast, and few feature points, median filters are employed to recover and reconstruct images to improve the quality of infrared images. Based on the theory of order statistics, median filters are an easy-calculating and fast non-linear signal processing technology that can denoise signals effectively. After pre-processing, the reference background images are established and saved on SDRAM. We then retrieve the sequence images and the reference background images to conduct background subtraction to calculate image differences. Following background subtraction, changes in light sources and the speed of moving objects can cause noise and object appears shattered. Thus, we use morphological closing operation to mend shattered, incomplete segments and morphological opening operation to remove unnecessary noises and small segments. To realize moving object tracking, we employ image labeling to segment various moving objects and the barycentric method to calculate the barycentric and boundary coordinates. Finally, the moving objects were retrieved.

Most monitoring systems are PC platform based and have the disadvantages of low efficiency and space-occupation. The system core of this study was an Altera Cyclone II FPGA DE2-70. Using the ADV7180 analog-to-digital conversion and the ITU-R 656 decoding circuit, interlaced scans were conducted on the images using SDRAM as the data buffer and numerous modules to calculate video algorithms. YCbCr signals were then converted to RGB color spaces. Finally, the processed results were displayed on an LCD. The system was completed by the Verilog hardware circuit that enables the rapid application of algorithms on images, thereby realizing real-time recognition.


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 研究動機與目的...............1
1.2 文獻探討...............1
1.2.1 中值濾波器...............1
1.2.2 移動物件追蹤...............2
1.3 論文架構...............7
第二章 系統架構...............8
2.1 FPGA(DE2_70)...............8
2.2 紅外線攝影機...............9
2.3 LTM(LCD Touch Panel Module)...............10
2.4 紅外線攝影機解碼原理...............14
2.5 數位訊號流程...............17
2.5.1 I2C配置...............17
2.5.2 ITU-R656解碼...............17
2.5.3 YCbCr...............17
2.5.4 數位訊號處理...............18
2.5.5 垂直消隱間隔...............20
2.6 鎖相迴路...............20
2.7 SDRAM基本原理...............21
2.7.1 基本介紹...............21
2.7.2 SDRAM接腳...............21
2.7.3 SDRAM Command...............22
2.7.4 SDRAM Controller結構...............23
第三章 影像相關技術...............26
3.1 雜訊模型...............26
3.1.1 高斯雜訊(Gaussian Noise)...............26
3.1.2 雷利雜訊(Rayleigh Noise)...............27
3.1.3 指數雜訊(Exponential Noise)...............28
3.1.4 均勻雜訊(Uniform Noise)...............28
3.1.5 脈衝雜訊(Impulse Noise)...............29
3.2 雜訊去除演算法...............30
3.2.1 算術平均濾波器...............30
3.2.2 幾何平均濾波器...............30
3.2.3 調和平均濾波器...............30
3.2.4 反向調和平均濾波器...............30
3.2.5 中值濾波器...............31
3.2.6 最大和最小濾波器...............32
3.2.7 中點濾波器...............32
3.2.8 Alpha微調平均濾波器...............32
3.2.9 自適性中值濾波器...............33
3.3 形態學處理...............34
3.3.1 侵蝕(Erosion)...............34
3.3.2 膨脹(Dilation)...............34
3.3.3 斷開(Opening)和閉合(Closing)...............35
第四章 研究方法...............37
4.1 中值濾波演算法...............37
4.1.1 電路架構與設計...............37
4.1.2 門檻值比較法...............39
4.2 背景相減法...............40
4.3 二值化...............42
4.4 形態學之電路設計...............43
4.5 影像標籤化...............45
4.6 物件追蹤偵測...............47
4.6.1 預測以知物件移動後的位置...............48
4.6.2 移動後與移動前之物件比對...............52
4.6.3 追蹤與更新決策...............53
4.6.4 搜尋其他新物件及背景更新...............54
4.7 重心法...............54
4.8 色彩空間轉換...............54
4.9 有限狀態機設計架構...............55
4.10 電路設計之管線處理...............56
第五章 實驗結果...............60
第六章 結論...............62
參考文獻 ...............63
英文論文大綱
簡歷

[1]A Bal, M. S. Alam, 2004, "Automatic target tracking in FLIR image sequences", SPIE Defense and Security Symp.
[2]A Strehl, 1. K. Aggarwal, 2000, "Detecting moving objects in airborne forward looking infrared sequences", Mach. Vis. Appl., vol. 11, pp. 267-276.
[3]Lu Yan, Dai Ming, Jiang Lei, Li Shi, 2010, "Sort Optimization Algorithm of Median Filtering Based on FPGA", Machine Vision and Human-Machine Interface , pp. 24-25.
[4]楊紹岩,劉萬成,周長春,2011,“基於IRFPA改進中值濾波演算法的FPGA實現”,Electro-Optic Technology Application, vol. 26, No. 2.
[5]王俊凱,2004,“基於改良式適應性背景相減法與多重影像特徵比對法之多功能即時視覺追蹤系統之設計與實現”,國立成功大學電機工程研究所碩士論文。
[6]劉庭瑋,2004,“Adaptive Parameter Tuning Technique for Designing Robust Motion Detection System”,逢甲大學資訊工程研究所碩士論文。
[7]Young-Kee Jung, Kyu-Won Lee, Yo-Sung Ho, 2004,"Content-based event retrieval using semantic scene interpretation for automated traffic surveillance", Intelligent Transportation Systems, vol. 2, No.3.
[8]S. Denman, V. Chandran, and S. Sridharan, 2007, "An adaptive optical flow technique for person tracking systems," Pattern Recognition Letters, vol. 28, no. 10, pp. 1232–1239.
[9]A. M. Elgammal,et al. 2002, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance", vol. 90, pp.1151–1163.
[10]Y.-T. Chen, C.-S. Chen, C.-R. Huang and Y.-P. Hung, 2007, "Efficient hierarchical method for background subtraction", Pattern Recognition, vol. 40, pp. 2706– 2715.
[11]Aguilar-Ponce, et al. 2005, "Real-time VLSI architecture for detection of moving object using Wronskian determinant", Circuits and Systems, pp. 7-10.
[12]Zheng Yi,Fan Liangzhong, 2010, "Moving object detection based on running average background and temporal difference", Intelligent Systems and Knowledge Engineering, pp. 15-16.
[13]W. Brand, 2001, "Morphable 3D models from video", Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 456-463.
[14]A. J. Lipton, 1999, "Local application of optic to analyze rigid versus non-rigid motion", Technical Report, CMU-RI-TR-99-13, Robotics Institute, Carnegie Mellon University.
[15]J. L. Barron,D.J. Fleet, S. S. Beauchemin and T. A. Burkitt, 1992, "Performance of Optical Flow Techniques", Computer Society Conference on Computer Vision and Pattern Recognition , pp. 236-242.
[16]Hai-Yan Zhang, 2010, "Multiple moving objects detection and tracking based on optical flow in polar-log images", Machine Learning and Cybernetics, vol. 3, pp. 11-14.
[17]Zafar, I., et al. 2010, "Human silhouette extraction on FPGAs for infrared night vision military surveillance", Circuit,Communications and System , vol. 1, pp. 1-2.
[18]Weihua Xiong, Junbin Guan, and Haipeng Pan, 2110, "A New Algorithm for Moving Objects Detection Based on Background and Consecutive Frames Subtraction", Intelligent Control and Automation , pp. 7-9.
[19]Dhome, Y., et al. 2010, "A Benchmark for Background Subtraction Algorithms in Monocular Vision: a Comparative Study", Image Processing Theory Tools and Applications, pp. 7-10.
[20]R. C. Gonzalez, R. E. Woods, 繆紹綱, Digital Image Processing. Pearson Education, Upper Saddle River, New Jersey.
[21]Maoxiang Huang, Chenhao Wang, Yuncai Liu, 2009, "High-Speed Video Transfer and Real-Time Infrared Spots Detection Based on FPGA", Computer Science and Engineering, vol. 2, pp. 28-30.
[22]陳碧東等,2009,“視訊品質改善之相鄰掃描線相關性演算法設計與實現”,清雲學報 第29卷,第3期,第1頁,七月。
[23]王裕謙,2004,“以行為模型建立鎖相迴路之非理想現象的研究”,國立中央大學電機工程研究所碩士論文。
[24]黃富民,2004,“支援動態存取排程與預充電策略的先進記憶體控制器”,國立成功大學電機工程研究所碩士論文。
[25]蔡長諺,2006,“用於突波雜訊移除之適應性中值影像濾波器”,國立成功大學資訊工程研究所碩士論文。
[26]Vasicek, Z., Sekanina, L., 2007, "An Area-Efficient Alternative to Adaptive Median Filtering in FPGAs", Field Programmable Logic and Applications, pp. 27-29.
[27]王敬美,2008,“一種自適應中值濾波器算法的FPGA實現”,哈爾濱工業大學電氣工程及自動化學院。
[28]陳泓諭,2004,“以FPGA實現即時移動物件偵測系統”,輔仁大學電子工程研究所碩士論文。
[29]張家銓,2009,“以追蹤眼睛狀態為基礎之駕駛者疲勞偵測系統”,國立成功大學工程科學研究所碩士論文。
[30]林起字,2007,“數位紅眼缺陷的全自動化檢測及校正研究”,大同大學通訊工程研究所碩士論文。
[31]S. W. Yang, et al. 2005, "VLSI Architecture Design for a Fast Parallel Label Assignment in Binary Image", International Symposium Circuits and Systems, vol. 3, pp. 2393–2396.
[32]簡宏恩,2004,“以軟/硬體共設計方式實現即時監控系統”,國立雲林科技大學電子工程研究所碩士論文。
[33]許毅然,2007,“嵌入式系統架構實現即時追熱系統”,南台科技大學電機工程研究所碩士論文。
[34]吳信彥,2009,“以FPGA實現移動適應性解交錯於弱視輔具之設計”,國立陽明大學醫學工程研究所碩士論文。
[35]Cao, C., Oelmann, B., 2004, "Mixed Synchronous/Asynchronous State Memory for Low Power FSM Design", Digital System Design, pp. 363-370.
[36]Devlin, B, et al. 2009, "Throughput Optimization by Pipeline Alignment of a Self Synchronous FPGA", Field-Programmable Technology, pp. 312-315.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top