臺灣博碩士論文加值系統

本文是針對影像作移動物體偵測。現今有非常多的方式對視訊監控影像作移動偵測的方法，在物體移動中，大部分最常見的方法是對物體找出特定的特徵點，並在兩張影像中計算此特徵點的移動，但有時這些特徵點有時候會較難被定義清楚，因為物體移動的時候容易使影像模糊，特別是在影像無法事先得知的情況下更為困難。
在本文主要是使用加速穩健特徵(SURF)演算法來定義移動物件的特徵點，因為SURF 偵測特徵的速度相對於SIFT 來說會比較快，但是不管是SIFT 還是SURF，在檢測的物體移動時，匹配結果則不如預期中良好，因為物體在移動時可能存在著不正確的特徵點，所以本文提出了邊緣和特徵偵測去作結合，以此提高特徵匹配的情況，除此之外本研究中我們各種不同的移動方式做偵測去計算正確的特徵點並做分析。在實驗中，我們可以進一步的了解此方法相較於傳統的方法上，能有更良好的辨識能力。

This thesis is detecting object for moving images. Nowadays, there are many methods for moving object detection on surveillance, and the method used is to find features and then to use the motion of those features between images to calculate features points moving. But the feature points sometimes are more difficult to define because the objects moving are easy to make images blur. Especially, when the objects may not be known in advance.
In this thesis, using SURF algorithm defines the features of motional images because it detecting speed is faster than SIFT. But whether it is SIFT or SURF when the detected object moves, the matching result is not as good as expected because the objects may have incorrect feature points on moving. In the thesis, we provide edge and feature detection to combine for increasing the feature matching. In addition, this study we use a lot of different detection to detect and calculate the correct feature points to analyze. In experiment, we can further understand our methods getting the better ability to identify compared to the traditional methods.

摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vii
表目錄 x

第一章 緒論 1
1.1 前言 1
1.2 文獻回顧 1
1.2.1 平滑影像 1
1.2.2 邊緣檢測 2
1.2.3特徵偵測 5
1.3 研究動機與目 10
1.4本論文之貢獻 10
1.5本論文之架構 10
第二章 理論基礎與應用 12
2.1 SIFT(Scale-invariant feature transform) 12
2.2 SURF 演算法 17
2.2.1 積分影像 17
2.2.2 構建Hessian矩陣 18
2.2.3 尺度空間 20
2.2.4 定位特徵點 20
2.2.5 特徵點主方向 21
2.2.6 特徵點描述子 22
2.3 Laplacian of Gaussian 23
2.3.1 拉普拉斯算子 23
2.4 隨機抽樣一致性(RANSAC) 25
2.5 比較SIFT和SURF差異 26
2.6 雜訊處理 27
2.7 影像銳化 29
2.8 特徵擷取結合邊緣銳化 30
第三章 實驗設備 33
3.1個人電腦 33
3.2 攝影機 33
3.3 資料庫 34
第四章 實驗結果與討論 35
4.1 偵測物體架構 35
4.2 實驗一 35
4.3 實驗二 39
4.4 比較實驗結果 43
4.5實驗三 43
4.6實驗四 45
第五章 結論及未來展望 47
參考文獻 48

[1] John Canny, “A Computational Approach to Edge Detection,” IEEE
Transactions on Pattern Analysis and Machine Intelligence , vol.PAMI-8,
no.6, Nov, 1986.
[2] Penghui Jiang, Shengjie Zhao, Samuel Cheng, “Rotational invariant LBPSURF
for fast and robust image matching,” International Conference on
Signal Processing and Communication Systems, Dec. 2015.
[3] L. Juan, O.Gwun, “A Comparison of SIFT, PCA-SIFT and SURF,”
International Journal of Image Processing, pp.143-152, 2009.
[4] Ondrej Miksik, Krystian Mikolajczyk, “Evaluation of Local Detectors and
Descriptors for Fast Feature Matching,” Pattern Recognition, pp.2681-2684,
2012.
[5] Lowe, David G. "Distinctive Image Features from Scale-Invariant
Keypoints ". International Journal of Computer Vision, pp. 91–110, 2004.
[6] Herbert Bay, Tinne Tuytelaars, and Luc Van Gool, “SURF: Speeded Up
Robust Features,” Computer Vision and Image Understanding, vol. 110, no.
3, pp. 346–359, 2008.
[7] Martin A. Fischler, Robert C. Bolles, “Random Sample Consensus: A
Paradigm for Model Fitting with Apphcatlons to Image Analysis and
Automated Cartography,” Communications of the ACM, vol. 24, pp.381-395,
1981.
[8] 錢逢祥，蔡政崇，楊傑文，Node.js 模組參考手冊，松崗出版社，2015
[9] Marko Heikkila, Matti Pietikainen “A Texture-Based Method for Modeling
the Background and Detecting Moving Objects,” IEEE TRANSACTIONS ON
49
PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 28, no. 4, Apr.
2006.
[10] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution Gray-Scale and
Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp.
971-987, July 2002.
[11] Marko Heikkila, Matti Pietiainen, and Cordelia Schmid, “Description of
interest regions with local binary patterns,” Pattern Recognition, vol. 42, Mar.,
pp. 425–436, 2009.
[12] Prabhakar C J and Praveen Kumar P U, “LBP-SURF Descriptor with Color
Invariant and Texture Based Features for Underwater Images,” ICVGIP, Dec.
2012.
[13] E. Mavridaki, V. Mezaris, “No-Reference blur assessment in natural images
using Fourier transform and spatial pyramids”, IEEE International
Conference on Image Processing, Paris, France, Oct., 2014.
[14] Ankur Handa, Richard A. Newcombe, Adrien Angeli and Andrew J. Davison,”
Real-Time Camera Tracking: When is High Frame-Rate Best,” Computer
Vision–ECCV 2012, pp. 222-235, 2012
[15] 朱庭葳，以邊緣強化之SIFT 偵測移動物件， 國立臺灣科技大學電機
系，碩士論文，2016 年
[16] 鍾秉剛，基於向量模型設計與實現蒙地卡羅定位與路徑規劃於輪型移動
機器人，國立臺灣師範大學機電工程系，碩士論文，2015 年
[17] 陳希哲，應用運動回復結構技術建立機器手臂夾取點與三維物體模型，
50
國立臺灣師範大學機電工程系，碩士論文，2013 年
[18] 鍾國亮，影像處理與電腦視覺，東華書局，2015 年
[19] Marius Muja and David G. Lowe, “Fast Approximate Nearest Neighbors
with Automatic Algorithm Configuration,” VISAPP, pp.331-340, 2009