图像处理与计算机视觉：基础，经典以及最近发展（5）计算机视觉

Last update: 2012-6-7

这一章是计算机视觉部分，主要侧重在底层特征提取，视频分析，跟踪，目标检测和识别方面等方面。对于自己不太熟悉的领域比如摄像机标定和立体视觉，仅仅列出上google上引用次数比较多的文献。有一些刚刚出版的文章，个人非常喜欢，也列出来了。

本章的下载地址：

http://iask.sina.com.cn/u/2252291285/ish?folderid=868772

1. Active Appearance Models

活动表观模型和活动轮廓模型基本思想来源Snake，现在在人脸三维建模方面得到了很成功的应用，这里列出了三篇最初最经典的文章。对这个领域有兴趣的可以从这三篇文章开始入手。

[1998 ECCV] ActiveAppearance Models

[2001 PAMI] ActiveAppearance Models

 

2. Active Shape Models

[1995 CVIU]Active ShapeModels-Their Training and Application

 

3. Background modeling andsubtraction

背景建模一直是视频分析尤其是目标检测中的一项关键技术。虽然最近一直有一些新技术的产生，demo效果也很好，比如基于dynamical texture的方法。但最经典的还是Stauffer等在1999年和2000年提出的GMM方法，他们最大的贡献在于不用EM去做高斯拟合，而是采用了一种迭代的算法，这样就不需要保存很多帧的数据，节省了buffer。Zivkovic在2004年的ICPR和PAMI上提出了动态确定高斯数目的方法，把混合高斯模型做到了极致。这种方法效果也很好，而且易于实现。在OpenCV中有现成的函数可以调用。在背景建模大家族里，无参数方法（2000 ECCV）和Vibe方法也值得关注。

[1997 PAMI] PfinderReal-Time Tracking of the Human Body

[1999 CVPR] Adaptivebackground mixture models for real-time tracking

[1999 ICCV] WallflowerPrinciples and Practice of Background Maintenance

[2000 ECCV] Non-parametricModel for Background Subtraction

[2000 PAMI] LearningPatterns of Activity Using Real-Time Tracking

[2002 PIEEE] Backgroundand foreground modeling using nonparametric kernel density estimation forvisual surveillance

[2004 ICPR] Improvedadaptive Gaussian mixture model for background subtraction

[2004 PAMI] Recursiveunsupervised learning of finite mixture models

[2006 PRL] Efficientadaptive density estimation per image pixel for the task of backgroundsubtraction

[2011 TIP] ViBe AUniversal Background Subtraction Algorithm for Video Sequences

 

4.  Bag of Words

词袋，在这方面暂时没有什么研究。列出三篇引用率很高的文章，以后逐步解剖之。

[2003 ICCV] Video Google AText Retrieval Approach to Object Matching in Videos

[2004 ECCV] VisualCategorization with Bags of Keypoints

[2006 CVPR] Beyond bags offeatures Spatial pyramid matching for recognizing natural scene categories

 

5.  BRIEF

BRIEF是BinaryRobust Independent Elementary Features的简称，是近年来比较受关注的特征描述的方法。ORB也是基于BRIEF的。

[2010 ECCV] BRIEF BinaryRobust Independent Elementary Features

[2011 ICCV] ORB anefficient alternative to SIFT or SURF

[2012 PAMI] BRIEFComputing a Local Binary Descriptor Very Fast

 

6. Camera Calibration and StereoVision

非常不熟悉的领域。仅仅列出了十来篇重要的文献，供以后学习。

[1979 Marr] AComputational Theory of Human Stereo Vision

[1985] Computationalvision and regularization theory

[1987 IEEE] A versatilecamera calibration technique for high-accuracy 3D machine vision metrologyusing off-the-shelf TV cameras and lenses

[1987] ProbabilisticSolution of Ill-Posed Problems in Computational Vision

[1988 PIEEE] Ill-PosedProblems in Early Vision

[1989 IJCV] KalmanFilter-based Algorithms for Estimating Depth from Image Sequences

[1990 IJCV] RelativeOrientation

[1990 IJCV] Usingvanishing points for camera calibration

[1992 ECCV] Cameraself-calibration Theory and experiments

[1992 IJCV] A theory ofself-calibration of a moving camera

[1992 PAMI] Cameracalibration with distortion models and accuracy evaluation

[1994 IJCV] TheFundamental Matrix Theory, Algorithms, and Stability Analysis

[1994 PAMI] a stereomatching algorithm with an adaptive window theory and experiment

[1999 ICCV] Flexiblecamera calibration by viewing a plane from unknown orientations

[1999 IWAR] Markertracking and hmd calibration for a video-based augmented reality conferencingsystem

[2000 PAMI] A flexible newtechnique for camera calibration

 

7. Color and Histogram Feature

这里面主要来源于图像检索，早期的图像检测基本基于全局的特征，其中最显著的就是颜色特征。这一部分可以和前面的Color知识放在一起的。

[1995 SPIE] Similarity ofcolor images

[1996 PR] IMAGE RETRIEVALUSING COLOR AND SHAPE

[1996] comparing imagesusing color coherence vectors

[1997 ] Image IndexingUsing Color Correlograms

[2001 TIP] An EfficientColor Representation for Image Retrieval

[2009 CVIU] Performanceevaluation of local colour invariants

 

8. Deformable Part Model

大红大热的DPM，在OpenCV中有一个专门的topic讲DPM和latent svm

[2008 CVPR] ADiscriminatively Trained, Multiscale, Deformable Part Model

[2010 CVPR] Cascade ObjectDetection with Deformable Part Models

[2010 PAMI] ObjectDetection with Discriminatively Trained Part-Based Models

 

9. Distance Transformations

距离变换，在OpenCV中也有实现。用来在二值图像中寻找种子点非常方便。

[1986 CVGIP] DistanceTransformations in Digital Images

[2008 ACM] 2D EuclideanDistance Transform Algorithms A Comparative Survey

 

10. Face Detection

最成熟最有名的当属Haar+Adaboost

[1998 PAMI] NeuralNetwork-Based Face Detection

[2002 PAMI] Detectingfaces in images a survey

[2002 PAMI] Face Detectionin Color Images

[2004 IJCV] RobustReal-Time Face Detection

 

11. Face Recognition

不熟悉，简单罗列之。

[1991] Face RecognitionUsing Eigenfaces

[2000 PAMI] AutomaticAnalysis of Facial Expressions The State of the Art

[2000] Face Recognition ALiterature Survey

[2006 PR] Face recognitionfrom a single image per person A survey

[2009 PAMI] Robust FaceRecognition via Sparse Representation

 

12. FAST

用机器学习的方法来提取角点，号称很快很好。

[2006 ECCV] Machinelearning for high-speed corner detection

[2010 PAMI] Faster andBetter A Machine Learning Approach to Corner Detection

 

13.  Feature Extraction

这里的特征主要都是各种不变性特征，SIFT，Harris，MSER等也属于这一类。把它们单独列出来是因为这些方法更流行一点。关于不变性特征，王永明与王贵锦合著的《图像局部不变性特征与描述》写的还不错。Mikolajczyk在2005年的PAMI上的文章以及2007年的综述是不错的学习材料。

[1989 PAMI] On thedetection of dominant points on digital curves

[1997 IJCV] SUSAN—A NewApproach to Low Level Image Processing

[2004 IJCV] MatchingWidely Separated Views Based on Affine Invariant Regions

[2004 IJCV] Scale &Affine Invariant Interest Point Detectors

[2005 PAMI] A performanceevaluation of local descriptors

[2006 IJCV] A Comparisonof Affine Region Detectors

[2007 FAT] Local InvariantFeature Detectors - A Survey

[2011 IJCV] Evaluation ofInterest Point Detectors and Feature Descriptors

 

14. Feature Matching

[2012 PAMI] LDAHashImproved Matching with Smaller Descriptors

 

15.  Harris

虽然过去了很多年，Harris角点检测仍然广泛使用，而且基于它有很多变形。如果仔细看了这种方法，从直观也可以感觉到这是一种很稳健的方法。

[1988 Harris] A combinedcorner and edge detector

 

16.   Histograms of OrientedGradients

HoG方法也在OpenCV中实现了：HOGDescriptor。

[2005 CVPR] Histograms ofOriented Gradients for Human Detection

NavneetDalalThesis.pdf

 

17. Image Distance

[1993 PAMI] ComparingImages Using the Hausdorff Distance

 

18. Image Stitching

图像拼接，另一个相关的词是Panoramic。在Computer Vision: Algorithms and Applications一书中，有专门一章是讨论这个问题。这里的两面文章一篇是综述，一篇是这方面很经典的文章。

[2006 Fnd] Image Alignmentand Stitching A Tutorial

[2007 IJCV] AutomaticPanoramic Image Stitching using Invariant Features

 

19.  KLT

KLT跟踪算法，基于Lucas-Kanade提出的配准算法。除了三篇很经典的文章，最后一篇给出了OpenCV实现KLT的细节。

[1981] An Iterative ImageRegistration Technique with an Application to Stereo Vision full version

[1994 CVPR] Good Featuresto Track

[2004 IJCV]  Lucas-Kanade 20 Years On A Unifying Framework

Pyramidal Implementationof the Lucas Kanade Feature Tracker OpenCV

 

20. Local Binary Pattern

LBP。OpenCV的Cascade分类器也支持LBP，用来取代Haar特征。

[2002 PAMI]Multiresolution gray-scale and rotation Invariant Texture Classification withLocal Binary Patterns

[2004 ECCV] FaceRecognition with Local Binary Patterns

[2006 PAMI] FaceDescription with Local Binary Patterns

[2011 TIP]Rotation-Invariant Image and Video Description With Local Binary PatternFeatures

 

21. Low-Level Vision

关于Low level vision的两篇很不错的文章

[1998 TIP] A generalframework for low level vision

[2000 IJCV] LearningLow-Level Vision

 

22. Mean Shift

均值漂移算法，在跟踪中非常流行的方法。Comaniciu在这个方面做出了重要的贡献。最后三篇，一篇是CVIU上的top download文章，一篇是最新的PAMI上关于Mean Shift的文章，一篇是OpenCV实现的文章。

[1995 PAMI] Mean shift,mode seeking, and clustering

[2002 PAMI] Mean shift arobust approach toward feature space analysis

[2003 CVPR] Mean-shiftblob tracking through scale space

[2009 CVIU] Objecttracking using SIFT features and mean shift

[2012 PAMI] Mean ShiftTrackers with Cross-Bin Metrics

OpenCV Computer VisionFace Tracking For Use in a Perceptual User Interface

 

23.  MSER

这篇文章发表在2002年的BMVC上，后来直接录用到2004年的IVC上，内容差不多。MSER在Sonka的书里面也有提到。

[2002 BMVC] Robust WideBaseline Stereo from Maximally Stable Extremal Regions

[2003] MSER AuthorPresentation

[2004 IVC] Robustwide-baseline stereo from maximally stable extremal regions

[2011 PAMI] Are MSERFeatures Really Interesting

 

24. Object Detection

首先要说的是第一篇文章的作者，Kah-Kay Sung。他是MIT的博士，后来到新加坡国立任教，极具潜力的一个老师。不幸的是，他和他的妻子都在2000年的新加坡空难中遇难，让人唏嘘不已。

http://en.wikipedia.org/wiki/Singapore_Airlines_Flight_006

最后一篇文章也是Fua课题组的，作者给出的demo效果相当好。

[1998 PAMI] Example-basedlearning for view-based human face detection

[2000 CVPR] A Statistical Method for 3D Object Detection Applied to Faces and Cars

[2003 IJCV] Learning theStatistics of People in Images and Video

[2011 PAMI] Learning toDetect a Salient Object

[2012 PAMI] A Real-TimeDeformable Detector

 

25. Object Tracking

跟踪也是计算机视觉中的经典问题。粒子滤波，卡尔曼滤波，KLT，mean shift，光流都跟它有关系。这里列出的是传统意义上的跟踪，尤其值得一看的是2008的Survey和2003年的Kernel based tracking。

[2003 PAMI] Kernel-basedobject tracking

[2007 PAMI] TrackingPeople by Learning Their Appearance

[2008 ACM] Object TrackingA Survey

[2008 PAMI] Segmentationand Tracking of Multiple Humans in Crowded Environments

[2011 PAMI] Hough Forestsfor Object Detection, Tracking, and Action Recognition

[2011 PAMI] Robust ObjectTracking with Online Multiple Instance Learning

[2012 IJCV] PWP3DReal-Time Segmentation and Tracking of 3D Objects

 

26. OCR

一个非常成熟的领域，已经很好的商业化了。

[1992 IEEE] Historical reviewof OCR research and development

Video OCR A Survey andPractitioner's Guide

 

27. Optical Flow

光流法，视频分析所必需掌握的一种算法。

[1981 AI] DetermineOptical Flow

[1994 IJCV] Performance ofoptical flow techniques

[1995 ACM] The Computationof Optical Flow

[2004 TR] TutorialComputing 2D and 3D Optical Flow

[2005 BOOK] Optical FlowEstimation

[2008 ECCV] LearningOptical Flow

[2011 IJCV] A Database andEvaluation Methodology for Optical Flow

 

28.  Particle Filter

粒子滤波，主要给出的是综述以及1998 IJCV上的关于粒子滤波发展早期的经典文章。

[1998 IJCV] CONDENSATION—ConditionalDensity Propagation for Visual Tracking

[2002 TSP] A tutorial onparticle filters for online nonlinear non-Gaussian Bayesian tracking

[2002 TSP] Particlefilters for positioning, navigation, and tracking

[2003 SPM] particle filter

 

29. Pedestrian and Human detection

仍然是综述类，关于行人和人体的运动检测和动作识别。

[1999 CVIU] Visualanalysis of human movement_ A survey

[2001 CVIU] A Survey ofComputer Vision-Based Human Motion Capture

[2005 TIP] Image changedetection algorithms a systematic survey

[2006 CVIU] a survey ofavdances in vision based human motion capture

[2007 CVIU] Vision-basedhuman motion analysis An overview

[2007 IJCV] PedestrianDetection via Periodic Motion Analysis

[2007 PR] A survey ofskin-color modeling and detection methods

[2010 IVC] A survey onvision-based human action recognition

[2012 PAMI] PedestrianDetection An Evaluation of the State of the Art

 

30. Scene Classification

当相机越来越傻瓜化的时候，自动场景识别就非常重要。这是比拼谁家的Auto功能做的比较好的时候了。

[2001 IJCV] Modeling theShape of the Scene A Holistic Representation of the Spatial Envelope

[2001 PAMI] Visual WordAmbiguity

[2007 PAMI] A ThousandWords in a Scene

[2010 PAMI] EvaluatingColor Descriptors for Object and Scene Recognition

[2011 PAMI] CENTRIST AVisual Descriptor for Scene Categorization

 

31. Shadow Detection

[2003 PAMI] Detectingmoving shadows-- algorithms and evaluation

32.  Shape

关于形状，主要是两个方面：形状的表示和形状的识别。形状的表示主要是从边缘或者区域当中提取不变性特征，用来做检索或者识别。这方面Sonka的书讲的比较系统。2008年的那篇综述在这方面也讲的不错。至于形状识别，最牛的当属J Malik等提出的Shape Context。

[1993 PR] IMPROVED MOMENTINVARIANTS FOR SHAPE DISCRIMINATION

[1993 PR] PatternRecognition by Affine Moment Invariants

[1996 PR] IMAGE RETRIEVALUSING COLOR AND SHAPE

[2001 SMI] Shape matchingsimilarity measures and algorithms

[2002 PAMI] Shape matchingand object recognition using shape contexts

[2004 PR] Review of shaperepresentation and description techniques

[2006 PAMI] IntegralInvariants for Shape Matching

[2008] A Survey of ShapeFeature Extraction Techniques

 

33.  SIFT

关于SIFT，实在不需要介绍太多，一万多次的引用已经说明问题了。SURF和PCA-SIFT也是属于这个系列。后面列出了几篇跟SIFT有关的问题。

[1999 ICCV] Objectrecognition from local scale-invariant features

[2000 IJCV] Evaluation ofInterest Point Detectors

[2003 CVIU] Speeded-UpRobust Features (SURF)

[2004 CVPR] PCA-SIFT AMore Distinctive Representation for Local Image Descriptors

[2004 IJCV] DistinctiveImage Features from Scale-Invariant Keypoints

[2010 IJCV] ImprovingBag-of-Features for Large Scale Image Search

[2011 PAMI] SIFTflow DenseCorrespondence across Scenes and its Applications

 

34.  SLAM

Simultaneous Localization and Mapping, 同步定位与建图。

SLAM问题可以描述为: 机器人在未知环境中从一个未知位置开始移动,在移动过程中根据位置估计和地图进行自身定位,同时在自身定位的基础上建造增量式地图，实现机器人的自主定位和导航。

[2002 PAMI] SimultaneousLocalization and Map-Building Using Active Vision

[2007 PAMI] MonoSLAMReal-Time Single Camera SLAM

 

35. Texture Feature

纹理特征也是物体识别和检索的一个重要特征集。

[1973] Textural featuresfor image classification

[1979 ] Statistical andstructural approaches to texture

[1996 PAMI] Texturefeatures for browsing and retrieval of image data

[2002 PR] Brief review ofinvariant texture analysis methods

[2012 TIP] Color LocalTexture Features for Color Face Recognition

 

36.  TLD

Kadal创立了TLD，跟踪学习检测同步进行，达到稳健跟踪的目的。他的两个导师也是大名鼎鼎，一个是发明MSER的Matas，一个是Mikolajczyk。他还创立了一个公司TLDVision s.r.o. 这里给出了他的系列文章，最后一篇是刚出来的PAMI。

[2009] Online learning ofrobust object detectors during unstable tracking

[2010 CVPR] P-N LearningBootstrapping Binary Classifiers by Structural Constraints

[2010 ICIP] FACE-TLDTRACKING-LEARNING-DETECTION APPLIED TO FACES

[2012 PAMI]Tracking-Learning-Detection

 

37.  Video Surveillance

前面两个是两个很有名的视频监控系统，里面包含了很丰富的信息量，比如CMU的那个系统里面的背景建模算法也是相当简单有效的。最后一篇是比较近的综述。

[2000 CMU TR] A System forVideo Surveillance and Monitoring

[2000 PAMI] W4-- real-timesurveillance of people and their activitie

[2008 MVA] The evolutionof video surveillance an overview

 

38.  Viola-Jones

Haar+Adaboost的弱弱联手，组成了最强大的利器。在OpenCV里面有它的实现，也可以选择用LBP来代替Haar特征。

[2001 CVPR] Rapid objectdetection using a boosted cascade of simple features

[2004 IJCV] RobustReal-time Face Detection