机器视觉开源代码集合

非常全面的计算机视觉和机器学习相关的开源项目工程。

一、特征提取FeatureExtraction：

·        SIFT [1] [Demo program][SIFTLibrary] [VLFeat]

·        PCA-SIFT [2] [Project]

·        Affine-SIFT [3] [Project]

·        SURF [4] [OpenSURF] [Matlab Wrapper]

·        Affine Covariant Features [5] [Oxford project]

·        MSER [6] [Oxford project] [VLFeat]

·        Geometric Blur [7] [Code]

·        Local Self-Similarity Descriptor [8] [Oxford implementation]

·        Global and Efficient Self-Similarity [9][Code]

·        Histogram of Oriented Graidents [10] [INRIAObject Localization Toolkit] [OLTtoolkit for Windows]

·        GIST [11] [Project]

·        Shape Context [12] [Project]

·        Color Descriptor [13] [Project]

·        Pyramids of Histograms of OrientedGradients [Code]

·        Space-Time Interest Points (STIP) [14][Project] [Code]

·        Boundary Preserving Dense Local Regions[15][Project]

·        Weighted Histogram[Code]

·        Histogram-based Interest PointsDetectors[Paper][Code]

·        An OpenCV - C++ implementation of LocalSelf Similarity Descriptors [Project]

·        Fast Sparse Representation with Prototypes[Project]

·        Corner Detection [Project]

·        AGAST Corner Detector: faster than FASTand even FAST-ER[Project]

·        Real-time Facial Feature Detection usingConditional Regression Forests[Project]

·        Global and Efficient Self-Similarity forObject Classification and Detection[code]

·        WαSH: Weighted α-Shapes for LocalFeature Detection[Project]

·        HOG[Project]

·        Online Selection of DiscriminativeTracking Features[Project]

 

二、图像分割ImageSegmentation：

·        Normalized Cut [1] [Matlabcode]

·        Gerg Mori’ Superpixel code [2] [Matlab code]

·        Efficient Graph-based Image Segmentation[3] [C++ code] [Matlab wrapper]

·        Mean-Shift Image Segmentation [4] [EDISON C++ code] [Matlab wrapper]

·        OWT-UCM Hierarchical Segmentation [5] [Resources]

·        Turbepixels [6] [Matlab code 32bit] [Matlab code 64bit] [Updated code]

·        Quick-Shift [7] [VLFeat]

·        SLIC Superpixels [8] [Project]

·        Segmentation by Minimum Code Length [9][Project]

·        Biased Normalized Cut [10] [Project]

·        Segmentation Tree [11-12] [Project]

·        Entropy Rate Superpixel Segmentation[13] [Code]

·        Fast Approximate Energy Minimization viaGraph Cuts[Paper][Code]

·        Efficient Planar Graph Cuts withApplications in Computer Vision[Paper][Code]

·        Isoperimetric Graph Partitioning forImage Segmentation[Paper][Code]

·        Random Walks for Image Segmentation[Paper][Code]

·        Blossom V: A new implementation of aminimum cost perfect matching algorithm[Code]

·        An Experimental Comparison ofMin-Cut/Max-Flow Algorithms for Energy Minimization in Computer Vision[Paper][Code]

·        Geodesic Star Convexity for InteractiveImage Segmentation[Project]

·        Contour Detection and Image SegmentationResources[Project][Code]

·        Biased Normalized Cuts[Project]

·        Max-flow/min-cut[Project]

·        Chan-Vese Segmentation using Level Set[Project]

·        A Toolbox of Level Set Methods[Project]

·        Re-initialization Free Level SetEvolution via Reaction Diffusion[Project]

·        Improved C-V active contour model[Paper][Code]

·        A Variational Multiphase Level SetApproach to Simultaneous Segmentation and Bias Correction[Paper][Code]

·        Level Set Method Research by ChunmingLi[Project]

·        ClassCut for Unsupervised ClassSegmentation[code]

·        SEEDS: Superpixels Extracted via Energy-DrivenSampling [Project][other]

 

三、目标检测Object Detection：

·        A simple object detector with boosting [Project]

·        INRIA Object Detection and LocalizationToolkit [1] [Project]

·        Discriminatively Trained Deformable PartModels [2] [Project]

·        Cascade Object Detection with DeformablePart Models [3] [Project]

·        Poselet [4] [Project]

·        Implicit Shape Model [5] [Project]

·        Viola and Jones’s Face Detection [6] [Project]

·        Bayesian Modelling of Dyanmic Scenes forObject Detection[Paper][Code]

·        Hand detection using multiple proposals[Project]

·        Color Constancy, Intrinsic Images, andShape Estimation[Paper][Code]

·        Discriminatively trained deformable partmodels[Project]

·        Gradient Response Maps for Real-TimeDetection of Texture-Less Objects: LineMOD [Project]

·        Image Processing On Line[Project]

·        Robust Optical Flow Estimation[Project]

·        Where's Waldo: Matching People in Imagesof Crowds[Project]

·        Scalable Multi-class Object Detection[Project]

·        Class-Specific Hough Forests for ObjectDetection[Project]

·        Deformed Lattice Detection In Real-WorldImages[Project]

·        Discriminatively trained deformable partmodels[Project]

 

四、显著性检测SaliencyDetection：

·        Itti, Koch, and Niebur’ saliencydetection [1] [Matlabcode]

·        Frequency-tuned salient region detection[2] [Project]

·        Saliency detection using maximumsymmetric surround [3] [Project]

·        Attention via Information Maximization[4] [Matlabcode]

·        Context-aware saliency detection [5] [Matlab code]

·        Graph-based visual saliency [6] [Matlab code]

·        Saliency detection: A spectral residualapproach. [7] [Matlab code]

·        Segmenting salient objects from imagesand videos. [8] [Matlab code]

·        Saliency Using Natural statistics. [9] [Matlabcode]

·        Discriminant Saliency for VisualRecognition from Cluttered Scenes. [10] [Code]

·        Learning to Predict Where Humans Look[11] [Project]

·        Global Contrast based Salient RegionDetection [12] [Project]

·        Bayesian Saliency via Low and Mid LevelCues[Project]

·        Top-Down Visual Saliency via Joint CRFand Dictionary Learning[Paper][Code]

·        Saliency Detection: A Spectral ResidualApproach[Code]

 

五、图像分类、聚类ImageClassification, Clustering

·        Pyramid Match [1] [Project]

·        Spatial Pyramid Matching [2] [Code]

·        Locality-constrained Linear Coding [3] [Project] [Matlab code]

·        Sparse Coding [4] [Project] [Matlab code]

·        Texture Classification [5] [Project]

·        Multiple Kernels for ImageClassification [6] [Project]

·        Feature Combination [7] [Project]

·        SuperParsing [Code]

·        Large Scale Correlation ClusteringOptimization[Matlab code]

·        Detecting and Sketching the Common[Project]

·        Self-Tuning Spectral Clustering[Project][Code]

·        User Assisted Separation of Reflectionsfrom a Single Image Using a Sparsity Prior[Paper][Code]

·        Filters for Texture Classification[Project]

·        Multiple Kernel Learning for ImageClassification[Project]

·        SLIC Superpixels[Project]

 

六、抠图Image Matting

·        A Closed Form Solution to Natural ImageMatting [Code]

·        Spectral Matting [Project]

·        Learning-based Matting [Code]

 

七、目标跟踪Object Tracking：

·        A Forest of Sensors - Tracking AdaptiveBackground Mixture Models [Project]

·        Object Tracking via Partial LeastSquares Analysis[Paper][Code]

·        Robust Object Tracking with OnlineMultiple Instance Learning[Paper][Code]

·        Online Visual Tracking with Histogramsand Articulating Blocks[Project]

·        Incremental Learning for Robust VisualTracking[Project]

·        Real-time Compressive Tracking[Project]

·        Robust Object Tracking viaSparsity-based Collaborative Model[Project]

·        Visual Tracking via Adaptive StructuralLocal Sparse Appearance Model[Project]

·        Online Discriminative Object Trackingwith Local Sparse Representation[Paper][Code]

·        Superpixel Tracking[Project]

·        Learning Hierarchical ImageRepresentation with Sparsity, Saliency and Locality[Paper][Code]

·        Online Multiple Support InstanceTracking [Paper][Code]

·        Visual Tracking with Online MultipleInstance Learning[Project]

·        Object detection and recognition[Project]

·        Compressive Sensing Resources[Project]

·        Robust Real-Time Visual Tracking usingPixel-Wise Posteriors[Project]

·        Tracking-Learning-Detection[Project][OpenTLD/C++Code]

·        the HandVu：vision-based hand gesture interface[Project]

·        Learning Probabilistic Non-Linear LatentVariable Models for Tracking Complex Activities[Project]

 

八、Kinect：

·        Kinect toolbox[Project]

·        OpenNI[Project]

·        zouxy09 CSDN Blog[Resource]

·        FingerTracker 手指跟踪[code]

 

九、3D相关：

·        3D Reconstruction of a Moving Object[Paper] [Code]

·        Shape From Shading Using LinearApproximation[Code]

·        Combining Shape from Shading and StereoDepth Maps[Project][Code]

·        Shape from Shading: A Survey[Paper][Code]

·        A Spatio-Temporal Descriptor based on 3DGradients (HOG3D)[Project][Code]

·        Multi-camera Scene Reconstruction viaGraph Cuts[Paper][Code]

·        A Fast Marching Formulation ofPerspective Shape from Shading under Frontal Illumination[Paper][Code]

·        Reconstruction:3D Shape, Illumination,Shading, Reflectance, Texture[Project]

·        Monocular Tracking of 3D Human Motionwith a Coordinated Mixture of Factor Analyzers[Code]

·        Learning 3-D Scene Structure from aSingle Still Image[Project]

 

十、机器学习算法：

·        Matlab class for computing ApproximateNearest Nieghbor (ANN) [Matlab class providing interface toANNlibrary]

·        Random Sampling[code]

·        Probabilistic Latent Semantic Analysis(pLSA)[Code]

·        FASTANN and FASTCLUSTER for approximatek-means (AKM)[Project]

·        Fast Intersection / Additive KernelSVMs[Project]

·        SVM[Code]

·        Ensemble learning[Project]

·        Deep Learning[Net]

·        Deep Learning Methods for Vision[Project]

·        Neural Network for Recognition ofHandwritten Digits[Project]

·        Training a deep autoencoder or aclassifier on MNIST digits[Project]

·        THE MNIST DATABASE of handwrittendigits[Project]

·        Ersatz：deep neural networks in the cloud[Project]

·        Deep Learning [Project]

·        sparseLM : Sparse Levenberg-Marquardtnonlinear least squares in C/C++[Project]

·        Weka 3: Data Mining Software in Java[Project]

·        Invited talk "A Tutorial on DeepLearning" by Dr. Kai Yu (余凯)[Video]

·        CNN - Convolutional neural networkclass[Matlab Tool]

·        Yann LeCun's Publications[Wedsite]

·        LeNet-5, convolutional neural networks[Project]

·        Training a deep autoencoder or aclassifier on MNIST digits[Project]

·        Deep Learning 大牛Geoffrey E. Hinton's HomePage[Website]

·        Multiple Instance LogisticDiscriminant-based Metric Learning (MildML) and Logistic Discriminant-basedMetric Learning (LDML)[Code]

·        Sparse coding simulation software[Project]

·        Visual Recognition and Machine LearningSummer School[Software]

 

十一、目标、行为识别Object, ActionRecognition：

·        Action Recognition by DenseTrajectories[Project][Code]

·        Action Recognition Using a DistributedRepresentation of Pose and Appearance[Project]

·        Recognition Using Regions[Paper][Code]

·        2D Articulated Human Pose Estimation[Project]

·        Fast Human Pose Estimation UsingAppearance and Motion via Multi-Dimensional Boosting Regression[Paper][Code]

·        Estimating Human Pose from OccludedImages[Paper][Code]

·        Quasi-dense wide baseline matching[Project]

·        ChaLearn GestureChallenge: Principal motion: PCA-based reconstruction of motionhistograms[Project]

·        Real Time Head Pose Estimation withRandom Regression Forests[Project]

·        2D Action Recognition Serves 3D HumanPose Estimation[Project]

·        A Hough Transform-Based Voting Frameworkfor Action Recognition[Project]

·        Motion Interchange Patterns for ActionRecognition in Unconstrained Videos[Project]

·        2D articulated human pose estimationsoftware[Project]

·        Learning and detecting shape models [code]

·        Progressive Search Space Reduction forHuman Pose Estimation[Project]

·        Learning Non-Rigid 3D Shape from 2DMotion[Project]

 

十二、图像处理：

·        Distance Transforms of SampledFunctions[Project]

·        The Computer Vision Homepage[Project]

·        Efficient appearance distances betweenwindows[code]

·        Image Exploration algorithm[code]

·        Motion Magnification 运动放大 [Project]

·        Bilateral Filtering for Gray and ColorImages 双边滤波器 [Project]

·        A Fast Approximation of the BilateralFilter using a Signal Processing Approach [Project]

 

十三、一些实用工具：

·        EGT: a Toolbox for Multiple ViewGeometry and Visual Servoing[Project] [Code]

·        a development kit of matlab mexfunctions for OpenCV library[Project]

·        Fast Artificial Neural Network Library[Project]

 

十四、人手及指尖检测与识别：

·        finger-detection-and-gesture-recognition [Code]

·        Hand and Finger Detection using JavaCV[Project]

·        Hand and fingers detection[Code]

 

十五、场景解释：

·        Nonparametric Scene Parsing via LabelTransfer [Project]

 

十六、光流Optical flow：

·        High accuracy optical flow using atheory for warping [Project]

·        Dense Trajectories VideoDescription [Project]

·        SIFT Flow: Dense Correspondence acrossScenes and its Applications[Project]

·        KLT: An Implementation of theKanade-Lucas-Tomasi Feature Tracker [Project]

·        Tracking Cars Using Optical Flow[Project]

·        Secrets of optical flow estimation andtheir principles[Project]

·        implmentation of the Black and Anandandense optical flow method[Project]

·        Optical Flow Computation[Project]

·        Beyond Pixels: Exploring NewRepresentations and Applications for Motion Analysis[Project]

·        A Database and Evaluation Methodologyfor Optical Flow[Project]

·        optical flow relative[Project]

·        Robust Optical Flow Estimation [Project]

·        optical flow[Project]

 

十七、图像检索Image Retrieval：

·        Semi-Supervised Distance Metric Learningfor Collaborative Image Retrieval [Paper][code]

 

十八、马尔科夫随机场Markov RandomFields：

·        Markov Random Fields forSuper-Resolution [Project]

·        A Comparative Study of EnergyMinimization Methods for Markov Random Fields with Smoothness-Based Priors [Project]

 

十九、运动检测Motion detection：

·        Moving Object Extraction, Using Modelsor Analysis of Regions [Project]

·        Background Subtraction: Experiments andImprovements for ViBe [Project]

·        A Self-Organizing Approach to BackgroundSubtraction for Visual Surveillance Applications [Project]

·        changedetection.net: A new changedetection benchmark dataset[Project]

·        ViBe - a powerful technique forbackground detection and subtraction in video sequences[Project]

·        Background Subtraction Program[Project]

·        Motion Detection Algorithms[Project]

·        Stuttgart Artificial BackgroundSubtraction Dataset[Project]

·        Object Detection, Motion Estimation, andTracking[Project]

 

Feature Detection and Description

General Libraries: 

·        VLFeat – Implementation of variousfeature descriptors (including SIFT, HOG, and LBP) and covariant featuredetectors (including DoG, Hessian, Harris Laplace, Hessian Laplace, MultiscaleHessian, Multiscale Harris). Easy-to-use Matlab interface. See Modern features: Software – Slidesproviding a demonstration of VLFeat and also links to other software. Checkalso VLFeat hands-on session training

·        OpenCV – Various implementations ofmodern feature detectors and descriptors (SIFT, SURF, FAST, BRIEF, ORB, FREAK,etc.)

 

Fast Keypoint Detectors for Real-time Applications: 

·        FAST – High-speed corner detectorimplementation for a wide variety of platforms

·        AGAST – Even faster than the FAST cornerdetector. A multi-scale version of this method is used for the BRISK descriptor(ECCV 2010).

 

Binary Descriptors for Real-Time Applications: 

·        BRIEF – C++ codefor a fast and accurate interest point descriptor (not invariant to rotationsand scale) (ECCV 2010)

·        ORB – OpenCVimplementation of the Oriented-Brief (ORB) descriptor (invariant to rotations,but not scale)

·        BRISK – Efficient Binary descriptorinvariant to rotations and scale. It includes a Matlab mex interface. (ICCV2011)

·        FREAK – Fasterthan BRISK (invariant to rotations and scale) (CVPR 2012)

 

SIFT and SURF Implementations: 

·        SIFT: VLFeat, OpenCV, Original code by David Lowe, GPUimplementation, OpenSIFT

·        SURF: Herbert Bay’s code, OpenCV, GPU-SURF

 

Other Local Feature Detectors and Descriptors: 

·        VGG Affine Covariant features – Oxfordcode for various affine covariant feature detectors and descriptors.

·        LIOP descriptor – Sourcecode for the Local Intensity order Pattern (LIOP) descriptor (ICCV 2011).

·        Local Symmetry Features – Sourcecode for matching of local symmetry features under large variations inlighting, age, and rendering style (CVPR 2012).

 

Global Image Descriptors: 

·        GIST – Matlabcode for the GIST descriptor

·        CENTRIST – Global visual descriptor forscene categorization and object detection (PAMI 2011)

 

Feature Coding and Pooling 

·        VGG Feature Encoding Toolkit – Sourcecode for various state-of-the-art feature encoding methods – including Standardhard encoding, Kernel codebook encoding, Locality-constrained linear encoding,and Fisher kernel encoding.

·        Spatial Pyramid Matching – Sourcecode for feature pooling based on spatial pyramid matching (widely used forimage classification)

 

Convolutional Nets and Deep Learning 

·        EBLearn – C++Library for Energy-Based Learning. It includes several demos and step-by-stepinstructions to train classifiers based on convolutional neural networks.

·        Torch7 – Provides a matlab-likeenvironment for state-of-the-art machine learning algorithms, including a fastimplementation of convolutional neural networks.

·        Deep Learning - Variouslinks for deep learning software.

 

Part-Based Models 

·        Deformable Part-based Detector – Libraryprovided by the authors of the original paper (state-of-the-art in PASCAL VOCdetection task)

·        Efficient Deformable Part-Based Detector – Branch-and-Boundimplementation for a deformable part-based detector.

·        Accelerated Deformable Part Model –Efficient implementation of a method that achieves the exact same performanceof deformable part-based detectors but with significant acceleration (ECCV2012).

·        Coarse-to-Fine Deformable PartModel – Fast approach for deformable object detection (CVPR 2011).

·        Poselets – C++ and Matlab versions forobject detection based on poselets.

·        Part-based Face Detector and PoseEstimation – Implementation of a unified approach for face detection, poseestimation, and landmark localization (CVPR 2012).

 

Attributes and Semantic Features 

·        Relative Attributes – Modified implementation ofRankSVM to train Relative Attributes (ICCV 2011).

·        Object Bank – Implementation of object banksemantic features (NIPS 2010). See also ActionBank

·        Classemes, Picodes, andMeta-class features – Software for extractinghigh-level image descriptors (ECCV 2010, NIPS 2011, CVPR 2012).

 

Large-Scale Learning 

·        Additive Kernels – Source code for fast additivekernel SVM classifiers (PAMI 2013).

·        LIBLINEAR – Library for large-scale linearSVM classification.

·        VLFeat – Implementation for Pegasos SVMand Homogeneous Kernel map.

 

Fast Indexing and Image Retrieval 

·        FLANN – Library for performing fastapproximate nearest neighbor.

·        Kernelized LSH – Source code for KernelizedLocality-Sensitive Hashing (ICCV 2009).

·        ITQ Binary codes – Code forgeneration of small binary codes using Iterative Quantization and otherbaselines such as Locality-Sensitive-Hashing (CVPR 2011).

·        INRIA Image Retrieval –Efficient code for state-of-the-art large-scale image retrieval (CVPR 2011).

 

Object Detection 

·        See Part-based Models and Convolutional Nets above.

·        Pedestrian Detection at 100fps – Veryfast and accurate pedestrian detector (CVPR 2012).

·        Caltech Pedestrian DetectionBenchmark – Excellent resource for pedestrian detection, with various linksfor state-of-the-art implementations.

·        OpenCV – Enhancedimplementation of Viola&Jones real-time object detector, with trainedmodels for face detection.

·        Efficient Subwindow Search – Sourcecode for branch-and-bound optimization for efficient object localization (CVPR2008).

 

3D Recognition 

·        Point-Cloud Library – Libraryfor 3D image and point cloud processing.

 

Action Recognition 

·        ActionBank – Source code for actionrecognition based on the ActionBank representation (CVPR 2012).

·        STIP Features – software for computingspace-time interest point descriptors

·        Independent Subspace Analysis – Look forStacked ISA for Videos (CVPR 2011)

·        Velocity Histories of Tracked Keypoints - C++ codefor activity recognition using the velocity histories of tracked keypoints(ICCV 2009)

---

 

Datasets

 

Attributes 

·        Animals with Attributes – 30,475images of 50 animals classes with 6 pre-extracted feature representations foreach image.

·        aYahoo and aPascal –Attribute annotations for images collected from Yahoo and Pascal VOC 2008.

·        FaceTracer – 15,000 faces annotated with 10attributes and fiducial points.

·        PubFig – 58,797 face images of 200 peoplewith 73 attribute classifier outputs.

·        LFW – 13,233face images of 5,749 people with 73 attribute classifier outputs.

·        Human Attributes – 8,000 people with annotatedattributes. Check also this link for another dataset of humanattributes.

·        SUN Attribute Database –Large-scale scene attribute database with a taxonomy of 102 attributes.

·        ImageNet Attributes – Variety of attribute labels forthe ImageNet dataset.

·        Relative attributes – Data for OSR and a subset ofPubFig datasets. Check also this link for the WhittleSearch data.

·        Attribute Discovery Dataset – Imagesof shopping categories associated with textual descriptions.

 

Fine-grained Visual Categorization 

·        Caltech-UCSD Birds Dataset – Hundredsof bird categories with annotated parts and attributes.

·        Stanford Dogs Dataset – 20,000images of 120 breeds of dogs from around the world.

·        Oxford-IIIT Pet Dataset – 37category pet dataset with roughly 200 images for each class. Pixel level trimapsegmentation is included.

·        Leeds Butterfly Dataset – 832images of 10 species of butterflies.

·        Oxford Flower Dataset – Hundredsof flower categories.

 

Face Detection 

·        FDDB – UMassface detection dataset and benchmark (5,000+ faces)

·        CMU/MIT –Classical face detection dataset.

 

Face Recognition 

·        Face Recognition Homepage – Largecollection of face recognition datasets.

·        LFW – UMassunconstrained face recognition dataset (13,000+ face images).

·        NIST Face Homepage – includesface recognition grand challenge (FRGC), vendor tests (FRVT) and others.

·        CMU Multi-PIE – containsmore than 750,000 images of 337 people, with 15 different views and 19 lightingconditions.

·        FERET – Classical face recognitiondataset.

·        Deng Cai’s face dataset in Matlab Format – Easy touse if you want play with simple face datasets including Yale, ORL, PIE, andExtended Yale B.

·        SCFace – Low-resolution face datasetcaptured from surveillance cameras.

 

Handwritten Digits 

·        MNIST – largedataset containing a training set of 60,000 examples, and a test set of 10,000examples.

 

Pedestrian Detection

·        Caltech Pedestrian DetectionBenchmark – 10 hours of video taken from a vehicle,350K bounding boxes forabout 2.3K unique pedestrians.

·        INRIA Person Dataset –Currently one of the most popular pedestrian detection datasets.

·        ETH Pedestrian Dataset – Urbandataset captured from a stereo rig mounted on a stroller.

·        TUD-Brussels Pedestrian Dataset – Datasetwith image pairs recorded in an crowded urban setting with an onboard camera.

·        PASCAL Human Detection – One of20 categories in PASCAL VOC detection challenges.

·        USC Pedestrian Dataset – Smalldataset captured from surveillance cameras.

 

Generic Object Recognition 

·        ImageNet –Currently the largest visual recognition dataset in terms of number ofcategories and images.

·        Tiny Images – 80 million 32x32 low resolutionimages.

·        Pascal VOC – One of the most influentialvisual recognition datasets.

·        Caltech 101 / Caltech 256 – Popular image datasetscontaining 101 and 256 object categories, respectively.

·        MIT LabelMe – Online annotation tool forbuilding computer vision databases.

 

Scene Recognition

·        MIT SUN Dataset – MITscene understanding dataset.

·        UIUC Fifteen Scene Categories – Datasetof 15 natural scene categories.

 

Feature Detection and Description 

·        VGG Affine Dataset – Widely used dataset formeasuring performance of feature detection and description. CheckVLBenchmarks for an evaluation framework.

 

Action Recognition

·        Benchmarking Activity Recognition – CVPR2012 tutorial covering various datasets for action recognition.

 

RGBD Recognition 

·        RGB-D Object Dataset – Datasetcontaining 300 common household objects

 

Reference:

[1]: http://rogerioferis.com/VisualRecognitionAndSearch/Resources.html