一、特征提取Feature Extraction：
l SIFT [1] [Demo program][SIFT Library] [VLFeat]
l PCA-SIFT [2] [Project]
l Affine-SIFT [3] [Project]
l SURF [4] [OpenSURF] [Matlab Wrapper]
l Affine Covariant Features [5] [Oxford project]
l MSER [6] [Oxford project] [VLFeat]
l Geometric Blur [7] [Code]
l Local Self-Similarity Descriptor [8] [Oxford implementation]
l Global and Efficient Self-Similarity [9] [Code]
l Histogram of Oriented Graidents [10] [INRIA Object Localization Toolkit] [OLT toolkit for Windows]
l GIST [11] [Project]
l Shape Context [12] [Project]
l Color Descriptor [13] [Project]
l Pyramids of Histograms of Oriented Gradients [Code]
l Space-Time Interest Points (STIP) [14][Project] [Code]
l Boundary Preserving Dense Local Regions [15][Project]
l Weighted Histogram[Code]
l Histogram-based Interest Points Detectors[Paper][Code]
l An OpenCV - C++ implementation of Local Self Similarity Descriptors [Project]
l Fast Sparse Representation with Prototypes[Project]
l Corner Detection [Project]
l AGAST Corner Detector: faster than FAST and even FAST-ER[Project]
l Real-time Facial Feature Detection using Conditional Regression Forests[Project]
l Global and Efficient Self-Similarity for Object Classification and Detection[code]
l WαSH: Weighted α-Shapes for Local Feature Detection[Project]
l HOG[Project]
l Online Selection of Discriminative Tracking Features[Project]
二、图像分割Image Segmentation：
l Normalized Cut [1] [Matlab code]
l Gerg Mori’ Superpixel code [2] [Matlab code]
l Efficient Graph-based Image Segmentation [3] [C++ code] [Matlab wrapper]
l Mean-Shift Image Segmentation [4] [EDISON C++ code] [Matlab wrapper]
l OWT-UCM Hierarchical Segmentation [5] [Resources]
l Turbepixels [6] [Matlab code 32bit] [Matlab code 64bit] [Updated code]
l Quick-Shift [7] [VLFeat]
l SLIC Superpixels [8] [Project]
l Segmentation by Minimum Code Length [9] [Project]
l Biased Normalized Cut [10] [Project]
l Segmentation Tree [11-12] [Project]
l Entropy Rate Superpixel Segmentation [13] [Code]
l Fast Approximate Energy Minimization via Graph Cuts[Paper][Code]
l Efficient Planar Graph Cuts with Applications in Computer Vision[Paper][Code]
l Isoperimetric Graph Partitioning for Image Segmentation[Paper][Code]
l Random Walks for Image Segmentation[Paper][Code]
l Blossom V: A new implementation of a minimum cost perfect matching algorithm[Code]
l An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Computer Vision[Paper][Code]
l Geodesic Star Convexity for Interactive Image Segmentation[Project]
l Contour Detection and Image Segmentation Resources[Project][Code]
l Biased Normalized Cuts[Project]
l Max-flow/min-cut[Project]
l Chan-Vese Segmentation using Level Set[Project]
l A Toolbox of Level Set Methods[Project]
l Re-initialization Free Level Set Evolution via Reaction Diffusion[Project]
l Improved C-V active contour model[Paper][Code]
l A Variational Multiphase Level Set Approach to Simultaneous Segmentation and Bias Correction[Paper][Code]
l Level Set Method Research by Chunming Li[Project]
l ClassCut for Unsupervised Class Segmentation[code]
l SEEDS: Superpixels Extracted via Energy-Driven Sampling [Project][other]
三、目标检测Object Detection：
l A simple object detector with boosting [Project]
l INRIA Object Detection and Localization Toolkit [1] [Project]
l Discriminatively Trained Deformable Part Models [2] [Project]
l Cascade Object Detection with Deformable Part Models [3] [Project]
l Poselet [4] [Project]
l Implicit Shape Model [5] [Project]
l Viola and Jones’s Face Detection [6] [Project]
l Bayesian Modelling of Dyanmic Scenes for Object Detection[Paper][Code]
l Hand detection using multiple proposals[Project]
l Color Constancy, Intrinsic Images, and Shape Estimation[Paper][Code]
l Discriminatively trained deformable part models[Project]
l Gradient Response Maps for Real-Time Detection of Texture-Less Objects: LineMOD [Project]
l Image Processing On Line[Project]
l Robust Optical Flow Estimation[Project]
l Where's Waldo: Matching People in Images of Crowds[Project]
l Scalable Multi-class Object Detection[Project]
l Class-Specific Hough Forests for Object Detection[Project]
l Deformed Lattice Detection In Real-World Images[Project]
l Discriminatively trained deformable part models[Project]
四、显著性检测Saliency Detection：
l Itti, Koch, and Niebur’ saliency detection [1] [Matlab code]
l Frequency-tuned salient region detection [2] [Project]
l Saliency detection using maximum symmetric surround [3] [Project]
l Attention via Information Maximization [4] [Matlab code]
l Context-aware saliency detection [5] [Matlab code]
l Graph-based visual saliency [6] [Matlab code]
l Saliency detection: A spectral residual approach. [7] [Matlab code]
l Segmenting salient objects from images and videos. [8] [Matlab code]
l Saliency Using Natural statistics. [9] [Matlab code]
l Discriminant Saliency for Visual Recognition from Cluttered Scenes. [10] [Code]
l Learning to Predict Where Humans Look [11] [Project]
l Global Contrast based Salient Region Detection [12] [Project]
l Bayesian Saliency via Low and Mid Level Cues[Project]
l Top-Down Visual Saliency via Joint CRF and Dictionary Learning[Paper][Code]
l Saliency Detection: A Spectral Residual Approach[Code]
五、图像分类、聚类Image Classification, Clustering
l Pyramid Match [1] [Project]
l Spatial Pyramid Matching [2] [Code]
l Locality-constrained Linear Coding [3] [Project] [Matlab code]
l Sparse Coding [4] [Project] [Matlab code]
l Texture Classification [5] [Project]
l Multiple Kernels for Image Classification [6] [Project]
l Feature Combination [7] [Project]
l SuperParsing [Code]
l Large Scale Correlation Clustering Optimization[Matlab code]
l Detecting and Sketching the Common[Project]
l Self-Tuning Spectral Clustering[Project][Code]
l User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior[Paper][Code]
l Filters for Texture Classification[Project]
l Multiple Kernel Learning for Image Classification[Project]
l SLIC Superpixels[Project]
六、抠图Image Matting
l A Closed Form Solution to Natural Image Matting [Code]
l Spectral Matting [Project]
l Learning-based Matting [Code]
七、目标跟踪Object Tracking：
l A Forest of Sensors - Tracking Adaptive Background Mixture Models [Project]
l Object Tracking via Partial Least Squares Analysis[Paper][Code]
l Robust Object Tracking with Online Multiple Instance Learning[Paper][Code]
l Online Visual Tracking with Histograms and Articulating Blocks[Project]
l Incremental Learning for Robust Visual Tracking[Project]
l Real-time Compressive Tracking[Project]
l Robust Object Tracking via Sparsity-based Collaborative Model[Project]
l Visual Tracking via Adaptive Structural Local Sparse Appearance Model[Project]
l Online Discriminative Object Tracking with Local Sparse Representation[Paper][Code]
l Superpixel Tracking[Project]
l Learning Hierarchical Image Representation with Sparsity, Saliency and Locality[Paper][Code]
l Online Multiple Support Instance Tracking [Paper][Code]
l Visual Tracking with Online Multiple Instance Learning[Project]
l Object detection and recognition[Project]
l Compressive Sensing Resources[Project]
l Robust Real-Time Visual Tracking using Pixel-Wise Posteriors[Project]
l Tracking-Learning-Detection[Project][OpenTLD/C++ Code]
l the HandVu：vision-based hand gesture interface[Project]
l Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities[Project]
八、Kinect：
l Kinect toolbox[Project]
l OpenNI[Project]
l zouxy09 CSDN Blog[Resource]
l FingerTracker 手指跟踪[code]
九、3D相关：
l 3D Reconstruction of a Moving Object[Paper] [Code]
l Shape From Shading Using Linear Approximation[Code]
l Combining Shape from Shading and Stereo Depth Maps[Project][Code]
l Shape from Shading: A Survey[Paper][Code]
l A Spatio-Temporal Descriptor based on 3D Gradients (HOG3D)[Project][Code]
l Multi-camera Scene Reconstruction via Graph Cuts[Paper][Code]
l A Fast Marching Formulation of Perspective Shape from Shading under Frontal Illumination[Paper][Code]
l Reconstruction:3D Shape, Illumination, Shading, Reflectance, Texture[Project]
l Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers[Code]
l Learning 3-D Scene Structure from a Single Still Image[Project]
十、机器学习算法：
l Matlab class for computing Approximate Nearest Nieghbor (ANN) [Matlab class providing interface toANN library]
l Random Sampling[code]
l Probabilistic Latent Semantic Analysis (pLSA)[Code]
l FASTANN and FASTCLUSTER for approximate k-means (AKM)[Project]
l Fast Intersection / Additive Kernel SVMs[Project]
l SVM[Code]
l Ensemble learning[Project]
l Deep Learning[Net]
l Deep Learning Methods for Vision[Project]
l Neural Network for Recognition of Handwritten Digits[Project]
l Training a deep autoencoder or a classifier on MNIST digits[Project]
l THE MNIST DATABASE of handwritten digits[Project]
l Ersatz：deep neural networks in the cloud[Project]
l Deep Learning [Project]
l sparseLM : Sparse Levenberg-Marquardt nonlinear least squares in C/C++[Project]
l Weka 3: Data Mining Software in Java[Project]
l Invited talk "A Tutorial on Deep Learning" by Dr. Kai Yu (余凯)[Video]
l CNN - Convolutional neural network class[Matlab Tool]
l Yann LeCun's Publications[Wedsite]
l LeNet-5, convolutional neural networks[Project]
l Training a deep autoencoder or a classifier on MNIST digits[Project]
l Deep Learning 大牛Geoffrey E. Hinton's HomePage[Website]
l Multiple Instance Logistic Discriminant-based Metric Learning (MildML) and Logistic Discriminant-based Metric Learning (LDML)[Code]
l Sparse coding simulation software[Project]
l Visual Recognition and Machine Learning Summer School[Software]
十一、目标、行为识别Object, Action Recognition：
l Action Recognition by Dense Trajectories[Project][Code]
l Action Recognition Using a Distributed Representation of Pose and Appearance[Project]
l Recognition Using Regions[Paper][Code]
l 2D Articulated Human Pose Estimation[Project]
l Fast Human Pose Estimation Using Appearance and Motion via Multi-Dimensional Boosting Regression[Paper][Code]
l Estimating Human Pose from Occluded Images[Paper][Code]
l Quasi-dense wide baseline matching[Project]
l ChaLearn Gesture Challenge: Principal motion: PCA-based reconstruction of motion histograms[Project]
l Real Time Head Pose Estimation with Random Regression Forests[Project]
l 2D Action Recognition Serves 3D Human Pose Estimation[Project]
l A Hough Transform-Based Voting Framework for Action Recognition[Project]
l Motion Interchange Patterns for Action Recognition in Unconstrained Videos[Project]
l 2D articulated human pose estimation software[Project]
l Learning and detecting shape models [code]
l Progressive Search Space Reduction for Human Pose Estimation[Project]
l Learning Non-Rigid 3D Shape from 2D Motion[Project]
十二、图像处理：
l Distance Transforms of Sampled Functions[Project]
l The Computer Vision Homepage[Project]
l Efficient appearance distances between windows[code]
l Image Exploration algorithm[code]
l Motion Magnification 运动放大 [Project]
l Bilateral Filtering for Gray and Color Images 双边滤波器 [Project]
l A Fast Approximation of the Bilateral Filter using a Signal Processing Approach [Project]
十三、一些实用工具：
l EGT: a Toolbox for Multiple View Geometry and Visual Servoing[Project] [Code]
l a development kit of matlab mex functions for OpenCV library[Project]
l Fast Artificial Neural Network Library[Project]
十四、人手及指尖检测与识别：
l finger-detection-and-gesture-recognition [Code]
l Hand and Finger Detection using JavaCV[Project]
l Hand and fingers detection[Code]
十五、场景解释：
l Nonparametric Scene Parsing via Label Transfer [Project]
十六、光流Optical flow：
l High accuracy optical flow using a theory for warping [Project]
l Dense Trajectories Video Description [Project]
l SIFT Flow: Dense Correspondence across Scenes and its Applications[Project]
l KLT: An Implementation of the Kanade-Lucas-Tomasi Feature Tracker [Project]
l Tracking Cars Using Optical Flow[Project]
l Secrets of optical flow estimation and their principles[Project]
l implmentation of the Black and Anandan dense optical flow method[Project]
l Optical Flow Computation[Project]
l Beyond Pixels: Exploring New Representations and Applications for Motion Analysis[Project]
l A Database and Evaluation Methodology for Optical Flow[Project]
l optical flow relative[Project]
l Robust Optical Flow Estimation [Project]
l optical flow[Project]
十七、图像检索Image Retrieval：
l Semi-Supervised Distance Metric Learning for Collaborative Image Retrieval [Paper][code]
十八、马尔科夫随机场Markov Random Fields：
l Markov Random Fields for Super-Resolution [Project]
l A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors [Project]
十九、运动检测Motion detection：
l Moving Object Extraction, Using Models or Analysis of Regions [Project]
l Background Subtraction: Experiments and Improvements for ViBe [Project]
l A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications [Project]
l changedetection.net: A new change detection benchmark dataset[Project]
l ViBe - a powerful technique for background detection and subtraction in video sequences[Project]
l Background Subtraction Program[Project]
l Motion Detection Algorithms[Project]
l Stuttgart Artificial Background Subtraction Dataset[Project]
l Object Detection, Motion Estimation, and Tracking[Project]
Feature Detection and Description
General Libraries:
l VLFeat – Implementation of various feature descriptors (including SIFT, HOG, and LBP) and covariant feature detectors (including DoG, Hessian, Harris Laplace, Hessian Laplace, Multiscale Hessian, Multiscale Harris). Easy-to-use Matlab interface. See Modern features: Software – Slides providing a demonstration of VLFeat and also links to other software. Check also VLFeat hands-on session training
l OpenCV – Various implementations of modern feature detectors and descriptors (SIFT, SURF, FAST, BRIEF, ORB, FREAK, etc.)
Fast Keypoint Detectors for Real-time Applications:
l FAST – High-speed corner detector implementation for a wide variety of platforms
l AGAST – Even faster than the FAST corner detector. A multi-scale version of this method is used for the BRISK descriptor (ECCV 2010).
Binary Descriptors for Real-Time Applications:
l BRIEF – C++ code for a fast and accurate interest point descriptor (not invariant to rotations and scale) (ECCV 2010)
l ORB – OpenCV implementation of the Oriented-Brief (ORB) descriptor (invariant to rotations, but not scale)
l BRISK – Efficient Binary descriptor invariant to rotations and scale. It includes a Matlab mex interface. (ICCV 2011)
l FREAK – Faster than BRISK (invariant to rotations and scale) (CVPR 2012)
SIFT and SURF Implementations:
l SIFT: VLFeat, OpenCV, Original code by David Lowe, GPU implementation, OpenSIFT
l SURF: Herbert Bay’s code, OpenCV, GPU-SURF
Other Local Feature Detectors and Descriptors:
l VGG Affine Covariant features – Oxford code for various affine covariant feature detectors and descriptors.
l LIOP descriptor – Source code for the Local Intensity order Pattern (LIOP) descriptor (ICCV 2011).
l Local Symmetry Features – Source code for matching of local symmetry features under large variations in lighting, age, and rendering style (CVPR 2012).
Global Image Descriptors:
l GIST – Matlab code for the GIST descriptor
l CENTRIST – Global visual descriptor for scene categorization and object detection (PAMI 2011)
Feature Coding and Pooling
l VGG Feature Encoding Toolkit – Source code for various state-of-the-art feature encoding methods – including Standard hard encoding, Kernel codebook encoding, Locality-constrained linear encoding, and Fisher kernel encoding.
l Spatial Pyramid Matching – Source code for feature pooling based on spatial pyramid matching (widely used for image classification)
Convolutional Nets and Deep Learning
l EBLearn – C++ Library for Energy-Based Learning. It includes several demos and step-by-step instructions to train classifiers based on convolutional neural networks.
l Torch7 – Provides a matlab-like environment for state-of-the-art machine learning algorithms, including a fast implementation of convolutional neural networks.
l Deep Learning - Various links for deep learning software.
Part-Based Models
l Deformable Part-based Detector – Library provided by the authors of the original paper (state-of-the-art in PASCAL VOC detection task)
l Efficient Deformable Part-Based Detector – Branch-and-Bound implementation for a deformable part-based detector.
l Accelerated Deformable Part Model – Efficient implementation of a method that achieves the exact same performance of deformable part-based detectors but with significant acceleration (ECCV 2012).
l Coarse-to-Fine Deformable Part Model – Fast approach for deformable object detection (CVPR 2011).
l Poselets – C++ and Matlab versions for object detection based on poselets.
l Part-based Face Detector and Pose Estimation – Implementation of a unified approach for face detection, pose estimation, and landmark localization (CVPR 2012).
Attributes and Semantic Features
l Relative Attributes – Modified implementation of RankSVM to train Relative Attributes (ICCV 2011).
l Object Bank – Implementation of object bank semantic features (NIPS 2010). See also ActionBank
l Classemes, Picodes, and Meta-class features – Software for extracting high-level image descriptors (ECCV 2010, NIPS 2011, CVPR 2012).
Large-Scale Learning
l Additive Kernels – Source code for fast additive kernel SVM classifiers (PAMI 2013).
l LIBLINEAR – Library for large-scale linear SVM classification.
l VLFeat – Implementation for Pegasos SVM and Homogeneous Kernel map.
Fast Indexing and Image Retrieval
l FLANN – Library for performing fast approximate nearest neighbor.
l Kernelized LSH – Source code for Kernelized Locality-Sensitive Hashing (ICCV 2009).
l ITQ Binary codes – Code for generation of small binary codes using Iterative Quantization and other baselines such as Locality-Sensitive-Hashing (CVPR 2011).
l INRIA Image Retrieval – Efficient code for state-of-the-art large-scale image retrieval (CVPR 2011).
Object Detection
l See Part-based Models and Convolutional Nets above.
l Pedestrian Detection at 100fps – Very fast and accurate pedestrian detector (CVPR 2012).
l Caltech Pedestrian Detection Benchmark – Excellent resource for pedestrian detection, with various links for state-of-the-art implementations.
l OpenCV – Enhanced implementation of Viola&Jones real-time object detector, with trained models for face detection.
l Efficient Subwindow Search – Source code for branch-and-bound optimization for efficient object localization (CVPR 2008).
3D Recognition
l Point-Cloud Library – Library for 3D image and point cloud processing.
Action Recognition
l ActionBank – Source code for action recognition based on the ActionBank representation (CVPR 2012).
l STIP Features – software for computing space-time interest point descriptors
l Independent Subspace Analysis – Look for Stacked ISA for Videos (CVPR 2011)
l Velocity Histories of Tracked Keypoints - C++ code for activity recognition using the velocity histories of tracked keypoints (ICCV 2009)
Datasets
Attributes
l Animals with Attributes – 30,475 images of 50 animals classes with 6 pre-extracted feature representations for each image.
l aYahoo and aPascal – Attribute annotations for images collected from Yahoo and Pascal VOC 2008.
l FaceTracer – 15,000 faces annotated with 10 attributes and fiducial points.
l PubFig – 58,797 face images of 200 people with 73 attribute classifier outputs.
l LFW – 13,233 face images of 5,749 people with 73 attribute classifier outputs.
l Human Attributes – 8,000 people with annotated attributes. Check also this link for another dataset of human attributes.
l SUN Attribute Database – Large-scale scene attribute database with a taxonomy of 102 attributes.
l ImageNet Attributes – Variety of attribute labels for the ImageNet dataset.
l Relative attributes – Data for OSR and a subset of PubFig datasets. Check also this link for the WhittleSearch data.
l Attribute Discovery Dataset – Images of shopping categories associated with textual descriptions.
Fine-grained Visual Categorization
l Caltech-UCSD Birds Dataset – Hundreds of bird categories with annotated parts and attributes.
l Stanford Dogs Dataset – 20,000 images of 120 breeds of dogs from around the world.
l Oxford-IIIT Pet Dataset – 37 category pet dataset with roughly 200 images for each class. Pixel level trimap segmentation is included.
l Leeds Butterfly Dataset – 832 images of 10 species of butterflies.
l Oxford Flower Dataset – Hundreds of flower categories.
Face Detection
l FDDB – UMass face detection dataset and benchmark (5,000+ faces)
l CMU/MIT – Classical face detection dataset.
Face Recognition
l Face Recognition Homepage – Large collection of face recognition datasets.
l LFW – UMass unconstrained face recognition dataset (13,000+ face images).
l NIST Face Homepage – includes face recognition grand challenge (FRGC), vendor tests (FRVT) and others.
l CMU Multi-PIE – contains more than 750,000 images of 337 people, with 15 different views and 19 lighting conditions.
l FERET – Classical face recognition dataset.
l Deng Cai’s face dataset in Matlab Format – Easy to use if you want play with simple face datasets including Yale, ORL, PIE, and Extended Yale B.
l SCFace – Low-resolution face dataset captured from surveillance cameras.
Handwritten Digits
l MNIST – large dataset containing a training set of 60,000 examples, and a test set of 10,000 examples.
Pedestrian Detection
l Caltech Pedestrian Detection Benchmark – 10 hours of video taken from a vehicle,350K bounding boxes for about 2.3K unique pedestrians.
l INRIA Person Dataset – Currently one of the most popular pedestrian detection datasets.
l ETH Pedestrian Dataset – Urban dataset captured from a stereo rig mounted on a stroller.
l TUD-Brussels Pedestrian Dataset – Dataset with image pairs recorded in an crowded urban setting with an onboard camera.
l PASCAL Human Detection – One of 20 categories in PASCAL VOC detection challenges.
l USC Pedestrian Dataset – Small dataset captured from surveillance cameras.
Generic Object Recognition
l ImageNet – Currently the largest visual recognition dataset in terms of number of categories and images.
l Tiny Images – 80 million 32x32 low resolution images.
l Pascal VOC – One of the most influential visual recognition datasets.
l Caltech 101 / Caltech 256 – Popular image datasets containing 101 and 256 object categories, respectively.
l MIT LabelMe – Online annotation tool for building computer vision databases.
Scene Recognition
l MIT SUN Dataset – MIT scene understanding dataset.
l UIUC Fifteen Scene Categories – Dataset of 15 natural scene categories.
Feature Detection and Description
l VGG Affine Dataset – Widely used dataset for measuring performance of feature detection and description. CheckVLBenchmarks for an evaluation framework.
Action Recognition
l Benchmarking Activity Recognition – CVPR 2012 tutorial covering various datasets for action recognition.
RGBD Recognition
l RGB-D Object Dataset – Dataset containing 300 common household objects
Reference:
[1]: http://rogerioferis.com/VisualRecognitionAndSearch/Resources.html