CV 资源汇总

In the last couple of years there has been a trend on make code available for many of the state of the art papers. In most of the cases the code is Matlab -like scripts. Nevertheless, for heavy duty tasks (like object detection) some code is available in c/c++. In this page there are some of the resources that I frequently visit. I have been updating the original list of Rogelio Feris page. 

Feature Detection and Description

General Libraries: 

• 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

• OpenCV – Various implementations of modern feature detectors and descriptors (SIFT, SURF, FAST, BRIEF, ORB, FREAK, etc.)

Fast Keypoint Detectors for Real-time Applications: 

• FAST – High-speed corner detector implementation for a wide variety of platforms

• 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: 

• BRIEF – C++ code for a fast and accurate interest point descriptor (not invariant to rotations and scale) (ECCV 2010)

• ORB – OpenCV implementation of the Oriented-Brief (ORB) descriptor (invariant to rotations, but not scale)

• BRISK – Efficient Binary descriptor invariant to rotations and scale. It includes a Matlab mex interface. (ICCV 2011)

• FREAK – Of my Good Friend Alex Alahi --- Faster than BRISK (invariant to rotations and scale) (CVPR 2012) 

SIFT and SURF Implementations: 

• SIFT: VLFeat, OpenCV, Original code by David Lowe, GPU implementation, OpenSIFT

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

Other Local Feature Detectors and Descriptors: 

• VGG Affine Covariant features – Oxford code for various affine covariant feature detectors and descriptors.

• LIOP descriptor – Source code for the Local Intensity order Pattern (LIOP) descriptor (ICCV 2011).

• 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: 

• GIST – Matlab code for the GIST descriptor

• CENTRIST – Global visual descriptor for scene categorization and object detection (PAMI 2011)

 

Feature Coding and Pooling 

• 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.

• Spatial Pyramid Matching – Source code for feature pooling based on spatial pyramid matching (widely used for image classification)

 

Convolutional Nets and Deep Learning 

 

• NEW DeepLEarnToolbox: CNN, DBN, NN, SAE, CAE - All the algorithms are implemented in matlab with training and testing examples on mnist. 

• NEW Caffe –Caffe aims to provide computer vision scientists with a clean, modifiable implementation of state-of-the-art deep learning algorithms. For example, network structure is easily specified in separate config files, with no mess of hard-coded parameters in the code.

• NEW Libccv – A C library for computer vision in general. Now also includes convolutional neural networks. 

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

• Torch7 – Provides a matlab-like environment for state-of-the-art machine learning algorithms, including a fast implementation of convolutional neural networks.

• Deep Learning - Various links for deep learning software.

 

Part-Based Models 

• Deformable Part-based Detector – Library provided by the authors of the original paper (state-of-the-art in PASCAL VOC detection task)

• Efficient Deformable Part-Based Detector – Branch-and-Bound implementation for a deformable part-based detector.

• 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).

• Coarse-to-Fine Deformable Part Model – Fast approach for deformable object detection (CVPR 2011).

• Poselets – C++ and Matlab versions for object detection based on poselets.

• 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 

• Relative Attributes – Modified implementation of RankSVM to train Relative Attributes (ICCV 2011).

• Object Bank – Implementation of object bank semantic features (NIPS 2010). See also ActionBank

• Classemes, Picodes, and Meta-class features – Software for extracting high-level image descriptors (ECCV 2010, NIPS 2011, CVPR 2012).

 

Large-Scale Learning 

• Additive Kernels – Source code for fast additive kernel SVM classifiers (PAMI 2013).

• LIBLINEAR – Library for large-scale linear SVM classification.

• VLFeat – Implementation for Pegasos SVM and Homogeneous Kernel map.

 

Fast Indexing and Image Retrieval 

• FLANN – Library for performing fast approximate nearest neighbor.

• Kernelized LSH – Source code for Kernelized Locality-Sensitive Hashing (ICCV 2009).

• ITQ Binary codes – Code for generation of small binary codes using Iterative Quantization and other baselines 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 – Very fast and accurate pedestrian detector (CVPR 2012).

• Caltech Pedestrian Detection Benchmark – Excellent resource for pedestrian detection, with various links for state-of-the-art implementations.

• OpenCV – Enhanced implementation of Viola&Jones real-time object detector, with trained models for face detection.

• Efficient Subwindow Search – Source code for branch-and-bound optimization for efficient object localization (CVPR 2008).

 

3D Recognition 

• Point-Cloud Library – Library for 3D image and point cloud processing.

 

Action Recognition 

• ActionBank – Source code for action recognition based on the ActionBank representation (CVPR 2012).

• STIP Features – software for computing space-time interest point descriptors

• Independent Subspace Analysis – Look for Stacked ISA for Videos (CVPR 2011)

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

 

---

Datasets

 

Attributes 

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

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

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

• PubFig – 58,797 face images of 200 people with 73 attribute classifier outputs.

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

• Human Attributes – 8,000 people with annotated attributes. Check also this link for another dataset of human attributes.

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

• ImageNet Attributes – Variety of attribute labels for the ImageNet dataset.

• Relative attributes – Data for OSR and a subset of PubFig datasets. Check also this link for the WhittleSearch data.

• Attribute Discovery Dataset – Images of shopping categories associated with textual descriptions.

 

Fine-grained Visual Categorization 

• Caltech-UCSD Birds Dataset – Hundreds of bird categories with annotated parts and attributes.

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

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

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

• Oxford Flower Dataset – Hundreds of flower categories.

 

Face Detection 

• FDDB – UMass face detection dataset and benchmark (5,000+ faces)

• CMU/MIT – Classical face detection dataset.

 

Face Recognition 

• Face Recognition Homepage – Large collection of face recognition datasets.

• LFW – UMass unconstrained face recognition dataset (13,000+ face images).

• NIST Face Homepage – includes face recognition grand challenge (FRGC), vendor tests (FRVT) and others.

• CMU Multi-PIE – contains more than 750,000 images of 337 people, with 15 different views and 19 lighting conditions.

• FERET – Classical face recognition dataset.

• 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.

• SCFace – Low-resolution face dataset captured from surveillance cameras.

 

Handwritten Digits 

• MNIST – large dataset containing a training set of 60,000 examples, and a test set of 10,000 examples.

 

Pedestrian Detection

• Caltech Pedestrian Detection Benchmark – 10 hours of video taken from a vehicle,350K bounding boxes for about 2.3K unique pedestrians.

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

• ETH Pedestrian Dataset – Urban dataset captured from a stereo rig mounted on a stroller.

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

• PASCAL Human Detection – One of 20 categories in PASCAL VOC detection challenges.

• USC Pedestrian Dataset – Small dataset captured from surveillance cameras.

 

Generic Object Recognition 

• ImageNet – Currently the largest visual recognition dataset in terms of number of categories and images.

• Tiny Images – 80 million 32x32 low resolution images.

• Pascal VOC – One of the most influential visual recognition datasets.

• Caltech 101 / Caltech 256 – Popular image datasets containing 101 and 256 object categories, respectively.

• MIT LabelMe – Online annotation tool for building computer vision databases.

 

Scene Recognition

• MIT SUN Dataset – MIT scene understanding dataset.

• UIUC Fifteen Scene Categories – Dataset of 15 natural scene categories.

 

Feature Detection and Description 

• VGG Affine Dataset – Widely used dataset for measuring performance of feature detection and description. Check VLBenchmarksfor an evaluation framework.

 

Action Recognition

• Benchmarking Activity Recognition – CVPR 2012 tutorial covering various datasets for action recognition.

 

RGBD Recognition 

• RGB-D Object Dataset – Dataset containing 300 common household objects

• RGB-D Pedestrian Dataset – The data contains mostly upright walking and standing persons seen from different orientations and with different levels of occlusions.

• Microsoft Research 7 Scenes – RGB-D Data for dense tracking

转自：http://nmr-spectrometers.com/vision/index.php/SOFTWARE

vlfeat网站：http://www.vlfeat.org/