Codes and downloads

Software

• Toolbox for generic lenses - Camera calibration toolbox for Matlab for calibrating different kinds of central cameras. The toolbox has been successfully used for both conventional and omnidirectional cameras such as fish-eye lens cameras and catadioptric cameras.
• Camera calibration toolbox for Matlab - The camera calibration toolbox for Matlab utilizes a bias correction procedure for circular control points and a nonrecursive method for reversing the distortion model.
• LBP implementation in multiple computing platforms - This is a software toolbox that collects the software implementations of the Local Binary Pattern Operator in several platforms such as OpenCL for CPU & GPU, C code optimized for ARM, etc.
• The DTSLAM API provides a framework and code for the approach introduced in "DT-SLAM: Deferred Triangulation for Robust SLAM" published in IEEE 3DV 2015.
• Implementation of Temporal Interpolation Model for Video Normalization (for Matlab)(TIM_Lipreading_CVPR2011.zip)
• Implementation of "A Compact Representation of Visual Speech Data Using Latent Variables" (for Matlab) (tpami2013_visual_speech_representation_code.zip)
• Implementation of "Combining LBP difference and feature correlation for texture description" (for Matlab) (TIP2014_LBPD_Matlab_v1.0.zip)
• Implementation of "Median Robust Extended Local Binary Pattern for Texture Classification" (for Matlab) (MRELBPcode.rar) (Note: One has to down load Outex_TC_00012 dataset and put it in the same folder with MRELBPcode, then run "MRELBP_Feature_Extraction" to obtain features.)
• C++ implementation of spatio-temporal LBP (STLBP_VC.zip)
• BSIF - The implementation for the BSIF local image descriptor.
• Fast LBP-TOP Matlab implementation based on tensor unfolding theory for fastening the computational time of the original LBP-TOP method.

Databases

• The Oulu Multi-pose Eye Gaze (OMEG) Dataset - The dataset includes 200 image sequences from 50 subjects for eye gaze analysis
• OUTEX - a framework for empirical evaluation of texture classification and segmentation algorithms
• OuluVS database - video and audio data for visual speech recognition
• OuluVS2 database - a multi-view audiovisual database. It contains video recordings from 52 subjects speaking three types of utterances: continuous digit strings, short phrases and TIMIT sentences. Speakers were filmed from 5 different views simultaneously, resulting in more than 20k video recordings
• Oulu-CASIA NIR&VIS facial expression database  - facial expression data captured with two imaging systems, NIR (Near Infrared) and VIS (Visible light)
• SPOS database - spontaneous and posed facial expressions database
• SMIC database - spontaneous micro-expressions database

Archive

For more codes (including implementations for LBP and it's variants) and databases, please see the archive page.