热视觉数据集(Thermo-Visual Datasets)_视频处理_科研数据集课件.pdf

热视觉数据集(Thermo-Visual Datasets) 数据介绍： The videos were recorded using two separate cameras in a beam-splitter configuration, using Pilkington K-glass as the beam-splitter medium. The IR camera was a Raytheon Thermal IR-2000B and the colour visual camera was a Panasonic WV-CP470. 关键词： 分开,光束分离器,配置,视觉影片,单应, separate,beam-splitter,configuration,visual videos,homography, 数据格式： VIDEO 数据详细介绍： Thermo-Visual Datasets If you find these videos useful, you are requested to cite: Ciarán Ó Conaire, Noel E. OConnor, Alan Smeaton, Thermo-Visual Feature Fusion for Object Tracking Using Multiple Spatiogram Trackers, Journal of Machine Vision and Applications, 11 May 2007 If you wish to use these sequences for commercial purposes please contact Prof. Noel OConnor, CLARITY: Centre for Sensor Web Technologies, Dublin City University, Email: oconnorn@eeng.dcu.ie, Pho: +353 1 700 5078 Capture and Alignment The videos were recorded using two separate cameras in a beam-splitter configuration, using Pilkington K-glass as the beam-splitter medium. The IR camera was a Raytheon Thermal IR-2000B and the colour visual camera was a Panasonic WV-CP470. Alignment of the thermal and visual videos was done by manually selecting corresponding points in both views and computing a least-squared error fitting homography for each sequence. The infrared video frames were warped to align with the visual pixels. Pixels that are outside the infrared image are marked with value 255 (unknown). Sequence 9021: 9 Person Meeting room (Audience) Visual Colour Video (44MB MPEG) Aligned thermal infrared Video (44MB MPEG) Tracking data: Object 1, Object 2, Object 3, Object 4, Object 5, Object 6. Sequence 9552: 2 person close-up sequence Visual Colour Video (7MB MPEG) Aligned thermal infrared Video (7MB MPEG) Tracking data: Object 1. Sequence 9