Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2017-12-16 000000m 04:32:54 - Overview

ok441
Attribute Current Content New
Name (Institute + Shorttitle)KAIST Multispectral Pedestrian Detection Benchmark 
Description (include details on usage, files and paper references)We developed imaging hardware consisting of a color camera, a thermal camera and a beam splitter to capture the aligned multispectral (RGB color + Thermal) images. With this hardware, we captured various regular traffic scenes at day and night time to consider changes in light conditions.

The KAIST Multispectral Pedestrian Dataset consists of 95k color-thermal pairs (640x480, 20Hz) taken from a vehicle. All the pairs are manually annotated (person, people, cyclist) for the total of 103,128 dense annotations and 1,182 unique pedestrians. The annotation includes temporal correspondence between bounding boxes like Caltech Pedestrian Dataset. More infomation can be found in our CVPR 2015 paper. 
URL Linkhttps://sites.google.com/site/pedestrianbenchmark/ 
Files (#)
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)pedestrian, thermal, RGB 
Last Changed2017-12-16 
Turing (2.12+3.25=?) :-)