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

Stand: 2017-03-25 000000m 12:29:47 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)Berkeley Urban Street tracking  
Description (include details on usage, files and paper references)The UrbanStreet dataset used in the paper can be downloaded here [188M] . It contains 18 stereo sequences of pedestrians taken from a stereo rig mounted on a car driving in the streets of Philadelphia during rush hours. The image resolution is 516x1024. Ground-truth is provided in the form of pedestrian segmentation masks for the left view. All pedestrians larger than 100 pixels in height are labelled every 4 frames (0.6 seconds) in each video sequence. The video below shows ground-truth label samples.

Two Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking under Occlusions Katerina Fragkiadaki, Weiyu Zhang, Geng Zhang, and Jianbo Shi in ECCV 2012 paper | poster 
URL Link 
Files (#)18 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)tracking detection segmentation multitarget recognition video pedestrian urban human 
Last Changed2017-03-25 
Turing (2.12+3.25=?) :-) 

Warning: mysql_close(): no MySQL-Link resource supplied in /home/www/web138/html/vision/dataset/task.php on line 222

Warning: mysql_close(): no MySQL-Link resource supplied in /home/www/web138/html/vision/dataset/task.php on line 223