Description

The SegTrack dataset consists of six videos (five are used) with ground truth pixelwise segmentation (6th penguin is not usable). The dataset is used for accurate video coherent segmentation of objects within stationary and moving cameras. Birdfall (static), Cheetah, Girl, Monkeydog, Parachute and not used Penguin. Error metric is per-frame pixel error ate compared to groundtruth (from [20] in the paper). David Tsai and Matthew Flagg and James M.Rehg Motion Coherent Tracking with Multi-label MRF optimization BMVC 2010 http://cpl.cc.gatech.edu/projects/SegTrack/SegTrack_201102.zip http://cpl.cc.gatech.edu/projects/SegTrack/Metrics.zip

Related datasets