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

Stand: 2017-11-22 000000m 02:38:41 - Overview

ok1324
Attribute Current Content New
Name (Institute + Shorttitle)The KITTI Vision Benchmark Suite 
Description (include details on usage, files and paper references)We take advantage of our autonomous driving platform Annieway to develop novel challenging real-world computer vision benchmarks. Our tasks of interest are: stereo, optical flow, visual odometry, 3D object detection and 3D tracking. For this purpose, we equipped a standard station wagon with two high-resolution color and grayscale video cameras. Accurate ground truth is provided by a Velodyne laser scanner and a GPS localization system. Our datsets are captured by driving around the mid-size city of Karlsruhe, in rural areas and on highways. Up to 15 cars and 30 pedestrians are visible per image. Besides providing all data in raw format, we extract benchmarks for each task. For each of our benchmarks, we also provide an evaluation metric and this evaluation website. Preliminary experiments show that methods ranking high on established benchmarks such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias and complement existing benchmarks by providing real-world benchmarks with novel difficulties to the community.


Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite, Andreas Geiger and Philip Lenz and Raquel Urtasun, CVPR 2012

Extra
There exists a 70 frame annotation by
http://cms.brookes.ac.uk/research/visiongroup/projects/SemanticUrbanModelling/index.php
See
Sunando Sengupta, Eric Greveson, Ali Shahrokni, Philip H.S. Torr, Semantic Modelling of Urban Scenes, ICRA 2013. pdf 
URL Linkhttp://www.cvlibs.net/datasets/kitti/ 
Files (#)
References (SKIPPED)
Category (SKIPPED)Stereo, Optical Flow, Object Detection, Object Tracking 
Tags (single words, spaced)stereo, depth, flow, detection tracking, reconstruction, sfm, odometry, segmentation, semantic car depth 
Last Changed2017-11-22 
Turing (2.12+3.25=?) :-)