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

Stand: 2017-05-28 000000m 18:31:03 - Overview

ok957
Attribute Current Content New
Name (Institute + Shorttitle)MPI VehicleScenes 
Description (include details on usage, files and paper references)
Abstract
Scene understanding has (again) become a focus of computer vision research, leveraging advances in detection, context modeling, and tracking. In this paper, we present a novel probabilistic 3D scene model that encompasses multi-class object detection, object tracking, scene labeling, and 3D geometric relations. This integrated 3D model is able to represent complex interactions like inter-object occlusion, physical exclusion between objects, and geometric context. Inference allows to recover 3D scene context and perform 3D multi-object tracking from a mobile observer, for objects of multiple categories, using only monocular video as input. In particular, we show that a joint scene tracklet model for the evidence collected over multiple frames substantially improves performance. The approach is evaluated for two different types of challenging onboard sequences. We first show a substantial improvement to the state-of-the-art in 3D multi-people tracking. Moreover, a similar performance gain is achieved for multi-class 3D tracking of cars and trucks on a new, challenging dataset.


Reference
Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes [1]
Christian Wojek, Stefan Roth, Konrad Schindler, and Bernt Schiele
in European Conference on Computer Vision (ECCV 2010), Part IV, pp. 467-481, September 5-11, 2010, Heraklion, Crete, Greece 
URL Linkhttp://www.d2.mpi-inf.mpg.de/monocular-3d-scene 
Files (#)
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)semantic segmentation scene understanding classification 3d car pedestrian 
Last Changed2017-05-28 
Turing (2.12+3.25=?) :-)