DocumentCode :
3036540
Title :
Model-Based Vehicle Pose Estimation and Tracking in Videos Using Random Forests
Author :
Hodlmoser, Michael ; Micusik, B. ; Pollefeys, Marc ; Ming-Yu Liu ; Kampel, Martin
fYear :
2013
fDate :
June 29 2013-July 1 2013
Firstpage :
430
Lastpage :
437
Abstract :
This paper presents a computational effective framework for tracking and pose estimation of vehicles in videos reaching comparable performance to state-of-the-art methods. We cast the problem of vehicle tracking as ranking possible poses for each frame and connecting subsequent poses by exploiting a feasible motion model over time. As a novelty, we use random forests trained on a set of existing 3D models for estimating the pose. We discretize the viewpoint space for training, where a synthetic camera is orbiting around the models. To compare projections of 3D models to real world 2D input frames, we introduce simple but discriminative principle gradient features to describe both images. A Markov Random Field ensures to pick the perfect pose over time and the vehicle to follow a feasible motion. As can be seen from our experiments performed on a variety of videos with vast variation of vehicle types, the proposed framework achieves similar results in less computational time compared to state-of-the-art methods.
Keywords :
Markov processes; image classification; object tracking; pose estimation; vehicles; 3D models; Markov random field; principle gradient features; random forests; synthetic camera; vehicle pose estimation; vehicle tracking; videos; Estimation; Radio frequency; Solid modeling; Three-dimensional displays; Training; Vehicles; Videos; 3D Vehicle Tracking; 3D Vision; Model-Based Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3D Vision - 3DV 2013, 2013 International Conference on
Conference_Location :
Seattle, WA
Type :
conf
DOI :
10.1109/3DV.2013.63
Filename :
6599106
Link To Document :
بازگشت