Incomplete 3D motion trajectory segmentation and 2D-to-3D label transfer for dynamic scene analysis

The knowledge of the static scene parts and the moving objects in a dynamic scene plays a vital role for scene modelling, understanding, and landmark-based robot navigation. The key information for these tasks lies on semantic labels of the scene parts and the motion trajectories of the dynamic obje...

Full description

Saved in:
Bibliographic Details
Main Authors: Cansen Jiang, Paudel, Danda Pani, Fougerolle, Yohan, Fofi, David, Demonceaux, Cedric
Format: Conference Proceeding
Language:English
Subjects:
Cameras
Computer vision
Dynamics
Motion segmentation
Semantics
Three-dimensional displays
Trajectory
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The knowledge of the static scene parts and the moving objects in a dynamic scene plays a vital role for scene modelling, understanding, and landmark-based robot navigation. The key information for these tasks lies on semantic labels of the scene parts and the motion trajectories of the dynamic objects. In this work, we propose a method that segments the 3D feature trajectories based on their motion behaviours, and assigns them semantic labels using 2D-to-3D label transfer. These feature trajectories are constructed by using the proposed trajectory recovery algorithm which takes the loss of feature tracking into account. We introduce a complete framework for static-map and dynamic objects' reconstruction, as well as semantic scene understanding for a calibrated and moving 2D-3D camera setup. Our motion segmentation approach is faster by two orders of magnitude, while performing better than the state-of-the-art 3D motion segmentation methods, and successfully handles the previously discarded incomplete trajectory scenarios.
ISSN:2153-0866
DOI:10.1109/IROS.2017.8202214