Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
MOVING OBJECT SEGMENTATION AND DYNAMIC SCENE RECONSTRUCTION USING Amit K Agrawal and Rama Chellappa
 

Summary: MOVING OBJECT SEGMENTATION AND DYNAMIC SCENE RECONSTRUCTION USING
TWO FRAMES
Amit K Agrawal and Rama Chellappa
University of Maryland
Dept. of Electrical and Computer Engineering
College Park, MD USA
ABSTRACT
We present an iterative algorithm for segmenting independently
moving objects and refining and updating a coarse depth map of
the scene under unconstrained camera motion (translation and ro-
tation) with the assumption that the independently moving objects
undergoes pure translation. Given a coarse depth map acquired by
a range-finder or extracted from a Digital Elevation Map (DEM),
the ego-motion is estimated by combining a global ego-motion
constraint and a local brightness constancy constraint using least
median of squares (LMedS) which treats independently moving
objects as outliers. Using the estimated camera motion and the
available depth estimate, motion of the 3D points is compensated.
We utilize the fact that the resulting surface parallax field is an
epipolar field and use a corresponding parametric model to esti-

  

Source: Agrawal, Amit - Mitsubishi Electric Research Labs

 

Collections: Engineering