Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Human Shadow Removal with Unknown Light Source Chia-Chih Chen and J. K. Aggarwal
 

Summary: Human Shadow Removal with Unknown Light Source
Chia-Chih Chen and J. K. Aggarwal
Computer & Vision Research Center / Department of ECE
The University of Texas at Austin
{ccchen | aggarwaljk}@mail.utexas.edu
Abstract
In this paper, we present a shadow removal tech-
nique which effectively eliminates a human shadow cast
from an unknown direction of light source. A multi-cue
shadow descriptor is proposed to characterize the dis-
tinctive properties of shadows. We employ a 3-stage
process to detect then remove shadows. Our algorithm
improves the shadow detection accuracy by imposing
the spatial constraint between the foreground subre-
gions of human and shadow. We collect a dataset con-
taining 81 human-shadow images for evaluation. Both
descriptor ROC curves and qualitative results demon-
strate the superior performance of our method.
1. Introduction
The existence of human shadows is a general prob-

  

Source: Aggarwal, J. K. - Department of Electrical and Computer Engineering, University of Texas at Austin

 

Collections: Computer Technologies and Information Sciences; Engineering