Paper Info
Title
Detecting changes in images of street scenes
Abstract
In this paper we propose an novel algorithm for detecting changes in street scenes when the vehicle revisits sections of the street at different times. The proposed algorithm detects structural geometric changes, changes due to dynamically moving objects and as well as changes in the street appearance (e.g. posters put up) between two traversal times. We exploit geometric, appearance and semantic information to determine which areas have changed and formulate the problem as an optimal image labeling problem in the Markov Random Field framework. The approach is evaluated on street sequences from 3 different locations which were visited multiple times by the vehicle. The proposed method is applicable to monitoring and updating models and images of urban environments.
Year
DOI
Venue
2012
10.1007/978-3-642-37447-0_45
ACCV (4)
Keywords
Field
DocType
different location,detecting change,structural geometric change,novel algorithm,street sequence,street scene,street appearance,proposed algorithm,different time,vehicle revisits section
Computer vision,Reprojection error,Tree traversal,Pattern recognition,Visual odometry,Computer science,Markov random field,Exploit,Semantic information,Artificial intelligence,Image labeling
Conference
Citations 
PageRank 
References 
2
0.37
22
Authors
1
Name
Order
Citations
PageRank
Jana Kosecká11523129.85