Paper Info
Title
A Real-Time Evolutionary Object Recognition System
Abstract
We have created a real-time evolutionary object recognition system. Genetic Programming is used to automatically search the space of possible computer vision programs guided through user interaction. The user selects the object to be extracted with the mouse pointer and follows it over multiple frames of a video sequence. Several different alternative algorithms are evaluated in the background for each input image. Real-time performance is achieved through the use of the GPU for image processing operations.
Year
DOI
Venue
2009
10.1007/978-3-642-01181-8_23
EuroGP
Keywords
Field
DocType
multiple frame,genetic programming,image processing operation,mouse pointer,real-time evolutionary object recognition,input image,user interaction,different alternative algorithm,real-time performance,possible computer vision program,image processing,object recognition,real time,computer vision
Computer vision,3D single-object recognition,Computer graphics (images),Method,Computer science,Pointer (user interface),Image processing,Theoretical computer science,Genetic programming,Artificial intelligence,Genetic program,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
Citations 
5481
0302-9743
7
PageRank 
References 
Authors
0.49
12
1
Name
Order
Citations
PageRank
Marc Ebner120519.59