Online learning and object recognition for AUV optical vision

2003 ◽  
Author(s):  
Xiaohai Yuan ◽  
Zhen Hu ◽  
Jianping Chen ◽  
Rongsheng Chen ◽  
Peilin Liu
Keyword(s):  
Online Learning ◽  
Object Recognition

scholarly journals Adaptive Computer Vision: Online Learning for Object Recognition

2004 ◽  
pp. 447-454 ◽  
Author(s):  
Holger Bekel ◽  
Ingo Bax ◽  
Gunther Heidemann ◽  
Helge Ritter
Keyword(s):  
Computer Vision ◽  
Online Learning ◽  
Object Recognition

Bayesian Online Learning for MEC Object Recognition Systems

2020 ◽  
Author(s):  
Apostolos Galanopoulos ◽  
Jose A. Ayala-Romero ◽  
George Iosifidis ◽  
Douglas J. Leith
Keyword(s):  
Online Learning ◽  
Object Recognition ◽  
Recognition Systems

scholarly journals Identify Occurrence of Substance Object of a Certain Classification in Fractional Videos and Pictures

2020 ◽  
Vol 9 (3) ◽  
pp. 3728-3731
Keyword(s):  
Computer Vision ◽  
Online Learning ◽  
Object Recognition ◽  
Object Detection ◽  
New Method ◽  
Learning Method ◽  
Dynamic Object ◽  
Geometric Shapes ◽  
New Learning ◽  
Detection And Recognition

Object detection and recognition are the meta-heuristic problems in computer vision. Practically usable dynamic object recognition methods are still unavailable. A new method was proposed which improves over existing methods in every stage. In that addition features like geometric shapes, ellipsis are added. An heuristic codebook was proposed of good generalization and discriminative properties, enabling multipath interferences mechanisms on propagation of1 conditional livelihood. A new learning method also proposed which is capable of online learning

FINE-GRAINED AND LAYERED OBJECT RECOGNITION

2012 ◽  
Vol 26 (02) ◽  
pp. 1255006 ◽  
Author(s):  
YANG WU ◽  
NANNING ZHENG ◽  
YUANLIU LIU ◽  
ZEJIAN YUAN
Keyword(s):  
Online Learning ◽  
Object Recognition ◽  
Learning Algorithm ◽  
Structured Prediction ◽  
Generic Model ◽  
Fine Grained ◽  
Relative Localization ◽  
Object Categories ◽  
Online Learning Algorithm ◽  
Semantic Object

This paper presents a novel research on promoting the performance and enriching the functionalities of object recognition. Instead of simply fitting various data to a few predefined semantic object categories, we propose to generate proper results for different object instances based on their actual visual appearances. The results can be fine-grained and layered categorization along with absolute or relative localization. We present a generic model based on structured prediction and an efficient online learning algorithm to solve it. Experiments on a new benchmark dataset demonstrate the effectiveness of our model and its superiority against traditional recognition methods.

scholarly journals Online Learning for Bootstrapping of Object Recognition and Localization in a Biologically Motivated Architecture

2008 ◽  
pp. 383-392 ◽  
Author(s):  
Heiko Wersing ◽  
Stephan Kirstein ◽  
Bernd Schneiders ◽  
Ute Bauer-Wersing ◽  
Edgar Körner
Keyword(s):  
Online Learning ◽  
Object Recognition

scholarly journals ONLINE LEARNING OF OBJECTS IN A BIOLOGICALLY MOTIVATED VISUAL ARCHITECTURE

2007 ◽  
Vol 17 (04) ◽  
pp. 219-230 ◽  
Author(s):  
HEIKO WERSING ◽  
STEPHAN KIRSTEIN ◽  
MICHAEL GÖTTING ◽  
HOLGER BRANDL ◽  
MARK DUNN ◽  
...  
Keyword(s):  
Online Learning ◽  
Object Recognition ◽  
Feature Detection ◽  
Memory Training ◽  
Camera System ◽  
Object Memory ◽  
Speech Input ◽  
Topographical Feature ◽  
Different Levels ◽  
Human Teacher

We present a biologically motivated architecture for object recognition that is capable of online learning of several objects based on interaction with a human teacher. The system combines biological principles such as appearance-based representation in topographical feature detection hierarchies and context-driven transfer between different levels of object memory. Training can be performed in an unconstrained environment by presenting objects in front of a stereo camera system and labeling them by speech input. The learning is fully online and thus avoids an artificial separation of the interaction into training and test phases. We demonstrate the performance on a challenging ensemble of 50 objects.

Sign in / Sign up

Export Citation Format

Share Document