Return to search

Partially Observable Markov Decision Processes for Faster Object Recognition

Object recognition in the real world is a big challenge in the field of computer vision. Given the potentially enormous size of the search space it is essential to be able to make intelligent decisions about where in the visual field to obtain information from to reduce the computational resources needed. In this report a POMDP (Partially Observable Markov Decision Process) learning framework, using a policy gradient method and information rewards as a training signal, has been implemented and used to train fixation policies that aim to maximize the information gathered in each fixation. The purpose of such policies is to make object recognition faster by reducing the number of fixations needed. The trained policies are evaluated by simulation and comparing them with several fixed policies. Finally it is shown that it is possible to use the framework to train policies that outperform the fixed policies for certain observation models.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-198632
Date January 2016
CreatorsOlafsson, Björgvin
PublisherKTH, Skolan för datavetenskap och kommunikation (CSC)
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess

Page generated in 0.0014 seconds