Hybrid POMDP based evolutionary adaptive framework for efficient visual tracking algorithms

Authors:
Yan Shen;Sarang Khim;Won Jun Sung;Sungjin Hong;Phill Kyu Rhee
Affiliations:
Inha University, Incheon, South Korea;Inha University, Incheon, South Korea;Inha University, Incheon, South Korea;Inha University, Incheon, South Korea;Inha University, Incheon, South Korea
Venue:
Proceedings of the 15th annual conference on Genetic and evolutionary computation
Year:
2013

Citing 12
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
A Bayesian Framework for Reinforcement Learning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Bayesian sparse sampling for on-line reward optimization

ICML '05 Proceedings of the 22nd international conference on Machine learning
Object count/area graphs for the evaluation of object detection and segmentation algorithms

International Journal on Document Analysis and Recognition
Object tracking: A survey

ACM Computing Surveys (CSUR)
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Online planning algorithms for POMDPs

Journal of Artificial Intelligence Research
AEMS: an anytime online search algorithm for approximate policy refinement in large POMDPs

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Learning to act using real-time dynamic programming

Artificial Intelligence
Tracking-Learning-Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs

Artificial Intelligence
Adaptive Object Tracking by Learning Hybrid Template Online

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an evolutionary and adaptive framework for efficient visual tracking based on a hybrid POMDP formulation. The main focus is to guarantee visual tracking performance under varying environments without strongly-controlled situations or high-cost devices. The performance optimization is formulated as a dynamic adaptation of the system control parameters, i.e., threshold and adjusting parameters in a visual tracking algorithm, based on the hybrid of offline and online POMDPs. The hybrid POMDP allows the agent to construct world-belief models under uncertain environments in offline, and focus on the optimization of the system control parameters over the current world model in real-time. Since the visual tracking should satisfy strict real-time constraints, we restrict our attention to simpler and faster approaches instead of exploring the belief space of each world model directly. The hybrid POMDP is thus solved by an evolutionary adaptive framework employing the GA (Genetic Algorithm) and real-time Q-learning approaches in the optimally reachable genotype and phenotype spaces, respectively. Experiments were carried out extensively in the area of eye tracking using videos of various structures and qualities, and yielded very encouraging results. The framework can achieve an optimal performance by balancing the tracking accuracy and real-time constraints.