Active Planning, Sensing and Recognition Using a Resource-Constrained Discriminant POMDP
Abstract
In this paper, we address the problem of object class recognition via observations from actively selected views/modalities/features under limited resource budgets. A Partially Observable Markov Decision Process (POMDP) is employed to find optimal sensing and recognition actions with the goal of long-term classification accuracy. Heterogeneous resource constraints such as motion, number of measurements and bandwidth are explicitly modeled in the state variable, and a prohibitively high penalty is used to prevent the violation of any resource constraint. To improve recognition performance, we further incorporate discriminative classification models with POMDP, and customize the reward function and observation model correspondingly. The proposed model is validated on several data sets for multi-view, multi-modal vehicle classification and multi-view face recognition, and demonstrates improvement in both recognition and resource management over greedy methods and previous POMDP formulations.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 28, 2014
- Accession Number
- ADA612425
Entities
People
- Devin Grady
- Lydia Kavraki
- Mark Hasegawa-johnson
- Mark Moll
- Nasser M. Nasrabadi
- Po-sen Huang
- Thomas Huang
- Zhangyang Wang
- Zhaowen Wang
Organizations
- Rice University