Motion Prior-Based Dual Markov Decision Processes for Multi-airplane Tracking.
Ruijing YangXiang ZhangGuoqiang WangHonggang WuPublished in: CVMI (2022)
Keyphrases
- markov decision processes
- motion model
- finite state
- particle filter
- state space
- optimal policy
- reinforcement learning
- image sequences
- dynamic programming
- transition matrices
- policy iteration
- finite horizon
- decision theoretic planning
- risk sensitive
- optical flow
- factored mdps
- infinite horizon
- planning under uncertainty
- reachability analysis
- decision processes
- action space
- markov decision process
- average cost
- reinforcement learning algorithms
- partially observable
- model based reinforcement learning
- reward function
- visual tracking
- human motion
- particle filtering
- action sets
- semi markov decision processes
- average reward
- moving objects