Deep Reinforcement Learning for Subpixel Neural Tracking.

Tianhong Dai Magda Dubois Kai Arulkumaran Jonathan Campbell Cher Bass Benjamin Billot Fatmatülzehra Uslu Vincenzo De Paola Claudia Clopath Anil Anthony Bharath

Published in: MIDL (2019)

Keyphrases

reinforcement learning
neural network
fitted q iteration
particle filter
function approximation
optical flow
real time

state space
visual tracking
reinforcement learning algorithms
network architecture
multi agent
mean shift
object tracking

motion model
markov decision processes
kalman filter
motion analysis
particle filtering
temporal difference

moving target
motion segmentation
model free
optimal control
supervised learning
optimal policy