Predicting driver left-turn behavior from few training samples using a maximum a posteriori method.

Dennis Orth Dorothea Kolossa Martin Heckmann

Published in: ITSC (2017)

Keyphrases

training samples
maximum a posteriori
em algorithm
test sample
energy function
feature space
training set
supervised learning
decision function
map estimation
cost function
denoising
markov random field
graph cuts
sample set
number of training samples