Activity Forecasting: An Invitation to Predictive Perception - Robotics Institute Carnegie Mellon University

Activity Forecasting: An Invitation to Predictive Perception

Book Section/Chapter, Group and Crowd Behavior for Computer Vision. Chapter 12, pp. 273 - 294, April, 2017

Abstract

We make a case for a decision-theoretic approach to human activity forecasting, which provides a principled framework for modeling the consequences of taking certain actions and the impact it can have on the future. We give an introductory exposition of the concept of Maximum Entropy Inverse Optimal Control in the context of visual future prediction. Presented examples show that such methods are able to generate more informed predictions over future actions of human activity.

BibTeX

@incollection{Kitani-2017-109862,
author = {Kris M. Kitani and Wei-Chiu Ma and De-An Huang},
title = {Activity Forecasting: An Invitation to Predictive Perception},
booktitle = {Group and Crowd Behavior for Computer Vision. Chapter 12},
publisher = {Elsevier},
editor = {Vittorio Murino, Marco Cristani, Shishir Shah, Silvio Savarese},
year = {2017},
month = {April},
pages = {273 - 294},
}