Learning Online Smooth Predictors for Realtime Camera Planning using Recurrent Decision Trees

 

We propose a recurrent decision tree framework that can directly incorporate temporal consistency into a data-driven predictor, as well as a learning algorithm that can efficiently learn such temporally smooth models.

June 24, 2016
IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016

 

Authors

Jianhui Chen (University of British Columbia)

Hoang M. Le (California Institute of Technology)

Peter Carr (Disney Research)

Yisong Yue (California Institute of Technology)

James J. Little (University of British Columbia)

 

Learning Online Smooth Predictors for Realtime Camera Planning using Recurrent Decision Trees

Abstract

We study the problem of online prediction for realtime camera planning, where the goal is to predict smooth trajectories that correctly track and frame objects of interest (e.g., players in a basketball game). The conventional approach for training predictors does not directly consider temporal consistency, and often produces undesirable jitter. Although post-hoc smoothing (e.g., via a Kalman filter) can mitigate this issue to some degree, it is not ideal due to overly stringent modeling assumptions (e.g., Gaussian noise). We propose a recurrent decision tree framework that can directly incorporate temporal consistency into a data-driven predictor, as well as a learning algorithm that can efficiently learn such temporally smooth models. Our approach does not require any post processing, making online smooth predictions much easier to generate when the noise model is unknown. We apply our approach to sports broadcasting: given noisy player detections, we learn where the camera should look based on human demonstrations. Our experiments exhibit significant improvements over conventional baselines and showcase the practicality of our approach.

Copyright Notice