Exploring Causal Relationships in Visual Object Tracking
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3065-3073
Abstract
Causal relationships can often be found in visual object tracking between the motions of the camera and that of the tracked object. This object motion may be an effect of the camera motion, e.g. an unsteady handheld camera. But it may also be the cause, e.g. the cameraman framing the object. In this paper we explore these relationships, and provide statistical tools to detect and quantify them, these are based on transfer entropy and stem from information theory. The relationships are then exploited to make predictions about the object location. The approach is shown to be an excellent measure for describing such relationships. On the VOT2013 dataset the prediction accuracy is increased by 62 % over the best non-causal predictor. We show that the location predictions are robust to camera shake and sudden motion, which is invaluable for any tracking algorithm and demonstrate this by applying causal prediction to two state-of-the-art trackers. Both of them benefit, Struck gaining a 7 % accuracy and 22 % robustness increase on the VTB1.1 benchmark, becoming the new state-of-the-art.Keywords
This publication has 30 references indexed in Scilit:
- Video Sensor-Based Complex Scene Analysis with Granger CausalitySensors, 2013
- Transfer entropy—a model-free measure of effective connectivity for the neurosciencesJournal of Computational Neuroscience, 2010
- Investigating neural primacy in Major Depressive Disorder: multivariate Granger causality analysis of resting-state fMRI time-series dataMolecular Psychiatry, 2010
- Causality detection based on information-theoretic approaches in time series analysisPhysics Reports, 2007
- Object trackingACM Computing Surveys, 2006
- Tests for causality between integrated variables using asymptotic and bootstrap distributions: theory and applicationApplied Economics, 2006
- Measuring Information TransferPhysical Review Letters, 2000
- Lag-Length Selection and Tests of Granger Causality Between Money and IncomeJournal of Money, Credit and Banking, 1985
- Investigating Causal Relations by Econometric Models and Cross-spectral MethodsEconometrica, 1969
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960