Estimation of Space-Varying Covariance Matrices

This paper considers the representation of human trajectories in video signals. These trajectories are modeled by switched dynamical models, based on motion fields that drive the pedestrian during consecutive time intervals. This paper addresses the estimation of uncertainty in trajectory generation by using space-varying covariance matrices estimated from the video data. Experimental results show that the proposed model outperforms previous methods, based on static and isotropic covariance matrices.

[1]  Eric Sommerlade,et al.  Modelling pedestrian trajectory patterns with Gaussian processes , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[2]  Carlo S. Regazzoni,et al.  Online Nonparametric Bayesian Activity Mining and Analysis From Surveillance Video , 2016, IEEE Transactions on Image Processing.

[3]  Jorge S. Marques,et al.  Information Geometric Algorithm for Estimating Switching Probabilities in Space-Varying HMM , 2014, IEEE Transactions on Image Processing.

[4]  S. Savarese,et al.  Learning an Image-Based Motion Context for Multiple People Tracking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Emilio Maggio,et al.  Video Tracking - Theory and Practice , 2011 .

[6]  Silvio Savarese,et al.  Learning to Predict Human Behavior in Crowded Scenes , 2017, Group and Crowd Behavior for Computer Vision.

[7]  Martial Hebert,et al.  Activity Forecasting , 2012, ECCV.

[8]  Cláudio T. Silva,et al.  Vector Field k‐Means: Clustering Trajectories by Fitting Multiple Vector Fields , 2012, Comput. Graph. Forum.

[9]  Sridha Sridharan,et al.  Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detection , 2017, Neural Networks.

[10]  J. Marques,et al.  Gaussian Random Vector Fields in Trajectory Modelling , 2017 .

[11]  Eric Sommerlade,et al.  Finding prototypes to estimate trajectory development in outdoor scenarios , 2008 .

[12]  J. Borwein,et al.  Two-Point Step Size Gradient Methods , 1988 .

[13]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Mohan M. Trivedi,et al.  Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Mário A. T. Figueiredo,et al.  Activity Recognition Using a Mixture of Vector Fields , 2013, IEEE Transactions on Image Processing.

[16]  Tim J. Ellis,et al.  Path detection in video surveillance , 2002, Image Vis. Comput..

[17]  Irfan A. Essa,et al.  Gaussian process regression flow for analysis of motion trajectories , 2011, 2011 International Conference on Computer Vision.

[18]  Philip H. S. Torr,et al.  DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Mohan M. Trivedi,et al.  A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[20]  Jorge S. Marques,et al.  A sparse approach to pedestrian trajectory modeling using multiple motion fields , 2017, 2017 IEEE International Conference on Image Processing (ICIP).