Trajectory-based vehicle tracking at low frame rates

A new vehicle tracking method is proposed for an embedded traffic surveillance system.The proposed method demonstrates efficient tracking performance at a low frame rate.The proposed method employs greedy data association based on appearance and position similarities.To manage abrupt appearance changes, manifold learning is used.To manage abrupt motion changes, trajectory information is used to predict the next probable position. In smart cities, an intelligent traffic surveillance system plays a crucial role in reducing traffic jams and air pollution, thus improving the quality of life. An intelligent traffic surveillance should be able to detect and track multiple vehicles in real-time using only limited resources. Conventional tracking methods usually run at a high video-sampling rate, assuming that the same vehicles in successive frames are similar and move only slightly. However, in cost effective embedded surveillance systems (e.g., a distributed wireless network of smart cameras), video frame rates are typically low because of limited system resources. Therefore, conventional tracking methods perform poorly in embedded surveillance systems because of discontinuity of the moving vehicles in the captured recordings. In this study, we present a fast and light algorithm that is suitable for an embedded real-time visual surveillance system to detect effectively and track multiple moving vehicles whose appearance and/or position changes abruptly at a low frame rate. For effective tracking at low frame rates, we propose a new matching criterion based on greedy data association using appearance and position similarities between detections and trackers. To manage abrupt appearance changes, manifold learning is used to calculate appearance similarity. To manage abrupt changes in motion, the next probable centroid area of the tracker is predicted using trajectory information. The position similarity is then calculated based on the predicted next position and progress direction of the tracker. The proposed method demonstrates efficient tracking performance during rapid feature changes and is tested on an embedded platform (ARM with DSP-based system).

[1]  Minho Lee,et al.  Identification of Moving Vehicle Trajectory Using Manifold Learning , 2012, ICONIP.

[2]  Neil M. White,et al.  A Tracking System for Wireless Embedded Nodes Using Time-of-Flight Ranging , 2013, IEEE Transactions on Mobile Computing.

[3]  L. J. M. Rothkrantz,et al.  A smart surveillance system of distributed smart multi cameras modelled as agents , 2016, 2016 Smart Cities Symposium Prague (SCSP).

[4]  Max Welling,et al.  Accelerated Variational Dirichlet Process Mixtures , 2006, NIPS.

[5]  Luc Van Gool,et al.  An adaptive color-based particle filter , 2003, Image Vis. Comput..

[6]  Hong Qiao,et al.  A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection , 2011, IEEE Transactions on Intelligent Transportation Systems.

[7]  Fatih Murat Porikli,et al.  Object tracking in low-frame-rate video , 2005, IS&T/SPIE Electronic Imaging.

[8]  Rama Chellappa,et al.  A Multiple-Hypothesis Approach for Multiobject Visual Tracking , 2007, IEEE Transactions on Image Processing.

[9]  M. T. Gopala Krishna,et al.  Ten-LoPP: Tensor Locality Preserving Projections Approach for Moving Object Detection and Tracking , 2013 .

[10]  Ang Li,et al.  Object tracking using learned feature manifolds , 2014, Comput. Vis. Image Underst..

[11]  Michael Felsberg,et al.  The Visual Object Tracking VOT2015 Challenge Results , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[12]  Minho Lee,et al.  A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance , 2015, IEEE Signal Processing Letters.

[13]  Gerhard P. Hancke,et al.  A Survey on Urban Traffic Management System Using Wireless Sensor Networks , 2016, Sensors.

[14]  Minho Lee,et al.  Intelligent Video Surveillance System Using Dynamic Saliency Map and Boosted Gaussian Mixture Model , 2011, ICONIP.

[15]  Ramakant Nevatia,et al.  Global data association for multi-object tracking using network flows , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  A. Ouamri,et al.  Vehicle detection algorithm based on horizontal/vertical edges , 2011, International Workshop on Systems, Signal Processing and their Applications, WOSSPA.

[17]  Bernhard Rinner,et al.  An Introduction to Distributed Smart Cameras , 2008, Proceedings of the IEEE.

[18]  Tomaso Poggio,et al.  Image Representations for Visual Learning , 1996, Science.

[19]  Adi Perry,et al.  A Visual Tracking Scheme for Accurate Object Retrieval in Low Frame Rate Videos , 2016, Int. J. Artif. Intell. Tools.

[20]  Wei Zhang,et al.  Multilevel Framework to Detect and Handle Vehicle Occlusion , 2008, IEEE Transactions on Intelligent Transportation Systems.

[21]  Gabriel-Miro Muntean,et al.  A Communications-Oriented Perspective on Traffic Management Systems for Smart Cities: Challenges and Innovative Approaches , 2015, IEEE Communications Surveys & Tutorials.

[22]  Lu Wang,et al.  Detection Based Low Frame Rate Human Tracking , 2010, 2010 20th International Conference on Pattern Recognition.

[23]  Hong Qiao,et al.  Tracking feature extraction based on manifold learning framework , 2011, J. Exp. Theor. Artif. Intell..

[24]  Minho Lee,et al.  Tracking Multiple Moving Vehicles in Low Frame Rate Videos Based on Trajectory Information , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[25]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[27]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[28]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[29]  Luc Van Gool,et al.  Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Hujun Bao,et al.  A Robust Tracking System for Low Frame Rate Video , 2015, International Journal of Computer Vision.

[31]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[32]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[33]  Simone Calderara,et al.  Visual Tracking: An Experimental Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Charless C. Fowlkes,et al.  Globally-optimal greedy algorithms for tracking a variable number of objects , 2011, CVPR 2011.

[35]  Ian D. Reid,et al.  Joint Probabilistic Data Association Revisited , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[36]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Mun Wai Lee,et al.  Traffic analysis with low frame rate camera networks , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.