Feature-Based Probabilistic Data Association and Tracking

In this contribution we present a concept for improvement of object tracking in applications that suffer from severe detection errors such as incomplete, merged, split, missing and clutter-based detections due to noisy data, sensory and algorithmic restrictions and occlusions. It is based on utilization of low-level information that is gained through tracking dedicated feature points with known relationship to the tracked objects. The proposed Feature-Based Probabilistic Data Association and Tracking Algorithm (FBPDA) can be applied not only in the field of driver assistance systems but also in surveillance applications and further video-based object tracking applications. The main requirement is the possibility to robustly track dedicated feature points in the image (and in 3D space). For this aim, both correlation-based techniques (optic flow) and correspondence-based techniques using e.g. SIFT [1] or SURF [2] features can be used.

[1]  W. Ritter,et al.  De-cluttering with Integrated Probabilistic Data Association for Multisensor Multitarget ACC Vehicle Tracking , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[2]  T. Koch,et al.  A new pre-crash system for side impact protection , 2008 .

[3]  J. Tandler,et al.  Data Analysis of the APROSYS Side Pre-Crash Sensing System , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[4]  Y. Bar-Shalom,et al.  Tracking in a cluttered environment with probabilistic data association , 1975, Autom..

[5]  D. Willersinn,et al.  Odometry-Based Structure from Motion , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[6]  Michael Grinberg,et al.  Handling of split-and-merge effects and occlusions using feature-based probabilistic data association , 2010, Electronic Imaging.

[7]  Darko Musicki,et al.  Joint Integrated Probabilistic Data Association - JIPDA , 2002, Proceedings of the Fifth International Conference on Information Fusion. FUSION 2002. (IEEE Cat.No.02EX5997).

[8]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[9]  Uwe Franke,et al.  6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception , 2005, DAGM-Symposium.

[10]  Dieter Willersinn,et al.  Empirical evaluation of motion models for a side-looking driver assistance system , 2008 .

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  Michael Grinberg,et al.  Feature-Based Probabilistic Data Association (FBPDA) for visual multi-target detection and tracking under occlusions and split and merge effects , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[13]  Yaakov Bar-Shalom,et al.  Sonar tracking of multiple targets using joint probabilistic data association , 1983 .