Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3650-3657
- https://doi.org/10.1109/cvpr.2013.468
Abstract
We generalize the network flow formulation for multiobject tracking to multi-camera setups. In the past, reconstruction of multi-camera data was done as a separate extension. In this work, we present a combined maximum a posteriori (MAP) formulation, which jointly models multicamera reconstruction as well as global temporal data association. A flow graph is constructed, which tracks objects in 3D world space. The multi-camera reconstruction can be efficiently incorporated as additional constraints on the flow graph without making the graph unnecessarily large. The final graph is efficiently solved using binary linear programming. On the PETS 2009 dataset we achieve results that significantly exceed the current state of the art.Keywords
This publication has 15 references indexed in Scilit:
- Discrete-continuous optimization for multi-target trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- An analytical formulation of global occlusion reasoning for multi-target trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Globally optimal solution to multi-object tracking with merged measurementsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Globally-optimal greedy algorithms for tracking a variable number of objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Multiple object tracking using flow linear programmingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Tracking-reconstruction or reconstruction-tracking? Comparison of two multiple hypothesis tracking approaches to interpret 3D object motion from several camera viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Object Detection with Discriminatively Trained Part-Based ModelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- Framework for Performance Evaluation of Face, Text, and Vehicle Detection and Tracking in Video: Data, Metrics, and ProtocolIeee Transactions On Pattern Analysis and Machine Intelligence, 2008
- An algorithm for tracking multiple targetsIEEE Transactions on Automatic Control, 1979
- Smoothing and Differentiation of Data by Simplified Least Squares Procedures.Analytical Chemistry, 1964