Online Object Tracking: A Benchmark
Top Cited Papers
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2411-2418
- https://doi.org/10.1109/cvpr.2013.312
Abstract
Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.Keywords
This publication has 40 references indexed in Scilit:
- A survey of appearance models in visual object trackingACM Transactions on Intelligent Systems and Technology, 2013
- Locally Orderless TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Struck: Structured output tracking with kernelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Robust tracking using local sparse appearance model and K-selectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Visual tracking decompositionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Tracking the invisible: Learning where the object might bePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Real-Time Tracking via On-line BoostingPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- The template update problemIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Efficient region tracking with parametric models of geometry and illuminationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998