Struck: Structured Output Tracking with Kernels
Top Cited Papers
- 17 December 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 38 (10), 2096-2109
- https://doi.org/10.1109/tpami.2015.2509974
Abstract
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we avoid the need for an intermediate classification step. Our method uses a kernelised structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow our tracker to run at high frame rates, we (a) introduce a budgeting mechanism that prevents the unbounded growth in the number of support vectors that would otherwise occur during tracking, and (b) show how to implement tracking on the GPU. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased tracking performance.Keywords
Funding Information
- ERC (ERC-2012-AdG 321162-HELIOS)
This publication has 39 references indexed in Scilit:
- Adaptive Color Attributes for Real-Time Visual TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Randomized Ensemble TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust Object Tracking with Online Multi-lifespan Dictionary LearningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Online Robust Non-negative Dictionary Learning for Visual TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust visual tracking via adaptive forestPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- PROST: Parallel robust online simple trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- On-line Random ForestsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Tracking as Repeated Figure/Ground SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002