Robust visual tracking via adaptive forest
- 1 June 2013
Abstract
In this paper, we address the visual object tracking problem in the so-called “Tracking-by-Detection” framework, which forms a dominating trend for target tracking recently. Combining ideas from random forest and multiple instance learning, we propose a novel online ensemble classifier selection procedure to conduct the tracking task. The proposed algorithm has been tested on several challenging image sequences. Experimental results validate the effectiveness of the proposed tracking method.Keywords
This publication has 24 references indexed in Scilit:
- Online Object Tracking: A BenchmarkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Class-Specific Hough Forests for Object DetectionPublished by Springer Science and Business Media LLC ,2013
- Real-time human pose recognition in parts from single depth imagesCommunications of the ACM, 2013
- Recent advances and trends in visual tracking: A reviewNeurocomputing, 2011
- Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised LearningFoundations and Trends® in Computer Graphics and Vision, 2011
- On-line Random ForestsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Semantic texton forests for image categorization and segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Implementing Decision Trees and Forests on a GPULecture Notes in Computer Science, 2008
- Object trackingACM Computing Surveys, 2006
- Random ForestsMachine Learning, 2001