Unsupervised incremental learning for improved object detection in a video
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3298-3305
Abstract
Most common approaches for object detection collect thousands of training examples and train a detector in an offline setting, using supervised learning methods, with the objective of obtaining a generalized detector that would give good performance on various test datasets. However, when an offline trained detector is applied on challenging test datasets, it may fail in some cases by not being able to detect some objects or by producing false alarms. We propose an unsupervised multiple instance learning (MIL) based incremental solution to deal with this issue. We introduce an MIL loss function for Real Adaboost and present a tracking based effective unsupervised online sample collection mechanism to collect the online samples for incremental learning. Experiments demonstrate the effectiveness of our approach by improving the performance of a state of the art offline trained detector on the challenging datasets for pedestrian category.Keywords
This publication has 11 references indexed in Scilit:
- Context tracker: Exploring supporters and distracters in unconstrained environments2011
- P-N learning: Bootstrapping binary classifiers by structural constraints2010
- High performance object detection by collaborative learning of Joint Ranking of Granules features2010
- People-tracking-by-detection and people-detection-by-tracking2008
- Improving Part based Object Detection by Unsupervised, Online Boosting2007
- On-line Boosting and Vision2006
- Online Bagging and Boosting2006
- Online Detection and Classification of Moving Objects Using Progressively Improving Detectors2005
- Histograms of Oriented Gradients for Human Detection2005
- Improved Boosting Algorithms Using Confidence-rated PredictionsMachine Learning, 1999