Subspace-Based Adaptation of Detectors for Video
Keywords:
Subspace, Detector, Adaptation, Histogram.Abstract
Object detection in videos has always been a challenging problem to work with. Detection of a particular class object plays an important role in many real-world applications. Since the domain of source and target video vary significantly, classifier being trained on source video does not give expected results on the target video. Thus, domain adaptation techniques are used, one of which is Subspace Based Adaptation. In this technique, first, we compute both source and target subspace from the features collected. Since we do not have target data directly, we use different ways to get data from the target video. Compute subspace after collecting the data from both source and target videos. Eigen vectors describe this generated source and target subspaces.
References
- M. Sebban B. Fernando1, A. Habrard2 and T. Tuytelaars1. Unsupervised visual domain adaptation using subspace alignment. In ICCV, 2013.
- M. Fritz K. Saenko, B. Kulis and T. Darrell. Adapting visual category models to new domains. In Computer Vision ECCV, 6314:213{226, 2010.
- K. Saenko B. Kulis and T. Darrell. What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In CVPR, pages 1785{1792, 2011.
- D. Foster J. Blitzer and S. Kakade. Domain adaptation with coupled subspaces.
- S. Ali O. Javed and M. Shah. Online detection and classi cation of moving ob-jects using progressively improving detectors. Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, pages 1063{6919, 2015.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.