Multi-Camera Action Recognition
 |
 |
 |
 |
 |
 |
People
Scott Spurlock Hui Wu Richard SouvenirWeighted View Selection with Multiple Kernel Learning
We present an algorithm for multi-view recognition in a distributed camera setting that learns which viewpoints are most discriminative for particular instances of ambiguity. Our method is built on top of 2D recognition algorithms and casts view selection as the problem of optimizing kernel weights in multiple kernel learning. The main contribution is a locality-sensitive meta-training step to learn a disambiguation function to select the relative weighting of available viewpoints needed to classify a 2D input example. Our method outperforms related approaches on benchmark multi-view action recognition data sets.
Citation
Scott Spurlock, Hui Wu, and Richard Souvenir. Multi-View Recognition Using Weighted View Selection. In Asian Conference on Computer Vision (ACCV), 2014.
One Camera at a Time
In another project, we focused on frame-based (online) action recognition with a method that operates in a multi-camera environment, but uses only a single camera at a time. We learn, for each keypose, the relative utility of a particular viewpoint compared with switching to a different available camera in the network for future classification. On a benchmark multi-camera action recognition dataset, our method outperforms approaches that incorporate all available cameras.
Citation
Scott Spurlock and Richard Souvenir. Multi-view action recognition one camera at a time. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2014.
Scott Spurlock and Richard Souvenir. Dynamic view selection for multi-camera action recognition. Machine Vision and Applications, 27(1), 53-63, 2016.