Unsupervised Distributed Feature Selection for Multi-view Object Recognition

Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem of distributed object recognition or indexing from multiple cameras, where the computational power available at each camera sensor is limited and communication between sensors is prohibitively expensive. In this scenario, it is desirable to avoid sending redundant visual features from multiple views, but traditional supervised feature selection approaches are inapplicable as the class label is unknown at the camera. In this paper we propose an unsupervised multi-view feature selection algorithm based on a distributed compression approach. With our method, a Gaussian Process model of the joint view statistics is used at the receiver to obtain a joint encoding of the views without directly sharing information across encoders. We demonstrate our approach on recognition and indexing tasks with multi-view image databases and show that our method compares favorably to an independent encoding of the features from each camera.