Dynamic Trees: Learning to Model Outdoor Scenes

Abstract. This paper considers the dynamic tree (DT) model, first introduced in [1]. A dynamic tree specifies a prior over structures of trees, each of which is a forest of one or more tree-structured belief networks (TSBN). In the literature standard tree-structured belief network models have been found to produce "blocky" segmentations when naturally occurring boundaries within an image did not coincide with those of the subtrees in the fixed structure of the network. Dynamic trees have a flexible architecture which allows the structure to vary to create configurations where the subtree and image boundaries align, and experimentation with the model has shown significant improvements. Here we derive an EM-style update based upon mean field inference for learning the parameters of the dynamic tree model and apply it to a database of images of outdoor scenes where all of its parameters are learned. DTs are seen to offer significant improvement in performance over the fixed-arc...

• Type: Conference
• Year: 2002
• Where: ECCV
• Authors: Nicholas J. Adams, Christopher K. I. Williams
• Keywords: Computer Vision, Dynamic Tree Model, Dynamic Trees, ECCV 2002, Mean Field Inference, Tree-structured Belief Network, Tree-structured Belief Networks