Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation

We propose a method for learning using a set of feature representations which retrieve different amounts of information at different costs. The goal is to create a more efficient terrain classification algorithm which can be used in real-time, onboard an autonomous vehicle. Instead of building a monolithic classifier with uniformly complex representation for each class, the main idea here is to actively consider the labels or misclassification cost while constructing the classifier. For example, some terrain classes might be easily separable from the rest, so very simple representation will be sufficient to learn and detect these classes. This is taken advantage of during learning, so the algorithm automatically builds a variable-length visual representation which varies according to the complexity of the classification task. This enables fast recognition of different terrain types during testing. We also show how to select a set of feature representations so that the desired terrain ...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Anelia Angelova, Larry Matthies, Daniel M. Helmick, Pietro Perona
• Keywords: Computer Vision, CVPR 2007, Terrain Classes, Terrain Classification Algorithm, Terrain Classification Task, Uniformly Complex Representation, Variable-length Visual Representation