Title | ||
---|---|---|
Fast Terrain Classification Using Variable-Length Representation for Autonomous Navigation |
Abstract | ||
---|---|---|
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 classification task is accomplished with high accuracy and is at the same time efficient. The proposed approach achieves a good trade-off between recognition performance and speedup on data collected by an autonomous robot. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/CVPR.2007.383024 | CVPR |
Keywords | Field | DocType |
feature representation,image representation,variable-length representation,autonomous vehicle navigation,mobile robots,autonomous robot,terrain classification algorithm,feature extraction,image classification,image retrieval,image colour analysis,information retrieval,data collection,human robot interaction,classification algorithms,computer science,real time,image sensors,propulsion | Complex representation,Computer science,Terrain,Artificial intelligence,Classifier (linguistics),Contextual image classification,Speedup,Computer vision,Pattern recognition,Feature extraction,Autonomous robot,Machine learning,Mobile robot | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1063-6919 E-ISBN : 1-4244-1180-7 |
ISBN | Citations | PageRank |
1-4244-1180-7 | 32 | 1.71 |
References | Authors | |
16 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anelia Angelova | 1 | 410 | 30.70 |
Larry Matthies | 2 | 111 | 7.19 |
Daniel M. Helmick | 3 | 208 | 15.78 |
pietro perona | 4 | 16433 | 1969.06 |