This paper considers visual feature selection to implement position estimation using an omnidirectional camera. The localization is based on a maximum likelihood estimation (MLE) with a map from optimally selected visual features using Gaussian process (GP) regression. In particular, the collection of selected features over a surveillance region is modeled by a multivariate GP with unknown hyperparameters. The hyperparameters are identified through the learning process by an MLE, which are used for prediction in an empirical Bayes fashion. To select features, we apply a backward sequential elimination technique in order to improve the quality of the position estimation with compressed features for efficient localization. The excellent results of the proposed algorithm are illustrated by the experimental studies with different visual features under both indoor and outdoor real-world scenarios.
Bibliographical noteFunding Information:
This work has been supported by the National Science Foundation through CAREER award CMMI-0846547 . Mr. Do has been supported by the Vietnam Education Foundation ( G-3-10180 ) fellowship. The authors would like to thank Mr. Alexander Robinson from Thornapple Kellogg High School and Ms. Tam Le from the Department of Computer Science and Engineering, Michigan State University for their contributions in the preparation of the experiments.
All Science Journal Classification (ASJC) codes
- Signal Processing
- Computer Vision and Pattern Recognition