Learning multiple experiences useful visual features for active maps localization in crowded environments. (2nd January 2016)

• Record Type: Journal Article
• Authors: Abdul Hafez, A. H.; Arora, Manpreet; Krishna, K. Madhava; Jawahar, C. V.
• Is Part Of: Advanced robotics. Volume 30:Number 1(2016)
• Page Start: 50
• Page End: 67
• Publication Date: 2016-01-02
• Subjects: Visual localization -- bag-of-words -- Bayes filtering -- active maps; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2015.1090336
• Languages: English
• ISSNs: 0169-1864

Abstract

Abstract : Crowded urban environments are composed of different types of dynamic and static elements. Learning and classification of features is a major task in solving the localization problem in such environments. This work presents a gradual learning methodology to learn the useful features using multiple experiences. The usefulness of an observed element is evaluated by a scoring mechanism which uses two scores – reliability and distinctiveness. The visual features thus learned are used to partition the visual map into smaller regions. The robot is efficiently localized in such a partitioned environment using two-level localization. The concept of active map (AM) is proposed here, which is a map that represents one partition of the environment in which there is a high probability of the robot existing. High-level localization is used to track the mode of the AMs using discrete Bayes filter. Low-level localization uses a bag-of-words model to retrieve images and accurately localize the robot. The pose of the robot is the one retrieved from the AM that has maximum a posteriori. Experiments have been conducted on a unique highly crowded data-set collected from Indian roads. The results support the proposed method due to speed and localization accuracy. Graphical Abstract: