|   | 
Author M. Oliveira; L. Seabra Lopes; G. Hyun Lim; S. Hamidreza Kasaei; Angel D. Sappa; A. Tomé
Title Concurrent Learning of Visual Codebooks and Object Categories in Open- ended Domains Type Conference Article
Year 2015 Publication Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on, Hamburg, Germany, 2015 Abbreviated Journal
Volume Issue Pages 2488 - 2495
Keywords Birds, Training, Legged locomotion, Visualization, Histograms, Object recognition, Gaussian mixture model
Abstract In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are usually constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using codebooks constructed offline.
Corporate Author Thesis
Publisher IEEE Place of Publication Hamburg, Germany Editor
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
Area Expedition Conference 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Notes Approved no
Call Number cidis @ cidis @ Serial (down) 41
Permanent link to this record