Context-Based Object Recognition: Indoor Versus Outdoor Environments

Alameer, A ORCID:, Degenaar, P and Nazarpour, K 2019, 'Context-Based Object Recognition: Indoor Versus Outdoor Environments' , in: CVC 2019: Advances in Computer Vision , Advances in Intelligent Systems and Computing (944) , Springer Nature, pp. 437-490.

Full text not available from this repository. (Request a copy)


Object recognition is a challenging problem in high-level vision. Models that perform well for the outdoor domain, perform poorly in the indoor domain and the reverse is also true. This is due to the dramatic discrepancies of the global properties of each environment, for instance, backgrounds and lighting conditions. Here, we show that inferring the environment before or during the recognition process can dramatically enhance the recognition performance. We used a combination of deep and shallow models for object and scene recognition, respectively. Also, we used three novel topologies that can provide a trade-off between classification accuracy and decision sensitivity. We achieved a classification accuracy of 97.91%, outperforming the performance of a single GoogLeNet by 13%. In another experiment, we achieved an accuracy of 95% to categorise indoor and outdoor scenes by inference.

Item Type: Book Section
Editors: Arai, K and Kapoor, S
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: Science and Information Conference
Publisher: Springer Nature
Series Name: Advances in Intelligent Systems and Computing
ISBN: 9783030177973
Depositing User: A Alameer
Date Deposited: 26 May 2022 13:10
Last Modified: 13 Jun 2022 11:54

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)