Learning Deep NBNN Representations for Robust Place Categorization
This work addresses robust place recognition for robotics, but it is incremental as it builds on existing CNN and NBNN approaches.
The paper tackles semantic place categorization from RGB images by integrating a Naïve Bayes Nearest Neighbor model into a fully-convolutional neural network, achieving improved accuracy over previous methods and demonstrating robustness to occlusions and environmental changes.
This paper presents an approach for semantic place categorization using data obtained from RGB cameras. Previous studies on visual place recognition and classification have shown that, by considering features derived from pre-trained Convolutional Neural Networks (CNNs) in combination with part-based classification models, high recognition accuracy can be achieved, even in presence of occlusions and severe viewpoint changes. Inspired by these works, we propose to exploit local deep representations, representing images as set of regions applying a Naïve Bayes Nearest Neighbor (NBNN) model for image classification. As opposed to previous methods where CNNs are merely used as feature extractors, our approach seamlessly integrates the NBNN model into a fully-convolutional neural network. Experimental results show that the proposed algorithm outperforms previous methods based on pre-trained CNN models and that, when employed in challenging robot place recognition tasks, it is robust to occlusions, environmental and sensor changes.