🤖 AI Summary
To address the robustness challenges in visual place recognition (VPR) for indoor mobile robots under drastic illumination changes, occlusions, dynamic disturbances, and limited training samples, this paper proposes a hierarchical localization framework based on panoramic imagery and a triplet convolutional neural network. Methodologically, it integrates panoramic representation learning with contrastive learning, systematically evaluating and enhancing various triplet loss functions—including BatchHard and SoftMargin—thereby establishing the first empirical validation of their generalization capability for indoor VPR. Crucially, the model achieves strong robustness using only a small number of images captured under specific lighting conditions. Experimental results demonstrate significant improvements over conventional VPR approaches across diverse scenarios, including varying illumination, partial occlusion, motion blur, and cross-scene evaluation. The proposed method consistently delivers higher localization accuracy and generalizability. The source code is publicly available.
📝 Abstract
The main objective of this paper is to tackle visual localization, which is essential for the safe navigation of mobile robots. The solution we propose employs panoramic images and triplet convolutional neural networks. We seek to exploit the properties of such architectures to address both hierarchical and global localization in indoor environments, which are prone to visual aliasing and other phenomena. Considering their importance in these architectures, a complete comparative evaluation of different triplet loss functions is performed. The experimental section proves that triplet networks can be trained with a relatively low number of images captured under a specific lighting condition and even so, the resulting networks are a robust tool to perform visual localization under dynamic conditions. Our approach has been evaluated against some of these effects, such as changes in the lighting conditions, occlusions, noise and motion blurring. Furthermore, to explore the limits of our approach, triplet networks have been tested in different indoor environments simultaneously. In all the cases, these architectures have demonstrated a great capability to generalize to diverse and challenging scenarios. The code used in the experiments is available at https://github.com/MarcosAlfaro/TripletNetworksIndoorLocalization.git.