Authors:
Marcos Alfaro
1
;
Juan Cabrera
1
;
Enrique Heredia
1
;
Oscar Reinoso
1
;
2
;
Arturo Gil
1
and
Luis Paya
1
;
2
Affiliations:
1
Research Institute for Engineering (I3E), Miguel Hernández University, Elche, Spain
;
2
Valencian Graduate School and Research Network of Artificial Intelligence, Valencia, Spain
Keyword(s):
Mobile Robotics, Place Recognition, Omnidirectional Cameras, Deep Learning, Late Fusion.
Abstract:
Place recognition is crucial for the safe navigation of mobile robots. Vision sensors are an effective solution to address this task due to their versatility and low cost, but the images are sensitive to changes in environmental conditions. Multi-modal approaches can overcome this limitation, but the integration of different sensors often leads to larger computing and hardware costs. Consequently, this paper proposes enhancing omnidirectional views with additional features derived from them. First, feature maps are extracted from the original omnidi-rectional images. Second, each feature map is processed by an independent deep network and embedded into a descriptor. Finally, embeddings are merged by means of a late approach that weights each feature according to the confidence in the prediction of the networks. The experiments conducted in indoor and outdoor scenarios revealed that the proposed method consistently improves the performance across different environments and lighting co
nditions, presenting itself as a precise, cost-effective solution for place recognition. The code is available at the project website: https://github.com/MarcosAlfaro/VPR LF VisualFeatures.
(More)