%0 Journal Article
%T Fast loop
%A Angelos Amanatiadis
%A Antonios Gasteratos
%A Loukas Bampis
%J The International Journal of Robotics Research
%@ 1741-3176
%D 2018
%R 10.1177/0278364917740639
%X In this paper, a novel pipeline for loop-closure detection is proposed. We base our work on a bag of binary feature words and we produce a description vector capable of characterizing a physical scene as a whole. Instead of relying on single camera measurements, the robot¡¯s trajectory is dynamically segmented into image sequences according to its content. The visual word occurrences from each sequence are then combined to create sequence-visual-word-vectors and provide additional information to the matching functionality. In this way, scenes with considerable visual differences are firstly discarded, while the respective image-to-image associations are provided subsequently. With the purpose of further enhancing the system¡¯s performance, a novel temporal consistency filter (trained offline) is also introduced to advance matches that persist over time. Evaluation results prove that the presented method compares favorably with other state-of-the-art techniques, while our algorithm is tested on a tablet device, verifying the computational efficiency of the approach
%K Loop-closure detection
%K image sequences
%K visual SLAM
%K mobile robotics
%K low-power embedded systems
%U https://journals.sagepub.com/doi/full/10.1177/0278364917740639