Filters








3 Hits in 3.9 sec

SeDAR - Semantic Detection and Ranging: Humans can localise without LiDAR, can robots? [article]

Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
2018 arXiv   pre-print
And yet, this is how most vision-based approaches localise. Humans do the exact opposite. Instead of depth, we use high level semantic cues.  ...  While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.  ...  Semantic Detection and Ranging (SeDAR) is an innovative human-inspired framework that combines new semantic sensing capabilities with a novel semantic Monte-Carlo Localisation (MCL) approach.  ... 
arXiv:1709.01500v2 fatcat:gxiyci7qyvg6hixcmcj7vwi7t4

SeDAR - Semantic Detection and Ranging: Humans can Localise without LiDAR, can Robots?

Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
2018 2018 IEEE International Conference on Robotics and Automation (ICRA)  
And yet, this is how most vision-based approaches localise. Humans do the exact opposite. Instead of depth, we use high level semantic cues.  ...  While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.  ...  Semantic Detection and Ranging (SeDAR) is an innovative human-inspired framework that combines new semantic sensing capabilities with a novel semantic Monte-Carlo Localisation (MCL) approach.  ... 
doi:10.1109/icra.2018.8461074 dblp:conf/icra/MaldonadoHPB18 fatcat:dqzyqgou4jdwtdgfmy5pyukkji

SeDAR: Reading Floorplans Like a Human—Using Deep Learning to Enable Human-Inspired Localisation

Oscar Mendez, Simon Hadfield, Nicolas Pugeault, Richard Bowden
2019 International Journal of Computer Vision  
The use of human-level semantic information to aid robotic tasks has recently become an important area for both Computer Vision and Robotics.  ...  While our approach is able to use range measurements if available, we demonstrate that they are unnecessary as we can achieve results comparable to state-of-the-art without them.  ...  Semantic Detection and Ranging (SeDAR) is an innovative human-inspired framework that combines new semantic sensing capabilities with a novel semantic Monte-Carlo Localisation (MCL) approach.  ... 
doi:10.1007/s11263-019-01239-4 fatcat:hd2lcseet5ecffjry3hbfjviia