Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115833473> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3115833473 abstract "This paper proposes the addition of a thermal camera to an RGB system with the goal of improving person and road detection reliability in unfavorable weather and illumination conditions. Custom data is gathered on an experimental vehicle and used for development and testing. For person detection, we propose a novel multi-modal approach, where bounding boxes are initially obtained from RGB and thermal images using YOLOv3-tiny. We then identify high-intensity connected components in thermal images to compensate for missed detections. Detections from the two cameras and the two algorithms are finally weighed and combined into a confidence map. Using the proposed fusion method, recall and precision are improved compared to using RGB only, without the need to retrain the network. For thermal-based road segmentation, we achieve an average precision of 94.2% after re-training MultiNet's KittiSeg decoder on a small thermal dataset, while using pre-trained weights for MultiNet's VGG-based encoder. These results show that the addition of thermal cameras to perception systems of autonomous vehicles can bring substantial benefits with minimal labelling, implementation effort and training requirements." @default.
- W3115833473 created "2021-01-05" @default.
- W3115833473 creator A5007480212 @default.
- W3115833473 creator A5020214405 @default.
- W3115833473 creator A5025864803 @default.
- W3115833473 creator A5034211466 @default.
- W3115833473 date "2020-09-20" @default.
- W3115833473 modified "2023-10-16" @default.
- W3115833473 title "Thermal Imaging on Smart Vehicles for Person and Road Detection: Can a Lazy Approach Work?" @default.
- W3115833473 cites W1494369943 @default.
- W3115833473 cites W1686810756 @default.
- W3115833473 cites W1861492603 @default.
- W3115833473 cites W2000721607 @default.
- W3115833473 cites W2108598243 @default.
- W3115833473 cites W2120646872 @default.
- W3115833473 cites W2133984628 @default.
- W3115833473 cites W2167222293 @default.
- W3115833473 cites W2512727433 @default.
- W3115833473 cites W2562137921 @default.
- W3115833473 cites W2737712196 @default.
- W3115833473 cites W2764012408 @default.
- W3115833473 cites W2796347433 @default.
- W3115833473 cites W2884367402 @default.
- W3115833473 cites W2897451716 @default.
- W3115833473 cites W2905094904 @default.
- W3115833473 cites W2950918436 @default.
- W3115833473 cites W2950935200 @default.
- W3115833473 cites W2963721253 @default.
- W3115833473 cites W2963881378 @default.
- W3115833473 cites W2967098543 @default.
- W3115833473 cites W2968443604 @default.
- W3115833473 cites W2969676669 @default.
- W3115833473 cites W2973613996 @default.
- W3115833473 doi "https://doi.org/10.1109/itsc45102.2020.9294671" @default.
- W3115833473 hasPublicationYear "2020" @default.
- W3115833473 type Work @default.
- W3115833473 sameAs 3115833473 @default.
- W3115833473 citedByCount "1" @default.
- W3115833473 countsByYear W31158334732023 @default.
- W3115833473 crossrefType "proceedings-article" @default.
- W3115833473 hasAuthorship W3115833473A5007480212 @default.
- W3115833473 hasAuthorship W3115833473A5020214405 @default.
- W3115833473 hasAuthorship W3115833473A5025864803 @default.
- W3115833473 hasAuthorship W3115833473A5034211466 @default.
- W3115833473 hasBestOaLocation W31158334732 @default.
- W3115833473 hasConcept C111919701 @default.
- W3115833473 hasConcept C115961682 @default.
- W3115833473 hasConcept C118505674 @default.
- W3115833473 hasConcept C147037132 @default.
- W3115833473 hasConcept C154945302 @default.
- W3115833473 hasConcept C31972630 @default.
- W3115833473 hasConcept C41008148 @default.
- W3115833473 hasConcept C63584917 @default.
- W3115833473 hasConcept C79403827 @default.
- W3115833473 hasConcept C82990744 @default.
- W3115833473 hasConcept C89600930 @default.
- W3115833473 hasConceptScore W3115833473C111919701 @default.
- W3115833473 hasConceptScore W3115833473C115961682 @default.
- W3115833473 hasConceptScore W3115833473C118505674 @default.
- W3115833473 hasConceptScore W3115833473C147037132 @default.
- W3115833473 hasConceptScore W3115833473C154945302 @default.
- W3115833473 hasConceptScore W3115833473C31972630 @default.
- W3115833473 hasConceptScore W3115833473C41008148 @default.
- W3115833473 hasConceptScore W3115833473C63584917 @default.
- W3115833473 hasConceptScore W3115833473C79403827 @default.
- W3115833473 hasConceptScore W3115833473C82990744 @default.
- W3115833473 hasConceptScore W3115833473C89600930 @default.
- W3115833473 hasLocation W31158334731 @default.
- W3115833473 hasLocation W31158334732 @default.
- W3115833473 hasOpenAccess W3115833473 @default.
- W3115833473 hasPrimaryLocation W31158334731 @default.
- W3115833473 hasRelatedWork W1987144139 @default.
- W3115833473 hasRelatedWork W2030712947 @default.
- W3115833473 hasRelatedWork W2134924024 @default.
- W3115833473 hasRelatedWork W2156863789 @default.
- W3115833473 hasRelatedWork W2369744843 @default.
- W3115833473 hasRelatedWork W2558375057 @default.
- W3115833473 hasRelatedWork W3147816421 @default.
- W3115833473 hasRelatedWork W3158600517 @default.
- W3115833473 hasRelatedWork W4206297187 @default.
- W3115833473 hasRelatedWork W4225923497 @default.
- W3115833473 isParatext "false" @default.
- W3115833473 isRetracted "false" @default.
- W3115833473 magId "3115833473" @default.
- W3115833473 workType "article" @default.