Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384158767> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4384158767 abstract "Thermal video can be used as a privacy-preserving and non-contact sensor for long-term health monitoring including respiratory activity. Face detection from thermal images is required to define the region of interest for automated respiration monitoring. In this study, we focus on thermal face detection using deep learning-based methods and transfer learning. First, YOLOv7, YOLOv7-tiny, and Detector Transformer (DeTr) object detection models were trained on an open thermal image dataset of faces. The weights from the pretrained models were transferred to a new model that was trained on our own target dataset. Results showed that transfer learning resulted in improved intersection-over-union (IoU) face detection performance. Moving beyond face detection in a single frame, we evaluated the stability of the trained face detection model with regard to the time-consistency of the detected bounding boxes in thermal videos. The DeTr model showed higher performance with 0.812 IoU and more stable predicted bounding boxes compared to YOLOv7 and YOLOv7-tiny. The proposed methods were also evaluated with regard to model size, as it pertains to viable deployment using edge computing, as part of a complete respiration rate estimation pipeline." @default.
- W4384158767 created "2023-07-14" @default.
- W4384158767 creator A5003562461 @default.
- W4384158767 creator A5017668310 @default.
- W4384158767 creator A5078223816 @default.
- W4384158767 creator A5081555529 @default.
- W4384158767 date "2023-05-22" @default.
- W4384158767 modified "2023-09-30" @default.
- W4384158767 title "Face Detection in Thermal Images with Improved Spatial Precision and Temporal Stability" @default.
- W4384158767 cites W2043123015 @default.
- W4384158767 cites W2082848186 @default.
- W4384158767 cites W2164208605 @default.
- W4384158767 cites W2194775991 @default.
- W4384158767 cites W2334671658 @default.
- W4384158767 cites W2838247043 @default.
- W4384158767 cites W2884367402 @default.
- W4384158767 cites W2890323852 @default.
- W4384158767 cites W2963037989 @default.
- W4384158767 cites W3034552680 @default.
- W4384158767 cites W3096609285 @default.
- W4384158767 cites W3161083802 @default.
- W4384158767 cites W3173710105 @default.
- W4384158767 cites W4205774012 @default.
- W4384158767 cites W4206938417 @default.
- W4384158767 cites W4230405732 @default.
- W4384158767 cites W4283721404 @default.
- W4384158767 cites W4283733031 @default.
- W4384158767 cites W4283755957 @default.
- W4384158767 cites W4285294981 @default.
- W4384158767 doi "https://doi.org/10.1109/i2mtc53148.2023.10176080" @default.
- W4384158767 hasPublicationYear "2023" @default.
- W4384158767 type Work @default.
- W4384158767 citedByCount "0" @default.
- W4384158767 crossrefType "proceedings-article" @default.
- W4384158767 hasAuthorship W4384158767A5003562461 @default.
- W4384158767 hasAuthorship W4384158767A5017668310 @default.
- W4384158767 hasAuthorship W4384158767A5078223816 @default.
- W4384158767 hasAuthorship W4384158767A5081555529 @default.
- W4384158767 hasConcept C108583219 @default.
- W4384158767 hasConcept C115961682 @default.
- W4384158767 hasConcept C147037132 @default.
- W4384158767 hasConcept C150899416 @default.
- W4384158767 hasConcept C153180895 @default.
- W4384158767 hasConcept C154945302 @default.
- W4384158767 hasConcept C2776151529 @default.
- W4384158767 hasConcept C31510193 @default.
- W4384158767 hasConcept C31972630 @default.
- W4384158767 hasConcept C41008148 @default.
- W4384158767 hasConcept C4641261 @default.
- W4384158767 hasConcept C63584917 @default.
- W4384158767 hasConcept C76155785 @default.
- W4384158767 hasConcept C94915269 @default.
- W4384158767 hasConceptScore W4384158767C108583219 @default.
- W4384158767 hasConceptScore W4384158767C115961682 @default.
- W4384158767 hasConceptScore W4384158767C147037132 @default.
- W4384158767 hasConceptScore W4384158767C150899416 @default.
- W4384158767 hasConceptScore W4384158767C153180895 @default.
- W4384158767 hasConceptScore W4384158767C154945302 @default.
- W4384158767 hasConceptScore W4384158767C2776151529 @default.
- W4384158767 hasConceptScore W4384158767C31510193 @default.
- W4384158767 hasConceptScore W4384158767C31972630 @default.
- W4384158767 hasConceptScore W4384158767C41008148 @default.
- W4384158767 hasConceptScore W4384158767C4641261 @default.
- W4384158767 hasConceptScore W4384158767C63584917 @default.
- W4384158767 hasConceptScore W4384158767C76155785 @default.
- W4384158767 hasConceptScore W4384158767C94915269 @default.
- W4384158767 hasLocation W43841587671 @default.
- W4384158767 hasOpenAccess W4384158767 @default.
- W4384158767 hasPrimaryLocation W43841587671 @default.
- W4384158767 hasRelatedWork W2003685048 @default.
- W4384158767 hasRelatedWork W2369744843 @default.
- W4384158767 hasRelatedWork W2766547489 @default.
- W4384158767 hasRelatedWork W2997667844 @default.
- W4384158767 hasRelatedWork W3005271701 @default.
- W4384158767 hasRelatedWork W3145385008 @default.
- W4384158767 hasRelatedWork W3217090486 @default.
- W4384158767 hasRelatedWork W4225418833 @default.
- W4384158767 hasRelatedWork W4292829955 @default.
- W4384158767 hasRelatedWork W4312789810 @default.
- W4384158767 isParatext "false" @default.
- W4384158767 isRetracted "false" @default.
- W4384158767 workType "article" @default.