Cargando…
Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection †
Weakly supervised pose estimation can be used to assist unsupervised body part segmentation and concealed item detection. The accuracy of pose estimation is essential for precise body part segmentation and accurate concealed item detection. In this paper, we show how poses obtained from an RGB pretr...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964725/ https://www.ncbi.nlm.nih.gov/pubmed/36850603 http://dx.doi.org/10.3390/s23042005 |
_version_ | 1784896579223683072 |
---|---|
author | Amadi, Lawrence Agam, Gady |
author_facet | Amadi, Lawrence Agam, Gady |
author_sort | Amadi, Lawrence |
collection | PubMed |
description | Weakly supervised pose estimation can be used to assist unsupervised body part segmentation and concealed item detection. The accuracy of pose estimation is essential for precise body part segmentation and accurate concealed item detection. In this paper, we show how poses obtained from an RGB pretrained 2D pose detector can be modified for the backscatter image domain. The 2D poses are refined using RANSAC bundle adjustment to minimize the projection loss in 3D. Furthermore, we show how 2D poses can be optimized using a newly proposed 3D-to-2D pose correction network weakly supervised with pose prior regularizers and multi-view pose and posture consistency losses. The optimized 2D poses are used to segment human body parts. We then train a body-part-aware anomaly detection network to detect foreign (concealed threat) objects on segmented body parts. Our work is applied to the TSA passenger screening dataset containing millimeter wave scan images of airport travelers annotated with only binary labels that indicate whether a foreign object is concealed on a body part. Our proposed approach significantly improves the detection accuracy of TSA 2D backscatter images in existing works with a state-of-the-art performance of 97% F1-score, 0.0559 log-loss on the TSA-PSD test-set, and a 74% reduction in 2D pose error. |
format | Online Article Text |
id | pubmed-9964725 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-99647252023-02-26 Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † Amadi, Lawrence Agam, Gady Sensors (Basel) Article Weakly supervised pose estimation can be used to assist unsupervised body part segmentation and concealed item detection. The accuracy of pose estimation is essential for precise body part segmentation and accurate concealed item detection. In this paper, we show how poses obtained from an RGB pretrained 2D pose detector can be modified for the backscatter image domain. The 2D poses are refined using RANSAC bundle adjustment to minimize the projection loss in 3D. Furthermore, we show how 2D poses can be optimized using a newly proposed 3D-to-2D pose correction network weakly supervised with pose prior regularizers and multi-view pose and posture consistency losses. The optimized 2D poses are used to segment human body parts. We then train a body-part-aware anomaly detection network to detect foreign (concealed threat) objects on segmented body parts. Our work is applied to the TSA passenger screening dataset containing millimeter wave scan images of airport travelers annotated with only binary labels that indicate whether a foreign object is concealed on a body part. Our proposed approach significantly improves the detection accuracy of TSA 2D backscatter images in existing works with a state-of-the-art performance of 97% F1-score, 0.0559 log-loss on the TSA-PSD test-set, and a 74% reduction in 2D pose error. MDPI 2023-02-10 /pmc/articles/PMC9964725/ /pubmed/36850603 http://dx.doi.org/10.3390/s23042005 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Amadi, Lawrence Agam, Gady Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title | Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title_full | Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title_fullStr | Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title_full_unstemmed | Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title_short | Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection † |
title_sort | weakly supervised 2d pose adaptation and body part segmentation for concealed object detection † |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964725/ https://www.ncbi.nlm.nih.gov/pubmed/36850603 http://dx.doi.org/10.3390/s23042005 |
work_keys_str_mv | AT amadilawrence weaklysupervised2dposeadaptationandbodypartsegmentationforconcealedobjectdetection AT agamgady weaklysupervised2dposeadaptationandbodypartsegmentationforconcealedobjectdetection |