{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T08:54:14Z","timestamp":1790931254758,"version":"4.1.0"},"reference-count":42,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003107","name":"German Ministry of Health","doi-asserted-by":"publisher","award":["2521DAT95C"],"award-info":[{"award-number":["2521DAT95C"]}],"id":[{"id":"10.13039\/501100003107","id-type":"DOI","asserted-by":"publisher"}]},{"award":["2521DAT95C"],"award-info":[{"award-number":["2521DAT95C"]}],"id":[{"id":"https:\/\/ror.org\/05vp4ka74","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human pose estimation in real-world indoor environments remains challenging due to privacy concerns, occlusions, varying numbers of people, and noisy sensor data. In this work, we investigate pose estimation from depth images captured over an extended period in a nursing home setting. We explore multiple input representations, including depth-only and silhouette-based representations, as well as depth-based Sobel gradient features. To systematically analyze the impact of model complexity and input representation, we design an experimental framework comparing lightweight Convolutional Neural Networks (CNNs), graph-based models, and deeper architectures, including ResNet and HRNet. Among the evaluated configurations, CNN+GCN with Depth+Sobel input achieved the highest test PCK on the seven-joint baseline, reaching 77.18% in the room-dependent setting and 76.03% in the room-independent setting. Lightweight models generally outperformed higher-capacity architectures on this dataset, but the experiments do not identify the mechanism behind this difference. CNN+LSTM reduced frame-level performance compared to the corresponding frame-wise CNN. Under realistic conditions, performance decreased for partially visible and multi-person scenes. Adding a visibility prediction head produced modest improvements in the evaluated scenarios. Unoccupied-room training reduced spurious pose predictions. The results indicate that lightweight architectures with structural depth representations are promising for privacy-sensitive pose estimation in real-world nursing home environments. However, substantial challenges remain for partial visibility, multi-person scenes, annotation uncertainty for occluded joints, and end-to-end deployment. Computational measurements show low model inference time on the tested hardware but do not establish end-to-end real-time system performance.<\/jats:p>","DOI":"10.3390\/s26196256","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T08:15:18Z","timestamp":1790928918000},"page":"6256","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Depth-Based Human Pose Estimation in Real-World Nursing Home Environments"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2327-5111","authenticated-orcid":false,"given":"Rinu Elizabeth","family":"Paul","sequence":"first","affiliation":[{"name":"Cognitive Systems Lab, University of Bremen, Enrique-Schmidt-Str. 5, 28359 Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9809-7028","authenticated-orcid":false,"given":"Tanja","family":"Schultz","sequence":"additional","affiliation":[{"name":"Cognitive Systems Lab, University of Bremen, Enrique-Schmidt-Str. 5, 28359 Bremen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"ref_1","unstructured":"Viso Suite (2026). Popular Applications of Computer Vision in Site Security, Viso Suite."},{"key":"ref_2","unstructured":"X-Byte Enterprise Solutions (2025). Computer Vision Applications: How Industries from Healthcare to Retail Are Benefiting?, X-Byte Enterprise Solutions."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Stenum, J., Cherry-Allen, K.M., Pyles, C.O., Reetzke, R.D., Vignos, M.F., and Roemmich, R.T. (2021). Applications of pose estimation in human health and performance across the lifespan. Sensors, 21.","DOI":"10.3390\/s21217315"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103931","DOI":"10.1016\/j.ergon.2026.103931","article-title":"A systematic review of computer vision-based human pose estimation for occupational safety","volume":"113","author":"Iyer","year":"2026","journal-title":"Int. J. Ind. Ergon."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Radanliev, P. (2025). Privacy, ethics, transparency, and accountability in AI systems for wearable devices. Front. Digit. Health, 7.","DOI":"10.3389\/fdgth.2025.1431246"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107615","DOI":"10.1016\/j.chb.2022.107615","article-title":"Psychological barriers of using wearable devices by seniors: A mixed-methods study","volume":"141","author":"Javdan","year":"2023","journal-title":"Comput. Hum. Behav."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/1743-0003-9-21","article-title":"A review of wearable sensors and systems with application in rehabilitation","volume":"9","author":"Patel","year":"2012","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10383","DOI":"10.1038\/s41598-026-39087-1","article-title":"Battery capacity degradation trajectory prediction for wearable medical devices with deep temporal decomposition","volume":"16","author":"Hu","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yao, H., Ge, C., Xue, J., and Zheng, N. (2017). A high spatial resolution depth sensing method based on binocular structured light. Sensors, 17.","DOI":"10.3390\/s17040805"},{"key":"ref_10","unstructured":"(2026, September 25). ToF Depth Perception. Available online: https:\/\/docs.luxonis.com\/hardware\/platform\/depth\/ToF-depth."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"8012","DOI":"10.1038\/s41598-024-58146-z","article-title":"An enhanced real-time human pose estimation method based on modified YOLOv8 framework","volume":"14","author":"Dong","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lindroth, H., Nalaie, K., Raghu, R., Ayala, I.N., Busch, C., Bhattacharyya, A., Moreno Franco, P., Diedrich, D.A., Pickering, B.W., and Herasevich, V. (2024). Applied artificial intelligence in healthcare: A review of computer vision technology application in hospital settings. J. Imaging, 10.","DOI":"10.3390\/jimaging10040081"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5","DOI":"10.3233\/AIS-180510","article-title":"Sensors, vision and networks: From video surveillance to activity recognition and health monitoring","volume":"11","author":"Prati","year":"2019","journal-title":"J. Ambient. Intell. Smart Environ."},{"key":"ref_14","unstructured":"Chou, E., Tan, M., Zou, C., Guo, M., Haque, A., Milstein, A., and Fei-Fei, L. (2018). Privacy-preserving action recognition for smart hospitals using low-resolution depth images. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100654","DOI":"10.1016\/j.smhl.2026.100654","article-title":"Unpacking scopes & challenges in AI-driven health safety monitoring: A systematic literature review toward real-time fall and wandering monitoring for patients with dementia","volume":"40","author":"Borty","year":"2026","journal-title":"Smart Health"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s13640-023-00606-z","article-title":"FitDepth: Fast and lite 16-bit depth image compression algorithm","volume":"2023","year":"2023","journal-title":"EURASIP J. Image Video Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Facil, J.M., Ummenhofer, B., Zhou, H., Montesano, L., Brox, T., and Civera, J. (2019). CAM-Convs: Camera-aware multi-scale convolutions for single-view depth. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE Computer Society.","DOI":"10.1109\/CVPR.2019.01210"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hartmann, Y., Kl\u00f6ckner, J., Deichsel, L., Paul, R.E., and Schultz, T. (2024). Gait Parameter Estimation from a Single Privacy Preserving Depth Sensor. Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies-Volume 1: BIOSIGNALS. INSTICC, SciTePress.","DOI":"10.5220\/0012383700003657"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1177\/27723577251320237","article-title":"Gait parameter estimation from a single depth sensor","volume":"4","author":"Hartmann","year":"2025","journal-title":"J. Smart Cities Soc."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., and Wang, G. (2016). NTU RGB+D: A large scale dataset for 3D human activity analysis. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J. (2019). Deep high-resolution representation learning for human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE Computer Society.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sun, X., Shang, J., Liang, S., and Wei, Y. (2017). Compositional Human Pose Regression. Proceedings of the IEEE International Conference on Computer Vision, IEEE Computer Society.","DOI":"10.1109\/ICCV.2017.284"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"Openpose: Realtime multi-person 2D pose estimation using part affinity fields","volume":"43","author":"Cao","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Guo, Y., Li, Z., Li, Z., Du, X., Quan, S., and Xu, Y. (2022). Pop-net: Pose over parts network for multi-person 3D pose estimation from a depth image. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE Computer Society.","DOI":"10.1109\/WACV51458.2022.00397"},{"key":"ref_26","unstructured":"Fredrik, H. (2015). Privacy Protecting Surveillance: A Proof-of-Concept Demonstrator, Link\u00f6ping University."},{"key":"ref_27","first-page":"759","article-title":"Silhouette extraction from depth sensors for older adult monitoring at nursing homes","volume":"Volume 14114","author":"Paul","year":"2026","journal-title":"Proceedings of the Eighteenth International Conference on Machine Vision (ICMV 2025)"},{"key":"ref_28","first-page":"71","article-title":"Extraction of Human Body Skeleton Based on Silhouette Images","volume":"Volume 1","author":"Ding","year":"2010","journal-title":"Proceedings of the Second International Workshop on Education Technology and Computer Science"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/ICPR.2006.640","article-title":"Human silhouette extraction based on HMM","volume":"Volume 2","author":"Zhao","year":"2006","journal-title":"Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906)"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Dutta, A., Lal, R., Raychaudhuri, D.S., Ta, C.K., and Roy-Chowdhury, A.K. (2024). Poise: Pose guided human silhouette extraction under occlusions. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE Computer Society.","DOI":"10.1109\/WACV57701.2024.00604"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"108046","DOI":"10.1016\/j.patcog.2021.108046","article-title":"Monocular multi-person pose estimation: A survey","volume":"118","author":"Seewald","year":"2021","journal-title":"Pattern Recognit."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Paul, R.E., Kock, P., Hartmann, Y., Ball, E., Seibert, K., Liu, H., and Schultz, T. (2025). Longitudinal Data Acquisition for AI Services in Long-Term Care Facilities for Older Adults. Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies-Scale-IT-Up. INSTICC, SciTePress.","DOI":"10.5220\/0013403900003911"},{"key":"ref_33","unstructured":"CVAT.ai Corporation (2023). Computer Vision Annotation Tool (CVAT), CVAT.ai Corporation."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mejia-Trujillo, J.D., Castano-Pino, Y.J., Navarro, A., Arango-Paredes, J.D., Rinc\u00f3n, D., Valderrama, J., Munoz, B., and Orozco, J.L. (2019). Kinect\u2122 and Intel RealSense\u2122 D435 comparison: A preliminary study for motion analysis. Proceedings of the 2019 IEEE International Conference on E-Health Networking, Application & Services (HealthCom), IEEE.","DOI":"10.1109\/HealthCom46333.2019.9009433"},{"key":"ref_35","unstructured":"Edge Detection Using OpenCV. 2025. Open Source Vision Foundation: 2025. Available online: https:\/\/opencv.org\/blog\/edge-detection-using-opencv\/."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Kim, H., Sakamoto, R., Kitahara, I., Toriyama, T., and Kogure, K. (2007). Robust silhouette extraction technique using background subtraction. Proceedings of the 10th Meeting on Image Recognition and Understanding (MIRU), Information Processing Society of Japan (IPSJ).","DOI":"10.1117\/1.2779022"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.patcog.2016.08.003","article-title":"Robust human activity recognition from depth video using spatiotemporal multi-fused features","volume":"61","author":"Jalal","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"32","DOI":"10.2174\/1874479610801010032","article-title":"Moving object detection in spatial domain using background removal techniques-state-of-art","volume":"1","author":"Elhabian","year":"2008","journal-title":"Recent Patents Comput. Sci."},{"key":"ref_39","unstructured":"Schwenk, K., and Huber, F. (2025). Connected Component Labeling Algorithm for very complex and high resolution images on an FPGA platform. Proceedings of the German Aerospace Center (DLR), German Space Operations Center (GSOC)."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3603618","article-title":"Deep Learning-Based Human Pose Estimation: A Survey","volume":"56","author":"Zheng","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Henderson, P., and Ferrari, V. (2016). End-to-end training of object class detectors for mean average precision. Proceedings of the Asian Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-54193-8_13"},{"key":"ref_42","first-page":"19000","article-title":"The origins and prevalence of texture bias in convolutional neural networks","volume":"33","author":"Hermann","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6256\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T08:17:50Z","timestamp":1790929070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":42,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196256"],"URL":"https:\/\/doi.org\/10.3390\/s26196256","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]}}}