{"id":15,"date":"2014-11-15T21:38:57","date_gmt":"2014-11-15T19:38:57","guid":{"rendered":"http:\/\/www.mpateraki.org\/?page_id=15"},"modified":"2026-08-30T09:00:03","modified_gmt":"2026-08-30T07:00:03","slug":"research","status":"publish","type":"page","link":"https:\/\/mpateraki.org\/?page_id=15","title":{"rendered":"Research"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Datasets &amp; Benchmarking<\/h2>\n\n\n\n<p class=\"isSelectedEnd\"><strong>IndustryShapes Dataset (ICRA 2026)<\/strong><\/p>\n\n\n\n<p class=\"isSelectedEnd\">IndustryShapes is a benchmark for instance-level and novel-object 6D pose estimation in realistic industrial environments. It includes challenging textureless, reflective and geometrically complex objects captured under clutter, occlusion and varying viewpoints. Its extended set provides RGB-D onboarding sequences designed to support the evaluation of model-free methods.<\/p>\n\n\n\n<p><a href=\"https:\/\/pose-lab.github.io\/IndustryShapes\/\">Project page<\/a> \u00b7 <a href=\"https:\/\/arxiv.org\/abs\/2602.05555\">Paper<\/a> \u00b7 <a href=\"https:\/\/huggingface.co\/datasets\/POSE-Lab\/IndustryShapes\">Dataset<\/a> \u00b7 <a href=\"https:\/\/github.com\/POSE-Lab\/IndustryShapes_benchmark\">Code<\/a><\/p>\n\n\n\n<p><strong>CarDA: <strong>Car-Door Assembly Activities Dataset<\/strong>(ECCV 2024)<\/strong><\/p>\n\n\n\n<p>CarDA is a multimodal dataset for vision-based human behaviour understanding in realistic automotive assembly environments. It provides synchronised multi-camera RGB-D recordings and motion-capture data, together with annotations for assembly activities and EAWS-based ergonomic assessment. The dataset supports research on worker localisation, 3D human-pose estimation, action recognition, posture analysis and task-progress monitoring.<\/p>\n\n\n\n<p><a href=\"https:\/\/doi.org\/10.1016\/j.cviu.2025.104592\">Paper<\/a> \u00b7 <a href=\"https:\/\/zenodo.org\/records\/13370888\">Dataset<\/a><\/p>\n\n\n\n<p><strong>harAGE: Multimodal Smartwatch-Based Human Activity Dataset (FG 2021)<\/strong><\/p>\n\n\n\n<p>harAGE is a multimodal dataset for recognising human activities from smartwatch sensor data. It supports research on wearable sensing and human-activity recognition, particularly in workplace and ageing contexts.<\/p>\n\n\n\n<p><a href=\"https:\/\/doi.org\/10.1109\/FG52635.2021.9666947\">Paper<\/a>&nbsp;\u00b7&nbsp;<a href=\"https:\/\/doi.org\/10.5281\/zenodo.6517688\">Dataset<\/a><\/p>\n\n\n\n<p><strong>f-Body: Occluded Articulated Human Body Dataset (TPAMI 2015)<\/strong><br>An annotated dataset for human body pose extraction and tracking under occlusions.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><tbody><tr><td><figure><a href=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t1.bmp\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-medium wp-image-449\" src=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t1-300x56.bmp\" alt=\"t1\" width=\"300\" height=\"56\" srcset=\"https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t1-300x56.bmp 300w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t1-1024x192.bmp 1024w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t1.bmp 1280w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/figure><\/td><td><figure><a href=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t2.bmp\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-medium wp-image-450\" src=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t2-300x56.bmp\" alt=\"t2\" width=\"300\" height=\"56\" srcset=\"https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t2-300x56.bmp 300w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t2-1024x192.bmp 1024w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t2.bmp 1280w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/figure><\/td><\/tr><tr><td><figure><a href=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t3.bmp\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-medium wp-image-451\" src=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t3-300x56.bmp\" alt=\"t3\" width=\"300\" height=\"56\" srcset=\"https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t3-300x56.bmp 300w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t3-1024x192.bmp 1024w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t3.bmp 1280w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/figure><\/td><td><figure><a href=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t4.bmp\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-medium wp-image-452\" src=\"http:\/\/www.mpateraki.org\/wp-content\/uploads\/2014\/11\/t4-300x56.bmp\" alt=\"t4\" width=\"300\" height=\"56\" srcset=\"https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t4-300x56.bmp 300w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t4-1024x192.bmp 1024w, https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/t4.bmp 1280w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/figure><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p><a href=\"http:\/\/www.ics.forth.gr\/cvrl\/fbody\/\">Project page<\/a> \u00b7 <a href=\"http:\/\/dx.doi.org\/10.1109\/TPAMI.2015.2502582\">Paper<\/a><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">3D Object Perception and 6D Pose Estimation<\/h2>\n\n\n\n<p class=\"isSelectedEnd\">This research addresses the estimation and tracking of the three-dimensional position and orientation of objects from visual observations. Current work focuses particularly on generalisable and model-free methods that can operate on previously unseen industrial objects, including objects with limited texture, reflective surfaces, complex geometry, clutter and occlusion. Earlier work investigated multi-hypothesis tracking and model-based pose estimation.<\/p>\n\n\n\n<p class=\"isSelectedEnd\">Selected publications:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>6D Object Localization in Car-Assembly Industrial Environment.<\/strong> Papadaki, A. &amp; Pateraki, M., 2023. <em>Journal of Imaging<\/em>, <em>9<\/em>(3), 72. &nbsp;<a href=\"https:\/\/doi.org\/10.3390\/jimaging9030072\">Paper<\/a><\/li>\n\n\n\n<li><strong>IndustryShapes: A Dataset and Benchmark for Generalisable 6D Object Pose Estimation in Industrial Environments. <\/strong>Sapoutzoglou, P., Vaggelis, O., Zacharia, A., Sartinas, E. &amp; Pateraki, M., 2026. In Proc. of IEEE Int.. Conf. on Robotics and Automation (ICRA)<b>&nbsp;<\/b>&nbsp;&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2602.05555\">Paper<\/a><\/li>\n\n\n\n<li><strong>Crane Spreader Pose Estimation from a Single View.<\/strong> Pateraki M., Sapoutzoglou P. &amp; Lourakis M., &nbsp;2023. In <i>Proc. of the 18th Intl. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023)<\/i>. <a href=\"https:\/\/doi.org\/10.5220\/0011788800003417\">Paper<\/a><\/li>\n\n\n\n<li><strong>Markerless Visual Tracking of a Container Crane Spreader.<\/strong> Lourakis, M. &amp; Pateraki, M., 2021. In Proc.<em> IEEE\/CVF Intl. Conf. on Computer Vision Workshops (ICCVW)<\/em>. <a href=\"https:\/\/openaccess.thecvf.com\/content\/ICCV2021W\/CVinHRC\/papers\/Lourakis_Markerless_Visual_Tracking_of_a_Container_Crane_Spreader_ICCVW_2021_paper.pdf\">Paper<\/a><\/li>\n\n\n\n<li><strong>Robust Multi-Hypothesis 3D Object Pose Tracking.<\/strong> <span class=\"smallfont\">Chliveros G., Pateraki M., Trahanias P., 2013. In Proc. of the 9th Intl. Conference on Computer Vision Systems (ICVS). <\/span><a href=\"https:\/\/doi.org\/10.1007\/978-3-642-39402-7_24\">Paper<\/a> \u00b7&nbsp; <a href=\"https:\/\/www.youtube.com\/watch?v=eBRV5yu7vtU\">Video<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">3D Shape Representation<\/h2>\n\n\n\n<p>Investigate compact and continuous representations of complex three-dimensional shapes. Rather than relying on computationally intensive neural architectures or dense explicit models, the work explores functional representations that describe surface geometry through local distance fields anchored at strategically selected reference points.<\/p>\n\n\n\n<p>Selected publications:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>SHARC: Reference Point Driven Spherical Harmonic Representation for Complex Shapes.<\/strong>&nbsp;Sapoutzoglou, P., Terzakis, G. &amp; Pateraki, M., 2026. In&nbsp;<em>Proc. of the Intl. Conf. on Pattern Recognition (ICPR 2026)<\/em>.&nbsp;<a href=\"https:\/\/pose-lab.github.io\/SHARC\/\">Project page<\/a>&nbsp;\u00b7&nbsp;<a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-032-31663-9_12\">Paper<\/a>&nbsp;\u00b7&nbsp;<a href=\"https:\/\/github.com\/POSE-Lab\/SHARC\">Code<\/a><\/li>\n\n\n\n<li><strong>Shape Representation Using Gaussian Process Mixture Models.<\/strong>&nbsp;Sapoutzoglou, P., Terzakis, G., Floros, G. &amp; Pateraki, M., 2026.&nbsp;<em>The Intl. Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences<\/em>.&nbsp;<a href=\"https:\/\/isprs-archives.copernicus.org\/articles\/XLIX-B2-2026\/271\/2026\/isprs-archives-XLIX-B2-2026-271-2026.html\">ISPRS paper<\/a>&nbsp;\u00b7&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2604.00862\">arXiv<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Human Behaviour Understanding and Human\u2013Robot Interaction<\/h2>\n\n\n\n<p class=\"isSelectedEnd\">This research uses visual and multimodal observations to understand human pose, posture, activity, attention and communicative intent. The work supports ergonomic assessment, task-progress monitoring and natural interaction between people and robotic systems in industrial and social environments.<\/p>\n\n\n\n<p class=\"isSelectedEnd\">Selected publications:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>A vision-based framework for human behavior understanding in industrial assembly lines.<\/strong>&nbsp;Papoutsakis, K., Bakalos, N., Zacharia, A., Fragkoulis, K., Kapetadimitri, G., &nbsp;&amp; Pateraki, M., 2026. Computer Vision and Image Understanding.&nbsp;<a href=\"https:\/\/doi.org\/10.1016\/j.cviu.2025.104592\">Paper<\/a> \u00b7 <a href=\"https:\/\/arxiv.org\/abs\/2409.17356\">arXiv<\/a> \u00b7 <a href=\"https:\/\/zenodo.org\/records\/13370888\">CarDA dataset<\/a><\/li>\n\n\n\n<li><strong>Detection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors.<\/strong> Papoutsakis, K., Papadopoulos, G., Maniadakis, M., Papadopoulos, T., Lourakis, M., Pateraki, M., &amp; Varlamis, I., 2022. <em>Technologies<\/em>, <em>10<\/em>(2), 42. <a href=\"https:\/\/doi.org\/10.3390\/technologies10020042\">Paper<\/a><\/li>\n\n\n\n<li><span class=\"smallfont\"><strong>Full-body Pose Tracking &#8211; the Top View Reprojection Approach.<\/strong> Sigalas M., Pateraki M., Trahanias P., 2016. IEEE Transaction on Pattern Analysis and Machine Intelligence.<\/span> <a href=\"https:\/\/doi.org\/10.1109\/TPAMI.2015.2502582\">Paper<\/a> <a href=\"https:\/\/www.youtube.com\/watch?v=33AsuE-WP64\">Video-01<\/a> <a href=\"https:\/\/www.youtube.com\/watch?v=jY5F2vj-QYc&amp;source_ve_path=MTc4NDI0\">Video-02<\/a><\/li>\n\n\n\n<li><span class=\"smallfont\"><strong>Visual estimation of attentive cues in HRI: The case of torso and head pose.<\/strong> Sigalas M., Pateraki M. and Trahanias P., 2015. In Proc. of the 10th Intl. Conference on Computer Vision Systems (ICVS), 6-9 July, Kopenhagen, Denmark. <a href=\"http:\/\/dx.doi.org\/10.1007\/978-3-319-20904-3_34\" target=\"_blank\" rel=\"noopener\">Paper<\/a>&nbsp;<\/span><\/li>\n\n\n\n<li><span class=\"smallfont\"><strong>Visual estimation of pointed targets for robot guidance via fusion of face pose and hand orientation.<\/strong> Pateraki M., Baltzakis H., Trahanias P., 2014. Computer Vision and Image Understanding.<\/span> <a href=\"https:\/\/doi.org\/10.1016\/j.cviu.2013.12.006\">Paper<\/a><\/li>\n\n\n\n<li><span class=\"smallfont\"><strong>Visual tracking of hands, faces and facial features of multiple persons.<\/strong> Baltzakis H., Pateraki M., Trahanias P., 2012. Machine Vision and Applications. <a href=\"http:\/\/dx.doi.org\/10.1007\/s00138-012-0409-5\" target=\"_blank\" rel=\"noopener\">Paper<\/a><\/span> <a href=\"https:\/\/www.youtube.com\/watch?v=FJl1ACEb7_w\">Video-01<\/a> <a href=\"https:\/\/www.youtube.com\/watch?v=oQSaCP6G4Ts\">Video-02<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Photogrammetric 3D Reconstruction and Documentation<\/h2>\n\n\n\n<p>This research addresses the generation of  three-dimensional information from images and range observations. It spans multi-image matching, digital surface modelling, surface-discontinuity preservation, point-cloud processing and the integration of heterogeneous imaging sources. These methods have been applied to built, natural and cultural-heritage environments, from airborne mapping and glacier monitoring to architectural and archaeological documentation.<\/p>\n\n\n\n<p>Selected publications:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Detecting Three-Dimensional Straight Edges in Point Clouds Based on Normal Vectors.<\/strong>&nbsp;Makka, A., Pateraki, M., Betsas, T. &amp; Georgopoulos, A., 2025.&nbsp;<em>Heritage<\/em>, 8, 91.&nbsp;<a href=\"https:\/\/doi.org\/10.3390\/heritage8030091\">Paper<\/a><\/li>\n\n\n\n<li><strong>Conventional or Automated Photogrammetry for Cultural Heritage Documentation?<\/strong>&nbsp;Tapinaki, S., Pateraki, M., Skamantzari, M. &amp; Georgopoulos, A., 2023.&nbsp;<em>The Intl. Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.5194\/isprs-archives-XLVIII-M-2-2023-1535-2023\">Paper<\/a><\/li>\n\n\n\n<li><strong>Photogrammetric Documentation and Digital Representation of the Macedonian Palace in Vergina\u2013Aegae.<\/strong>Patias, P., Paliadeli, C., Georgoula, O., Pateraki, M., Stamnas, A. &amp; Kyriakou, N., 2007. In&nbsp;<em>XXI International CIPA Symposium<\/em>.&nbsp;<a href=\"https:\/\/mpateraki.org\/wp-content\/uploads\/2014\/11\/cipa_patias07.pdf\">Paper<\/a><\/li>\n\n\n\n<li><strong>From Point Samples to Surfaces\u2014On Meshing and Alternatives.<\/strong>&nbsp;Boehm, J. &amp; Pateraki, M., 2006. In&nbsp;<em>ISPRS Commission V Symposium: Image Engineering and Vision Metrology<\/em>.&nbsp;<a href=\"http:\/\/www.isprs.org\/proceedings\/XXXVI\/part5\/paper\/BOEHM_640.pdf\">Paper<\/a><\/li>\n\n\n\n<li><strong>Adaptive Multi-Image Matching for DSM Generation from Airborne Linear Array CCD Data.<\/strong>&nbsp;Pateraki, M., 2005. Doctoral dissertation, ETH Z\u00fcrich, Diss. ETH No. 15915.&nbsp;<a href=\"https:\/\/doi.org\/10.3929\/ethz-a-005011104\">Publication<\/a><\/li>\n\n\n\n<li><strong>Digital Surface Modelling by Airborne Laser Scanning and Digital Photogrammetry for Glacier Monitoring.<\/strong>Baltsavias, E. P., Favey, E., Bauder, A., Boesch, H. &amp; Pateraki, M., 2001.&nbsp;<em>The Photogrammetric Record<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1111\/0031-868X.00182\">Paper<\/a><\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Extended Reality and Immersive Environments<\/h2>\n\n\n\n<p>This research explores how immersive technologies, interactive digital environments and distributed computing infrastructures can support collaborative, educational and training applications. It includes extended-reality authoring and deployment, medical training, cultural-heritage experiences and edge\u2013cloud support for computationally demanding immersive environments.<\/p>\n\n\n\n<p>Selected publications:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Edge-driven docker registry: facilitating XR application deployment.<\/strong>&nbsp;Makris, A., Psomakelis, E., Korontanis, I., Theodoropoulos, T., Kontopoulos, I., Pateraki, M., Diou, C. &amp; Tserpes, K., 2024.&nbsp;<em>Computing<\/em>, 106, 3479\u20133501.&nbsp;<a href=\"https:\/\/doi.org\/10.1007\/s00607-024-01310-0\">Paper<\/a><\/li>\n\n\n\n<li><strong>MAGES 4.0: Accelerating the World\u2019s Transition to VR Training and Democratizing the Authoring of the Medical Metaverse.<\/strong>&nbsp;Zikas, P. et al., 2023.&nbsp;<em>IEEE Computer Graphics and Applications<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1109\/MCG.2023.3242686\">Paper<\/a><\/li>\n\n\n\n<li><strong>XR-RF Imaging Enabled by Software-Defined Metasurfaces and Machine Learning: Foundational Vision, Technologies and Challenges.<\/strong>&nbsp;Liaskos, C. et al., 2022.&nbsp;<em>IEEE Access<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1109\/ACCESS.2022.3219871\">Paper<\/a><\/li>\n\n\n\n<li><strong>Cloud for Holography and Augmented Reality.<\/strong>&nbsp;Makris, A. et al., 2021. In&nbsp;<em>IEEE International Conference on Cloud Networking<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1109\/CloudNet53349.2021.9657125\">Paper<\/a><\/li>\n\n\n\n<li><strong>Mixed Reality Gamified Presence and Storytelling for Virtual Museums.<\/strong>&nbsp;Papagiannakis, G. et al., 2018. In&nbsp;<em>Encyclopedia of Computer Graphics and Games<\/em>.&nbsp;<a href=\"https:\/\/doi.org\/10.1007\/978-3-319-08234-9_249-1\">Paper<\/a><\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><\/h2>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Datasets &amp; Benchmarking IndustryShapes Dataset (ICRA 2026) IndustryShapes is a benchmark for instance-level and novel-object 6D pose estimation in realistic industrial environments. It includes challenging textureless, reflective and geometrically complex objects captured under clutter, occlusion and varying viewpoints. Its extended set provides RGB-D onboarding sequences designed to support the evaluation of model-free methods. Project page [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-15","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/pages\/15","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mpateraki.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15"}],"version-history":[{"count":79,"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/pages\/15\/revisions"}],"predecessor-version":[{"id":851,"href":"https:\/\/mpateraki.org\/index.php?rest_route=\/wp\/v2\/pages\/15\/revisions\/851"}],"wp:attachment":[{"href":"https:\/\/mpateraki.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}