{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T12:09:14Z","timestamp":1758629354291,"version":"3.41.2"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:p>Object pose estimation is essential for computer vision applications such as quality inspection, robotic bin picking, and warehouse logistics. However, this task often requires expensive equipment such as 3D cameras or Lidar sensors, as well as significant computational resources. Many state-of-the-art methods for 6D pose estimation depend on deep neural networks, which are computationally demanding and require GPUs for real-time performance. Moreover, they usually involve the collection and labeling of large training datasets, which is costly and time-consuming. In this study, we propose a template-based matching algorithm that utilizes a novel perceptual hashing method for binary images, enabling fast and robust pose estimation. This approach allows the automatic preselection of a subset of templates, significantly reducing inference time while maintaining similar accuracy. Our solution runs efficiently on multiple devices without GPU support, offering reduced runtime and high accuracy on cost-effective hardware. We benchmarked our proposed approach on a body-in-white automotive part and a widely used publicly available dataset. Our set of experiments on a synthetically generated dataset reveals a trade-off between accuracy and computation time superior to a previous work on the same automotive-production use case. Additionally, our algorithm efficiently utilizes all CPU cores and includes adjustable parameters for balancing computation time and accuracy, making it suitable for a wide range of applications where hardware cost and power efficiency are critical. For instance, with a rotation step of 10\u00b0 in the template database, we achieve an average rotation error of <jats:inline-formula><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"m1\"><mml:mrow><mml:mn>10<\/mml:mn><mml:mo>\u00b0<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:inline-formula>, matching the template quantization level, and an average translation error of 14% of the object\u2019s size, with an average processing time of <jats:inline-formula><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"m3\"><mml:mrow><mml:mn>0.3<\/mml:mn><mml:mi>s<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:inline-formula> per image on a small form-factor NVIDIA AGX Orin device. We also evaluate robustness under partial occlusions (up to 10% occlusion) and noisy inputs (signal-to-noise ratios [SNRs] up to 10 dB), with only minor losses in accuracy. Additionally, we compare our method to state-of-the-art deep learning models on a public dataset. Although our algorithm does not outperform them in absolute accuracy, it provides a more favorable trade-off between accuracy and processing time, which is especially relevant to applications using resource-constrained devices.<\/jats:p>","DOI":"10.3389\/frobt.2024.1424036","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T06:24:05Z","timestamp":1736317445000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A fast monocular 6D pose estimation method for textureless objects based on perceptual hashing and template matching"],"prefix":"10.3389","volume":"11","author":[{"given":"Jose Moises","family":"Araya-Martinez","sequence":"first","affiliation":[]},{"given":"Vinicius Soares","family":"Matthiesen","sequence":"additional","affiliation":[]},{"given":"Simon","family":"B\u00f8gh","sequence":"additional","affiliation":[]},{"given":"Jens","family":"Lambrecht","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Pimentel de Figueiredo","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,1,8]]},"reference":[{"key":"B1","article-title":"Near-linear time algorithm for the chamfer distance","volume":"36","author":"Bakshi","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"A tutorial on SE(3) transformation parameterizations and on-manifold optimization","year":"2022","author":"Blanco-Claraco","key":"B2"},{"key":"B3","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1007\/978-3-319-10605-2_35","article-title":"Learning 6d object pose estimation using 3d object coordinates","volume-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, september 6-12, 2014, proceedings, Part II 13","author":"Brachmann","year":"2014"},{"key":"B4","doi-asserted-by":"crossref","first-page":"4048","DOI":"10.1109\/ROBOT.2010.5509171","article-title":"Real-time 3d model-based tracking using edge and keypoint features for robotic manipulation","volume-title":"2010 IEEE international conference on robotics and automation","author":"Choi","year":"2010"},{"key":"B5","doi-asserted-by":"crossref","first-page":"3877","DOI":"10.1109\/IROS.2012.6386065","article-title":"3d textureless object detection and tracking: an edge-based approach","volume-title":"2012 IEEE\/RSJ international conference on intelligent robots and systems","author":"Choi","year":"2012"},{"key":"B6","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.neucom.2014.07.070","article-title":"Efficient pose estimation of rotationally symmetric objects","volume":"150","author":"de Figueiredo","year":"2015","journal-title":"Neurocomputing"},{"key":"B7","doi-asserted-by":"publisher","first-page":"4901","DOI":"10.21105\/joss.04901","article-title":"Blenderproc2: a procedural pipeline for photorealistic rendering","volume":"8","author":"Denninger","year":"","journal-title":"J. Open Source Softw."},{"key":"B8","doi-asserted-by":"publisher","first-page":"4901","DOI":"10.21105\/joss.04901","article-title":"Blenderproc2: a procedural pipeline for photorealistic rendering","volume":"8","author":"Denninger","year":"","journal-title":"J. Open Source Softw."},{"key":"B9","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1109\/CVPR.2010.5540108","article-title":"Model globally, match locally: efficient and robust 3d object recognition","volume-title":"2010 IEEE computer society conference on computer vision and pattern recognition","author":"Drost","year":"2010"},{"key":"B10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ETFA54631.2023.10275651","article-title":"A hybrid approach for accurate 6d pose estimation of textureless objects from monocular images","volume-title":"2023 IEEE 28th international conference on emerging technologies and factory automation (ETFA)","author":"Druskinis","year":"2023"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1007\/s10462-020-09888-5","article-title":"Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review","volume":"54","author":"Du","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.54501\/jots.v1i1.24","article-title":"An overview of perceptual hashing","volume":"1","author":"Farid","year":"2021","journal-title":"J. Online Trust Saf."},{"key":"B13","doi-asserted-by":"publisher","first-page":"4617","DOI":"10.1007\/s11042-016-3723-5","article-title":"Real-time visual tracking based on improved perceptual hashing","volume":"76","author":"Fei","year":"2017","journal-title":"Multimedia Tools Appl."},{"key":"B14","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"","journal-title":"Commun. ACM"},{"key":"B15","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","article-title":"Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography","volume":"24","author":"Fischler","year":"","journal-title":"Commun. ACM"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.3390\/s24041076","article-title":"A survey of 6dof object pose estimation methods for different application scenarios","volume":"24","author":"Guan","year":"2024","journal-title":"Sensors"},{"volume-title":"Coding and information theory","year":"1986","author":"Hamming","key":"B17"},{"article-title":"Multiple view geometry in computer vision","year":"2006","author":"Harltey","key":"B18"},{"key":"B19","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","article-title":"Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes","volume-title":"Computer vision\u2013ACCV 2012: 11th asian conference on computer vision, daejeon, korea, november 5-9, 2012, revised selected papers, Part I 11","author":"Hinterstoisser","year":"2013"},{"key":"B20","first-page":"606","article-title":"On evaluation of 6d object pose estimation","volume-title":"European conference on computer vision","author":"Hodan","year":"2016"},{"key":"B21","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.procs.2018.05.069","article-title":"Conceptual understanding of convolutional neural network-a deep learning approach","volume":"132","author":"Indolia","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"B22","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1007\/978-3-030-58520-4_34","article-title":"Cosypose: consistent multi-view multi-object 6d pose estimation","volume-title":"Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, august 23\u201328, 2020, proceedings, Part XVII 16","author":"Labb\u00e9","year":"2020"},{"article-title":"Megapose: 6d pose estimation of novel objects via render compare","year":"2022","author":"Labb\u00e9","key":"B23"},{"key":"B24","doi-asserted-by":"publisher","first-page":"24605","DOI":"10.1007\/s11042-022-14213-z","article-title":"6d object position estimation from 2d images: a literature review","volume":"82","author":"Marullo","year":"2022","journal-title":"Multimedia Tools Appl."},{"key":"B25","first-page":"13","article-title":"New iterative geometric methods for robust perceptual image hashing","volume-title":"ACM workshop on digital rights management","author":"M\u0131h\u00e7ak","year":"2001"},{"key":"B26","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/978-3-030-17795-9_10","article-title":"Deep learning vs. traditional computer vision","volume-title":"Advances in computer vision: proceedings of the 2019 computer vision conference (CVC)","author":"O\u2019Mahony","year":"2020"},{"key":"B27","doi-asserted-by":"crossref","first-page":"7667","DOI":"10.1109\/ICCV.2019.00776","article-title":"Pix2pose: pixel-wise coordinate regression of objects for 6d pose estimation","volume-title":"2019 IEEE\/CVF international conference on computer vision (ICCV)","author":"Park","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","first-page":"103898","DOI":"10.1016\/j.imavis.2020.103898","article-title":"A review on object pose recovery: from 3d bounding box detectors to full 6d pose estimators","volume":"96","author":"Sahin","year":"2020","journal-title":"Image Vis. Comput."},{"key":"B29","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/s11263-019-01243-8","article-title":"Augmented autoencoders: implicit 3d orientation learning for 6d object detection","volume":"128","author":"Sundermeyer","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2805","DOI":"10.1109\/TRO.2023.3271568","article-title":"Certifiable object pose estimation: foundations, learning models, and self-training","volume":"39","author":"Talak","year":"2023","journal-title":"IEEE Trans. Robotics"},{"volume-title":"Real-time object pose estimation with pose interpreter networks","year":"2022","author":"Wu","key":"B31"},{"key":"B32","doi-asserted-by":"crossref","first-page":"2905","DOI":"10.1109\/ICRA48891.2023.10160529","article-title":"6d pose estimation for textureless objects on rgb frames using multi-view optimization","volume-title":"2023 IEEE international conference on robotics and automation (ICRA)","author":"Yang","year":"2023"},{"key":"B33","article-title":"Dpod: dense 6d pose object detector in rgb images","author":"Zakharov","year":"2019","journal-title":"arXiv Prepr. arXiv:1902"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1109\/TMM.2021.3070138","article-title":"Deep-irtarget: an automatic target detector in infrared imagery using dual-domain feature extraction and allocation","volume":"24","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Multimedia"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/tnnls.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. neural Netw. Learn. Syst."},{"key":"B36","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1016\/1049-9652(91)90031-E","article-title":"Generation of noise in binary images","volume":"53","author":"Zhou","year":"1991","journal-title":"CVGIP Graph. Models Image Process."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2024.1424036\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T06:24:14Z","timestamp":1736317454000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2024.1424036\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,8]]},"references-count":36,"alternative-id":["10.3389\/frobt.2024.1424036"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2024.1424036","relation":{},"ISSN":["2296-9144"],"issn-type":[{"type":"electronic","value":"2296-9144"}],"subject":[],"published":{"date-parts":[[2025,1,8]]},"article-number":"1424036"}}