{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T16:04:04Z","timestamp":1766678644966,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17524-x","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T08:02:22Z","timestamp":1699344142000},"page":"52973-52987","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Context-aware 6D pose estimation of known objects using RGB-D data"],"prefix":"10.1007","volume":"83","author":[{"given":"Ankit","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priya","family":"Shukla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8071-3585","authenticated-orcid":false,"given":"Vandana","family":"Kushwaha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gora Chand","family":"Nandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"17524_CR1","unstructured":"Tremblay J, To T, Sundaralingam B, Xiang Y, Fox D, Birchfield S (2018) Deep object pose estimation for semantic robotic grasping of household objects. arXiv:1809.10790"},{"key":"17524_CR2","doi-asserted-by":"publisher","unstructured":"Zhu M, Derpanis KG, Yang Y, Brahmbhatt S, Zhang M, Phillips C, Lecce M, Daniilidis K (2014) Single image 3d object detection and pose estimation for grasping, 3936\u20133943. https:\/\/doi.org\/10.1109\/ICRA.2014.6907430","DOI":"10.1109\/ICRA.2014.6907430"},{"key":"17524_CR3","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"17524_CR4","doi-asserted-by":"crossref","unstructured":"Xu D, Anguelov D, Jain A (2018) Pointfusion: deep sensor fusion for 3d bounding box estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0244\u2013253","DOI":"10.1109\/CVPR.2018.00033"},{"issue":"2","key":"17524_CR5","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/34.121791","volume":"14","author":"PJ Besl","year":"1992","unstructured":"Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239\u2013256. https:\/\/doi.org\/10.1109\/34.121791","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"17524_CR6","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ (2018) Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0918\u2013927","DOI":"10.1109\/CVPR.2018.00102"},{"key":"17524_CR7","doi-asserted-by":"crossref","unstructured":"Hinterstoisser S, Lepetit V, Ilic S, Holzer S, Bradski G, Konolige K, Navab N (2013) Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Lee KM, Matsushita Y, Rehg JM, Hu Z (eds) Computer vision - ACCV 2012. Springer, Berlin, Heidelberg, pp 548\u2013562","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"17524_CR8","doi-asserted-by":"crossref","unstructured":"Kehl W, Milletari F, Tombari F, Ilic S, Navab N (2016) Deep learning of local rgb-d patches for 3d object detection and 6d pose estimation. In: European conference on computer vision, pp\u00a0205\u2013220","DOI":"10.1007\/978-3-319-46487-9_13"},{"key":"17524_CR9","doi-asserted-by":"publisher","unstructured":"Rios-Cabrera R, Tuytelaars T (2013) Discriminatively trained templates for 3d object detection: a real time scalable approach. In: Proceedings of the 2013 IEEE international conference on computer vision. ICCV \u201913, IEEE Computer Society, USA pp\u00a02048\u20132055. https:\/\/doi.org\/10.1109\/ICCV.2013.256","DOI":"10.1109\/ICCV.2013.256"},{"key":"17524_CR10","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1007\/978-3-319-10599-4_30","volume-title":"Computer vision - ECCV 2014","author":"A Tejani","year":"2014","unstructured":"Tejani A, Tang D, Kouskouridas R, Kim T-K (2014) Latent-class hough forests for 3d object detection and pose estimation. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision - ECCV 2014. Springer, Cham, pp 462\u2013477"},{"key":"17524_CR11","doi-asserted-by":"publisher","unstructured":"Wohlhart P, Lepetit V (2015) Learning descriptors for object recognition and 3d pose estimation. 2015 IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2015.7298930","DOI":"10.1109\/cvpr.2015.7298930"},{"key":"17524_CR12","doi-asserted-by":"crossref","unstructured":"Xiang Y, Schmidt T, Narayanan V, Fox D (2017) Posecnn: a convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv:1711.00199","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"17524_CR13","doi-asserted-by":"crossref","unstructured":"Li C, Bai J, Hager GD (2018) A unified framework for multi-view multi-class object pose estimation. In: Proceedings of the European conference on computer vision (ECCV), pp\u00a0254\u2013269","DOI":"10.1007\/978-3-030-01270-0_16"},{"key":"17524_CR14","doi-asserted-by":"crossref","unstructured":"Wang C, Xu D, Zhu Y, Mart\u00edn-Mart\u00edn R, Lu C, Fei-Fei L, Savarese S (2019) Densefusion: 6d object pose estimation by iterative dense fusion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp\u00a03343\u20133352","DOI":"10.1109\/CVPR.2019.00346"},{"key":"17524_CR15","doi-asserted-by":"publisher","unstructured":"Hinterstoisser S, Holzer S, Cagniart C, Ilic S, Konolige K, Navab N, Lepetit V (2011) Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: 2011 international conference on computer vision, pp\u00a0858\u2013865. https:\/\/doi.org\/10.1109\/ICCV.2011.6126326","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"17524_CR16","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s11263-005-3964-7","volume":"67","author":"V Ferrari","year":"2006","unstructured":"Ferrari V, Tuytelaars T, Van Gool L (2006) Simultaneous object recognition and segmentation from single or multiple model views. Int J Comput Vis 67:159\u2013188. https:\/\/doi.org\/10.1007\/s11263-005-3964-7","journal-title":"Int J Comput Vis"},{"key":"17524_CR17","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s11263-005-3674-1","volume":"66","author":"F Rothganger","year":"2006","unstructured":"Rothganger F, Lazebnik S, Schmid C, Ponce J (2006) 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int J Comput Vis 66:231\u2013259. https:\/\/doi.org\/10.1007\/s11263-005-3674-1","journal-title":"Int J Comput Vis"},{"key":"17524_CR18","doi-asserted-by":"crossref","unstructured":"Pavlakos G, Zhou X, Chan A, Derpanis KG, Daniilidis K (2017) 6-dof object pose from semantic keypoints. In: 2017 IEEE international conference on robotics and automation (ICRA), IEEE, pp\u00a02011\u20132018","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"17524_CR19","unstructured":"Suwajanakorn S, Snavely N, Tompson J, Norouzi M (2018) Discovery of latent 3d keypoints via end-to-end geometric reasoning. In: Proceedings of the 32nd international conference on neural information processing systems NIPS\u201918, Curran Associates Inc. Red Hook, NY, USA, pp\u00a02063\u20132074"},{"key":"17524_CR20","doi-asserted-by":"crossref","unstructured":"Tekin B, Sinha SN, Fua P (2018) Real-time seamless single shot 6d object pose prediction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0292\u2013301","DOI":"10.1109\/CVPR.2018.00038"},{"issue":"6","key":"17524_CR21","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381\u2013395","journal-title":"Commun ACM"},{"key":"17524_CR22","doi-asserted-by":"publisher","unstructured":"Schwarz M, Schulz H, Behnke S (2015) Rgb-d object recognition and pose estimation based on pre-trained convolutional neural network features, 2015. https:\/\/doi.org\/10.1109\/ICRA.2015.7139363","DOI":"10.1109\/ICRA.2015.7139363"},{"key":"17524_CR23","doi-asserted-by":"publisher","unstructured":"Xiang Y, Choi W, Lin Y, Savarese S (2015) Data-driven 3d voxel patterns for object category recognition. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp\u00a01903\u20131911. https:\/\/doi.org\/10.1109\/CVPR.2015.7298800","DOI":"10.1109\/CVPR.2015.7298800"},{"key":"17524_CR24","doi-asserted-by":"crossref","unstructured":"Xiang Y, Choi W, Lin Y, Savarese S (2017) Subcategory-aware convolutional neural networks for object proposals and detection. In: 2017 IEEE winter conference on applications of computer vision (WACV), IEEE, pp\u00a0924\u2013933","DOI":"10.1109\/WACV.2017.108"},{"key":"17524_CR25","doi-asserted-by":"crossref","unstructured":"Mousavian A, Anguelov D, Flynn J, Kosecka J (2017) 3d bounding box estimation using deep learning and geometry. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a07074\u20137082","DOI":"10.1109\/CVPR.2017.597"},{"key":"17524_CR26","doi-asserted-by":"crossref","unstructured":"Sundermeyer M, Marton Z-C, Durner M, Brucker M, Triebel R (2018) Implicit 3d orientation learning for 6d object detection from rgb images. In: Proceedings of the European conference on computer vision (ECCV), pp\u00a0699\u2013715","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"17524_CR27","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1007\/978-3-319-10599-4_41","volume-title":"Computer vision - ECCV 2014","author":"S Song","year":"2014","unstructured":"Song S, Xiao J (2014) Sliding shapes for 3d object detection in depth images. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision - ECCV 2014. Springer, Cham, pp 634\u2013651"},{"key":"17524_CR28","doi-asserted-by":"publisher","unstructured":"Song S, Xiao J (2016) Deep sliding shapes for amodal 3d object detection in rgb-d images. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp\u00a0808\u2013816. https:\/\/doi.org\/10.1109\/CVPR.2016.94","DOI":"10.1109\/CVPR.2016.94"},{"key":"17524_CR29","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a04490\u20134499","DOI":"10.1109\/CVPR.2018.00472"},{"key":"17524_CR30","unstructured":"Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp\u00a0652\u2013660"},{"key":"17524_CR31","doi-asserted-by":"publisher","unstructured":"Aubry M, Maturana D, Efros AA, Russell BC, Sivic J (2014) Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models. In: 2014 IEEE Conference on computer vision and pattern recognition, pp\u00a03762\u20133769. https:\/\/doi.org\/10.1109\/CVPR.2014.487","DOI":"10.1109\/CVPR.2014.487"},{"key":"17524_CR32","doi-asserted-by":"crossref","unstructured":"Li Y, Wang G, Ji X, Xiang Y, Fox D (2018) Deepim: deep iterative matching for 6d pose estimation. In: Proceedings of the European conference on computer vision (ECCV) pp\u00a0683\u2013698","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"17524_CR33","unstructured":"Shukla P, Kushwaha V, Nandi G.C (2023) Vision-based intelligent robot grasping using sparse neural network. arXiv:2308.11590"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17524-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17524-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17524-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T07:21:48Z","timestamp":1715757708000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17524-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":33,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17524"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17524-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,11,7]]},"assertion":[{"value":"9 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}