{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:23Z","timestamp":1750309463671,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1145\/3702250.3702269","type":"proceedings-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T12:11:38Z","timestamp":1735647098000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Pose Estimation and Tracking of Autonomous Mobile Robots using Infrastructure Vision Sensors - An End-to-End Perception Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6111-0551","authenticated-orcid":false,"given":"Dharini","family":"Raghavan","sequence":"first","affiliation":[{"name":"Artpark IISc, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2979-8186","authenticated-orcid":false,"given":"Raghu","family":"Krishnapuram","sequence":"additional","affiliation":[{"name":"IISc Bangalore, Bengaluru, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5062-6174","authenticated-orcid":false,"given":"Bharadwaj","family":"Amrutur","sequence":"additional","affiliation":[{"name":"IISc Bangalore, Bengaluru, India"}]}],"member":"320","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Simone\u00a0Nardi Alessandro\u00a0Faralli Niko\u00a0Giovannini and Lucia Pallot-tino. 2016. Indoor Real-Time Localisation for Multiple Autonomous Vehicles Fusing Vision Odometry and IMU Data. In Modelling and Simulation for Autonomous Systems Springer Cham (Jan. 2016) 288\u2013-297\u00a0pages.","DOI":"10.1007\/978-3-319-47605-6_24"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.410"},{"key":"e_1_3_3_3_4_2","unstructured":"Shariq\u00a0Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. airXv (2023)."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"e_1_3_3_3_6_2","volume-title":"Australasian Conference on Robotics and Automation (ACRA)","author":"Chakravarty Punarjay","year":"2009","unstructured":"Punarjay Chakravarty and Ray Jarvis. 2009. External Cameras & A Mobile Robot: A Collaborative Surveillance System. In Australasian Conference on Robotics and Automation (ACRA). Sydney, Australia."},{"key":"e_1_3_3_3_7_2","unstructured":"Inc Charles River\u00a0Analytics. 2023. robot localization package. GitHub (2023)."},{"key":"e_1_3_3_3_8_2","unstructured":"Andrew\u00a0Rabinovich Daniel\u00a0DeTone Tomasz\u00a0Malisiewicz. 2018. Super- Point: Self-Supervised Interest Point Detection and Description. AirXv (2018)."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Kristof\u00a0Csorba David\u00a0Szaloki Sandor\u00a0Kolumban and Gabor Tevesz. 2015. Camera Placement Optimization in Object Localization Systems. Acta Cybernetica (2015) 211\u2013228.","DOI":"10.14232\/actacyb.22.1.2015.13"},{"key":"e_1_3_3_3_10_2","unstructured":"PuLP documentation team. 2009. Optimization with PuLP. https:\/\/coin-or.github.io\/pulp\/ (2009)."},{"key":"e_1_3_3_3_11_2","first-page":"5200","volume-title":"2021 IEEE International Conference on Robotics and Automation (ICRA)","author":"al. G.\u00a0Shi et","year":"2021","unstructured":"G.\u00a0Shi et al.2021. Fast Uncertainty Quantification for Deep Object Pose Estimation. In 2021 IEEE International Conference on Robotics and Automation (ICRA). China, 5200\u20135207. https:\/\/doi.org\/doi: 10.1109\/ICRA48506.2021.9561483"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Liu et al.2021. Robotic Communications for 5G and Beyond: Challenges and Research Opportunities. in IEEE Communica- tions Magazine 59 (2021) 92\u201398. 10.1109\/MCOM.111.2001118","DOI":"10.1109\/MCOM.111.2001118"},{"key":"e_1_3_3_3_13_2","volume-title":"In ICLR","author":"I. Sahoo R. Schwarting W. Alexander Amini S. K. Rus\u00a0D. Gilitschenski,","year":"2020","unstructured":"Sahoo R. Schwarting W. Alexander Amini S. K. Rus\u00a0D. Gilitschenski, I.2020. Deep orientation uncertainty learning based on a bingham loss. In In ICLR."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"&\u00a0Zisserman\u00a0A. Hartley R.2003. Multiple View Geometry in Computer Vision Chapter 4. Cambridge University Press (2003).","DOI":"10.1017\/CBO9780511811685"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Richard Hartley and Andrew Zisserman. 2003. Multiple View Geometry in Computer Vision. Cambridge University Press (2003).","DOI":"10.1017\/CBO9780511811685"},{"key":"e_1_3_3_3_16_2","first-page":"2082\u2013\u20132091","volume-title":"In ICCVW","author":"R.\u00a0L. Hagelskj\u00e6r F. Iversen T.\u00a0M. Haugaard,","year":"2023","unstructured":"Hagelskj\u00e6r F. Iversen T.\u00a0M. Haugaard, R.\u00a0L.2023. SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimation. In In ICCVW. 2082\u2013\u20132091."},{"key":"e_1_3_3_3_17_2","volume-title":"In Advances in Neural Information Processing Systems","author":"He Xingyi","year":"2022","unstructured":"Xingyi He, Jiaming Sun, Yuang Wang, Di Huang, Hujun Bao, and Xiaowei Zhou. 2022. Onepose++: Keypoint-free one-shot object pose estimation without CAD models. In In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_3_18_2","unstructured":"Hiwonder. [n. d.]. Hiwonder ArmPi Pro Raspberry Pi. https:\/\/www.hiwonder.com\/products\/armpi-pro?variant=40308380958807 ([n. d.])."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Gregory\u00a0Dudek Ioannis\u00a0Rekleitis David\u00a0Meger. 2006. Simultaneous planning localization and mapping in a camera sensor network. Robotics and Autonomous Systems 54 11 (Nov. 2006) 921\u2013932\u00a0pages. 10.1016\/j.robot.2006.05.009","DOI":"10.1016\/j.robot.2006.05.009"},{"key":"e_1_3_3_3_20_2","first-page":"pp. 844\u2013848","volume-title":"2009 IEEE International Conference on Robotics and Automation","author":"Garcia-Ramirez J.\u00a0Salas J. B. Hurtado-Ramos J.\u00a0J. Gonzalez-Barbosa, T.","year":"2009","unstructured":"J.\u00a0Salas J. B. Hurtado-Ramos J.\u00a0J. Gonzalez-Barbosa, T. Garcia-Ramirez and J. d. J.\u00a0Rico-Jimenez. 2009. Optimal camera place- ment for total coverage. In 2009 IEEE International Conference on Robotics and Automation (Kobe, Japan). pp. 844\u2013848."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"F.\u00a0Richter J.\u00a0Lu and M.\u00a0C. Yip. 2022. Pose Estimation for Robot Manipulators via Keypoint Optimization and Sim-to-Real Transfer. IEEE Robotics and Automation Letters 7 2 (April 2022) 4622\u20134629\u00a0pages.","DOI":"10.1109\/LRA.2022.3151981"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Young-Im\u00a0Cho Jae-Hong\u00a0Shim. 2015. A Mobile Robot Localization using External Surveillance Cameras at Indoor. Procedia Computer Science 56 1 (Jan. 2015) 502\u2013507. 10.1016\/j.procs.2015.07.242","DOI":"10.1016\/j.procs.2015.07.242"},{"key":"e_1_3_3_3_23_2","volume-title":"In CVPR","author":"Zehong\u00a0Shen Yuang Wang-Hujun\u00a0Bao Jiaming\u00a0Sun,","year":"2021","unstructured":"Yuang Wang-Hujun\u00a0Bao Jiaming\u00a0Sun, Zehong\u00a0Shen and Xiaowei Zhou. 2021. Loftr: Detector-free local feature matching with transformers. In In CVPR."},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arXiv:https:\/\/arXiv.org\/abs\/2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Mathieu Labbe and Francois Michaud. 2019. RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation. in Journal of Field Robotics (2019).","DOI":"10.1002\/rob.21831"},{"key":"e_1_3_3_3_26_2","unstructured":"Jiehong Lin Lihua Liu Dekun Lu and Kui Jia. 2023. SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15707 (2023)."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"e_1_3_3_3_28_2","first-page":"2784\u2013\u20132793","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hoda\u02c7\u00a0n Yann Labbe Gu Wang Eric Brachmann Bertram Drost Carsten\u00a0Rother Martin\u00a0Sundermeyer, Tom\u00b4 a\u02c7 s","year":"2023","unstructured":"Yann Labbe Gu Wang Eric Brachmann Bertram Drost Carsten\u00a0Rother Martin\u00a0Sundermeyer, Tom\u00b4 a\u02c7 s Hoda\u02c7\u00a0n and Ji\u02c7 r\u00b4 \u0131\u00a0Matas. 2023. Bop challenge 2022 on detection, segmentation and pose estimation of specific rigid objects. In In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2784\u2013\u20132793."},{"key":"e_1_3_3_3_29_2","unstructured":"Ati Motors. [n. d.]. Sherpa Lite by Ati Motors. https:\/\/atimotors.com\/ ([n. d.])."},{"key":"e_1_3_3_3_30_2","volume-title":"In NeurIPS","author":"Y. Fertig E. Ren J. Nado Z. Sculley D. Nowozin S. Dillon J. Lakshminarayanan B. Snoek\u00a0J. Ovadia,","year":"2019","unstructured":"Fertig E. Ren J. Nado Z. Sculley D. Nowozin S. Dillon J. Lakshminarayanan B. Snoek\u00a0J. Ovadia, Y.2019. Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift. In In NeurIPS."},{"key":"e_1_3_3_3_31_2","volume-title":"In ICCV","author":"Pierre\u00a0Gleize Weiyao\u00a0Wang","year":"2023","unstructured":"Weiyao\u00a0Wang Pierre\u00a0Gleize and Matt Feiszli. 2023. SiLK - Simple Learned Keypoints. In In ICCV."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610419.3610460"},{"key":"e_1_3_3_3_33_2","volume-title":"In NeurIPS","author":"Revaud Jerome","year":"2019","unstructured":"Jerome Revaud, Philippe Weinzaepfel, C\u00e9sar\u00a0Roberto de Souza, and Martin Humenberger. 2019. R2D2: Repeatable and Reliable Detector and Descriptor. In In NeurIPS."},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160892"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"e_1_3_3_3_36_2","volume-title":"IEEE International Confer- ence on Robotics and Automation (ICRA)","author":"Jonathan\u00a0Tremblay Thang To Jia Cheng Terry Mosier Oliver Kroemer Dieter\u00a0Fox Timothy E.\u00a0Lee,","year":"2020","unstructured":"Thang To Jia Cheng Terry Mosier Oliver Kroemer Dieter\u00a0Fox Timothy E.\u00a0Lee, Jonathan\u00a0Tremblay and Stan Birchfield. 2020. Camera-to-Robot Pose Estimation from a Single Image. In IEEE International Confer- ence on Robotics and Automation (ICRA). Paris, France."},{"key":"e_1_3_3_3_37_2","volume-title":"Advances in Neural Information Processing Systems","author":"Tyszkiewicz Micha\u0142","year":"2020","unstructured":"Micha\u0142 Tyszkiewicz, Pascal Fua, and Eduard Trulls. 2020. DISK: Learning local features with policy gradient. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_3_38_2","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Thibault\u00a0Groueix Mathieu\u00a0Salzmann Van Nguyen\u00a0Nguyen,","year":"2024","unstructured":"Mathieu\u00a0Salzmann Van Nguyen\u00a0Nguyen, Thibault\u00a0Groueix and Vincent Lepetit. 2024. Gigapose: Fast and robust novel object pose estimation via one correspondence. In In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_3_3_39_2","unstructured":"Botsync Volta. [n. d.]. A compact and powerful indoor mobile robot for ROS learning teaching and research. https:\/\/github.com\/botsync\/volta ([n. d.])."},{"key":"e_1_3_3_3_40_2","volume-title":"In Proceedings of the European Conference on Computer Vision","author":"Sagar\u00a0Vaze Ioannis\u00a0Havoutis Walter\u00a0Goodwin,","year":"2022","unstructured":"Ioannis\u00a0Havoutis Walter\u00a0Goodwin, Sagar\u00a0Vaze and Ingmar Posner. 2022. Zero-shot category-level object pose estimation. In In Proceedings of the European Conference on Computer Vision."},{"key":"e_1_3_3_3_41_2","unstructured":"J.-J.; Liu H.; Hu Y.H.; Jiang\u00a0H Watras A.J.;\u00a0Kim. 2018. Optimal Camera Pose and Placement Configuration for Maximum Field-of-View Video Stitching. Sensors (2018)."},{"key":"e_1_3_3_3_42_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yang Zongxin","year":"2022","unstructured":"Zongxin Yang and Yi Yang. 2022. Decoupling Features in Hierarchical Propagation for Video Object Segmentation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_3_43_2","volume-title":"In Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Lucas\u00a0Manuelli Arsalan Mousavian Stephen Tyree Stan Birchfield Jonathan Tremblay Justin Carpentier Mathieu Aubry Dieter\u00a0Fox Yann Labb\u00b4\u00a0e,","year":"2022","unstructured":"Arsalan Mousavian Stephen Tyree Stan Birchfield Jonathan Tremblay Justin Carpentier Mathieu Aubry Dieter\u00a0Fox Yann Labb\u00b4\u00a0e, Lucas\u00a0Manuelli and Josef Sivic. 2022. Megapose: 6d pose estimation of novel objects via render & compare. In In Proceedings of the 6th Conference on Robot Learning (CoRL)."},{"key":"e_1_3_3_3_44_2","volume-title":"In CVPR","author":"Yisheng He","year":"2022","unstructured":"He Yisheng, Wang Yao, Fan Haoqiang, Chen Qifeng, and Sun Jian. 2022. FS6D: Few-shot 6D pose estimation of novel objects. In In CVPR."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Xiaoming Zhao Xingming Wu Jinyu Miao Weihai Chen Peter C.\u00a0Y. Chen and Zhengguo Li. 2022. ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction. IEEE Transactions on Multimedia (2022).","DOI":"10.1109\/TMM.2022.3155927"}],"event":{"name":"ICVGIP 2024: Indian Conference on Computer Vision Graphics and Image Processing","acronym":"ICVGIP 2024","location":"Bengaluru Karnataka India"},"container-title":["Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702250.3702269","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3702250.3702269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:32Z","timestamp":1750295432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702250.3702269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":44,"alternative-id":["10.1145\/3702250.3702269","10.1145\/3702250"],"URL":"https:\/\/doi.org\/10.1145\/3702250.3702269","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2024-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}