{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:40:58Z","timestamp":1742913658194,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031314063"},{"type":"electronic","value":"9783031314070"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-31407-0_53","type":"book-chapter","created":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T12:02:31Z","timestamp":1683374551000},"page":"707-719","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The UNICT-TEAM Vision Modules for\u00a0the\u00a0Mohamed Bin Zayed International Robotics Challenge 2020"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-2470","authenticated-orcid":false,"given":"Sebastiano","family":"Battiato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3948-217X","authenticated-orcid":false,"given":"Luciano","family":"Cantelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"D\u2019Urso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6034-0432","authenticated-orcid":false,"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8315-351X","authenticated-orcid":false,"given":"Luca","family":"Guarnera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-7207","authenticated-orcid":false,"given":"Dario Calogero","family":"Guastella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosario","family":"Leonardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessia Li","family":"Noce","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5027-9239","authenticated-orcid":false,"given":"Giovanni","family":"Muscato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Piazza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6368-1910","authenticated-orcid":false,"given":"Francesco","family":"Ragusa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Corrado","family":"Santoro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6424-6286","authenticated-orcid":false,"given":"Giuseppe","family":"Sutera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Zappal\u00e0","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,7]]},"reference":[{"key":"53_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-319-68560-1_12","volume-title":"Image Analysis and Processing","author":"S Battiato","year":"2017","unstructured":"Battiato, S., et al.: A system for autonomous landing of a UAV on\u00a0a moving vehicle. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10484, pp. 129\u2013139. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68560-1_12"},{"key":"53_CR2","unstructured":"blender online community: blender - a 3d modelling and rendering package. Blender foundation, blender institute, Amsterdam. https:\/\/www.blender.org"},{"key":"53_CR3","doi-asserted-by":"crossref","unstructured":"Cantelli, L., et al.: Autonomous landing of a UAV on a moving vehicle for the mbzirc. In: Human-Centric Robotics- Proceedings of the 20th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2017, pp. 197\u2013204 (2018)","DOI":"10.1142\/9789813231047_0026"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Choi, J., Chun, D., Kim, H., Lee, H.J.: Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00059"},{"key":"53_CR5","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1177\/0278364911401765","volume":"30","author":"A Collet","year":"2011","unstructured":"Collet, A., Martinez, M., Srinivasa, S.: The moped framework: object recognition and pose estimation for manipulation. I. J. Robot. Res. 30, 1284\u20131306 (2011)","journal-title":"I. J. Robot. Res."},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia. MM 2019, ACM, New York, NY, USA (2019)","DOI":"10.1145\/3343031.3350535"},{"key":"53_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"53_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"53_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arXiv preprint arXiv:1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"53_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. CoRR abs\/1406.4729 (2014)","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., et al.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: 2011 International Conference on Computer Vision, pp. 858\u2013865, November 2011","DOI":"10.1109\/ICCV.2011.6126326"},{"key":"53_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"53_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"53_CR14","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: Convolutional networks for real-time 6-dof camera relocalization. CoRR abs\/1505.07427 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"53_CR15","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: The European Conference on Computer Vision (ECCV), September 2018","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV 2019 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"53_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"12","key":"53_CR18","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1109\/TVCG.2015.2513408","volume":"22","author":"E Marchand","year":"2016","unstructured":"Marchand, E., Uchiyama, H., Spindler, F.: Pose estimation for augmented reality: a hands-on survey. IEEE Trans. Vis. Comput. Graph. 22(12), 2633\u20132651 (2016)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"53_CR19","doi-asserted-by":"crossref","unstructured":"Marder-Eppstein, E.: Project tango. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2016, Anaheim, CA, USA, 24\u201328 July 2016, Real-Time Live! p. 25 (2016)","DOI":"10.1145\/2933540.2933550"},{"key":"53_CR20","doi-asserted-by":"publisher","first-page":"22323","DOI":"10.1007\/s11042-019-08312-7","volume":"80","author":"A Ortis","year":"2020","unstructured":"Ortis, A., Farinella, G., Torrisi, G., Battiato, S.: Exploiting objective text description of images for visual sentiment analysis. Multimedia Tools Appl. 80, 22323\u201322346 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"53_CR21","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"53_CR22","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. arXiv preprint arXiv:1612.08242 (2016)","DOI":"10.1109\/CVPR.2017.690"},{"key":"53_CR23","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. CoRR abs\/1804.02767 (2018)"},{"key":"53_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"53_CR25","doi-asserted-by":"crossref","unstructured":"Rosano, M., Furnari, A., Farinella, G.M.: A comparison of visual navigation approaches based on localization and reinforcement learning in virtual and real environments. In: International Conference on Computer Vision Theory and Applications (VISAPP) (2020)","DOI":"10.5220\/0008950806280635"},{"key":"53_CR26","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: International Conference on Learning Representations (ICLR2014) (2014)"},{"issue":"3","key":"53_CR27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.21014\/acta_imeko.v10i3.1036","volume":"10","author":"G Sutera","year":"2021","unstructured":"Sutera, G., Guastella, D.C., Muscato, G.: A lightweight magnetic gripper for an aerial delivery vehicle: design and applications. ACTA IMEKO 10(3), 61\u201365 (2021)","journal-title":"ACTA IMEKO"},{"key":"53_CR28","doi-asserted-by":"crossref","unstructured":"Tan, Z., Nie, X., Qian, Q., Li, N., Li, H.: Learning to rank proposals for object detection. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00836"},{"key":"53_CR29","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. In: Conference on Robot Learning (CoRL) (2018)"},{"key":"53_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Densefusion: 6d object pose estimation by iterative dense fusion (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"53_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, L., Bertinetto, L., Hu, W., Torr, P.H.: Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00142"},{"key":"53_CR32","doi-asserted-by":"crossref","unstructured":"Wang, T., Anwer, R.M., Cholakkal, H., Khan, F.S., Pang, Y., Shao, L.: Learning rich features at high-speed for single-shot object detection. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00206"},{"key":"53_CR33","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"53_CR34","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00203"},{"key":"53_CR35","doi-asserted-by":"crossref","unstructured":"Zhu, R., et al.: Scratchdet: training single-shot object detectors from scratch. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2268\u20132277 (2019)","DOI":"10.1109\/CVPR.2019.00237"}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31407-0_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T12:09:58Z","timestamp":1683374998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31407-0_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314063","9783031314070"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31407-0_53","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"7 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nagpur","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/vnit.ac.in\/cvip2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"110","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}