mycoreobjectrosdok_document_0000026712rosdok_document_0000026712rosdokdocumentrosdok_derivate_0000229110rosdok_derivate_00002291162026-08-27T14:56:27.967Z2026-01-16T07:26:44.556ZeditorAMeditorAMpublished2rosdok_derivate_0000229110rosdok_derivate_0000229116truetruederivate_types:documentationDokumentationdocumentationwf_edit_data wf_register_dataderivate_types:dataDatendatawf_edit_data wf_register_datastate:publishedstate:publishedveröffentlichtpublishedrosdok_id000050501982579714Oau2026-08-272026-08-27T10:18:04ZrdaConverted from PICA to MODS using Pica2MODS XSLT Transformer 2.14-SNAPSHOT [SCM: "" "" ""] with mode 'DEFAULT'.DatenpublikationForschungsdatenSynthetic MBES Dataset for Underwater 3D Object Detection[research data]This dataset contains 100 synthetically generated multi-beam echosounder (MBES) 3D point clouds for the development and evaluation of underwater 3D object detection methods. The simulated environments were inspired by the artificial reef at the Digital Ocean Lab (DOL) near Nienhagen, Germany, and consist of procedurally generated seabeds populated with four types of artificial reef structures: small tetrapods, large tetrapods, reef cones, and concrete rings. The dataset contains a total of 5,491 annotated object instances. Each point cloud is accompanied by ground-truth 3D bounding-box annotations specifying the object class, dimensions, position, and orientation. The dataset was generated using a physics-based simulation pipeline and is intended to support research on 3D object detection from sonar point clouds, particularly in scenarios where annotated real-world sonar data are scarce.Muhammad SalmanShaukatVerfasserInaut0000-0002-3436-4879University of Rostock, Institute of Computer Sciencehttps://purl.uni-rostock.de/rosdok/id00005050urn:nbn:de:gbv:28-rosdok_id00005050-310.18453/rosdok_id00005050004 InformatikFakultät für Informatik und ElektrotechnikCC BY 4.0Nutzungsrechte erteiltLizenz Metadaten: CC0frei zugänglich (Open Access)en2026University of RostockRostockmonographic20262025University Library of RostockRostock2025Universitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005050This research was supported by the BMBF, OTC-Digital Twin & Analytics (OTC-DaTA) project (03ZU1107FB)[{"name":"Shaukat, Muhammad Salman","affil":"University of Rostock, Institute of Computer Science","orcid":"0000-0002-3436-4879"}]M. Salman ShaukatM. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.10.1109/JOE.2026.3675841Forschungsdaten zuShaukat, Muhammad SalmanUniversity of Rostock, Institute of Computer Science0000-0002-3436-4879doctype:epubdoctype:epubDokumenttypDocument typedoctype:datadoctype:dataDatenpublikationdata publicationdiniPublType:ResearchData diniPublType2022:ResearchDatainfo:eu-repo/semantics/otherdocumentnatureOfContent:ppn_857755366natureOfContent:ppn_857755366ForschungsdatendiniPublType2022:ResearchDatadiniPublType2022:ResearchDataForschungsdatenResearch dataKDSFSDNB:004SDNB:004004 Informatik004 Data processing Computer sciencesinstitution:unirostockinstitution:unirostockUniversität RostockUniversity of RostockUniversität RostockUniversität RostockUni.Rostockhttp://d-nb.info/gnd/38329-6institution:unirostock.iefinstitution:unirostock.iefFakultät für Informatik und ElektrotechnikFaculty of Computer Science and Electrical EngineeringUniversität Rostock. Fakultät für Informatik und ElektrotechnikFakultät für Informatik<br />und ElektrotechnikUni.Rostock.Fakultaet.IEFhttp://d-nb.info/gnd/10085032-7licenseinfo:worklicenseinfo:workWerkworklicenseinfo:work.cclicenselicenseinfo:work.cclicenseCC-LizenzCC-licenselicenseinfo:work.cclicense.cc-bylicenseinfo:work.cclicense.cc-byCC BYCC BYlicenseinfo:work.cclicense.cc-by.v40licenseinfo:work.cclicense.cc-by.v40CC BY 4.0CC BY 4.0/creativecommons/l/by/4.0/88x31.png[DE-28]Namensnennung 4.0 International$cCC BY 4.0$gCreative Commons$uhttps://creativecommons.org/licenses/by/4.0/https://creativecommons.org/licenses/by/4.0/https://creativecommons.org/licenses/by/4.0/licenseinfo:depositlicenseinfo:depositVeröffentlichungsgenehmigungpermission to storelicenseinfo:deposit.rightsgrantedlicenseinfo:deposit.rightsgrantedNutzungsrechte erteiltrights grantedlicenseinfo:metadatalicenseinfo:metadataLizenzen für Metadatenlicenseinfo:metadata.cc0licenseinfo:metadata.cc0Lizenz Metadaten: CC0license metadata: CC0/creativecommons/p/zero/1.0/88x31.pnghttps://creativecommons.org/publicdomain/zero/1.0/accesscondition:openaccessaccesscondition:openaccessfrei zugänglich (Open Access)open accesshttp://purl.org/coar/access_right/c_abf2OAfreeinfo:eu-repo/semantics/openAccess[DE-28]Open Access$gControlled Vocabulary for Access Rights$uhttp://purl.org/coar/access_right/c_abf2rfc5646:enrfc5646:enEnglischEnglishengengSynthetic MBES Dataset for Underwater 3D Object Detection[research data]Synthetic MBES Dataset for Underwater 3D Object Detection[research data]orcid:0000-0002-3436-4879orcid:0000-0002-3436-4879rosdok_document_0000026712-d3955682e65orcid:0000-0002-3436-4879Muhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatRostockUniversity of Rostockdatahttps://purl.uni-rostock.de/rosdok/id00005050urn:nbn:de:gbv:28-rosdok_id00005050-310.18453/rosdok_id00005050This dataset contains 100 synthetically generated multi-beam echosounder (MBES) 3D point clouds for the development and evaluation of underwater 3D object detection methods. The simulated environments were inspired by the artificial reef at the Digital Ocean Lab (DOL) near Nienhagen, Germany, and consist of procedurally generated seabeds populated with four types of artificial reef structures: small tetrapods, large tetrapods, reef cones, and concrete rings. The dataset contains a total of 5,491 annotated object instances. Each point cloud is accompanied by ground-truth 3D bounding-box annotations specifying the object class, dimensions, position, and orientation. The dataset was generated using a physics-based simulation pipeline and is intended to support research on 3D object detection from sonar point clouds, particularly in scenarios where annotated real-world sonar data are scarce.20262026M. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.M. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.10.1109/JOE.2026.3675841Forschungsdaten zu10.1109/JOE.2026.3675841This research was supported by the BMBF, OTC-Digital Twin & Analytics (OTC-DaTA) project (03ZU1107FB)[{"name":"Shaukat, Muhammad Salman","affil":"University of Rostock, Institute of Computer Science","orcid":"0000-0002-3436-4879"}]M. Salman Shaukatdata1 Shaukat_2026_Dokumentation.pdf 56694 d29fbd676a6baf0428af816dbb0fdba6 2 Shaukat_2026_Daten.zip 847175064 b063587987bce225371a69bd340377db rosdok_id000050501982579714Oau2026-08-272026-08-27T10:18:04ZrdaConverted from PICA to MODS using Pica2MODS XSLT Transformer 2.14-SNAPSHOT [SCM: "" "" ""] with mode 'DEFAULT'.DatenpublikationForschungsdatenSynthetic MBES Dataset for Underwater 3D Object Detection[research data]This dataset contains 100 synthetically generated multi-beam echosounder (MBES) 3D point clouds for the development and evaluation of underwater 3D object detection methods. The simulated environments were inspired by the artificial reef at the Digital Ocean Lab (DOL) near Nienhagen, Germany, and consist of procedurally generated seabeds populated with four types of artificial reef structures: small tetrapods, large tetrapods, reef cones, and concrete rings. The dataset contains a total of 5,491 annotated object instances. Each point cloud is accompanied by ground-truth 3D bounding-box annotations specifying the object class, dimensions, position, and orientation. The dataset was generated using a physics-based simulation pipeline and is intended to support research on 3D object detection from sonar point clouds, particularly in scenarios where annotated real-world sonar data are scarce.Muhammad SalmanShaukatVerfasserInaut0000-0002-3436-4879University of Rostock, Institute of Computer Sciencehttps://purl.uni-rostock.de/rosdok/id00005050urn:nbn:de:gbv:28-rosdok_id00005050-310.18453/rosdok_id00005050004 InformatikFakultät für Informatik und ElektrotechnikCC BY 4.0Nutzungsrechte erteiltLizenz Metadaten: CC0frei zugänglich (Open Access)en2026University of RostockRostockmonographic20262025University Library of RostockRostock2025Universitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005050This research was supported by the BMBF, OTC-Digital Twin & Analytics (OTC-DaTA) project (03ZU1107FB)[{"name":"Shaukat, Muhammad Salman","affil":"University of Rostock, Institute of Computer Science","orcid":"0000-0002-3436-4879"}]M. Salman ShaukatM. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.10.1109/JOE.2026.3675841Forschungsdaten zu Shaukat, Muhammad Salman University of Rostock, Institute of Computer Science 0000-0002-3436-4879 2026-01-16T07:26:44.556Z 2026-08-27T14:56:27.967Z 2026-09-06T14:56:27.977Z editorAM {"identifier":"rosdok/id00005050","type":"local_id","additional":"","service":"MCRLocalID","created":"2026-01-16T07:26:44.862Z"} {"identifier":"https://purl.uni-rostock.de/rosdok/id00005050","type":"purl","additional":"","service":"RosDokPURL","created":"2026-01-16T07:26:44.946Z","registrationStarted":"2026-08-27T11:04:57.191Z"} {"identifier":"10.18453/rosdok_id00005050","type":"doi","additional":"","service":"RosDokDOI","created":"2026-01-16T07:26:44.964Z","registrationStarted":"2026-08-27T11:04:56.087Z","registered":"2026-08-27T11:18:02.199Z"} editorAMdocumentationdataSynthetic MBES Dataset for Underwater 3D Object Detection[research data]Synthetic MBES Dataset for Underwater 3D Object Detection[research data]orcid:0000-0002-3436-4879orcid:0000-0002-3436-4879rosdok_document_0000026712-d3955682e65orcid:0000-0002-3436-4879Muhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatMuhammad Salman ShaukatRostockUniversity of Rostockdatahttps://purl.uni-rostock.de/rosdok/id00005050urn:nbn:de:gbv:28-rosdok_id00005050-310.18453/rosdok_id00005050This dataset contains 100 synthetically generated multi-beam echosounder (MBES) 3D point clouds for the development and evaluation of underwater 3D object detection methods. The simulated environments were inspired by the artificial reef at the Digital Ocean Lab (DOL) near Nienhagen, Germany, and consist of procedurally generated seabeds populated with four types of artificial reef structures: small tetrapods, large tetrapods, reef cones, and concrete rings. The dataset contains a total of 5,491 annotated object instances. Each point cloud is accompanied by ground-truth 3D bounding-box annotations specifying the object class, dimensions, position, and orientation. The dataset was generated using a physics-based simulation pipeline and is intended to support research on 3D object detection from sonar point clouds, particularly in scenarios where annotated real-world sonar data are scarce.20262026M. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.M. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.10.1109/JOE.2026.3675841Forschungsdaten zu10.1109/JOE.2026.3675841This research was supported by the BMBF, OTC-Digital Twin & Analytics (OTC-DaTA) project (03ZU1107FB)[{"name":"Shaukat, Muhammad Salman","affil":"University of Rostock, Institute of Computer Science","orcid":"0000-0002-3436-4879"}]M. Salman Shaukat[xslt]Saxonrosdok_id00005050https://purl.uni-rostock.de/rosdok/id00005050198257971410.18453/rosdok_id00005050urn:nbn:de:gbv:28-rosdok_id00005050-3Muhammad Salman ShaukatShaukat Muhammad SalmanSynthetic MBES Dataset for Underwater 3D Object Detection : [research data]Datenpublikationdata publicationUniversity of Rostock, 2026This dataset contains 100 synthetically generated multi-beam echosounder (MBES) 3D point clouds for the development and evaluation of underwater 3D object detection methods. The simulated environments were inspired by the artificial reef at the Digital Ocean Lab (DOL) near Nienhagen, Germany, and…Muhammad Salman ShaukatSynthetic MBES Dataset for Underwater 3D Object Detection[research data]M. S. Shaukat, Y. Käckenmeister, S. Bader and T. Kirste, "Toward Training-Free Underwater 3-D Object Detection From Sonar Point Clouds: A Comparison of Traditional and Deep Learning Approaches," in IEEE Journal of Oceanic Engineering, vol. 51, no. 3, pp. 2284-2297, July 2026.Universitätsbibliothek Rostockhttps://purl.uni-rostock.de/rosdok/id00005050Muhammad SalmanShaukatVerfasserInaut0000-0002-3436-4879University of Rostock, Institute of Computer Science[purl]https://purl.uni-rostock.de/rosdok/id00005050[urn]urn:nbn:de:gbv:28-rosdok_id00005050-3[doi]10.18453/rosdok_id00005050open_access20262026epoch:21th_centuryrfc5646:endoctype:dataaccesscondition:openaccessSDNB:004institution:unirostock.iefstate:published