{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T12:31:55Z","timestamp":1740141115738,"version":"3.37.3"},"reference-count":13,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Phys.: Conf. Ser."],"published-print":{"date-parts":[[2022,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Safe self-driving vehicles require precise 3D Object Identification. LiDAR sensors are key in accomplishing such a task, as LiDARs produce high-definition point clouds. Such point clouds are then processed by 3D Object Detection models to finally detect objects.<\/jats:p>\n               <jats:p>Most Object Detection models require massive amounts of data to be trained. Gathering and processing this data is an expensive and time-consuming task, which is why the information taken from each sample must be fully harnessed. Such can be done through Data Augmentation. Data Augmentation contributes significantly for improving performance, being at least as relevant as the advances in the Object Detection models themselves.<\/jats:p>\n               <jats:p>A few studies have been reported regarding the effectiveness of Data Augmentation. However, the role played by original and augmented samples has been neglected. This work reports the first-ever detailed quantification of the impact that the inclusion of original and augmented samples in a dataset has in 3D Object Detection in the context of autonomous driving. The obtained results show that although a good augmentation strategy is crucial to the model\u2019s performance, it is only as good as the quality of the original samples allows it to be.<\/jats:p>","DOI":"10.1088\/1742-6596\/2407\/1\/012044","type":"journal-article","created":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T18:36:44Z","timestamp":1671129404000},"page":"012044","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Data Augmentation in 3D Object Detection for self-driving vehicles: the role of original and augmented training samples"],"prefix":"10.1088","volume":"2407","author":[{"given":"X","family":"Santos","sequence":"first","affiliation":[]},{"given":"P","family":"Georgieva","sequence":"additional","affiliation":[]},{"given":"P","family":"Gir\u00e3o","sequence":"additional","affiliation":[]},{"given":"M","family":"Drummond","sequence":"additional","affiliation":[]}],"member":"266","reference":[{"key":"JPCS_2407_1_012044bib1","first-page":"852","article-title":"Review of LiDAR Sensor Data Acquisition and Compression for Automotive Applications","volume":"2","author":"Maksymova","year":"2018","journal-title":"Proceedings 2018"},{"key":"JPCS_2407_1_012044bib2","article-title":"Object identification for autonomous vehicles based on Machine Learning","author":"Guedes","year":"2020","journal-title":"Master\u2019s thesis, Universidade de Aveiro"},{"key":"JPCS_2407_1_012044bib3","first-page":"566","volume":"12372","author":"Zoph","year":"2019"},{"key":"JPCS_2407_1_012044bib4","first-page":"4490","article-title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","author":"Zhou","year":"2017","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"JPCS_2407_1_012044bib5","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"JPCS_2407_1_012044bib6","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"SECOND: Sparsely Embedded Convolutional Detection","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors"},{"key":"JPCS_2407_1_012044bib7","first-page":"12689","article-title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","volume":"2019","author":"Lang","year":"2018","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"article-title":"StarNet: Targeted Computation for Object Detection in Point Clouds","year":"2019","author":"Ngiam","key":"JPCS_2407_1_012044bib8"},{"article-title":"Quantifying Data Augmentation for LiDAR based 3D Object Detection","year":"2020","author":"Hahner","key":"JPCS_2407_1_012044bib9"},{"first-page":"3354","year":"2012","author":"Geiger","key":"JPCS_2407_1_012044bib10"},{"article-title":"OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Clouds","year":"2020","author":"","key":"JPCS_2407_1_012044bib11"},{"key":"JPCS_2407_1_012044bib12","doi-asserted-by":"crossref","DOI":"10.1177\/0278364913491297","article-title":"Vision meets Robotics: The KITTI Dataset","author":"Geiger","year":"2013"},{"key":"JPCS_2407_1_012044bib13","first-page":"10526","article-title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","author":"Shi","year":"2019","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"}],"container-title":["Journal of Physics: Conference Series"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2407\/1\/012044","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2407\/1\/012044\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2407\/1\/012044\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2407\/1\/012044\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T18:36:48Z","timestamp":1671129408000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1742-6596\/2407\/1\/012044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":13,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1742-6596\/2407\/1\/012044","relation":{},"ISSN":["1742-6588","1742-6596"],"issn-type":[{"type":"print","value":"1742-6588"},{"type":"electronic","value":"1742-6596"}],"subject":[],"published":{"date-parts":[[2022,12,1]]},"assertion":[{"value":"Data Augmentation in 3D Object Detection for self-driving vehicles: the role of original and augmented training samples","name":"article_title","label":"Article Title"},{"value":"Journal of Physics: Conference Series","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"Published under licence by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}