https://m2.mtmt.hu/ hun 2026-04-16 15:38 BookChapter 34742515 APPROVED true IEEE Control Systems Chapter; IEEE Hungary Section; IEEE Joint Chapter of IES and RAS; IEEE SMC Chapter Conference code: 197504 Export Date: 18 March 2024 Funding details: RRF-2.3.1-21-2022-00002 Funding details: European Commission, EC Funding text 1: ACKNOWLEDGMENT The research was supported by the European Union within the framework of the National Laboratory for Autonomous Systems. (RRF-2.3.1-21-2022-00002) 0 false 2025-03-11T19:23:19.158+0000 2024-03-18T08:56:03.943+0000 2024-03-18T07:57:34.324+0000 true 10072271 Andódy Katalin /api/admin/10072271 Admin Andódy Katalin (BME admin4) true 2024-03-18T08:56:03.967+0000 2024-03-18T08:56:03.967+0000 true false true 25 25 /api/publicationtype/25 PublicationType Könyvrészlet 2 true 25 BookChapter true 10000312 Conference paper true 25 25 /api/publicationtype/25 PublicationType Könyvrészlet 2 true 25 BookChapter /api/subtype/10000312 Konferenciaközlemény SubType Konferenciaközlemény (Könyvrészlet) 228 true 10000312 true 1 /api/category/1 Category Tudományos true 1 Cserni, Márton 17 22 17 6 2024 Vehicle orientation estimation is one of the hardest challenges in automotive perception. Point cloud and sensor fusion-based methods are effective, provided there are enough points associated with the target object. This can be challenging for even the most expensive LIDAR sensors over longer distances. In most cases, orientation can be inferred from the movement of an object, however there are edge cases where this does not work such as stationary vehicles, or vehicles that are spinning out of control. Additionally, there are cases, where movement can be predicted from the orientation, which is far more useful. This paper focuses on the development of an extremely light-weight image-based vehicle orientation detector. Previous methods using mono-cameras either jointly estimate orientation, size and position, making the networks large and slow, or are jointly trained with the 2d object detector, decreasing the usability of new object detectors. Our method uses the outputs of a 2D object detector to cut the patches containing objects out of images, and estimate the allocentric orientation of the object in each image patch. This can be transformed into world coordinates, in the case of known camera calibration parameters. This model was trained on a subset of the KITTI dataset and achieves a validation and test accuracy of over 70%. Different techniques for image resizing were evaluated to see whether viewpoint estimation is affected. The method was also tested in real-world conditions at the ZalaZONE proving ground, from a different camera perspective, and different camera parameters compared to the training set. © 2024 IEEE. 2024 true true true true true false NONE 2025-03-11 false 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 false false false false 2024-06-16T07:56:03.700+0000 Gépjárműtechnológia Tanszék (BME / KJK) 2 6 1 2 0 true 539 true 10002 English /api/language/10002 Angol Language Angol true 2 false true 10939 true 10017 /api/country/10017 Country Amerikai Egyesült Államok true 13 /api/city/10939 City Piscataway (NJ), Amerikai Egyesült Államok true 2054246 true 28712336 IDENTICAL /api/publicationidentifier/28712336 https://doi.org/10.1109/SAMI60510.2024 10.1109/SAMI60510.2024 PublicationIdentifier DOI: 10.1109/SAMI60510.2024 true 6 DOI https://doi.org/@@@ /api/publicationsource/6 DOI PlainSource DOI true true 10001 /api/publicationsourcetype/10001 PublicationSourceType DOI true true 6 true false true 25360919 /api/publicationidentifier/25360919 https://www.worldcat.org/search?q=isbn%3A9798350317190 9798350317190 PublicationIdentifier ISBN: 9798350317190 true 122 ISBN https://www.worldcat.org/search?q=isbn%3A@@@ /api/publicationsource/122 ISBN PlainSource ISBN true true 10002 /api/publicationsourcetype/10002 PublicationSourceType Egyéb true false 122 true false true 25360920 IDENTICAL /api/publicationidentifier/25360920 https://www.worldcat.org/search?q=isbn%3A9798350317206 9798350317206 PublicationIdentifier ISBN: 9798350317206 true 122 ISBN https://www.worldcat.org/search?q=isbn%3A@@@ /api/publicationsource/122 ISBN PlainSource ISBN true true 10002 /api/publicationsourcetype/10002 PublicationSourceType Egyéb true false 122 true false true 28712337 /api/publicationidentifier/28712337 https://www.worldcat.org/search?q=isbn%3A9798350317213 9798350317213 PublicationIdentifier ISBN: 9798350317213 true 122 ISBN https://www.worldcat.org/search?q=isbn%3A@@@ /api/publicationsource/122 ISBN PlainSource ISBN true true 10002 /api/publicationsourcetype/10002 PublicationSourceType Egyéb true false 122 true false /api/publication/34531738 IEEE [szerk.]. 22nd IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024: Proceedings. (2024) ISBN:9798350317190; 9798350317206; 9798350317213 true true 23 23 /api/publicationtype/23 PublicationType Könyv 3 true 23 Book false false 34531738 true true true true true 10000144 Conference proceedings true 23 23 /api/publicationtype/23 PublicationType Könyv 3 true 23 Book /api/subtype/10000144 Konferenciakötet SubType Konferenciakötet (Könyv) 345 true 10000144 false Book 2024 true 1 /api/category/1 Category Tudományos true 1 false Language 10002 /api/language/10002 Angol Angol English true 2 true PersonAuthorship 115836864 /api/authorship/115836864 Cserni, Márton [Cserni, Márton (Kamera alapú 3D é...), szerző] Gépjárműtechnológia Tanszék (BME / KJK) 1 0.5 true false false Author 10090982 /api/author/10090982 Cserni Márton (Kamera alapú 3D érzékelés az önvezetés támogatására) Cserni Márton true true Cserni Márton true false false AuthorshipType 1 /api/authorshiptype/1 Szerző 0 true 0 true false true PersonAuthorship 115836865 /api/authorship/115836865 Rövid, András [Rövid, András (Digitális képfeld...), szerző] Gépjárműtechnológia Tanszék (BME / KJK) 2 0.5 false true false Author 10003200 /api/author/10003200 Rövid András (Digitális képfeldolgozás, gépi látás) Rövid András true 10003200 true Rövid András true false false AuthorshipType 1 /api/authorshiptype/1 Szerző 0 true 0 true false true PublicationIdentifier 25877551 /api/publicationidentifier/25877551 DOI: 10.1109/SAMI60510.2024.10432803 PlainSource 6 /api/publicationsource/6 DOI PublicationSourceType 10001 /api/publicationsourcetype/10001 DOI true true true DOI DOI https://doi.org/@@@ true true 6 true 10.1109/SAMI60510.2024.10432803 https://doi.org/10.1109/SAMI60510.2024.10432803 false true PublicationIdentifier 25877550 /api/publicationidentifier/25877550 Scopus: 85186767747 PlainSource 3 /api/publicationsource/3 Scopus PublicationSourceType 10003 /api/publicationsourcetype/10003 Indexelő adatbázis false true true Scopus http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-@@@ true true 3 true 85186767747 http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85186767747 false true Keyword 1072693 /api/keyword/1072693 Statistical tests true 1072693 true Keyword 1090335 /api/keyword/1090335 Optical radar true 1090335 true Keyword 1109343 /api/keyword/1109343 Cameras true 1109343 true Keyword 1183876 /api/keyword/1183876 Object Detection true 1183876 true Keyword 1186433 /api/keyword/1186433 Orientation estimation true 1186433 true Keyword 1258856 /api/keyword/1258856 Autonomous Vehicles true 1258856 true Keyword 1489736 /api/keyword/1489736 autonomous driving true 1489736 true Keyword 1489736 /api/keyword/1489736 autonomous driving true 1489736 true Keyword 2284338 /api/keyword/2284338 Automobile proving grounds true true Keyword 2483285 /api/keyword/2483285 mono-camera true true Keyword 2483285 /api/keyword/2483285 mono-camera true true Keyword 2537802 /api/keyword/2537802 Objects detection true true Keyword 2549492 /api/keyword/2549492 Automotives true true Keyword 2667181 /api/keyword/2667181 Object detectors true true Keyword 2779884 /api/keyword/2779884 object-detection true true Keyword 3018073 /api/keyword/3018073 Camera-based true true Keyword 3362754 /api/keyword/3362754 viewpoint-estimation true true Keyword 3362754 /api/keyword/3362754 viewpoint-estimation true true Keyword 3362755 /api/keyword/3362755 2D objects true true Keyword 3362756 /api/keyword/3362756 Vehicle orientation true true Reference 51101036 /api/reference/51101036 1. Magistri, S., Boschi, M., Sambo, F., De Andrade, D.C., Simoncini, M., Kubin, L., Taccari, L., Salti, S., Lightweight and effective convolutional neural networks for vehicle viewpoint estimation from monocular images (2023) IEEE Transactions on Intelligent Transportation Systems, 24 (1), pp. 191-200 1 false true Reference 51101037 /api/reference/51101037 2. Massa, F., Marlet, R., Aubry, M., (2016) Crafting A Multi-Task Cnn for Viewpoint Estimation, , arXiv preprint arXiv 1609.03894 2 false true Reference 51101038 /api/reference/51101038 3. Divon, G., Tal, A., Viewpoint estimation-insights & model (2018) Proceedings of the European Conference on Computer Vision (ECCV, pp. 252-268 3 false true Reference 51101039 /api/reference/51101039 4. Ren, S., He, K., Girshick, R., Sun, J., Faster r-cnn: Towards real-Time object detection with region proposal networks (2016) IEEE Transactions on Pattern Analysis and Machine Intelligence, 39 (6), pp. 1137-1149 4 false true Reference 51101040 /api/reference/51101040 5. Guindel, C., Martin, D., Armingol, J.M., Joint object detection and viewpoint estimation using cnn features (2017) 2017 IEEE International Conference on Vehicular Electronics and Safety (ICVES). IEEE, pp. 145-150 5 false true Reference 51101032 /api/reference/51101032 6. Zhang, Y., Li, Q., Lu, H., Liu, X., Huang, X., Song, C., Huang, S., Huang, J., Optimized 3d street scene reconstruction from driving recorder images (2015) Remote Sensing, 7 (7), pp. 9091-9121 6 false true Reference 51101033 /api/reference/51101033 7. Cornelis, N., Leibe, B., Cornelis, K., Van Gool, L., 3d urban scene modeling integrating recognition and reconstruction (2008) International Journal of Computer Vision, 78, pp. 121-141 7 false true Reference 51101034 /api/reference/51101034 8. Rezaei, M., Azarmi, M., Mir, F.M.P., 3d-net: Monocular 3d object recognition for traffic monitoring (2023) Expert Systems with Applications, 227, p. 120253 8 false true Reference 51101035 /api/reference/51101035 9. Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A., Is pseudolidar needed for monocular 3d object detection? (2021) Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3142-3152 9 false true Reference 51101041 /api/reference/51101041 10. Chen, T., Lu, S., Robust vehicle detection and viewpoint estimation with soft discriminative mixture model (2015) IEEE Transactions on Circuits and Systems for Video Technology, 27 (2), pp. 394-403 10 false true Reference 51101042 /api/reference/51101042 11. Joung, S., Kim, S., Kim, H., Kim, M., Kim, I.-J., Cho, J., Sohn, K., Cylindrical convolutional networks for joint object detection and viewpoint estimation (2020) Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14163-14172 11 false true Reference 51101043 /api/reference/51101043 12. Magistri, S., Sambo, F., Schoen, F., De Andrade, D.C., Simoncini, M., Caprasecca, S., Kubin, L., Taccari, L., A lightweight deep learning model for vehicle viewpoint estimation from dashcam images (2020) 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp. 1-6 12 false true Reference 51101044 /api/reference/51101044 13. Hartley, R., Zisserman, A., (2003) Multiple View Geometry in Computer Vision, , Cambridge university press 13 false true Reference 51101045 /api/reference/51101045 14. Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J., 3d bounding box estimation using deep learning and geometry (2017) Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7074-7082 14 false true Reference 51101046 /api/reference/51101046 15. Yolov8 Ultralytics, , https://github.com/ultralytics/ultralytics 15 false true /api/publication/34742515 Cserni Márton et al. Mono-Camera Based Vehicle Orientation Detector for Autonomous Driving. (2024) Megjelent: 22nd IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024 pp. 17-22<div class="BookChapter Publication long-list"> <div class="authors"> <img title="Forrásközlemény" style="float: left" src="/frontend/resources/grid/publication-core-icon.png"> <div class="autype autype0"> <span class="author-name" mtid="10090982"><a href="/gui2/?type=authors&mode=browse&sel=10090982" target="_blank">Cserni Márton (<span class="authorship-author-name">Cserni Márton</span> <span class="authorAux-mtmt"> Kamera alapú 3D érzékelés az önvezetés támogatá...</span>) </a> </span> <span class="author-affil"><span title="Budapesti Műszaki és Gazdaságtudományi Egyetem">BME</span>/<span title="Közlekedésmérnöki és Járműmérnöki Kar">KJK</span>/Gépjárműtechnológia Tanszék</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" mtid="10003200"><a href="/gui2/?type=authors&mode=browse&sel=10003200" target="_blank">Rövid András (<span class="authorship-author-name">Rövid András</span> <span class="authorAux-mtmt"> Digitális képfeldolgozás, gépi látás</span>) </a> </span> <span class="author-affil"><span title="Budapesti Műszaki és Gazdaságtudományi Egyetem">BME</span>/<span title="Közlekedésmérnöki és Járműmérnöki Kar">KJK</span>/Gépjárműtechnológia Tanszék</span> </div> </div> <div class="title"><a href="/gui2/?mode=browse&params=publication;34742515" target="_blank">Mono-Camera Based Vehicle Orientation Detector for Autonomous Driving</a></div> <div class="InBook"><div class="chapter-in">In:</div> <div class="authors"> <div class="autype autype-1"> <span class="author-affil">IEEE</span> (szerk.) </div> </div> <div class="booktitle"><a href="/gui2/?mode=browse&params=publication;34531738" target="_blank">22nd IEEE World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024 : Proceedings </a></div> <div class="conference"> Konferencia helye, ideje: <span class="location">Stará Lesna, Szlovákia <span class="conference-date">2024.01.25. - 2024.01.27.</span> </div> <span class="editionNumber">(1)</span> <span class="publishedAt">Piscataway (NJ): <span class="publishers">Institute of Electrical and Electronics Engineers (IEEE)</span>, <span class="page"> pp 17-22 </span> <span class="year">(2024)</span> ( <span class="seriesTitle">Proceedings - International Symposium on Applied Machine Intelligence and Informatics, SAMI</span> <span class="issn">2836-0834</span> <span class="issn">2767-9438</span> ) </div> <div class="pub-footer"> <span class="language" xmlns="http://www.w3.org/1999/html">Nyelv: Angol | </span> <span class="identifiers"> <span class="id identifier oa_none" title="none"> <a style="color:black" title="10.1109/SAMI60510.2024.10432803" target="_blank" href="https://doi.org/10.1109/SAMI60510.2024.10432803"> DOI </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:black" title="85186767747" target="_blank" href="http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85186767747"> Scopus </a> </span> </span> <span class="bookchapter-ids">Befoglaló link(ek):</span> <span class="identifiers"> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="10.1109/SAMI60510.2024" target="_blank" href="https://doi.org/10.1109/SAMI60510.2024"> DOI </a> </span> <span class="id identifier oa_none" title="none"> <span class="isbnOrIssn"> ISBN: </span> <a style="color:black" title="9798350317190" target="_blank" href="https://www.worldcat.org/search?q=isbn%3A9798350317190"> 9798350317190 </a> </span> <span class="id identifier oa_none" title="none"> <span class="isbnOrIssn"> ISBN: </span> <a style="color:blue" title="9798350317206" target="_blank" href="https://www.worldcat.org/search?q=isbn%3A9798350317206"> 9798350317206 </a> </span> <span class="id identifier oa_none" title="none"> <span class="isbnOrIssn"> ISBN: </span> <a style="color:black" title="9798350317213" target="_blank" href="https://www.worldcat.org/search?q=isbn%3A9798350317213"> 9798350317213 </a> </span> </span> <div class="mtid"><span class="long-pub-mtid">Közlemény: 34742515</span> | <span class="status-data status-APPROVED"> Nyilvános </span> <span class="long-book-mtid">Befoglaló: 34531738</span> Forrás | <span class="type-subtype">Könyvrészlet ( Konferenciaközlemény ) </span> | <span class="pub-category">Tudományos</span> | <span class="publication-sourceOfData">Scopus</span> </div> <div class="lastModified">Utolsó módosítás: 2024.03.18. 09:56 Andódy Katalin (BME admin4) </div> <pre class="comment" style="margin-top: 0; margin-bottom: 0;"><u>Megjegyzés</u>: IEEE Control Systems Chapter; IEEE Hungary Section; IEEE Joint Chapter of IES and RAS; IEEE SMC Chapter Conference code: 197504 Export Date: 18 March 2024 Funding details: RRF-2.3.1-21-2022-00002 Funding details: European Commission, EC Funding text 1: ACKNOWLEDGMENT The resea...</pre> </div> </div>