{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:03:11Z","timestamp":1783180991096,"version":"3.54.6"},"reference-count":18,"publisher":"Walter de Gruyter GmbH","issue":"5","license":[{"start":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T00:00:00Z","timestamp":1588204800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004895","name":"European Social Fund","doi-asserted-by":"publisher","award":["EFOP-3.6.2-16-2017-00002"],"award-info":[{"award-number":["EFOP-3.6.2-16-2017-00002"]}],"id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Environment perception plays a significant role in autonomous driving since all traffic participants in the vehicle\u2019s surroundings must be reliably recognized and localized in order to take any subsequent action. The main goal of this paper is to present a neural network approach for fusing camera images and LiDAR point clouds in order to detect traffic participants in the vehicle\u2019s surroundings more reliably. Our approach primarily addresses the problem of sparse LiDAR data (point clouds of distant objects), where due to sparsity the point cloud based detection might become ambiguous. In the proposed model each 3D point in the LiDAR point cloud is augmented by semantically strong image features allowing us to inject additional information for the network to learn from. Experimental results show that our method increases the number of correctly detected 3D bounding boxes in sparse point clouds by at least 13\u201321\u2009% and thus raw sensor fusion is validated as a viable approach for enhancing autonomous driving safety in difficult sensory conditions.<\/jats:p>","DOI":"10.1515\/auto-2019-0086","type":"journal-article","created":{"date-parts":[[2020,5,26]],"date-time":"2020-05-26T17:11:04Z","timestamp":1590513064000},"page":"337-346","source":"Crossref","is-referenced-by-count":12,"title":["Raw fusion of camera and sparse LiDAR for detecting distant objects"],"prefix":"10.1515","volume":"68","author":[{"given":"Andr\u00e1s","family":"R\u00f6vid","sequence":"first","affiliation":[{"name":"Department of Automotive Technologies at the Faculty of Transportation Engineering and Vehicle Engineering , Budapest University of Technology and Economics , Budapest , Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor","family":"Remeli","sequence":"additional","affiliation":[{"name":"Department of Automotive Technologies at the Faculty of Transportation Engineering and Vehicle Engineering , Budapest University of Technology and Economics , Budapest , Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zsolt","family":"Szalay","sequence":"additional","affiliation":[{"name":"Department of Automotive Technologies at the Faculty of Transportation Engineering and Vehicle Engineering , Budapest University of Technology and Economics , Budapest , Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"374","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"2023033109505878161_j_auto-2019-0086_ref_001_w2aab3b8d272b1b7b1ab2ab1Aa","doi-asserted-by":"crossref","unstructured":"Geiger, Andreas, Philip Lenz, Christoph Stiller and Raquel Urtasun. 2013. Vision meets Robotics: The KITTI Dataset. Technical Report October. http:\/\/www.cvlibs.net\/datasets\/kitti.","DOI":"10.1177\/0278364913491297"},{"key":"2023033109505878161_j_auto-2019-0086_ref_002_w2aab3b8d272b1b7b1ab2ab2Aa","doi-asserted-by":"crossref","unstructured":"Geiger, Andreas, Philip Lenz and Raquel Urtasun. 2012. \u201cAre we ready for autonomous driving? The KITTI vision benchmark suite.\u201d In 2012 IEEE Conference on Computer Vision and Pattern Recognition, jun, 3354\u20133361. IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2023033109505878161_j_auto-2019-0086_ref_003_w2aab3b8d272b1b7b1ab2ab3Aa","doi-asserted-by":"crossref","unstructured":"Hall, David L. and James Llinas. 1997. \u201cAn introduction to multisensor data fusion.\u201d Proceedings of the IEEE 85 (1): 6\u201323.","DOI":"10.1109\/5.554205"},{"key":"2023033109505878161_j_auto-2019-0086_ref_004_w2aab3b8d272b1b7b1ab2ab4Aa","doi-asserted-by":"crossref","unstructured":"He, Kaiming, Xiangyu Zhang, Shaoqing Ren and Jian Sun. 2016. \u201cDeep residual learning for image recognition.\u201d In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem: 770\u2013778. http:\/\/arxiv.org\/abs\/1512.03385.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2023033109505878161_j_auto-2019-0086_ref_005_w2aab3b8d272b1b7b1ab2ab5Aa","doi-asserted-by":"crossref","unstructured":"Kim, Seungki, Hyunkyu Kim, Wonseok Yoo and Kunsoo Huh. 2016. \u201cSensor Fusion Algorithm Design in Detecting Vehicles Using Laser Scanner and Stereo Vision.\u201d IEEE Transactions on Intelligent Transportation Systems 17 (4): 1072\u20131084. http:\/\/ieeexplore.ieee.org\/document\/7322252\/.","DOI":"10.1109\/TITS.2015.2493160"},{"key":"2023033109505878161_j_auto-2019-0086_ref_006_w2aab3b8d272b1b7b1ab2ab6Aa","unstructured":"Kovacs, L., L. Lindenmaier, H. Nemeth, V. Tihanyi and A. Zarandy. 2018. \u201cPerformance Evaluation of a Track to Track Sensor Fusion Algorithm.\u201d In CNNA 2018; The 16th International Workshop on Cellular Nanoscale Networks and their Applications, aug, 1\u20132."},{"key":"2023033109505878161_j_auto-2019-0086_ref_007_w2aab3b8d272b1b7b1ab2ab7Aa","doi-asserted-by":"crossref","unstructured":"Ku, Jason, Melissa Mozifian, Jungwook Lee, Ali Harakeh and Steven Waslander. 2017. \u201cJoint 3D Proposal Generation and Object Detection from View Aggregation.\u201d http:\/\/arxiv.org\/abs\/1712.02294.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"2023033109505878161_j_auto-2019-0086_ref_008_w2aab3b8d272b1b7b1ab2ab8Aa","doi-asserted-by":"crossref","unstructured":"Lang, Alex H., Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang and Oscar Beijbom. 2018. \u201cPointPillars: Fast Encoders for Object Detection from Point Clouds.\u201d http:\/\/arxiv.org\/abs\/1812.05784.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2023033109505878161_j_auto-2019-0086_ref_009_w2aab3b8d272b1b7b1ab2ab9Aa","doi-asserted-by":"crossref","unstructured":"Liang, Ming, Bin Yang, Shenlong Wang and Raquel Urtasun. 2018. \u201cDeep Continuous Fusion for Multi-Sensor 3D Object Detection.\u201d In Cvpr 2018, 16. http:\/\/openaccess.thecvf.com\/content_ECCV_2018\/papers\/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.pdf.","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"2023033109505878161_j_auto-2019-0086_ref_010_w2aab3b8d272b1b7b1ab2ac10Aa","doi-asserted-by":"crossref","unstructured":"Lin, Tsung-yi, Piotr Doll, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie, Facebook Ai and Cornell Tech. 2017. (FPN) Feature Pyramid Networks for Object Detection. Technical Report. http:\/\/openaccess.thecvf.com\/content_cvpr_2017\/papers\/Lin_Feature_Pyramid_Networks_CVPR_2017_paper.pdf.","DOI":"10.1109\/CVPR.2017.106"},{"key":"2023033109505878161_j_auto-2019-0086_ref_011_w2aab3b8d272b1b7b1ab2ac11Aa","doi-asserted-by":"crossref","unstructured":"Lin, Tsung Yi, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r and C. Lawrence Zitnick. 2014. \u201cMicrosoft COCO: Common objects in context.\u201d Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 8693 LNCS (PART 5): 740\u2013755. http:\/\/arxiv.org\/abs\/1405.0312.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2023033109505878161_j_auto-2019-0086_ref_012_w2aab3b8d272b1b7b1ab2ac12Aa","doi-asserted-by":"crossref","unstructured":"Qi, Charles R., Wei Liu, Chenxia Wu, Hao Su and Leonidas J. Guibas. 2017. \u201cFrustum PointNets for 3D Object Detection from RGB-D Data.\u201d http:\/\/arxiv.org\/abs\/1711.08488.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"2023033109505878161_j_auto-2019-0086_ref_013_w2aab3b8d272b1b7b1ab2ac13Aa","doi-asserted-by":"crossref","unstructured":"Qi, Charles R., Hao Su, Kaichun Mo and Leonidas J. Guibas. 2016. \u201cPointNet: Deep Learning on Point Sets for 3D Classification and Segmentation.\u201d http:\/\/arxiv.org\/abs\/1612.00593.","DOI":"10.1109\/CVPR.2017.16"},{"key":"2023033109505878161_j_auto-2019-0086_ref_014_w2aab3b8d272b1b7b1ab2ac14Aa","unstructured":"Redmon, Joseph and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. Technical Report. http:\/\/arxiv.org\/abs\/1804.02767."},{"key":"2023033109505878161_j_auto-2019-0086_ref_015_w2aab3b8d272b1b7b1ab2ac15Aa","doi-asserted-by":"crossref","unstructured":"Shi, Shaoshuai, Xiaogang Wang and Hongsheng Li. 2018. \u201cPointRCNN: 3D Object Proposal Generation and Detection from Point Cloud.\u201d http:\/\/arxiv.org\/abs\/1812.04244.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2023033109505878161_j_auto-2019-0086_ref_016_w2aab3b8d272b1b7b1ab2ac16Aa","doi-asserted-by":"crossref","unstructured":"Wang, Zhixin and Kui Jia. 2019. \u201cFrustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection.\u201d http:\/\/arxiv.org\/abs\/1903.01864.","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"2023033109505878161_j_auto-2019-0086_ref_017_w2aab3b8d272b1b7b1ab2ac17Aa","doi-asserted-by":"crossref","unstructured":"Xu, Danfei, Dragomir Anguelov and Ashesh Jain. 2017. \u201cPointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation.\u201d 10. http:\/\/arxiv.org\/abs\/1711.10871.","DOI":"10.1109\/CVPR.2018.00033"},{"key":"2023033109505878161_j_auto-2019-0086_ref_018_w2aab3b8d272b1b7b1ab2ac18Aa","doi-asserted-by":"crossref","unstructured":"Zhou, Yin and Oncel Tuzel. 2018. \u201cVoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection.\u201d In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 4490\u20134499. http:\/\/arxiv.org\/abs\/1711.06396.","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/view\/journals\/auto\/68\/5\/article-p337.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2019-0086\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2019-0086\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,31]],"date-time":"2023-03-31T10:11:09Z","timestamp":1680257469000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/auto-2019-0086\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,30]]},"references-count":18,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2020,4,30]]},"published-print":{"date-parts":[[2020,5,27]]}},"alternative-id":["10.1515\/auto-2019-0086"],"URL":"https:\/\/doi.org\/10.1515\/auto-2019-0086","relation":{},"ISSN":["2196-677X","0178-2312"],"issn-type":[{"value":"2196-677X","type":"electronic"},{"value":"0178-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2020,4,30]]}}}