{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:38:02Z","timestamp":1784169482260,"version":"3.55.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T00:00:00Z","timestamp":1622246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T00:00:00Z","timestamp":1622246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012325","name":"Bergische Universit\u00e4t Wuppertal","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012325","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2021,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The last decade has witnessed important advancements in the field of computer vision and scene understanding, enabling applications such us autonomous vehicles. Radar is a commonly adopted sensor in automotive industry, but its suitability to machine learning techniques still remains an open question. In this work, we propose a neural network (NN) based solution to efficiently process radar data. We introduce RadarPCNN, an architecture specifically designed for performing semantic segmentation on radar point clouds. It uses PointNet<jats:inline-formula><jats:alternatives><jats:tex-math>$$++$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mo>+<\/mml:mo>\n                    <mml:mo>+<\/mml:mo>\n                  <\/mml:mrow>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula> as a building-block\u2014enhancing the sampling stage with mean-shift\u2014and an attention mechanism to fuse information. Additionally, we propose a machine learning radar pre-processing module that confers the network the ability to learn from radar features. We show that our solutions are effective, yielding superior performance than the state-of-the-art.\n<\/jats:p>","DOI":"10.1007\/s11063-021-10544-4","type":"journal-article","created":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T04:05:33Z","timestamp":1622261133000},"page":"3217-3235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Neural Network Based System for Efficient Semantic Segmentation of Radar Point Clouds"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6475-1354","authenticated-orcid":false,"given":"Alessandro","family":"Cennamo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Kaestner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Kummert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,29]]},"reference":[{"issue":"1","key":"10544_CR1","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1109\/TITS.2006.888597","volume":"8","author":"G Alessandretti","year":"2007","unstructured":"Alessandretti G et al (2007) Vehicle and guard rail detection using radar and vision data fusion. IEEE Trans Intell Transp Syst 8(1):95\u2013105","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"10544_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"10544_CR3","doi-asserted-by":"crossref","unstructured":"Caesar H et al (2019) nuscenes: a multimodal dataset for autonomous driving. CoRR","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"10544_CR4","doi-asserted-by":"publisher","unstructured":"Cennamo A, K\u00e4stner F, Kummert A (2020) Leveraging radar features to improve point clouds segmentation with neural networks. In: Proceedings of the 21st EANN 2020 conference, Springer, pp 119\u2013131. https:\/\/doi.org\/10.1007\/978-3-030-48791-1_8","DOI":"10.1007\/978-3-030-48791-1_8"},{"key":"10544_CR5","doi-asserted-by":"publisher","unstructured":"Engelcke M, et\u00a0al (2017) Vote3deep: fast object detection in 3d point clouds using efficient convolutional neural networks. In: 2017 IEEE international conference on robotics and automation, ICRA, pp 1355\u20131361. https:\/\/doi.org\/10.1109\/ICRA.2017.7989161","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"10544_CR6","doi-asserted-by":"publisher","unstructured":"Eriksson LH, As B (1997) Automotive radar for adaptive cruise control and collision warning\/avoidance. In: Radar 97 (Conf Publ No 449), pp 16\u201320. https:\/\/doi.org\/10.1049\/cp:19971623","DOI":"10.1049\/cp:19971623"},{"key":"10544_CR7","unstructured":"Ester M et\u00a0al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the second international conference on knowledge discovery and data mining (KDD-96), pp 226\u2013231"},{"issue":"7639","key":"10544_CR8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115\u2013118. https:\/\/doi.org\/10.1038\/nature21056","journal-title":"Nature"},{"key":"10544_CR9","doi-asserted-by":"publisher","unstructured":"Feng Y et\u00a0al (2018) GVCNN: group-view convolutional neural networks for 3d shape recognition. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR, pp 264\u2013272. https:\/\/doi.org\/10.1109\/CVPR.2018.00035","DOI":"10.1109\/CVPR.2018.00035"},{"key":"10544_CR10","unstructured":"Feng Z et\u00a0al (2019) Point cloud segmentation with a high-resolution automotive radar. In: AmE 2019\u2014automotive meets electronics; 10th GMM-symposium, pp 1\u20135"},{"issue":"1","key":"10544_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/TIT.1975.1055330","volume":"21","author":"K Fukunaga","year":"1975","unstructured":"Fukunaga K, Hostetler LD (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans Inf Theory 21(1):32\u201340. https:\/\/doi.org\/10.1109\/TIT.1975.1055330","journal-title":"IEEE Trans Inf Theory"},{"issue":"8","key":"10544_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"10544_CR13","doi-asserted-by":"crossref","unstructured":"Jose A et\u00a0al (2019) A novel traffic sign recognition system combining viola\u2013jones framework and deep learning. In: Soft computing and signal processing, Springer, pp 507\u2013517","DOI":"10.1007\/978-981-13-3600-3_48"},{"key":"10544_CR14","unstructured":"Li Y et\u00a0al (2018) Pointcnn: convolution on x-transformed points. In: Advances in neural information processing systems 31: annual conference on neural information processing systems, NeurIPS, pp 828\u2013838"},{"key":"10544_CR15","doi-asserted-by":"publisher","unstructured":"Lin T et\u00a0al (2017) Focal loss for dense object detection. In: IEEE international conference on computer vision, ICCV, pp 2999\u20133007. https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"10544_CR16","doi-asserted-by":"crossref","unstructured":"Lombacher J, Hahn M, Dickmann J, W\u00f6hler C (2017) Object classification in radar using ensemble methods. In: 2017 IEEE MTT-S international conference on microwaves for intelligent mobility (ICMIM), pp 87\u201390","DOI":"10.1109\/ICMIM.2017.7918863"},{"key":"10544_CR17","doi-asserted-by":"crossref","unstructured":"Lombacher J, Laudt K, Hahn M, Dickmann J, W\u00f6hler C (2017) Semantic radar grids. In: 2017 IEEE intelligent vehicles symposium (IV), pp 1170\u20131175","DOI":"10.1109\/IVS.2017.7995871"},{"key":"10544_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060037","author":"E Pintelas","year":"2020","unstructured":"Pintelas E et al (2020) Explainable machine learning framework for image classification problems: case study on glioma cancer prediction. J Imaging. https:\/\/doi.org\/10.3390\/jimaging6060037","journal-title":"J Imaging"},{"key":"10544_CR19","unstructured":"Prakash A, Brockett C, Agrawal P (2016) Emulating human conversations using convolutional neural network-based ir. arXiv:1606.07056"},{"key":"10544_CR20","doi-asserted-by":"publisher","unstructured":"Prophet R et\u00a0al (2018) Pedestrian classification for 79 ghz automotive radar systems. In: 2018 IEEE intelligent vehicles symposium, IV, pp 1265\u20131270. https:\/\/doi.org\/10.1109\/IVS.2018.8500554","DOI":"10.1109\/IVS.2018.8500554"},{"key":"10544_CR21","unstructured":"Qi CR et\u00a0al (2017) Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in neural information processing systems 30: annual conference on neural information processing systems, pp 5099\u20135108"},{"key":"10544_CR22","doi-asserted-by":"publisher","unstructured":"Qi CR et\u00a0al (2017) Pointnet: seep learning on point sets for 3d classification and segmentation. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR, pp 77\u201385. https:\/\/doi.org\/10.1109\/CVPR.2017.16","DOI":"10.1109\/CVPR.2017.16"},{"key":"10544_CR23","doi-asserted-by":"publisher","unstructured":"Schumann O et\u00a0al (2018) Semantic segmentation on radar point clouds. In: 21st International conference on information fusion, FUSION, pp 2179\u20132186. https:\/\/doi.org\/10.23919\/ICIF.2018.8455344","DOI":"10.23919\/ICIF.2018.8455344"},{"key":"10544_CR24","doi-asserted-by":"crossref","unstructured":"Werber K, Rapp M, Klappstein J, Hahn M, Dickmann J, Dietmayer K, Waldschmidt C (2015) Automotive radar gridmap representations. In: 2015 IEEE MTT-S international conference on microwaves for intelligent mobility (ICMIM), pp 1\u20134","DOI":"10.1109\/ICMIM.2015.7117922"},{"key":"10544_CR25","doi-asserted-by":"publisher","unstructured":"W\u00f6hler C et\u00a0al (2017) Comparison of random forest and long short-term memory network performances in classification tasks using radar. In: Sensor data fusion: trends, solutions, applications, SDF, pp 1\u20136. https:\/\/doi.org\/10.1109\/SDF.2017.8126350","DOI":"10.1109\/SDF.2017.8126350"},{"key":"10544_CR26","doi-asserted-by":"crossref","unstructured":"Yang B et al (2018) Attentional aggregation of deep feature sets for multi-view 3d reconstruction. CoRR","DOI":"10.1007\/s11263-019-01217-w"},{"issue":"4","key":"10544_CR27","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1109\/TCYB.2020.2969046","volume":"51","author":"J Yu","year":"2021","unstructured":"Yu J, Yao J, Zhang J, Yu Z, Tao D (2021) Sprnet: single-pixel reconstruction for one-stage instance segmentation. IEEE Trans Cybern 51(4):1731\u20131742. https:\/\/doi.org\/10.1109\/TCYB.2020.2969046","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"10544_CR28","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TNNLS.2019.2908982","volume":"31","author":"J Yu","year":"2020","unstructured":"Yu J, Zhu C, Zhang J, Huang Q, Tao D (2020) Spatial pyramid-enhanced netvlad with weighted triplet loss for place recognition. IEEE Trans Neural Netw Learn Syst 31(2):661\u2013674. https:\/\/doi.org\/10.1109\/TNNLS.2019.2908982","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10544_CR29","unstructured":"Zaheer M et\u00a0al (2017) Deep sets. In: Advances in neural information processing systems 30: annual conference on neural information processing systems, pp 3391\u20133401"},{"key":"10544_CR30","doi-asserted-by":"publisher","DOI":"10.4271\/2020-01-1210","author":"X Zhou","year":"2020","unstructured":"Zhou X, Wingert T, Sauer M, Kundu S (2020) Development of a camera-based driver state monitoring system for cost-effective embedded solution. SAE Tech Paper SAE Int. https:\/\/doi.org\/10.4271\/2020-01-1210","journal-title":"SAE Tech Paper SAE Int"},{"key":"10544_CR31","doi-asserted-by":"publisher","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: End-to-end learning for point cloud based 3d object detection. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR, pp 4490\u20134499. https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-021-10544-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-021-10544-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-021-10544-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T17:51:19Z","timestamp":1634320279000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-021-10544-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,29]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["10544"],"URL":"https:\/\/doi.org\/10.1007\/s11063-021-10544-4","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,29]]},"assertion":[{"value":"24 May 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}