{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:02:35Z","timestamp":1769695355049,"version":"3.49.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T00:00:00Z","timestamp":1704153600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T00:00:00Z","timestamp":1704153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"helsinki institute of physics"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>3D road user detection is an essential task for autonomous vehicles and mobile robots, and it plays a key role, for instance, in obstacle avoidance and route planning tasks. Existing solutions for detection require expensive GPU units to run in real-time. This paper presents a light algorithm that runs in real-time without a GPU. The algorithm combines a classical point cloud proposal generator approach with a modern deep learning technique to achieve a small computational requirement and comparable accuracy to the state-of-the-art. Typical downsides of this approach, such as many out-of-distribution proposals and loss of location information, are examined, and solutions are proposed. We have evaluated the performance of the method with the KITTI dataset and with our own annotated dataset collected with a compact mobile robot platform equipped with a low-resolution LiDAR (16-channel). Our approach reaches a real-time inference on a standard CPU, unlike other solutions in the literature. Furthermore, we achieve superior speed on a GPU, which indicates that our method has a high degree of parallelism. Our method enables low-cost mobile robots to detect road users in real-time.<\/jats:p>","DOI":"10.1186\/s40537-023-00859-5","type":"journal-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T17:02:40Z","timestamp":1704214960000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Out-of-distribution- and location-aware PointNets for real-time 3D road user detection without a GPU"],"prefix":"10.1186","volume":"11","author":[{"given":"Alvari","family":"Sepp\u00e4nen","sequence":"first","affiliation":[]},{"given":"Eerik","family":"Alamikkotervo","sequence":"additional","affiliation":[]},{"given":"Risto","family":"Ojala","sequence":"additional","affiliation":[]},{"given":"Giacomo","family":"Dario","sequence":"additional","affiliation":[]},{"given":"Kari","family":"Tammi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,2]]},"reference":[{"key":"859_CR1","doi-asserted-by":"crossref","unstructured":"Horowitz M. 1.1 computing\u2019s energy problem (and what we can do about it). In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), 2014; pp. 10\u201314. IEEE.","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"859_CR2","doi-asserted-by":"crossref","unstructured":"Huang C, Nguyen VD, Abdelzad V, Mannes CG, Rowe L, Therien B, Salay R, Czarnecki K Out-of-distribution detection for lidar-based 3d object detection. In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), 2022; pp. 4265\u20134271.","DOI":"10.1109\/ITSC55140.2022.9922026"},{"key":"859_CR3","doi-asserted-by":"crossref","unstructured":"Zhou Y, Tuzel O. Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018; pp. 4490\u20134499.","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"859_CR4","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan Y, Mao Y, Li B. Second: sparsely embedded convolutional detection. Sensors. 2018;18(10):3337.","journal-title":"Sensors"},{"key":"859_CR5","doi-asserted-by":"crossref","unstructured":"Fan L, Xiong X, Wang F, Wang N, Zhang Z. Rangedet: in defense of range view for lidar-based 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021; pp. 2918\u20132927.","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"859_CR6","doi-asserted-by":"crossref","unstructured":"Chai Y, Sun P, Ngiam J, Wang W, Caine B, Vasudevan V, Zhang X, Anguelov D. To the point: Efficient 3d object detection in the range image with graph convolution kernels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021; pp. 16000\u201316009.","DOI":"10.1109\/CVPR46437.2021.01574"},{"key":"859_CR7","unstructured":"Liang Z, Zhang M, Zhang Z, Zhao X, Pu S. Rangercnn: towards fast and accurate 3d object detection with range image representation, 2020; arXiv preprint arXiv:2009.00206."},{"key":"859_CR8","doi-asserted-by":"crossref","unstructured":"Meyer GP, Laddha A, Kee E, Vallespi-Gonzalez C, Wellington CK. Lasernet: an efficient probabilistic 3d object detector for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019; pp. 12677\u201312686.","DOI":"10.1109\/CVPR.2019.01296"},{"key":"859_CR9","doi-asserted-by":"crossref","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O. Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019; pp. 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"859_CR10","doi-asserted-by":"crossref","unstructured":"Yang B, Luo W, Urtasun R. Pixor: real-time 3d object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018; pp. 7652\u20137660.","DOI":"10.1109\/CVPR.2018.00798"},{"key":"859_CR11","doi-asserted-by":"crossref","unstructured":"Zheng W, Tang W, Jiang L, Fu C-W. Se-ssd: self-ensembling single-stage object detector from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021; pp. 14494\u201314503.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"859_CR12","doi-asserted-by":"crossref","unstructured":"Zheng W, Tang W, Chen S, Jiang L, Fu C-W. Cia-ssd: confident iou-aware single-stage object detector from point cloud. arXiv preprint, 2020; arXiv:2012.03015.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"859_CR13","doi-asserted-by":"crossref","unstructured":"Shi W, Rajkumar R. Point-gnn: graph neural network for 3d object detection in a point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020; pp. 1711\u20131719.","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"859_CR14","unstructured":"Qi CR, Yi L, Su H, Guibas LJ. Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Proc Syst. 2017;30."},{"key":"859_CR15","doi-asserted-by":"crossref","unstructured":"Zhang Y, Hu Q, Xu G, Ma Y, Wan J, Guo Y. Not all points are equal: learning highly efficient point-based detectors for 3d lidar point clouds. Accepted to CVPR 2022, arXiv preprint, 2022; arXiv:2203.11139.","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"859_CR16","doi-asserted-by":"crossref","unstructured":"Qi CR, Litany O, He K, Guibas LJ. Deep Hough voting for 3d object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019; pp. 9277\u20139286.","DOI":"10.1109\/ICCV.2019.00937"},{"key":"859_CR17","doi-asserted-by":"crossref","unstructured":"Shi S, Wang X, Li H. Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019; pp. 770\u2013779.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"859_CR18","unstructured":"Ngiam J, Caine B, Han W, Yang B, Chai Y, Sun P, Zhou Y, Yi X, Alsharif O, Nguyen P, et\u00a0al. Starnet: targeted computation for object detection in point clouds. arXiv preprint , 2019;arXiv:1908.11069."},{"key":"859_CR19","unstructured":"Sobel I. An isotropic 3x3 image gradient operator. Presentation at Stanford A.I. Project 1968; 2014."},{"key":"859_CR20","doi-asserted-by":"crossref","unstructured":"Bogoslavskyi I, Stachniss C. Fast range image-based segmentation of sparse 3d laser scans for online operation. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016; pp. 163\u2013169. IEEE.","DOI":"10.1109\/IROS.2016.7759050"},{"key":"859_CR21","doi-asserted-by":"crossref","unstructured":"Zhao Y, Zhang X, Huang X. A technical survey and evaluation of traditional point cloud clustering methods for lidar panoptic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021; pp. 2464\u20132473.","DOI":"10.1109\/ICCVW54120.2021.00279"},{"issue":"4","key":"859_CR22","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s13218-010-0059-6","volume":"24","author":"RB Rusu","year":"2010","unstructured":"Rusu RB. Semantic 3d object maps for everyday manipulation in human living environments. KI-K\u00fcnstliche Intelligenz. 2010;24(4):345\u20138.","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"key":"859_CR23","doi-asserted-by":"crossref","unstructured":"Rusu RB, Cousins S. 3d is here: point cloud library (pcl). In: 2011 IEEE International Conference on Robotics and Automation, 2011; pp. 1\u20134. IEEE.","DOI":"10.1109\/ICRA.2011.5980567"},{"key":"859_CR24","doi-asserted-by":"crossref","unstructured":"Papon J, Abramov A, Schoeler M, Worgotter F. Voxel cloud connectivity segmentation-supervoxels for point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2013; pp. 2027\u20132034.","DOI":"10.1109\/CVPR.2013.264"},{"key":"859_CR25","doi-asserted-by":"crossref","unstructured":"Zermas D, Izzat I, Papanikolopoulos N. Fast segmentation of 3d point clouds: a paradigm on lidar data for autonomous vehicle applications. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017; pp. 5067\u20135073. IEEE.","DOI":"10.1109\/ICRA.2017.7989591"},{"key":"859_CR26","doi-asserted-by":"crossref","unstructured":"Dong X, Guo J, Li A, Ting W-T, Liu C, Kung H. Neural mean discrepancy for efficient out-of-distribution detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022; pp. 19217\u201319227.","DOI":"10.1109\/CVPR52688.2022.01862"},{"key":"859_CR27","unstructured":"Liang S, Li Y, Srikant R. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint, 2017; arXiv:1706.02690."},{"key":"859_CR28","doi-asserted-by":"crossref","unstructured":"Hsu Y-C, Shen Y, Jin H, Kira Z. Generalized odin: detecting out-of-distribution image without learning from out-of-distribution data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020; pp. 10951\u201310960.","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"859_CR29","unstructured":"Ren J, Fort S, Liu J, Roy AG, Padhy S, Lakshminarayanan B. A simple fix to mahalanobis distance for improving near-ood detection. arXiv preprint, 2021; arXiv:2106.09022."},{"key":"859_CR30","unstructured":"Lee K, Lee K, Lee H, Shin J. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Adv Neural Inf Proc Syst 2018; 31."},{"key":"859_CR31","doi-asserted-by":"crossref","unstructured":"LeCun Y, Chopra S, Hadsell R, Ranzato M, Huang F. A tutorial on energy-based learning. Predicting structured Data. 2006; 1(0).","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"859_CR32","first-page":"21464","volume":"33","author":"W Liu","year":"2020","unstructured":"Liu W, Wang X, Owens J, Li Y. Energy-based out-of-distribution detection. Adv Neural Inf Process Syst. 2020;33:21464\u201375.","journal-title":"Adv Neural Inf Process Syst"},{"key":"859_CR33","unstructured":"Hinton GE, Zemel R. Autoencoders, minimum description length and helmholtz free energy. Adv Neural Inf Proc Syst. 1993; 6."},{"key":"859_CR34","unstructured":"Qi CR, Su H, Mo K, Guibas LJ. Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017; pp. 652\u2013660."},{"key":"859_CR35","doi-asserted-by":"crossref","unstructured":"Huber PJ. Robust estimation of a location parameter. In: Breakthroughs in Statistics, 1992; pp. 492\u2013518. Springer.","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"859_CR36","doi-asserted-by":"crossref","unstructured":"Qi CR, Liu W, Wu C, Su H, Guibas LJ. Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018; pp. 918\u2013927.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"859_CR37","doi-asserted-by":"crossref","unstructured":"Geiger A, Lenz P, Urtasun R. Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012; pp. 3354\u20133361 . IEEE.","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"8\u20139","key":"859_CR38","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1177\/02783649211006735","volume":"40","author":"J Behley","year":"2021","unstructured":"Behley J, Garbade M, Milioto A, Quenzel J, Behnke S, Gall J, Stachniss C. Towards 3D LiDAR-based semantic scene understanding of 3D point cloud sequences: the SemanticKITTI Dataset. Int J Robot Res. 2021;40(8\u20139):959\u201367.","journal-title":"Int J Robot Res"},{"key":"859_CR39","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014."},{"key":"859_CR40","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n J, Guindel C, Moreno FM, Cruzado D, Garcia F, De\u00a0La\u00a0Escalera A. Birdnet: a 3d object detection framework from lidar information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), 2018; pp. 3517\u20133523. IEEE.","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"859_CR41","doi-asserted-by":"publisher","first-page":"160299","DOI":"10.1109\/ACCESS.2021.3131389","volume":"9","author":"A Barrera","year":"2021","unstructured":"Barrera A, Beltr\u00e1n J, Guindel C, Iglesias JA, Garc\u00eda F. Birdnet+: two-stage 3d object detection in lidar through a sparsity-invariant bird\u2019s eye view. IEEE Access. 2021;9:160299\u2013316.","journal-title":"IEEE Access"},{"key":"859_CR42","doi-asserted-by":"crossref","unstructured":"Ku J, Mozifian M, Lee J, Harakeh A, Waslander SL. Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018; pp. 1\u20138. IEEE.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"859_CR43","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et\u00a0al. Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Proc Syst. 2019; 32."},{"key":"859_CR44","doi-asserted-by":"crossref","unstructured":"Ouyang Z, Dong X, Cui J, Niu J, Guizani M. Pv-enconet: fast object detection based on colored point cloud. IEEE Trans Intel Transport Syst. 2021.","DOI":"10.1109\/TITS.2021.3114062"},{"key":"859_CR45","doi-asserted-by":"publisher","first-page":"23270","DOI":"10.1109\/ACCESS.2019.2899674","volume":"7","author":"K Liu","year":"2019","unstructured":"Liu K, Wang W, Tharmarasa R, Wang J, Zuo Y. Ground surface filtering of 3d point clouds based on hybrid regression technique. IEEE Access. 2019;7:23270\u201384.","journal-title":"IEEE Access"},{"key":"859_CR46","doi-asserted-by":"crossref","unstructured":"Velas M, Spanel M, Hradis M, Herout A. Cnn for very fast ground segmentation in velodyne lidar data. In: 2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2018; pp. 97\u2013103. IEEE.","DOI":"10.1109\/ICARSC.2018.8374167"},{"key":"859_CR47","doi-asserted-by":"crossref","unstructured":"Rummelhard L, Paigwar A, N\u00e8gre A, Laugier C. Ground estimation and point cloud segmentation using spatiotemporal conditional random field. In: 2017 IEEE Intelligent Vehicles Symposium (IV),2017; pp. 1105\u20131110. IEEE.","DOI":"10.1109\/IVS.2017.7995861"},{"key":"859_CR48","doi-asserted-by":"crossref","unstructured":"Paigwar A, Erkent \u00d6, Sierra-Gonzalez D, Laugier C. Gndnet: fast ground plane estimation and point cloud segmentation for autonomous vehicles. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020; pp. 2150\u20132156 . IEEE.","DOI":"10.1109\/IROS45743.2020.9340979"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00859-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-023-00859-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-023-00859-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T17:11:19Z","timestamp":1704215479000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-023-00859-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,2]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["859"],"URL":"https:\/\/doi.org\/10.1186\/s40537-023-00859-5","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,2]]},"assertion":[{"value":"27 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2"}}