{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:51:09Z","timestamp":1780332669079,"version":"3.54.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Bogazici University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This study details the adaptation and deployment of a customized SalsaNext model for semantic segmentation of LiDAR point clouds on edge devices, benchmarked using the SemanticKITTI and Waymo Open datasets. We introduce an innovative multi-dataset training framework designed specifically for range image-based segmentation models. Central to this approach is our double-head SalsaNext model, which features two output heads to facilitate simultaneous training and inference on the Waymo and SemanticKITTI datasets. Following training, the model is streamlined by removing the head dedicated to Waymo, resulting in a compact, single-headed version optimized for SemanticKITTI. This simplified model is then quantized to employ fixed-point arithmetic, significantly enhancing computational efficiency and enabling real-time operation on the Xilinx Kria KV260 board. The quantization process markedly reduces resource consumption while preserving competitive accuracy. Our deployment on this low-power, FPGA-based platform underscores the potential of energy-efficient systems for advanced 3D semantic segmentation, with promising applications in autonomous systems and robotics. Experimental results validate the effectiveness of our training schema and the success of the optimized implementation of the double-head model on resource-constrained hardware.<\/jats:p>","DOI":"10.1007\/s11554-025-01643-9","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T12:07:28Z","timestamp":1741694848000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["FPGA implementation of double-head SalsaNext: a CNN-based model for LiDAR point cloud segmentation"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2400-9897","authenticated-orcid":false,"given":"Muhammed Yasin","family":"Adiyaman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6743-3992","authenticated-orcid":false,"given":"Faik","family":"Baskaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"1643_CR1","doi-asserted-by":"crossref","unstructured":"Wu, X., Jiang, L., Wang, P.-S., Liu, Z., Liu, X., Qiao, Y., Ouyang, W., He, T., Zhao, H.: Point transformer v3: Simpler faster stronger. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4840\u20134851 (2024)","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"1643_CR2","doi-asserted-by":"publisher","unstructured":"Lai, X., Chen, Y., Lu, F., Liu, J., Jia, J.: Spherical transformer for lidar-based 3d recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17545\u201317555 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01683","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"1643_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection (2017). arxiv:1711.06396","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1643_CR4","doi-asserted-by":"publisher","unstructured":"Aksoy, E.E., Baci, S., Cavdar, S.: Salsanet: Fast road and vehicle segmentation in lidar point clouds for autonomous driving. In: 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 926\u2013932 (2020). https:\/\/doi.org\/10.1109\/IV47402.2020.9304694","DOI":"10.1109\/IV47402.2020.9304694"},{"key":"1643_CR5","doi-asserted-by":"publisher","unstructured":"Cortinhal, T., Tzelepis, G., Erdal\u00a0Aksoy, E.: Salsanext: Fast, uncertainty-aware semantic segmentation of lidar point clouds. In: Advances in Visual Computing: 15th International Symposium, ISVC 2020, San Diego, CA, USA, October 5-7, 2020, Proceedings, Part II, pp. 207\u2013222. Springer, Berlin, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-030-64559-5_16","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"1643_CR6","first-page":"1","volume-title":"Computer Vision - ECCV 2020","author":"C Xu","year":"2020","unstructured":"Xu, C., Wu, B., Wang, Z., Zhan, W., Vajda, P., Keutzer, K., Tomizuka, M.: Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) Computer Vision - ECCV 2020, pp. 1\u201319. Springer, Cham (2020)"},{"key":"1643_CR7","doi-asserted-by":"publisher","unstructured":"Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet ++: Fast and accurate lidar semantic segmentation. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4213\u20134220 (2019). https:\/\/doi.org\/10.1109\/IROS40897.2019.8967762","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"1643_CR8","doi-asserted-by":"publisher","unstructured":"Liu, Y., Chen, R., Li, X., Kong, L., Yang, Y., Xia, Z., Bai, Y., Zhu, X., Ma, Y., Li, Y., Qiao, Y., Hou, Y.: UniSeg: a unified multi-modal LiDAR segmentation network and the OpenPCSeg Codebase. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 21605\u201321616. IEEE Computer Society, Los Alamitos, CA, USA (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01980","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"1643_CR9","unstructured":"Xu, X., Kong, L., Shuai, H., Liu, Q.: FRNet: Frustum-range networks for scalable LiDAR segmentation (2024). arxiv:2312.04484"},{"key":"1643_CR10","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C., Deschaud, J.-E., Marcotegui, B., Goulette, F., Guibas, L.J.: Kpconv: flexible and deformable convolution for point clouds. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6410\u20136419 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"1643_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127940","volume":"597","author":"Y Bai","year":"2024","unstructured":"Bai, Y., Li, G., Yang, C., Li, Y., Xiao, Q., Li, Z.: Differential graph convolution network for point cloud understanding. Neurocomputing 597, 127940 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2024.127940","journal-title":"Neurocomputing"},{"key":"1643_CR12","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space (2017). arxiv:1706.02413"},{"key":"1643_CR13","doi-asserted-by":"publisher","unstructured":"Kong, L., Liu, Y., Chen, R., Ma, Y., Zhu, X., Li, Y., Hou, Y., Qiao, Y., Liu, Z.: Rethinking range view representation for lidar segmentation. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 228\u2013240 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00028","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"1643_CR14","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.neuroimage.2016.01.024","volume":"129","author":"J Kleesiek","year":"2016","unstructured":"Kleesiek, J., Urban, G., Hubert, A., Schwarz, D., Maier-Hein, K., Bendszus, M., Biller, A.: Deep MRI brain extraction: a 3D convolutional neural network for skull stripping. NeuroImage 129, 460\u2013469 (2016). https:\/\/doi.org\/10.1016\/j.neuroimage.2016.01.024","journal-title":"NeuroImage"},{"key":"1643_CR15","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation (2016). arxiv:1606.06650","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"1643_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection (2017). arXiv:1711.06396","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1643_CR17","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: Deep learning on point sets for 3D classification and segmentation (2017). arXiv:1612.00593"},{"key":"1643_CR18","doi-asserted-by":"publisher","unstructured":"Bai, L., Lyu, Y., Xu, X., Huang, X.: Pointnet on FPGA for real-time lidar point cloud processing. In: 2020 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20135 (2020). https:\/\/doi.org\/10.1109\/ISCAS45731.2020.9180841","DOI":"10.1109\/ISCAS45731.2020.9180841"},{"key":"1643_CR19","unstructured":"Zhang, X., Huang, Z., Antony, G.G., Jachimczyk, W., Huang, X.: Stream-based ground segmentation for real-time LiDAR point cloud processing on FPGA (2024). arXiv:2408.10410"},{"key":"1643_CR20","doi-asserted-by":"publisher","unstructured":"Zhang, X., Huang, Z., Antony, G.G., Jachimczyk, W., Huang, X.: Parallel processing of point cloud ground segmentation for mechanical and solid-state lidars. CoRR arXiv:2408.10404 (2024) https:\/\/doi.org\/10.48550\/ARXIV.2408.10404","DOI":"10.48550\/ARXIV.2408.10404"},{"issue":"1","key":"1643_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/electronics11010011","volume":"11","author":"X Xie","year":"2021","unstructured":"Xie, X., Bai, L., Huang, X.: Real-time lidar point cloud semantic segmentation for autonomous driving. Electronics 11(1), 11 (2021)","journal-title":"Electronics"},{"key":"1643_CR22","unstructured":"Delgado, P.P.F.: Real-time implementation of 3D LiDAR point cloud semantic segmentation in an FPGA (2022)"},{"key":"1643_CR23","doi-asserted-by":"publisher","unstructured":"Bai, L., Zhao, Y., Huang, X.: A near sensor edge computing system for point cloud semantic segmentation. In: 2022 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1818\u20131822 (2022). https:\/\/doi.org\/10.1109\/ISCAS48785.2022.9937678","DOI":"10.1109\/ISCAS48785.2022.9937678"},{"key":"1643_CR24","unstructured":"Xilinx, I.: Vitis AI Model Zoo: Reference Guide. (2024). Accessed: 2024-12-14. https:\/\/xilinx.github.io\/Vitis-AI\/3.0\/html\/docs\/reference\/ModelZoo_VAI3.0_Github_web.htm"},{"key":"1643_CR25","unstructured":"NVDLA: Open Source Deep Learning Inference Accelerator. https:\/\/nvdla.org. Accessed: 2025-02-02"},{"key":"1643_CR26","unstructured":"Xilinx Deep Learning Processor Unit (DPU). https:\/\/docs.amd.com\/r\/3.3-English\/pg338-dpu. Accessed: 2025-02-02"},{"key":"1643_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"1643_CR28","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). arXiv:1706.05587"},{"key":"1643_CR29","doi-asserted-by":"crossref","unstructured":"Yi, L., Gong, B., Funkhouser, T.: Complete & Label: a domain adaptation approach to semantic segmentation of LiDAR point clouds (2021). arXiv:2007.08488","DOI":"10.1109\/CVPR46437.2021.01511"},{"key":"1643_CR30","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhou, X., Zhao, S., Yue, X., Keutzer, K.: SqueezeSegV2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud (2018). arXiv:1809.08495","DOI":"10.1109\/ICRA.2019.8793495"},{"key":"1643_CR31","doi-asserted-by":"crossref","unstructured":"Saleh, K., Abobakr, A., Attia, M., Iskander, J., Nahavandi, D., Hossny, M.: Domain adaptation for vehicle detection from bird\u2019s eye view LiDAR point cloud data (2019). arXiv:1905.08955","DOI":"10.1109\/ICCVW.2019.00404"},{"key":"1643_CR32","unstructured":"Qin, C., You, H., Wang, L., Kuo, C.-C.J., Fu, Y.: Pointdan: A multi-scale 3D domain adaption network for point cloud representation. In: Wallach, H., Larochelle, H., Beygelzimer, A., Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc., Red Hook (2019)"},{"key":"1643_CR33","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., Blaschko, M.B.: The Lov\u00e1sz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks (2018). arXiv:1705.08790","DOI":"10.1109\/CVPR.2018.00464"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01643-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01643-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01643-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T06:23:43Z","timestamp":1746253423000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01643-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1643"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01643-9","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"assertion":[{"value":"22 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"78"}}