{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:48:18Z","timestamp":1776678498009,"version":"3.51.2"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104588","type":"print"},{"value":"9783032104595","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-10459-5_24","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:07:07Z","timestamp":1763190427000},"page":"298-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FPGA-Accelerated CNN-Transformer Hybrid Model for\u00a0Real-Time Semantic Segmentation in\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Ao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjiang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingzeng","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"issue":"12","key":"24_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR2","doi-asserted-by":"publisher","unstructured":"Blevec, H.L., L\u00e9onardon, M., Tessier, H., Arzel, M.: Pipelined architecture for a semantic segmentation neural network on fpga. In: 2023 30th IEEE International Conference on Electronics, Circuits and Systems (ICECS), pp.\u00a01\u20134. Istanbul, Turkiye (2023). https:\/\/doi.org\/10.1109\/ICECS58634.2023.10382715","DOI":"10.1109\/ICECS58634.2023.10382715"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder\u2013decoder with atrous separable convolution for semantic image segmentation. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"4","key":"24_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, ATROUS convolution, and fully connected CRFS. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Jiang, J., Ma, Y.: An FPGA-based lightweight semantic segmentation neural network with optimized ghost module. IEEE Internet Things J. (2024)","DOI":"10.1109\/JIOT.2024.3391248"},{"issue":"6","key":"24_CR6","doi-asserted-by":"publisher","first-page":"3258","DOI":"10.1109\/TITS.2020.2980426","volume":"22","author":"G Dong","year":"2020","unstructured":"Dong, G., Yan, Y., Shen, C., Wang, H.: Real-time high-performance semantic image segmentation of urban street scenes. IEEE Trans. Intell. Transp. Syst. 22(6), 3258\u20133274 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"24_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"24_CR8","unstructured":"Fu, J., et\u00a0al.: Dual attention network for scene segmentation. In: Proc. IEEE\/CVF Conf. Comput. Vis. Patt. Recognit. (CVPR), pp. 3146\u20133154 (2019)"},{"issue":"16","key":"24_CR9","doi-asserted-by":"publisher","first-page":"2962","DOI":"10.3390\/rs16162962","volume":"16","author":"X Gao","year":"2024","unstructured":"Gao, X., Wu, B., Li, P., Jing, Z.: 1d-CNN-transformer for radar emitter identification and implemented on FPGA. Remote Sensing 16(16), 2962 (2024)","journal-title":"Remote Sensing"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Ghielmetti, N., et al.: Real-time semantic segmentation on Fpgas for autonomous vehicles with hls4ml (2022). https:\/\/arxiv.org\/abs\/2205.07690","DOI":"10.1088\/2632-2153\/ac9cb5"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Le\u00a0Blevec, H., L\u00e9onardon, M., Weithoffer, S., Arzel, M.: Fpga-oriented design space exploration of a real-time road scene semantic segmentation deep neural network. In: Proceedings of the 2025 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays, pp. 54\u201354 (2025)","DOI":"10.1145\/3706628.3708862"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: Espnet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp. 552\u2013568 (2018)","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Shapiro, L., Hajishirzi, H.: Espnetv2: a light-weight, power efficient, and general purpose convolutional neural network. In: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 9190\u20139200 (2019)","DOI":"10.1109\/CVPR.2019.00941"},{"key":"24_CR15","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Shaker, A.M., Maaz, M., Rasheed, H., Khan, S., Yang, M.H., Khan, F.S.: Unetr++: delving into efficient and accurate 3d medical image segmentation. IEEE Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3398728"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Shen, T., Zuo, Y., Zheng, H., Zhang, L., Hu, C., Liu, H.: Fpga-accelerated semantic segmentation for urban scenes. In: 2024 2nd International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT), pp. 84\u201389. IEEE (2024)","DOI":"10.1109\/MVIPIT65697.2024.00014"},{"key":"24_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105605","volume":"88","author":"H Tang","year":"2024","unstructured":"Tang, H., et al.: Htc-net: a hybrid CNN-transformer framework for medical image segmentation. Biomed. Signal Process. Control 88, 105605 (2024)","journal-title":"Biomed. Signal Process. Control"},{"key":"24_CR19","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. In: Proc. Conf. Neural Inf. Process. Syst. (NeurIPS). vol.\u00a034, pp. 12077\u201312090 (2021)"},{"issue":"11","key":"24_CR20","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129(11), 3051\u20133068 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: bilateral segmentation network for real-time semantic segmentation. In: Proc. Eur. Conf. Comput. Vis. (ECCV), pp. 325\u2013341 (2018)","DOI":"10.1007\/978-3-030-01261-8_20"},{"issue":"5s","key":"24_CR22","first-page":"1","volume":"20","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Wu, Y., Zhou, P., Tang, X., Hu, J.: Algorithm-hardware co-design of attention mechanism on Fpga devices. ACM Trans. Embedded Comput. Syst. (TECS) 20(5s), 1\u201324 (2021)","journal-title":"ACM Trans. Embedded Comput. Syst. (TECS)"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10459-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T08:54:30Z","timestamp":1776675270000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10459-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104588","9783032104595"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10459-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}