{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:31:06Z","timestamp":1776443466835,"version":"3.51.2"},"reference-count":56,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T00:00:00Z","timestamp":1689811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52002285"],"award-info":[{"award-number":["52002285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21ZR1467400"],"award-info":[{"award-number":["21ZR1467400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22120220593"],"award-info":[{"award-number":["22120220593"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2023NSCQ-MSX4511"],"award-info":[{"award-number":["2023NSCQ-MSX4511"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["52002285"],"award-info":[{"award-number":["52002285"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["21ZR1467400"],"award-info":[{"award-number":["21ZR1467400"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["22120220593"],"award-info":[{"award-number":["22120220593"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Science and Technology Commission","doi-asserted-by":"publisher","award":["2023NSCQ-MSX4511"],"award-info":[{"award-number":["2023NSCQ-MSX4511"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"original research project of Tongji University","award":["52002285"],"award-info":[{"award-number":["52002285"]}]},{"name":"original research project of Tongji University","award":["21ZR1467400"],"award-info":[{"award-number":["21ZR1467400"]}]},{"name":"original research project of Tongji University","award":["22120220593"],"award-info":[{"award-number":["22120220593"]}]},{"name":"original research project of Tongji University","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}]},{"name":"original research project of Tongji University","award":["2023NSCQ-MSX4511"],"award-info":[{"award-number":["2023NSCQ-MSX4511"]}]},{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["52002285"],"award-info":[{"award-number":["52002285"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["21ZR1467400"],"award-info":[{"award-number":["21ZR1467400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["22120220593"],"award-info":[{"award-number":["22120220593"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["2023NSCQ-MSX4511"],"award-info":[{"award-number":["2023NSCQ-MSX4511"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Chongqing","award":["52002285"],"award-info":[{"award-number":["52002285"]}]},{"name":"Natural Science Foundation of Chongqing","award":["21ZR1467400"],"award-info":[{"award-number":["21ZR1467400"]}]},{"name":"Natural Science Foundation of Chongqing","award":["22120220593"],"award-info":[{"award-number":["22120220593"]}]},{"name":"Natural Science Foundation of Chongqing","award":["2021YFB2501104"],"award-info":[{"award-number":["2021YFB2501104"]}]},{"name":"Natural Science Foundation of Chongqing","award":["2023NSCQ-MSX4511"],"award-info":[{"award-number":["2023NSCQ-MSX4511"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Vision-based identification of lane area and lane marking on the road is an indispensable function for intelligent driving vehicles, especially for localization, mapping and planning tasks. However, due to the increasing complexity of traffic scenes, such as occlusion and discontinuity, detecting lanes and lane markings from an image captured by a monocular camera becomes persistently challenging. The lanes and lane markings have a strong position correlation and are constrained by a spatial geometry prior to the driving scene. Most existing studies only explore a single task, i.e., either lane marking or lane detection, and do not consider the inherent connection or exploit the modeling of this kind of relationship between both elements to improve the detection performance of both tasks. In this paper, we establish a novel multi-task encoder\u2013decoder framework for the simultaneous detection of lanes and lane markings. This approach deploys a dual-branch architecture to extract image information from different scales. By revealing the spatial constraints between lanes and lane markings, we propose an interactive attention learning for their feature information, which involves a Deformable Feature Fusion module for feature encoding, a Cross-Context module as information decoder, a Cross-IoU loss and a Focal-style loss weighting for robust training. Without bells and whistles, our method achieves state-of-the-art results on tasks of lane marking detection (with 32.53% on IoU, 81.61% on accuracy) and lane segmentation (with 91.72% on mIoU) of the BDD100K dataset, which showcases an improvement of 6.33% on IoU, 11.11% on accuracy in lane marking detection and 0.22% on mIoU in lane detection compared to the previous methods.<\/jats:p>","DOI":"10.3390\/s23146545","type":"journal-article","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T05:42:01Z","timestamp":1689831721000},"page":"6545","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Interactive Attention Learning on Detection of Lane and Lane Marking on the Road by Monocular Camera Image"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5085-7219","authenticated-orcid":false,"given":"Wei","family":"Tian","sequence":"first","affiliation":[{"name":"Tongji University, Shanghai 201804, China"}]},{"given":"Xianwang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai 201804, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9828-5790","authenticated-orcid":false,"given":"Haohao","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Measurement and Control Systems, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,20]]},"reference":[{"key":"ref_1","unstructured":"HERE (2022, December 01). HERE HD Live Map: The Most Intelligent Sensor for Autonomous Driving. Available online: https:\/\/www.here.com\/platform\/automotive-services\/hd-maps."},{"key":"ref_2","unstructured":"TomTom (2022, December 01). HD Maps\u2014Highly Accurate Border-to-Border Model of the Road. Available online: https:\/\/www.tomtom.com\/products\/hd-map."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Homayounfar, N., Ma, W.C., Liang, J., Wu, X., Fan, J., and Urtasun, R. (2019, January 15\u201320). DAGmapper: Learning to map by discovering lane topology. Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/ICCV.2019.00300"},{"key":"ref_4","unstructured":"Chiu, K.Y., and Lin, S.F. (2005, January 6\u20138). Lane detection using color-based segmentation. Proceedings of the IEEE Intelligent Vehicles Symposium, Las Vegas, NV, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/LES.2010.2051412","article-title":"Hierarchical additive Hough transform for lane detection","volume":"2","author":"Satzoda","year":"2010","journal-title":"IEEE Embed. Syst. Lett."},{"key":"ref_6","unstructured":"Hou, Y., Ma, Z., Liu, C., and Loy, C.C. (November, January 27). Learning lightweight lane detection cnns by self attention distillation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liu, Q., and Lian, C. (2019, January 9\u201312). Pointlanenet: Efficient end-to-end cnns for accurate real-time lane detection. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Paris, France.","DOI":"10.1109\/IVS.2019.8813778"},{"key":"ref_8","first-page":"102851","article-title":"Vision-based mapping of lane semantics and topology for intelligent vehicles","volume":"111","author":"Tian","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pan, X., Shi, J., Luo, P., Wang, X., and Tang, X. (2018, January 2\u20137). Spatial as deep: Spatial cnn for traffic scene understanding. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.12301"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zheng, T., Fang, H., Zhang, Y., Tang, W., Yang, Z., Liu, H., and Cai, D. (2021, January 2\u20139). Resa: Recurrent feature-shift aggregator for lane detection. Proceedings of the AAAI Conference on Artificial Intelligence, Online.","DOI":"10.1609\/aaai.v35i4.16469"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/TITS.2019.2890870","article-title":"Line-cnn: End-to-end traffic line detection with line proposal unit","volume":"21","author":"Li","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Tabelini, L., Berriel, R., Paixao, T.M., Badue, C., De Souza, A.F., and Oliveira-Santos, T. (2021, January 20\u201325). Keep your eyes on the lane: Real-time attention-guided lane detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00036"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tabelini, L., Berriel, R., Paixao, T.M., Badue, C., De Souza, A.F., and Oliveira-Santos, T. (2021, January 20\u201324). Polylanenet: Lane estimation via deep polynomial regression. Proceedings of the International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR48806.2021.9412265"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, R., Yuan, Z., Liu, T., and Xiong, Z. (2021, January 5\u20139). End-to-end lane shape prediction with transformers. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Online.","DOI":"10.1109\/WACV48630.2021.00374"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, S., Tan, X., Xu, K., Wang, M., and Ma, L. (2022, January 18\u201324). Rethinking Efficient Lane Detection via Curve Modeling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01655"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., and Darrell, T. (2020, January 13\u201319). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref_17","unstructured":"(2022, December 01). TuSimple. Available online: http:\/\/benchmark.tusimple.ai\/."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Loose, H., Franke, U., and Stiller, C. (2009, January 3\u20135). Kalman particle filter for lane recognition on rural roads. Proceedings of the IEEE Intelligent Vehicles Symposium, Xi\u2019an, China.","DOI":"10.1109\/IVS.2009.5164253"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Teng, Z., Kim, J.H., and Kang, D.J. (2010, January 27\u201330). Real-time lane detection by using multiple cues. Proceedings of the International Conference on Control Automation and Systems (ICCAS 2010), Suwon, Republic of Korea.","DOI":"10.1109\/ICCAS.2010.5669923"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aly, M. (2008, January 4\u20136). Real time detection of lane markers in urban streets. Proceedings of the IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands.","DOI":"10.1109\/IVS.2008.4621152"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Assidiq, A.A., Khalifa, O.O., Islam, M.R., and Khan, S. (2008, January 13\u201315). Real time lane detection for autonomous vehicles. Proceedings of the International Conference on Computer and Communication Engineering, Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICCCE.2008.4580573"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2920","DOI":"10.1109\/TGRS.2018.2878510","article-title":"Aerial LaneNet: Lane-marking semantic segmentation in aerial imagery using wavelet-enhanced cost-sensitive symmetric fully convolutional neural networks","volume":"57","author":"Azimi","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","first-page":"102677","article-title":"Road marking extraction in UAV imagery using attentive capsule feature pyramid network","volume":"107","author":"Guan","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xu, H., Wang, S., Cai, X., Zhang, W., Liang, X., and Li, Z. (2020, January 23\u201328). Curvelane-nas: Unifying lane-sensitive architecture search and adaptive point blending. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58555-6_41"},{"key":"ref_25","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, H., and Li, X. (2020, January 23\u201328). Ultra fast structure-aware deep lane detection. Proceedings of the European Conference on Computer Vision, Glasgow, UK.","DOI":"10.1007\/978-3-030-58586-0_17"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Yoo, S., Lee, H.S., Myeong, H., Yun, S., Park, H., Cho, J., and Kim, D.H. (2020, January 14\u201319). End-to-end lane marker detection via row-wise classification. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00511"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, L., Chen, X., Zhu, S., and Tan, P. (2021, January 11\u201317). Condlanenet: A top-to-down lane detection framework based on conditional convolution. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00375"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wang, L., Chi, Y., Shen, T., Song, J., Gao, J., and Shen, S. (2023). Dynamic Data Augmentation Based on Imitating Real Scene for Lane Line Detection. Remote Sens., 15.","DOI":"10.3390\/rs15051212"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_33","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21\u201326). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3230846","article-title":"Swin Transformer Embedding UNet for Remote Sensing Image Semantic Segmentation","volume":"60","author":"He","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","first-page":"1","article-title":"Moving object segmentation and detection for robust RGBD-SLAM in dynamic environments","volume":"70","author":"Xie","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Meyer, A., Salscheider, N.O., Orzechowski, P.F., and Stiller, C. (2018, January 1\u20135). Deep semantic lane segmentation for mapless driving. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.","DOI":"10.1109\/IROS.2018.8594450"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27\u201330). The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sun, T., Di, Z., Che, P., Liu, C., and Wang, Y. (2019, January 15\u201320). Leveraging crowdsourced GPS data for road extraction from aerial imagery. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00769"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1109\/TIM.2013.2289091","article-title":"Vision-based robust path reconstruction for robot control","volume":"63","author":"Fontanelli","year":"2013","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Teichmann, M., Weber, M., Zoellner, M., Cipolla, R., and Urtasun, R. (2018, January 26\u201330). Multinet: Real-time joint semantic reasoning for autonomous driving. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Suzhou, China.","DOI":"10.1109\/IVS.2018.8500504"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4670","DOI":"10.1109\/TITS.2019.2943777","article-title":"DLT-Net: Joint detection of drivable areas, lane lines, and traffic objects","volume":"21","author":"Qian","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chen, Z., and Chen, Z. (2017, January 4\u20139). Rbnet: A deep neural network for unified road and road boundary detection. Proceedings of the International Conference on Neural Information Processing, Long Beach, CA, USA.","DOI":"10.1007\/978-3-319-70087-8_70"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, J., Xu, Y., Ni, B., and Duan, Z. (2018, January 8\u201314). Geometric constrained joint lane segmentation and lane boundary detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01246-5_30"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1109\/TGRS.2018.2870871","article-title":"RoadNet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images","volume":"57","author":"Liu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Meng, Z., Xia, X., Xu, R., Liu, W., and Ma, J. (2023). HYDRO-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D LiDAR. IEEE Trans. Intell. Veh., 1\u201313.","DOI":"10.1109\/TIV.2023.3282567"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"104120","DOI":"10.1016\/j.trc.2023.104120","article-title":"An automated driving systems data acquisition and analytics platform","volume":"151","author":"Xia","year":"2023","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18\u201324). A convnet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wu, D., Liao, M., Zhang, W., and Wang, X. (2021). Yolop: You only look once for panoptic driving perception. arXiv.","DOI":"10.1007\/s11633-022-1339-y"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017, January 22\u201329). Deformable convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.A. (2016, January 25\u201328). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Rahman, M.A., and Wang, Y. (2016, January 12\u201314). Optimizing intersection-over-union in deep neural networks for image segmentation. Proceedings of the International Symposium on Visual Computing, Las Vegas, NV, USA.","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"ref_54","unstructured":"Paszke, A., Chaurasia, A., Kim, S., and Culurciello, E. (2016). Enet: A deep neural network architecture for real-time semantic segmentation. arXiv."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","article-title":"Erfnet: Efficient residual factorized convnet for real-time semantic segmentation","volume":"19","author":"Romera","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6545\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:15:30Z","timestamp":1760127330000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":56,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23146545"],"URL":"https:\/\/doi.org\/10.3390\/s23146545","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]}}}