{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T09:00:16Z","timestamp":1766221216190,"version":"3.48.0"},"reference-count":30,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Line segment detection can offer essential technical assistance for various visual tasks, aiding computer systems in comprehending image content more effectively and executing advanced analysis and applications. Focusing on the fact that most current line segment detection methods predict the center and the displacement maps of two endpoints of a line segment separately without exploiting the coupling between them, this article proposed a dynamic label assignment strategy and an improved deformable convolution for center prediction using displacement priors, which enhances the model\u2019s line segment sensing capability and effectively improves the detection performance. The predicted displacements are used as\n                    <jats:italic>a priori<\/jats:italic>\n                    information to guide the centroid label assignment and deformable convolution sampling of center branches, which significantly improves the performance of centroid prediction. In addition, HRNet and UNet3+ are introduced to enhance the feature expression capability of the backbone network. Finally, experiments show that the\n                    <jats:inline-formula>\n                      <jats:alternatives>\n                        <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"graphic\/j_comp-2025-0035_eq_001.png\"\/>\n                        <m:math xmlns:m=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                          <m:mi>s<\/m:mi>\n                          <m:mi>A<\/m:mi>\n                          <m:msup>\n                            <m:mrow>\n                              <m:mi>P<\/m:mi>\n                            <\/m:mrow>\n                            <m:mrow>\n                              <m:mn>10<\/m:mn>\n                            <\/m:mrow>\n                          <\/m:msup>\n                        <\/m:math>\n                        <jats:tex-math>sA{P}^{10}<\/jats:tex-math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    metrics of the proposed one-stage model are 0.8 and 6.6% higher than  those of the two-stage model efficient line segment detector and descriptor with the best performance in line segment detection on the Wireframe dataset and YorkUrban dataset, respectively.\n                  <\/jats:p>","DOI":"10.1515\/comp-2025-0035","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T11:37:25Z","timestamp":1756467445000},"source":"Crossref","is-referenced-by-count":0,"title":["Line segment using displacement prior"],"prefix":"10.1515","volume":"15","author":[{"given":"Xin","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics , Nanjing , 211106 , P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hancheng","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics , Nanjing , 211106 , P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupu","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics , Nanjing , 211106 , P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics , Nanjing , 211106 , P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"2025122008514880506_j_comp-2025-0035_ref_001","doi-asserted-by":"crossref","unstructured":"R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2014, pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"2025122008514880506_j_comp-2025-0035_ref_002","doi-asserted-by":"crossref","unstructured":"J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"2025122008514880506_j_comp-2025-0035_ref_003","doi-asserted-by":"crossref","unstructured":"W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Fu, et al., \u201cSsd: Single shot multibox detector,\u201d In: Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2025122008514880506_j_comp-2025-0035_ref_004","doi-asserted-by":"crossref","unstructured":"M. Bai, and R. Urtasun, \u201cDeep watershed transform for instance segmentation,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 5221\u20135229.","DOI":"10.1109\/CVPR.2017.305"},{"key":"2025122008514880506_j_comp-2025-0035_ref_005","doi-asserted-by":"crossref","unstructured":"S. Peng, W. Jiang, H. Pi, H. Bao, and X. Zhou, \u201cDeep snake for real-time instance segmentation,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 8533\u20138542.","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"2025122008514880506_j_comp-2025-0035_ref_006","doi-asserted-by":"crossref","unstructured":"P. Denis, J. H. Elder, and F. J. Estrada, \u201cEfficient edge-based methods for estimating manhattan frames in urban imagery,\u201d In: Proc. Eur. Conf. Comput. Vis. (ECCV), 2008, pp. 197\u2013210.","DOI":"10.1007\/978-3-540-88688-4_15"},{"key":"2025122008514880506_j_comp-2025-0035_ref_007","unstructured":"Y. Zhou, J. Huang, X. Dai, L. Luo, Z. Chen, and Y. Ma, HoliCity: A city-scale data platform for learning holistic 3D structures, 2020, arXiv:2008.03286."},{"key":"2025122008514880506_j_comp-2025-0035_ref_008","doi-asserted-by":"crossref","unstructured":"Y. Zhou, H. Qi, Y. Zhai, Q. Sun, Z. Chen, and L. Y. Wei, \u201cLearning to reconstruct 3d manhattan wireframes from a single image,\u201d In: Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 7698\u20137707.","DOI":"10.1109\/ICCV.2019.00779"},{"key":"2025122008514880506_j_comp-2025-0035_ref_009","doi-asserted-by":"crossref","unstructured":"B. P\u0159ibyl, P. Zem\u00e7\u00edk, and M. \u010cad\u00edk, \u201cAbsolute pose estimation from line correspondences using direct linear transformation,\u201d Comput vis Image UND., vol. 161, pp. 130\u2013144, Aug. 2017.","DOI":"10.1016\/j.cviu.2017.05.002"},{"key":"2025122008514880506_j_comp-2025-0035_ref_010","doi-asserted-by":"crossref","unstructured":"C. Xu, L. Zhang, L. Cheng, and R. Koch, \u201cPose estimation from line correspondences: A complete analysis and a series of solutions,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, pp. 1209\u20131222, 2016.","DOI":"10.1109\/TPAMI.2016.2582162"},{"key":"2025122008514880506_j_comp-2025-0035_ref_011","doi-asserted-by":"crossref","unstructured":"A. Elqursh, and A. Elgammal, \u201cLine-based relative pose estimation,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2011, pp. 3049\u20133056.","DOI":"10.1109\/CVPR.2011.5995512"},{"key":"2025122008514880506_j_comp-2025-0035_ref_012","doi-asserted-by":"crossref","unstructured":"N. Xue, G. S. Xia, X. Bai, L. Zhang, and W. Shen, \u201cAnisotropic-scale junction detection and matching for indoor images,\u201d IEEE Trans. Image Process., vol. 27, pp. 78\u201391, 2017.","DOI":"10.1109\/TIP.2017.2754945"},{"key":"2025122008514880506_j_comp-2025-0035_ref_013","unstructured":"Y. Zhou, H. Qi, J. Huang, and Y. Ma, \u201cNeurvps: Neural vanishing point scanning via conic convolution,\u201d In: Proc. Adv. Neural Inform. Process. Syst. (NeurIPS), vol. 32, 2019."},{"key":"2025122008514880506_j_comp-2025-0035_ref_014","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, and A N Gomez, et al., \u201cAttention is all you need,\u201d In: Proc. Adv. Neural Inform. Process. Syst. (NeurIPS), vol. 30, 2017, pp. 6000\u20136010."},{"key":"2025122008514880506_j_comp-2025-0035_ref_015","doi-asserted-by":"crossref","unstructured":"K. Huang, Y. Wang, Z. Zhou, T. Ding, S. Gao, and Y. Ma, \u201cLearning to parse wireframes in images of man-made environments,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 626\u2013635.","DOI":"10.1109\/CVPR.2018.00072"},{"key":"2025122008514880506_j_comp-2025-0035_ref_016","doi-asserted-by":"crossref","unstructured":"Y. Zhou, H. Qi, and Y. Ma, \u201cEnd-to-end wireframe parsing,\u201d In: Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), 2019, pp. 962\u2013971.","DOI":"10.1109\/ICCV.2019.00105"},{"key":"2025122008514880506_j_comp-2025-0035_ref_017","doi-asserted-by":"crossref","unstructured":"N. Xue, T. Wu, S. Bai, F. Wang, G. S. Xia, and L. Zhang, et al., \u201cHolistically-attracted wireframe parsing,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 2788\u20132797.","DOI":"10.1109\/CVPR42600.2020.00286"},{"key":"2025122008514880506_j_comp-2025-0035_ref_018","doi-asserted-by":"crossref","unstructured":"Y. Xu, W. Xu, D. Cheung, and Z. Tu, \u201cLine segment detection using transformers without edges,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 4257\u20134266.","DOI":"10.1109\/CVPR46437.2021.00424"},{"key":"2025122008514880506_j_comp-2025-0035_ref_019","doi-asserted-by":"crossref","unstructured":"X. Zhou, D. Wang, and P. Kr\u00e4henb\u00fchl, Objects as points, 2019, arXiv:1904.07850.","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"2025122008514880506_j_comp-2025-0035_ref_020","doi-asserted-by":"crossref","unstructured":"S. Huang, F. Qin, P. Xiong, N. Ding, Y. He, and X. Liu, \u201cTP-LSD: Tri-points based line segment detector,\u201d In: Proc. Eur. Conf. Comput. Vis. (ECCV), 2020, pp. 770\u2013785.","DOI":"10.1007\/978-3-030-58583-9_46"},{"key":"2025122008514880506_j_comp-2025-0035_ref_021","doi-asserted-by":"crossref","unstructured":"X. Dai, H. Gong, S. Wu, X. Yuan, and Y. Ma, \u201cFully convolutional line parsing,\u201d Neurocomputing., vol. 506, pp. 1\u201311, 2022.","DOI":"10.1016\/j.neucom.2022.07.026"},{"key":"2025122008514880506_j_comp-2025-0035_ref_022","doi-asserted-by":"crossref","unstructured":"H. Zhang, Y. Luo, F. Qin, Y. He, and X. Liu, \u201cELSD: Efficient line segment detector and descriptor,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 2969\u20132978.","DOI":"10.1109\/ICCV48922.2021.00296"},{"key":"2025122008514880506_j_comp-2025-0035_ref_023","doi-asserted-by":"crossref","unstructured":"G. Gu, B. Ko, S. H. Go, S. H. Lee, J. Lee, and M. Shin, \u201cTowards light-weight and real-time line segment detection,\u201d In: Proc. AAAI Conf. Artif. Intell., 2022, pp. 726\u2013734.","DOI":"10.1609\/aaai.v36i1.19953"},{"key":"2025122008514880506_j_comp-2025-0035_ref_024","unstructured":"F. Yu, and V. Koltun, Multi-scale context aggregation by dilated convolutions, 2015, arXiv:1511. 07122."},{"key":"2025122008514880506_j_comp-2025-0035_ref_025","doi-asserted-by":"crossref","unstructured":"J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, and H. Hu, \u201cDeformable convolutional networks,\u201d In: Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV), 2017, pp. 764\u2013773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"2025122008514880506_j_comp-2025-0035_ref_026","doi-asserted-by":"crossref","unstructured":"S. U. Rehman, S. Tu, O. U. Rehman, Y. Huang, C. M. S. Magurawalage, and C. C. Chang, \u201cOptimization of CNN through novel training strategy for visual classification problems,\u201d Entropy., vol. 20, 2018, id. 290.","DOI":"10.3390\/e20040290"},{"key":"2025122008514880506_j_comp-2025-0035_ref_027","doi-asserted-by":"crossref","unstructured":"S. U. Rehman, S. Tu, M. Waqas, Y. F. Huang, O. U. Rehman, and B. Ahmad, et al., \u201cUnsupervised pre-trained filter learning approach for efficient convolution neural network,\u201d Neurocomputing, vol. 365, pp. 171\u2013190, 2019.","DOI":"10.1016\/j.neucom.2019.06.084"},{"key":"2025122008514880506_j_comp-2025-0035_ref_028","doi-asserted-by":"crossref","unstructured":"J. Wang, K. Sun, T. Cheng, B. Jiang, C. Deng, and Y. Zhao, et al., \u201cDeep high-resolution representation learning for visual recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, pp. 3349\u20133364, 2020.","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"2025122008514880506_j_comp-2025-0035_ref_029","doi-asserted-by":"crossref","unstructured":"H. Huang, L. Lin, R. Tong, H. Hu, Q. Zhang, and Y. Iwamoto, et al., \u201cUnet 3.: A full-scale connected unet for medical image segmentation,\u201d In:Proc. ICASSP., 2020, pp. 1055\u20131059.","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"2025122008514880506_j_comp-2025-0035_ref_030","doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Chen, \u201cMobilenetv2: Inverted residuals and linear bottlenecks,\u201d In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Open Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0035\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0035\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:57:29Z","timestamp":1766221049000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/comp-2025-0035\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,1]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,9,17]]},"published-print":{"date-parts":[[2025,9,17]]}},"alternative-id":["10.1515\/comp-2025-0035"],"URL":"https:\/\/doi.org\/10.1515\/comp-2025-0035","relation":{},"ISSN":["2299-1093"],"issn-type":[{"type":"electronic","value":"2299-1093"}],"subject":[],"published":{"date-parts":[[2025,1,1]]},"article-number":"20250035"}}