{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:31:02Z","timestamp":1775579462035,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030033972","type":"print"},{"value":"9783030033989","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-03398-9_30","type":"book-chapter","created":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T09:12:41Z","timestamp":1541063561000},"page":"347-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Large-Scale Structure from Motion with Semantic Constraints of Aerial Images"],"prefix":"10.1007","author":[{"given":"Yu","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yisong","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Guoping","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,2]]},"reference":[{"issue":"3","key":"30_CR1","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1145\/1141911.1141964","volume":"25","author":"SM Seitz","year":"2006","unstructured":"Seitz, S.M., Szeliski, R., Snavely, N.: Photo tourism: exploring photo collections in 3D. ACM Trans. Graph. 25(3), 835\u2013846 (2006)","journal-title":"ACM Trans. Graph."},{"issue":"10","key":"30_CR2","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., Snavely, N., Simon, I.: Building Rome in a day. Commun. ACM 54(10), 105\u2013112 (2011)","journal-title":"Commun. ACM"},{"key":"30_CR3","unstructured":"Snavely, K.N.: Scene Reconstruction and Visualization from Internet Photo Collections. University of Washington (2008)"},{"key":"30_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/978-3-642-15561-1_27","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J-M Frahm","year":"2010","unstructured":"Frahm, J.-M., et al.: Building Rome on a cloudless day. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 368\u2013381. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_27"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Wu, C.: Towards linear-time incremental structure from motion. In: International Conference on 3DTV-Conference. IEEE, pp. 127\u2013134 (2013)","DOI":"10.1109\/3DV.2013.25"},{"key":"30_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-642-37447-0_20","volume-title":"Computer Vision \u2013 ACCV 2012","author":"P Moulon","year":"2013","unstructured":"Moulon, P., Monasse, P., Marlet, R.: Adaptive structure from motion with a\u00a0Contrario model estimation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7727, pp. 257\u2013270. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37447-0_20"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Computer Vision and Pattern Recognition. IEEE (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Sweeney, C., Hollerer, T., Turk, M.: Theia: a fast and scalable structure-from-motion library, pp. 693\u2013696 (2015)","DOI":"10.1145\/2733373.2807405"},{"issue":"6","key":"30_CR9","first-page":"726","volume":"24","author":"MA Fischler","year":"1987","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Read. Comput. Vis. 24(6), 726\u2013740 (1987)","journal-title":"Read. Comput. Vis."},{"key":"30_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/3-540-44480-7_21","volume-title":"Vision Algorithms: Theory and Practice","author":"B Triggs","year":"2000","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment \u2014 a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298\u2013372. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_21"},{"key":"30_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-319-10578-9_5","volume-title":"Computer Vision \u2013 ECCV 2014","author":"K Wilson","year":"2014","unstructured":"Wilson, K., Snavely, N.: Robust global translations with 1DSfM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 61\u201375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_5"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Crandall, D., Owens, A., Snavely, N., et al.: Discrete-continuous optimization for large-scale structure from motion. In: Computer Vision and Pattern Recognition, pp. 3001\u20133008. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995626"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Farenzena, M., Fusiello, A., Gherardi, R.: Structure-and-motion pipeline on a hierarchical cluster tree. In: IEEE International Conference on Computer Vision Workshops. IEEE, 1489\u20131496 (2009)","DOI":"10.1109\/ICCVW.2009.5457435"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Gherardi, R., Farenzena, M., Fusiello, A.: Improving the efficiency of hierarchical structure-and-motion. In: Computer Vision and Pattern Recognition, pp. 1594\u20131600. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539782"},{"key":"30_CR15","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.cviu.2015.05.011","volume":"140","author":"Roberto Toldo","year":"2015","unstructured":"Toldo, R., Gherardi, R., Farenzena, M., et al.: Hierarchical structure-and-motion recovery from uncalibrated images. Comput. Vis. Image Underst. 140(C), 27\u2013143 (2015)","journal-title":"Computer Vision and Image Understanding"},{"key":"30_CR16","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.cviu.2017.02.005","volume":"157","author":"Yisong Chen","year":"2017","unstructured":"Chen, Y., Chan, A.B., Lin, Z., et al.: Efficient tree-structured SfM by RANSAC generalized Procrustes analysis. Comput. Vis. Image Underst. 157(C), 179\u2013189 (2017)","journal-title":"Computer Vision and Image Understanding"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Bao, S.Y., Savarese, S.: Semantic structure from motion. In: Computer Vision and Pattern Recognition, pp. 2025\u20132032. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130358"},{"issue":"10","key":"30_CR18","first-page":"2703","volume":"157","author":"SY Bao","year":"2012","unstructured":"Bao, S.Y., Bagra, M., Chao, Y.W.: Semantic structure from motion with points, regions, and objects. IEEE 157(10), 2703\u20132710 (2012)","journal-title":"IEEE"},{"key":"30_CR19","doi-asserted-by":"crossref","DOI":"10.1561\/9781601988379","volume-title":"Multi-View Stereo: A Tutorial","author":"Y Furukawa","year":"2015","unstructured":"Furukawa, Y.: Multi-View Stereo: A Tutorial. Now Publishers Inc., Hanover (2015)"},{"issue":"9","key":"30_CR20","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.1109\/TPAMI.2016.2613051","volume":"39","author":"C Haene","year":"2016","unstructured":"Haene, C., Zach, C., Cohen, A.: Dense semantic 3D reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1730\u20131743 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Blaha, M., Vogel, C., Richard, A., et al.: Large-scale semantic 3D reconstruction: an adaptive multi-resolution model for multi-class volumetric labeling. In: Computer Vision and Pattern Recognition, pp. 3176\u20133184. IEEE (2016)","DOI":"10.1109\/CVPR.2016.346"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., et al.: A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 573\u2013580. IEEE (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"30_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/978-3-540-88682-2_5","volume-title":"Computer Vision \u2013 ECCV 2008","author":"GJ Brostow","year":"2008","unstructured":"Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 44\u201357. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88682-2_5"},{"key":"30_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Mueller","year":"2016","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445\u2013461. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27"},{"key":"30_CR26","unstructured":"Robicquet, A., Alahi, A., Sadeghian, A., et al.: Forecasting social navigation in crowded complex scenes. arXiv preprint arXiv:1601.00998 (2016)"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Maggiori, E., Tarabalka, Y., Charpiat, G., et al.: Can semantic labeling methods generalize to any city? The inria aerial image labeling benchmark. IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) (2017)","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Xia, G.S., Bai, X., Ding, J., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of CVPR (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"issue":"2","key":"30_CR29","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G., Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"30_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-319-49409-8_13","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"A Salehi","year":"2016","unstructured":"Salehi, A., Gay-Bellile, V., Bourgeois, S., Chausse, F.: Improving constrained bundle adjustment through semantic scene labeling. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 133\u2013142. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_13"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Savinov, N., Ladicky, L., Hane, C., et al.: Discrete optimization of ray potentials for semantic 3d reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5511\u20135518 (2015)","DOI":"10.1109\/CVPR.2015.7299190"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Hne, C., Zach, C., Cohen, A., et al.: Joint 3D scene reconstruction and class segmentation. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 97\u2013104. IEEE (2013)","DOI":"10.1109\/CVPR.2013.20"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR34","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"4","key":"30_CR35","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Cheng, J., Leng, C., Wu, J., et al.: Fast and accurate image matching with cascade hashing for 3D reconstruction. In: Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2014)","DOI":"10.1109\/CVPR.2014.8"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Muja, M.: Fast approximate nearest neighbors with automatic algorithm configuration. In: International Conference on Computer Vision Theory and Application VISSAPP, pp. 331\u2013340 (2009)","DOI":"10.5220\/0001787803310340"},{"key":"30_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46466-4_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"KM Yi","year":"2016","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: Learned Invariant Feature Transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467\u2013483. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_28"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03398-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T22:53:29Z","timestamp":1775256809000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03398-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030033972","9783030033989"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03398-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"2 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prcv.qyhw.net.cn\/?lang=en&meeting_id=255","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}