{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T22:12:09Z","timestamp":1775859129391,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Singapore","isbn-type":[{"value":"9789811073045","type":"print"},{"value":"9789811073052","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-981-10-7305-2_43","type":"book-chapter","created":{"date-parts":[[2017,12,7]],"date-time":"2017-12-07T16:16:54Z","timestamp":1512663414000},"page":"500-511","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning the Frame-2-Frame Ego-Motion for Visual Odometry with Convolutional Neural Network"],"prefix":"10.1007","author":[{"given":"Mingqi","family":"Qiao","sequence":"first","affiliation":[]},{"given":"Zilei","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,8]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., llg, E.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"43_CR2","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: Deep image homography estimation. arXiv preprint arXiv:1606.03798 (2016)"},{"key":"43_CR3","first-page":"486","volume":"1","author":"KR Konda","year":"2015","unstructured":"Konda, K.R., Memisevic, R.: Learning visual odometry with a convolutional network. VISAPP 1, 486\u2013490 (2015)","journal-title":"VISAPP"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Clipolla, R.: Posenet: a convolutional network for real-time 6-DOF camera relocalization. Proceedings of the IEEE international conference on computer vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Roberts, R., Nguyen, H., Krishnamurthi, N., Balch, T.: Memory-based learning for visual odometry. In: IEEE International Conference on Robotics and Automation, pp. 47\u201352 (2008)","DOI":"10.1109\/ROBOT.2008.4543185"},{"issue":"5","key":"43_CR6","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1177\/0278364912472245","volume":"32","author":"V Guizilini","year":"2013","unstructured":"Guizilini, V., Ramos, F.: Semi-parametric learning for visual odometry. Int. J. Robot. Res. 32(5), 526\u2013546 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"43_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24673-2_3"},{"issue":"6","key":"43_CR8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Leonard, J.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans. Robot. 32(6), 1309\u20131332 (2016)","journal-title":"IEEE Trans. Robot."},{"issue":"5","key":"43_CR9","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Robot. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Robot."},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Klein, G., Murray, D.: Parallel tracking and mapping for small AR workspaces. In: The IEEE International Symposium on Mixed and Augmented Reality, pp. 225\u2013234, November 2007","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Forster, C., Pizzoli, M., Scaramuzza, D.: SVO: fast semi-direct monocular visual odometry. In: IEEE International Conference on Robotics and Automation, pp. 15\u201322, May 2014","DOI":"10.1109\/ICRA.2014.6906584"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: DTAM: dense tracking and mapping in real-time. In: International Conference on Computer Vision, pp. 2320\u20132327, November 2011","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"43_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"issue":"3","key":"43_CR14","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1177\/0278364914554813","volume":"34","author":"S Leutenegger","year":"2015","unstructured":"Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R., Furgale, P.: Keyframe-based visualCinertial odometry using nonlinear optimization. Int. J. Robot. Res. 34(3), 314\u2013334 (2015)","journal-title":"Int. J. Robot. Res."},{"issue":"1","key":"43_CR15","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/LRA.2015.2505717","volume":"1","author":"G Costante","year":"2016","unstructured":"Costante, G., Mancini, M., Valigi, P., Ciarfuglia, T.A.: Exploring representation learning with CNNs for frame-to-frame ego-motion estimation. IEEE Robot. Autom. Lett. 1(1), 18\u201325 (2016)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"43_CR17","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Conference on Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"43_CR18","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361, June 2012","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Geiger, A., Ziegler, J., Stiller, C.: Stereoscan: dense 3D reconstruction in real-time. In: Intelligent Vehicles Symposium (IV), pp. 963\u2013968, June 2011","DOI":"10.1109\/IVS.2011.5940405"},{"issue":"4","key":"43_CR21","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1364\/JOSAA.4.000629","volume":"4","author":"BK Horn","year":"1987","unstructured":"Horn, B.K.: Closed-form solution of absolute orientation using unit quaternions. JOSA A 4(4), 629\u2013642 (1987)","journal-title":"JOSA A"},{"key":"43_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Conference on Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Instance-aware semantic segmentation via multi-task network cascades. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3150\u20133158 (2016)","DOI":"10.1109\/CVPR.2016.343"},{"key":"43_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"43_CR25","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2016.12.038","volume":"234","author":"W Liu","year":"2017","unstructured":"Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., Alsaadi, F.E.: A survey of deep neural network architectures and their applications. Neurocomputing 234, 11\u201326 (2017)","journal-title":"Neurocomputing"},{"issue":"12","key":"43_CR26","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong, C., Yu, J., Wan, J., Tao, D., Wang, M.: Multimodal deep autoencoder for human pose recovery. IEEE Trans. Image Process. 24(12), 5659\u20135670 (2015)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"43_CR27","first-page":"3742","volume":"62","author":"C Hong","year":"2015","unstructured":"Hong, C., Yu, J., Tao, D., Wang, M.: Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans. Industr. Electron. 62(6), 3742\u20133751 (2015)","journal-title":"IEEE Trans. Industr. Electron."},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ramos, F.: Semi-parametric models for visual odometry. In: IEEE International Conference on Robotics and Automation, pp. 3482\u20133489, May 2012","DOI":"10.1109\/ICRA.2012.6224775"}],"container-title":["Communications in Computer and Information Science","Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-7305-2_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:27:40Z","timestamp":1709832460000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-10-7305-2_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9789811073045","9789811073052"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-7305-2_43","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"8 December 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Chinese Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cccv2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ccf-cccv.org\/2017\/","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"}]}}