{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:36:40Z","timestamp":1753922200259},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319945439"},{"type":"electronic","value":"9783319945446"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-94544-6_10","type":"book-chapter","created":{"date-parts":[[2018,6,16]],"date-time":"2018-06-16T07:09:40Z","timestamp":1529132980000},"page":"95-105","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal Deep Learning for Advanced Driving Systems"],"prefix":"10.1007","author":[{"given":"Nerea","family":"Aranjuelo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis","family":"Unzueta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignacio","family":"Arganda-Carreras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oihana","family":"Otaegui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,17]]},"reference":[{"issue":"2","key":"10_CR1","first-page":"87","volume":"7","author":"Y Guo","year":"2017","unstructured":"Guo, Y., Liu, Y., Georgiou, T., Lew, M.S.: A review of semantic segmentation using deep neural networks. IJMIR 7(2), 87\u201393 (2017)","journal-title":"IJMIR"},{"issue":"1","key":"10_CR2","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han, J., Zhang, D., Cheng, G., Liu, N., Xu, D.: Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Process. Magaz. 35(1), 84\u2013100 (2018)","journal-title":"IEEE Signal Process. Magaz."},{"key":"10_CR3","unstructured":"Chowdhuri, S., Pankaj, T., Zipser, K.: Multi-modal multi-task deep learning for autonomous driving. CoRR abs\/1709.05581 (2017)"},{"key":"10_CR4","unstructured":"Liu, G.H., Siravuru, A., Prabhakar, S., Veloso, M., Kantor, G.: Learning end-to-end multimodal sensor policies for autonomous navigation. arXiv preprint arXiv:1705.10422 (2017)"},{"key":"10_CR5","unstructured":"Janai, J., G\u00fcney, F., Behl, A., Geiger, A.: Computer vision for autonomous vehicles: problems, datasets and state-of-the-art. arXiv preprint arXiv:1704.05519 (2017)"},{"key":"10_CR6","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th ICML 2011, pp. 689\u2013696 (2011)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. arXiv preprint arXiv:1711.06396 (2017)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.ins.2017.04.048","volume":"432","author":"Liang Xiao","year":"2018","unstructured":"Xiao, L., Wang, R., Dai, B., Fang, Y., Liu, D., Wu, T.: Hybrid conditional random field based camera-LiDAR fusion for road detection. Inf. Sci. 432, 543\u2013558 (2017)","journal-title":"Information Sciences"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3D bounding box estimation using deep learning and geometry. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5632\u20135640. IEEE (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Oliveira, G.L., Burgard, W., Brox, T.: Efficient deep models for monocular road segmentation. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4885\u20134891. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759717"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S., Metaxas, D.N.: Multispectral deep neural networks for pedestrian detection. arXiv preprint arXiv:1611.02644 (2016)","DOI":"10.5244\/C.30.73"},{"issue":"2","key":"10_CR12","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/JSEN.2001.936931","volume":"1","author":"A Carullo","year":"2001","unstructured":"Carullo, A., Parvis, M.: An ultrasonic sensor for distance measurement in automotive applications. IEEE Sensors J. 1(2), 143\u2013147 (2001)","journal-title":"IEEE Sensors J."},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Lombacher, J., Hahn, M., Dickmann, J., W\u00f6hler, C.: Potential of radar for static object classification using deep learning methods. In: IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM), pp. 1\u20134. IEEE (2016)","DOI":"10.1109\/ICMIM.2016.7533931"},{"key":"10_CR14","unstructured":"Virdi, J.: Using deep learning to predict obstacle trajectories for collision avoidance in autonomous vehicles. Ph.D. thesis, UC, San Diego (2017)"},{"issue":"02","key":"10_CR15","doi-asserted-by":"publisher","first-page":"102","DOI":"10.4236\/jtts.2015.52010","volume":"5","author":"H Shimada","year":"2015","unstructured":"Shimada, H., Yamaguchi, A., Takada, H., Sato, K.: Implementation and evaluation of local dynamic map in safety driving systems. JTTs 5(02), 102 (2015)","journal-title":"JTTs"},{"key":"10_CR16","unstructured":"Intempora: RTMaps. https:\/\/intempora.com . Accessed 18 Mar 2018"},{"key":"10_CR17","unstructured":"Elektrobit: EB Assist ADTF. https:\/\/www.elektrobit.com\/products\/eb-assist\/adtf\/ . Accessed 18 Mar 2018"},{"key":"10_CR18","unstructured":"ROS. http:\/\/www.ros.org\/ . Accessed 18 Mar 2018"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Vonference on CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Wang, S., Bai, M., Mattyus, G., Chu, H., Luo, W., Yang, B., Liang, J., Cheverie, J., Fidler, S., Urtasun, R.: Torontocity: seeing the world with a million eyes. arXiv preprint arXiv:1612.00423 (2016)","DOI":"10.1109\/ICCV.2017.327"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Roynard, X., Deschaud, J.E., Goulette, F.: Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification. arXiv preprint arXiv:1712.00032 (2017)","DOI":"10.1109\/CVPRW.2018.00272"},{"issue":"1","key":"10_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364916679498","volume":"36","author":"W Maddern","year":"2017","unstructured":"Maddern, W., Pascoe, G., Linegar, C., Newman, P.: 1 year, 1000 km: the Oxford robotcar dataset. Int. J. Robot. Res. 36(1), 3\u201315 (2017)","journal-title":"Int. J. Robot. Res."},{"key":"10_CR24","unstructured":"Santana, E., Hotz, G.: Learning a driving simulator. arXiv:1608.01230 (2016)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Xu, H., Gao, Y., Yu, F., Darrell, T.: End-to-end learning of driving models from large-scale video datasets. arXiv preprint (2017)","DOI":"10.1109\/CVPR.2017.376"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bul\u00f2, S.R., Kontschieder, P.: The mapillary vistas dataset for semantic understanding of street scenes. In: Proceedings of ICCV, pp. 22\u201329 (2017)","DOI":"10.1109\/ICCV.2017.534"},{"issue":"3","key":"10_CR27","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1109\/TITS.2018.2791533","volume":"19","author":"Yukyung Choi","year":"2018","unstructured":"Choi, Y., Kim, N., Hwang, S., Park, K., Yoon, J.S., An, K., Kweon, I.S.: KAIST multi-spectral day\/night data set for autonomous and assisted driving. IEEE Trans. Intell. Transp. Syst. 19 (2018)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D., Lopez, A.: The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes (2016)","DOI":"10.1109\/CVPR.2016.352"},{"key":"10_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-46475-6_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"SR Richter","year":"2016","unstructured":"Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102\u2013118. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7"},{"key":"10_CR30","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/978-3-319-67361-5_40","volume-title":"Field and Service Robotics","author":"S Shah","year":"2018","unstructured":"Shah, S., Dey, D., Lovett, C., Kapoor, A.: AirSim: high-fidelity visual and physical simulation for autonomous vehicles. In: Hutter, M., Siegwart, R. (eds.) Field and Service Robotics. SPAR, vol. 5, pp. 621\u2013635. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-67361-5_40"},{"key":"10_CR31","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A., Koltun, V.: CARLA: an open urban driving simulator. arXiv preprint arXiv:1711.03938 (2017)"},{"issue":"3","key":"10_CR32","first-page":"373","volume":"3","author":"S Ullman","year":"1980","unstructured":"Ullman, S.: Against direct perception. BBS 3(3), 373\u2013381 (1980)","journal-title":"BBS"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Chabot, F., Chaouch, M., Rabarisoa, J., Teuli\u00e8re, C., Chateau, T.: Deep MANTA: a coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image. In: Proceedings of IEEE CVPR, pp. 2040\u20132049 (2017)","DOI":"10.1109\/CVPR.2017.198"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Li, B.: 3D fully convolutional network for vehicle detection in point cloud. arXiv preprint arXiv:1611.08069 (2016)","DOI":"10.1109\/IROS.2017.8205955"},{"key":"10_CR35","unstructured":"Li, B., Zhang, T., Xia, T.: Vehicle detection from 3D LiDAR using fully convolutional network. arXiv preprint arXiv:1608.07916 (2016)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: IEEE CVPR, vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"10_CR37","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in NIPS, pp. 91\u201399 (2015)"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.: Joint 3D proposal generation and object detection from view aggregation. arXiv preprint arXiv:1712.02294 (2017)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhan, W., Tomizuka, M.: Fusing bird view LIDAR point cloud and front view camera image for deep object detection. arXiv:1711.06703 (2017)","DOI":"10.1109\/IVS.2018.8500387"},{"key":"10_CR40","unstructured":"Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L.D., Monfort, M., Muller, U., Zhang, J., et al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"10_CR41","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Chi, L., Mu, Y.: Deep steering: learning end-to-end driving model from spatial and temporal visual cues. arXiv preprint arXiv:1708.03798 (2017)","DOI":"10.1145\/3132734.3132737"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Patel, N., Choromanska, A., Krishnamurthy, P., Khorrami, F.: Sensor modality fusion with CNNs for UGV autonomous driving in indoor environments. In: International Conference on Intelligent Robots and Systems (IROS). IEEE (2017)","DOI":"10.1109\/IROS.2017.8205958"}],"container-title":["Lecture Notes in Computer Science","Articulated Motion and Deformable Objects"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-94544-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,19]],"date-time":"2019-10-19T10:49:00Z","timestamp":1571482140000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-94544-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319945439","9783319945446"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-94544-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}