{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:58:18Z","timestamp":1784836698209,"version":"3.55.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030114787","type":"print"},{"value":"9783030114794","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-11479-4_9","type":"book-chapter","created":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T14:03:33Z","timestamp":1551103413000},"page":"161-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving"],"prefix":"10.1007","author":[{"given":"\u00c7a\u011fr\u0131","family":"Kaymak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ay\u015feg\u00fcl","family":"U\u00e7ar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,2,26]]},"reference":[{"key":"9_CR1","unstructured":"R.C. Weisbin et al., Autonomous rover technology for mars sample return, in Artificial Intelligence, Robotics and Automation in Space, vol. 440 (1999), p. 1"},{"key":"9_CR2","unstructured":"R.N. Colwell, History and place of photographic interpretation, in Manual of Photographic Interpretation, vol. 2 (1997), pp. 33\u201348"},{"key":"9_CR3","unstructured":"I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (Book in Preparation for MIT Press, 2016)"},{"key":"9_CR4","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA (2016), pp. 770\u2013778"},{"key":"9_CR5","unstructured":"A. Karpathy, Convolutional neural networks for visual recognition. Course Notes. \n                  http:\/\/cs231n.github.io\/convolutional-networks\/\n                  \n                . Accessed 5 Apr 2017"},{"key":"9_CR6","unstructured":"L. Van Woensel, G. Archer, L. Panades-Estruch, D. Vrscaj, Ten technologies which could change our lives. Technical report (European Parliamentary Research Service (EPRC), Brussels, Belgium, 2015)"},{"issue":"2","key":"9_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"D.G. Lowe, Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV) 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"issue":"7","key":"9_CR8","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"T. Ojala, M. Pietikainen, T. Maenpaa, Multiresolution gray scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971\u2013987 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR9","unstructured":"N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, San Diego, CA, USA (2005), pp. 886\u2013893"},{"issue":"7","key":"9_CR10","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"G.E. Hinton, S. Osindero, Y.W. Teh, A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"issue":"3","key":"9_CR11","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"C. Cortes, V.N. Vapnik, Support vector networks. Mach. Learn. 20(3), 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Y. Freund, R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 119\u2013139 (1997)","journal-title":"J. Comput. Syst. Sci."},{"issue":"6","key":"9_CR13","doi-asserted-by":"publisher","first-page":"1664","DOI":"10.3906\/elk-1301-190","volume":"22","author":"A U\u00e7ar","year":"2014","unstructured":"A. U\u00e7ar, Y. Demir, C. G\u00fczeli\u015f, A penalty function method for designing efficient robust classifiers with input space optimal separating surfaces. Turk. J. Electr. Eng. Comput. Sci. 22(6), 1664\u20131685 (2014)","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"issue":"3","key":"9_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"O. Russakovsky et al., ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"9_CR15","unstructured":"Q.V. Le, Building high-level features using large scale unsupervised learning, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada (2013), pp. 8595\u20138598"},{"key":"9_CR16","unstructured":"Y. Taigman, M. Yang, M.A. Ranzato, L. Wolf, Deepface: closing the gap to human-level performance in face verification, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colombus, Ohio, USA (2014), pp. 1701\u20131708"},{"issue":"3-4","key":"9_CR17","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"Li Deng","year":"2014","unstructured":"L. Deng, D. Yu, Deep learning: methods and applications, in Foundations and Trends\u00ae in Signal Processing, vol. 7 (2014), pp. 197\u2013387","journal-title":"Foundations and Trends\u00ae in Signal Processing"},{"key":"9_CR18","unstructured":"D. Amodei et al., Deep speech 2: end-to-end speech recognition in English and Mandarin, in Proceedings of the International Conference on Machine Learning (ICML), New York, USA (2016), pp. 173\u2013182"},{"key":"9_CR19","unstructured":"Trend Search of \u201cDeep Learning\u201d in Google, \n                  https:\/\/trends.google.com\/trend\/explore?q=deep%20learning\n                  \n                . Accessed 12 Apr 2017"},{"key":"9_CR20","unstructured":"J. Long, E. Shelhamer,T. Darrell, Fully convolutional networks for semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA (2015), pp. 3431\u20133440"},{"key":"9_CR21","unstructured":"L.C. Chen et al., Semantic image segmentation with deep convolutional nets and fully connected CRFs, in Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA (2015), pp. 1\u201314"},{"key":"9_CR22","unstructured":"H. Noh, S. Hong, B. Han, Learning deconvolution network for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA (2015), pp. 1520\u20131528"},{"key":"9_CR23","unstructured":"S. Zheng et al., Conditional random fields as recurrent neural networks, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA (2015), pp. 1529\u20131537"},{"key":"9_CR24","unstructured":"G. Papandreou, L.C. Chen, K. Murphy, A.L. Yuille, Weakly-and semi-supervised learning of a DCNN for semantic image segmentation, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Los Alamitos, CA, USA (2015), pp. 1742\u20131750"},{"key":"9_CR25","unstructured":"F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, in Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico (2016), pp. 1\u201313"},{"issue":"8","key":"9_CR26","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"C. Farabet, C. Couprie, L. Najman, Y. LeCun, Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915\u20131929 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR27","unstructured":"V. Badrinarayanan, A. Kendall, R. Cipolla, SegNet: a deep convolutional encoder-decoder architecture for image segmentation. \n                  arXiv:1511.00561\n                  \n                 (2015)"},{"key":"9_CR28","unstructured":"A. Kendall, V. Badrinarayanan, R. Cipolla, Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. \n                  arXiv:1511.02680\n                  \n                 (2015)"},{"key":"9_CR29","first-page":"333","volume-title":"Lecture Notes in Computer Science","author":"Damien Fourure","year":"2016","unstructured":"D. Fourure et al., Semantic segmentation via multi-task, multi-domain learning, in Joint IAPR International Workshop on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), M\u00e9rida, Mexico (2016), pp. 333\u2013343"},{"key":"9_CR30","unstructured":"M. Treml et al., Speeding up semantic segmentation for autonomous driving, in Proceedings of the Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain (2016), pp. 1\u20137"},{"key":"9_CR31","unstructured":"J. Hoffman, D. Wang, F. Yu, T. Darrell, FCNs in the wild: pixel-level adversarial and constraint-based adaptation. \n                  arXiv:1612.02649\n                  \n                 (2016)"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"473","DOI":"10.5194\/isprsannals-III-3-473-2016","volume":"3","author":"D Marmanis","year":"2016","unstructured":"D. Marmanis et al., Semantic segmentation of aerial images with an ensemble of CNSS. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. 3, 473\u2013480 (2016)","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"9_CR33","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, in Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA (2015), pp. 1\u201314"},{"key":"9_CR34","unstructured":"S. Song, S.P. Lichtenberg, J. Xiao, Sun RGB-D: a RGB-D scene understanding benchmark suite, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA (2015), pp. 567\u2013576"},{"issue":"2","key":"9_CR35","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"G.J. Brostow, J. Fauqueur, R. Cipolla, Semantic object classes in video: a high-definition ground truth database. Pattern Recognit. Lett. 30(2), 88\u201397 (2009)","journal-title":"Pattern Recognit. Lett."},{"issue":"11","key":"9_CR36","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"A. Geiger, P. Lenz, C. Stiller, R. Urtasun, Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"9_CR37","unstructured":"F.N. Iandola et al., SqueezeNet: AlexNet-level accuracy with 50\u00d7 fewer parameters and <0.5\u00a0MB model size. \n                  arXiv:1602.07360\n                  \n                 (2016)"},{"key":"9_CR38","unstructured":"P.O. Pinheiro, T.Y. Lin, R. Collobert, P. Doll\u00e1r, Learning to refine object segments, in Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, Netherlands (2016), pp. 75\u201391"},{"key":"9_CR39","unstructured":"S.R. Richter, V. Vineet, S. Roth, V. Koltun, Playing for data: ground truth from computer games, in Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, Netherlands (2016), pp. 102\u2013118"},{"key":"9_CR40","unstructured":"G. Ros et al., The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA (2016), pp. 3234\u20133243"},{"key":"9_CR41","unstructured":"M. Cordts et al., The cityscapes dataset for semantic urban scene understanding, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA (2016), pp. 3213\u20133223"},{"key":"9_CR42","unstructured":"Machine Learning, \n                  http:\/\/www.nvidia.com\/object\/machine-learning.html\n                  \n                . Accessed 25 Apr 2017"},{"key":"9_CR43","unstructured":"Deep Learning Architectures, \n                  https:\/\/qph.ec.quoracdn.net\/main-qimg-4fbecaea0b4043d5450a1ca0ebe30623\n                  \n                . Accessed 1 May 2017"},{"key":"9_CR44","unstructured":"S.S. Haykin, Neural Networks: A Comprehensive Foundation (Tsinghua University Press, 2001)"},{"key":"9_CR45","unstructured":"CUDA, \n                  http:\/\/www.nvidia.com\/object\/cuda_home_new.html\n                  \n                . Accessed 5 May 2017"},{"key":"9_CR46","unstructured":"BVLC Caffe, \n                  http:\/\/caffe.berkeleyvision.org\/\n                  \n                . Accessed 7 May 2017"},{"key":"9_CR47","unstructured":"What is Torch?, \n                  http:\/\/torch.ch\/\n                  \n                . Accessed 7 May 2017"},{"key":"9_CR48","unstructured":"Introduction to the Python Deep Learning Library Theano, \n                  http:\/\/machinelearningmastery.com\/introduction-python-deep-learning-library-theano\/\n                  \n                . Accessed 8 May 2017"},{"key":"9_CR49","unstructured":"About TensorFlow, \n                  https:\/\/www.tensorflow.org\/\n                  \n                . Accessed 9 May 2017"},{"key":"9_CR50","unstructured":"Keras: Deep Learning Library for Theano and TensorFlow, \n                  https:\/\/keras.io\/\n                  \n                . Accessed 9 May 2017"},{"key":"9_CR51","unstructured":"NVIDIA CuDNN, \n                  https:\/\/developer.nvidia.com\/cudnn\n                  \n                . Accessed 10 May 2017"},{"issue":"4","key":"9_CR52","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"Y. LeCun, Backpropagation applied to handwritten ZIP code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"9_CR53","unstructured":"M. Shivaprakash, Semantic segmentation of satellite images using deep learning. Master\u2019s thesis (Czech Technical University in Prague & Lule\u00e5 University of Technology, Institute of Science, Prague, Czech Republic, 2016)"},{"key":"9_CR54","unstructured":"V. Dumoulin, F. Visin, A guide to convolution arithmetic for deep learning. \n                  arXiv:1603.07285\n                  \n                 (2016)"},{"key":"9_CR55","unstructured":"Convolution, \n                  https:\/\/leonardoaraujosantos.gitbooks.io\/artificial-inteligence\/content\/convolution.html\n                  \n                . Accessed 15 May 2017"},{"key":"9_CR56","unstructured":"A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012), pp. 1097\u20131105"},{"key":"9_CR57","unstructured":"An Intuitive Explanation of Convolutional Neural Networks, \n                  https:\/\/ujjwalkarn.me\/2016\/08\/11\/intuitive-explanation-convnets\/\n                  \n                . Accessed 16 May 2017"},{"issue":"1","key":"9_CR58","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"N. Srivastava et al., Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR59","first-page":"437","volume-title":"Lecture Notes in Computer Science","author":"Yoshua Bengio","year":"2012","unstructured":"Y. Bengio, Practical recommendations for gradient-based training of deep architectures, in Neural Networks: Tricks of the Trade (Springer Berlin, Heidelberg, 2012), pp. 437\u2013478"},{"key":"9_CR60","unstructured":"C. Szegedy et al., Going Deeper with convolutions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, USA (2015), pp. 1\u20139"},{"key":"9_CR61","unstructured":"Full-day CVPR 2013 Tutorial, \n                  http:\/\/mpawankumar.info\/tutorials\/cvpr2013\/\n                  \n                . Accessed 22 May 2017"},{"key":"9_CR62","unstructured":"Unity Development Platform, \n                  https:\/\/unity3d.com\/"},{"key":"9_CR63","unstructured":"Image Segmentation using DIGITS 5, \n                  https:\/\/devblogs.nvidia.com\/parallelforall\/image-segmentation-using-digits-5\/\n                  \n                . Accessed 25 May 2017"},{"issue":"9","key":"9_CR64","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1177\/0037549717709932","volume":"93","author":"A U\u00e7ar","year":"2017","unstructured":"A. U\u00e7ar, Y. Demir, C. G\u00fczeli\u015f, Object recognition and detection with deep learning for autonomous driving applications. Simulation 93(9), 759\u2013769 (2017)","journal-title":"Simulation"},{"key":"9_CR65","unstructured":"J. Yosinski et al., How transferable are features in deep neural networks?. Adv. Neural Inf. Process. Syst. 3320\u20133328 (2014)"}],"container-title":["Smart Innovation, Systems and Technologies","Handbook of Deep Learning Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-11479-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T08:13:31Z","timestamp":1557994411000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-11479-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030114787","9783030114794"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-11479-4_9","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"value":"2190-3018","type":"print"},{"value":"2190-3026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"26 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}