dc.contributorRomero Cano, Victor
dc.contributorUniversidad Autónoma de Occidente
dc.creatorObando Ceron, Johan Samir
dc.date.accessioned2021-06-11T15:19:41Z
dc.date.accessioned2022-09-22T18:45:41Z
dc.date.available2021-06-11T15:19:41Z
dc.date.available2022-09-22T18:45:41Z
dc.date.created2021-06-11T15:19:41Z
dc.date.issued2021-06-02
dc.identifierhttps://hdl.handle.net/10614/13046
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/3458001
dc.description.abstractLa estimación de profundidad usando diferentes sensores es uno de los desafíos clave para dotar a las máquinas autónomas de sólidas capacidades de percepción robótica. Ha habido un avance sobresaliente en el desarrollo de técnicas de estimación de profundidad unimodales basadas en cámaras monoculares, debido a su alta resolución o sensores LiDAR, debido a los datos geométricos precisos que proporcionan. Sin embargo, cada uno de ellos presenta inconvenientes inherentes, como la alta sensibilidad a los cambios en las condiciones de iluminación en el caso delas cámaras y la resolución limitada de los sensores LiDAR. La fusión de sensores se puede utilizar para combinar los méritos y compensar las desventajas de estos dos tipos de sensores. Sin embargo, los métodos de fusión actuales funcionan a un alto nivel. Procesan los flujos de datos de los sensores de forma independiente y combinan las estimaciones de alto nivel obtenidas para cada sensor. En este proyecto, abordamos el problema en un nivel bajo, fusionando los flujos de sensores sin procesar, obteniendo así estimaciones de profundidad que son densas y precisas, y pueden usarse como una fuente de datos multimodal unificada para problemas de estimación de nivel superior. Este trabajo propone un modelo de campo aleatorio condicional (CRF) con múltiples potenciales de geometría y apariencia que representa a la perfección el problema de estimar mapas de profundidad densos a partir de datos de cámara y LiDAR. El modelo se puede optimizar de manera eficiente utilizando el algoritmo Conjúgate Gradient Squared (CGS). El método propuesto se evalúa y compara utilizando el conjunto de datos proporcionado por KITTI Datset. Adicionalmente, se evalúa cualitativamente el modelo, usando datos adquiridos por el autor de esté trabajo
dc.description.abstractMulti-modal depth estimation is one of the key challenges for endowing autonomous machines with robust robotic perception capabilities. There has been an outstanding advance in the development of uni-modal depth estimation techniques based on either monocular cameras, because of their rich resolution or LiDAR sensors due to the precise geometric data they provide. However, each of them suffers from some inherent drawbacks like high sensitivity to changes in illumination conditions in the case of cameras and limited resolution for the LiDARs. Sensor fusion can be used to combine the merits and compensate the downsides of these two kinds of sensors. Nevertheless, current fusion methods work at a high level. They processes sensor data streams independently and combine the high level estimates obtained for each sensor. In this thesis, I tackle the problem at a low level, fusing the raw sensor streams, thus obtaining depth estimates which are both dense and precise, and can be used as a unified multi-modal data source for higher level estimation problems. This work proposes a Conditional Random Field (CRF) model with multiple geometry and appearance potentials that seamlessly represents the problem of estimating dense depth maps from camera and LiDAR data. The model can be optimized efficiently using the Conjugate Gradient Squared (CGS) algorithm. The proposed method was evaluated and compared with the state-of-the-art using the commonly used KITTI benchmark dataset. In addition, the model is qualitatively evaluated using data acquired by the author of this work.
dc.languageeng
dc.publisherUniversidad Autónoma de Occidente
dc.publisherMaestría en Ingeniería de Desarrollo de Productos
dc.publisherFacultad de Ingeniería
dc.publisherSantiago de Cali
dc.relation[1] R. Alterovitz, S. Koenig, and M. Likhachev, “Robot Planning in the Real World:Research Challenges and Opportunities”, AIMag, vol. 37, no. 2, pp. 76-84, Jul.2016.
dc.relation[2] M. Melin, A. C. Shapiro, and P. Glover-Kapfer, “LIDAR for ecology and con-servation,” WWF Conserv. Technol. Ser., vol. 1, no. 3, p. 40, 2017, doi:10.13140/RG.2.2.22352.76801.
dc.relation[3] D. Scharstein, R. Szeliski and R. Zabih, .Ataxonomy and evaluation of den-se two-frame stereo correspondence algorithms,"Proceedings IEEE Workshopon Stereo and Multi-Baseline Vision (SMBV 2001), 2001, pp. 131-140, doi:10.1109/SMBV.2001.988771.
dc.relation[4] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, 2nded. Cambridge: Cambridge University Press, 2004.
dc.relation[5] Rasshofer, R. H., Spies, M., and Spies, H., “Influences of weather phenomenaon automotive laser radar systems”, Advances in Radio Science, vol. 9, pp.49–60, 2011. doi:10.5194/ars-9-49-2011.
dc.relation[6] S. Bargoti, J. P. Underwood, J. I. Nieto and S. Sukkarieh, .Apipeline for trunkdetection in trellis structured apple orchards", Journal of Field Robotics, vol. 32,no. 8, pp. 1075-1094, 2015.
dc.relation[7] D. Lahat, T. Adali, and C. Jutten, “Multimodal data fusion: an overview ofmethods, challenges, and prospects,” Proceedings of the IEEE, vol. 103, no.9, pp. 1449–1477, 2015.
dc.relation[8] V. DeSilva, J. Roche and A. Kondoz, "Fusion of LiDAR and camera sensor da-ta for environment sensing in driverless vehiclesïn arXiv:1710.06230v2, 2018,[online] Available: https://arxiv.org/abs/1710.06230v2.
dc.relation[9] Pandey, Gaurav. “An Information Theoretic Framework for Camera and LidarSensor Data Fusion and its Applications in Autonomous Navigation of Vehicles”,2014.
dc.relation[10] D. Ceylan, N. J. Mitra, Y. Zheng and M. Pauly, Çoupled structure-from-motionand 3d symmetry detection for urban facades", ACM Trans. Graph., vol. 33, no.1, pp. 2:1-2:15, Feb. 2014.
dc.relation[11] R. Benenson, "Perception for driverless vehicles: design and implementation",Ph.D. Thesis École Nationale Supérieure des Mines de Paris, no. 2008, [online]Available: https://pastel.archivesouvertes. fr/pastel-00005327.
dc.relation[12] S. Petti, "Safe navigation within dynamic environments: a partial motion plan-ning approach", Ph.D. dissertation, École des Mines de Paris, 2007[13] K. Yamaguchi, D. McAllester and R. Urtasun, .Efficient joint segmentation occlusion labeling stereo and flow estimation", Proc. Eur. Conf. Comput. Vis., pp.756-771, 2014.
dc.relation[14] A. Vatavu, R. Danescu and S. Nedevschi, "Stereovision-Based Multiple ObjectTracking in Traffic Scenarios Using Free-Form Obstacle Delimiters and ParticleFilters,ïn IEEE Transactions on Intelligent Transportation Systems, vol. 16, no.1, pp. 498-511, Feb. 2015, doi: 10.1109/TITS.2014.2366248.
dc.relation[15] A. Petrovskaya and S. Thrun, "Model Based Vehicle Tracking for AutonomousDriving in Urban Environments", Proceedings of Robotics: Science and Sys-tems, Jun. 2008.
dc.relation[16] T. Vu, O. Aycard and F. Tango, .Object perception for intelligent vehicle applica-tions: A multi-sensor fusion approach,"2014 IEEE Intelligent Vehicles Sympo-sium Proceedings, 2014, pp. 774-780, doi: 10.1109/IVS.2014.6856588.
dc.relation[17] R. Omar Chavez-Garcia, "Multiple Sensor Fusion for Detection Classication andTracking of Moving Objects in Driving Environments", HAL, 2014.
dc.relation[18] R. B. Rusu and S. Cousins, "3D is here: Point Cloud Library (PCL),"2011IEEE International Conference on Robotics and Automation, 2011, pp. 1-4, doi:10.1109/ICRA.2011.5980567.
dc.relation[19] A. Knapitsch, J. Park, Q.-Y. Zhou and V. Koltun, "Tanks and temples: Bench-marking large-scale scene reconstruction", ACM Trans. Graph., vol. 36, no. 4,2017.
dc.relation[20] A. Delaunoy and M. Pollefeys, "Photometric bundle adjustment for dense multi-view 3d modeling", Proc. IEEE Conf. on Computer Vision and Pattern Recogni-tion (CVPR), 2014.
dc.relation[21] Y. Furukawa and C. Hernandez, "Multi-View Stereo: A Tutorial", Foundationsand Trends in Computer Graphics and Vision Series Now Publishers Incorpora-ted, 2015.64
dc.relation[22] Q.-Y. Zhou, J. Park and V. Koltun, .Open3D: A modern library for 3D data pro-cessing", 2018.
dc.relation[23] J. Park, Q.-Y. Zhou and V. Koltun, Çolored point cloud registration revisited",Proc. IEEE Conf. Comput. Vision Pattern Recognit., pp. 143-152, 2017.
dc.relation[24] G. Agamennoni, P. Furgale and R. Siegwart, "Self-tuning M-estimators,"2015IEEE International Conference on Robotics and Automation (ICRA), 2015, pp.4628-4635, doi: 10.1109/ICRA.2015.7139840[25] F. Castanedo, .Areview of data fusion techniques", Sci. World J., vol. 2013, 2013.
dc.relation[26] P. Piniés, L. M. Paz and P. Newman, "Too much TV is bad: Dense reconstruc-tion from sparse laser with non-convex regularisation,"2015 IEEE Internatio-nal Conference on Robotics and Automation (ICRA), 2015, pp. 135-142, doi:10.1109/ICRA.2015.7138991[27] V. Romero-Cano and J. I. Nieto, "Stereo-based motion detection and trackingfrom a moving platform,"2013 IEEE Intelligent Vehicles Symposium (IV), 2013,pp. 499-504, doi: 10.1109/IVS.2013.6629517.
dc.relation[28] M. Tanner, P. Piniés, L. M. Paz and P. Newman, "What lies behind: Re-covering hidden shape in dense mapping,"2016 IEEE International Con-ference on Robotics and Automation (ICRA), 2016, pp. 979-986, doi:10.1109/ICRA.2016.7487230.
dc.relation[29] A. Eitel, J. T. Springenberg, L. Spinello, M. Riedmiller and W. Burgard, "Multi-modal deep learning for robust RGB-D object recognition,"2015 IEEE/RSJ In-ternational Conference on Intelligent Robots and Systems (IROS), 2015, pp.681-687, doi: 10.1109/IROS.2015.7353446.
dc.relation[30] J. Obando, V. Romero, N. Llanos, W. Toro. ProbabilisticPerception System forObject Classification Based on Camera -LiDAR Sensor Fusion. LatinX in AIResearch at ICML 2019, Jun 2019, Long Beach, United States.
dc.relation[31] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua and S. Süsstrunk, "SLIC Super-pixels Compared to State-of-the-Art Superpixel Methods,ïn IEEE Transactionson Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282,Nov. 2012, doi: 10.1109/TPAMI.2012.120.
dc.relation[32] S. van der Walt et al., "scikit-image: Image processing in Python", PeerJ, vol. 2,pp. e453, Jun. 2014, [online] Available: http://dx.doi.org/10.7717/peerj.453.65
dc.relation[33] A. Geiger, P. Lenz, C. Stiller and R. Urtasun, "Vision meets robotics: The KITTIdataset", Int. J. Robot. Res., vol. 32, no. 11, pp. 1231-1237, 2013.
dc.relation[34] A KOUBAA, Robot operating system (ROS) [J]", Studies in computational inte-lligence, vol. 1, no. 6, pp. 342-348, 2016.
dc.relation[35] M. Quigley, K. Conley, B. Gerkey, J. Faust, T. B. Foote, J. Leibs, et al., -OS: An open-source robot operating system", Proc. ICRA Open-Source Softw.Workshop, 2009.
dc.relation[36] M. Quigley, E. Berger and A. Ng, "Stair: Hardware and software architecture",Proc. AAAI Robot. Workshop, 2007.
dc.relation[37] D. Koller and N. Friedman, Probabilistic Graphical Models: Principles and Tech-niques, USA, MA, Cambridge:MIT Press, 2009.
dc.relation[38] C. M. Bishop, Pattern Recognition and Machine Learning, New York, NY,USA:Springer, 2011..
dc.relation[39] K. A. Stroud and D. J. Booth, Advanced Engineering Mathematics, New York,NY, USA:Palgrave Macmillan, 2003.
dc.relation[40] G. Roussas, An Introduction to Probability and Statistical Inference, San Fran-cisco, CA, USA:Academic, 2003.
dc.relation[41] F. M. Dekking, A Modern Introduction to Probability and Statistics, U.K.,London:Springer-Verlag, pp. 313-328, 2005.
dc.relation[42] M. R. Spiegel, J. J. Schiller, R. A. Srinivasan and M. LeVan, Probability andStatistics, New York, NY, USA:McGraw-Hill, 2009.
dc.relation[43] W. Mendenhall and R. J. Beaver. Introduction to Probability and Statistics-9thedition. Duxbury Press, International Thomson Publishing, Pacific Grove, CA,1994.
dc.relation[44] A First Course in Probability, New York:Collier Macmillan, 1976.
dc.relation[45] D. Koller and N. Friedman, Probabilistic Graphical Models: Principles and Tech-niques, Cambridge, MA, USA:MIT Press, 2009.
dc.relation[46] C.M. Bishop, Pattern Recognition and Machine Learning., Aug. 2006.
dc.relation[47] J.E. Freund, Mathematical Statistics with Applications, pp. 524-529, 2004.66
dc.relation[48] P. Bessière, E. Mazer, J. M. Ahuactzin-Larios, and K. Mekhnacha, BayesianProgramming. CRC Press, Dec. 2013. [Online]. Available: http://hal.inria.fr/hal-00905797.
dc.relation[49] S. Lauritzen, Graphical Models, New York:Clarendon, 1996.
dc.relation[50] L. E. Sucar, "Probabilistic graphical modelsïn Advances in Computer Vision andPattern Recognition, London, U.K.:Springer, pp. 978, 2015.
dc.relation[51] K. P. Murphy, Machine learning: a probabilistic perspective. MIT, 2012[52] C. R. Rao, E. J. Wegman and J. L. Solka, Handbook of Statistics, Wiley, vol. 24,2005.
dc.relation[53] P. Perez, "Markov Random Fields and Images", CWI Quarterly, vol. 11, no. 4,pp. 413-437, 1998.
dc.relation[54] J. Lafferty, A. McCallum and F. Pereira, Çonditional Random Fields: ProbabilisticModels for Segmenting and Labeling Sequence Data", Proc. Int’l Conf. MachineLearning, pp. 282-289, 2001.
dc.relation[55] X. He, R. S. Zemel and M. Carreira-Perpindn, "Multiscale conditional randomfields for image labeling", Proc. IEEE Comput. Soc. Conf. Comput. Vis. PatternRecog., pp. 695-703, 2004..
dc.relation[56] S. Kumar and M. Herbert, "Discriminative Fields for Modeling Spatial Depen-dencies in Natural Images", Proc. 18th Ann. Conf. Neural Information Proces-sing Systems, 2004.
dc.relation[57] P. Awasthi, A. Gagrani and B. Ravindran, Ïmage modeling using tree structuredconditional random fields", Proceedings of the 20th International Joint Confe-rence on Artificial Intelligence (IJCAI 2007), pp. 2060-2065, 2007.
dc.relation[58] Ruo Zhang, Ping-Sing Tsai, J. E. Cryer and M. Shah, "Shape-from-shading: asurvey,ïn IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, no. 8, pp. 690-706, Aug. 1999, doi: 10.1109/34.784284.
dc.relation[59] S. Suwajanakorn and C. Hernandez, "Depth from focus with your mobile pho-ne", Proceedings of the IEEE Conference on Computer Vision and Pattern Re-cognition, 2015.
dc.relation[60] D. Eigen, C. Puhrsch and R. Fergus, "Depth map prediction from a single imageusing a multi-scale deep network", Proc. Advances Neural Inf. Process. Syst.,67 pp. 2366-2374, 2014.
dc.relation[61] J. Xie, R. Girshick and A. Farhadi, "Deep3D: Fully automatic 2D-to-3D videoconversion with deep convolutional neural networks", Proc. Eur. Conf. Comput.Vis., pp. 842-857, 2016.
dc.relation[62] A. Saxena, S. H. Chung and A. Y. Ng, "Learning depth from single monocularimages", Proc. Adv. Neural Inf. Process. Syst., pp. 1161-1168, 2005.
dc.relation[63] D. Eigen, C. Puhrsch and R. Fergus, "Depth map prediction from a single imageusing a multi-scale deep network", Adv. Neural Inf. Proc. Syst., 2014.
dc.relation[64] D. Eigen and R. Fergus, "Predicting depth surface normals and semantic labelswith a common multi-scale convolutional architecture", Proc. IEEE Int. Conf.Comput. Vis., pp. 2650-2658, 2015.
dc.relation[65] A. Roy and S. Todorovic, "Monocular depth estimation using neural regressionforest", Proceedings of the IEEE Conference on Computer Vision and PatternRecognition CVPR (CVPR), 2016.
dc.relation[66] D. Xu, W. Wang, H. Tang, H. Liu, N. Sebe and E. Ricci, "Structured attention gui-ded convolutional neural fields for monocular depth estimation", CVPR, 2018.
dc.relation[67] B. Li, C. Shen, Y. Dai, A. V. den Hengel and M. He, "Depth and surface normalestimation from monocular images using regression on deep features and hie-rarchical CRFs", Proc. Conf. Computer Vision and Pattern Recognition (CVPR),pp. 1119-1127, 2015.
dc.relation[68] A. Krizhevsky, I. Sutskever and G. Hinton, ÏmageNet Classification with DeepConvolutional Neural Networks", Proc. Neural Information and Processing Sys-tems, 2012.
dc.relation[69] F. Liu, C. Shen and G. Lin, "Deep convolutional neural fields for depth estimationfrom a single image", Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp.5162-5170, 2015.
dc.relation[70] M. Liu, M. Salzmann and X. He, "Discrete-continuous depth estimation froma single image", Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 716-723, 2014.
dc.relation[71] D. Eigen and R. Fergus, "Predicting depth surface normals and semantic labelswith a common multi-scale convolutional architecture", 2014.68
dc.relation[72] T. Zhou, M. Brown, N. Snavely and D. G. Lowe, Ünsupervised learning of depthand ego-motion from video", Conference on Computer Vision and Pattern Re-cognition (CVPR), 2017.
dc.relation[73] P. Wang, X. Shen, Z. Lin, S. Cohen, B. Price and A. Yuille, "Towards unifieddepth and semantic prediction from a single image", Proc. IEEE Conf. Comput.Vis. Pattern Recog., pp. 2800-2809, 2015.
dc.relation[74] C. Godard, O. Mac Aodha and G. J. Brostow, Ünsupervised monocular depthestimation with left-right consistency", Conference on Computer Vision and Pat-tern Recognition (CVPR), 2017.
dc.relation[75] Y. Kuznietsov, J. Stückler and B. Leibe, "Semi-supervised deep learning for mo-nocular depth map prediction", IEEE Conference on Computer Vision and Pat-tern Recognition (CVPR), pp. 6647-6655, 2017.
dc.relation[76] C. Zhao, Q. Sun, C. Zhang, Y. Tang, and F. Qian, “Monocular depthestimationbased on deep learning: An overview,”Sci. China Technol.Sci., vol. 63, no. 9, pp.1612–1627, Sep. 2020.
dc.relation[77] F. Ma and S. Karaman, "Sparse-to-Dense: Depth Prediction from Spar-se Depth Samples and a Single Image,"2018 IEEE International Con-ference on Robotics and Automation (ICRA), 2018, pp. 4796-4803, doi:10.1109/ICRA.2018.8460184.
dc.relation[78] Q. Yang, R. Yang, J. Davis and D. Nister, "Spatial-Depth Super Resolution forRange Images,"2007 IEEE Conference on Computer Vision and Pattern Re-cognition, 2007, pp. 1-8, doi: 10.1109/CVPR.2007.383211.
dc.relation[79] J. Diebel and S. Thrun. An application of markov random fields to range sensing.In NIPS, 2005. 1, 4, 5, 7.
dc.relation[80] H. Andreasson, R. Triebel and A. Lilienthal, "Vision-based interpolation of 3dlaser scans", Proceedings of the 2006 IEEE International Conference on Auto-nomous Robots and Agents (ICARA 2006), 2006.
dc.relation[81] B. Wang, Y. Feng and H. Liu, "Multi-scale features fusion from sparse lidar dataand single image for depth completion", Electronics Letters, 2018.
dc.relation[82] F. Ma and S. Karaman, "Sparse-to-Dense: Depth Prediction from Spar-se Depth Samples and a Single Image,"2018 IEEE International Con-ference on Robotics and Automation (ICRA), 2018, pp. 4796-4803, doi:10.1109/ICRA.2018.8460184.69
dc.relation[83] F. Ma, G. V. Cavalheiro and S. Karaman, "Self-Supervised Sparse-to-Dense:Self-Supervised Depth Completion from LiDAR and Monocular Camera,"2019International Conference on Robotics and Automation (ICRA), 2019, pp. 3288-3295, doi: 10.1109/ICRA.2019.8793637.
dc.relation[84] B. -U. Lee, H. -G. Jeon, S. Im and I. S. Kweon, "Depth Comple-tion with Deep Geometry and Context Guidance,"2019 International Con-ference on Robotics and Automation (ICRA), 2019, pp. 3281-3287, doi:10.1109/ICRA.2019.8794161.
dc.relation[85] Y. Zhang and T. Funkhouser, "Deep depth completion of a single rgb-d image",Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition, pp. 175-185, 2018.
dc.relation[86] W. Maddern and P. Newman, Real-time probabilistic fusion of spar-se 3D LIDAR and dense stereo,"2016 IEEE/RSJ International Conferen-ce on Intelligent Robots and Systems (IROS), 2016, pp. 2181-2188, doi:10.1109/IROS.2016.7759342.
dc.relation[87] K. Nickels, A. Castano and C. Cianci, "Fusion of lidar and stereo range for mo-bile robots", Int. Conf. on Advanced Robotics, 2003.
dc.relation[88] A Harrison and P Newman Image and sparse laser fusion for dense scenereconstruction In Proc of the Int Conf on Field and Service Robotics (FSR),Cambridge, Massachusetts, July 2009.
dc.relation[89] K. Park, S. Kim and K. Sohn, "High-Precision Depth Estimation with the 3D Li-DAR and Stereo Fusion,"2018 IEEE International Conference on Robotics andAutomation (ICRA), 2018, pp. 2156-2163, doi: 10.1109/ICRA.2018.8461048.
dc.relation[90] J. Lafferty, A. McCallum and F. Pereira, Çonditional random fields: Probabilisticmodels for segmenting and labeling sequence data", Proc. 18th Int. Conf. Mach.Learn., pp. 282-289, 2001.
dc.relation[91] T. Qin, T.-Y. Liu, X.-D. Zhang, D.-S. Wang and H. Li, "Global ranking using con-tinuous conditional random fields", Proc. Adv. Neural Inf. Process. Syst., pp.1281-1288, 2008.
dc.relation[92] J. Diebel and S. Thrun. An application of markov random fields to range sensing.In NIPS, 2005.
dc.relation[93] A Harrison and P Newman Image and sparse laser fusion for dense scenereconstruction In Proc of the Int Conf on Field and Service Robotics (FSR),70.
dc.relation[94] G. Sidorov, A. Gelbukh, H. Gómez-Adorno and D. Pinto, "Soft similarity and softcosine measure: Similarity of features in vector space model", Computación ySistemas, vol. 18, no. 3, pp. 491-504, 2014.
dc.relation[95] S. Walz, T. Gruber, W. Ritter and K. Dietmayer, Üncertainty depth estima-tion with gated images for 3D reconstruction," 020 IEEE 23rd InternationalConference on Intelligent Transportation Systems (ITSC), 2020, pp. 1-8, doi:10.1109/ITSC45102.2020.929457.
dc.relation[96] H. Fu, M. Gong, C. Wang, K. Batmanghelich and D. Tao, "Deep ordinal regres-sion network for monocular depth estimation", Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition, pp. 2002-2011, 2018.
dc.relation[97] A. Kendall and Y. Gal, What uncertainties do we need in bayesian deep learningfor computer vision?, 2017.
dc.relation[98] D. Eigen, C. Puhrsch, and R. Fergus. Depth map prediction from a single imageusing a multi-scale deep network. arXiv preprint arXiv:1406.2283, 2014.
dc.relation[99] Q. Yang, R. Yang, J. Davis and D. Nister, "Spatial-Depth Super Resolution forRange Images,"2007 IEEE Conference on Computer Vision and Pattern Re-cognition, 2007, pp. 1-8, doi: 10.1109/CVPR.2007.383211.
dc.relation[100] T. Qin, T.-Y. Liu, X.-D. Zhang, D.-S. Wang and H. Li, "Global ranking usingcontinuous conditional random fields", Proc. Adv. Neural Inf. Process. Syst., pp.1281-1288, 2008.
dc.relation[101] Y. Kuznietsov, J. Stuckler and B. Leibe, "Semi-supervised deep learning formonocular depth map prediction", arXiv preprint arXiv:1702.02706, 2017.
dc.relation[102] J. Qiu, Z. Cui, Y. Zhang, X. Zhang, S. Liu, B. Zeng, et al., "Deeplidar: Deepsurface normal guided depth prediction for outdoor scene from sparse lidar dataand single color image", CoRR, vol. abs/1812.00488, 2018.
dc.relation[103] W. Van Gansbeke, D. Neven, B. De Brabandere and L. Van Gool, "Sparseand Noisy LiDAR Completion with RGB Guidance and Uncertainty,"2019 16thInternational Conference on Machine Vision Applications (MVA), 2019, pp. 1-6,doi: 10.23919/MVA.2019.8757939.
dc.relation[104] C. Godard, O. Mac Aodha and G. J. Brostow, Ünsupervised monocular depthestimation with left-right consistency", Conference on Computer Vision and Pat-71 tern Recognition (CVPR), 2017.
dc.relation[105] N. Schneider, L. Schneider, P. Pinggera, U. Franke, M. Pollefeys and C. Sti-ller, "Semantically guided depth upsampling", German Conference on PatternRecognition, pp. 37-48, 2016.
dc.relation[106] X. Cheng, P. Wang and R. Yang, "Depth estimation via affinity learned with con-volutional spatial propagation network", arXiv preprint arXiv:1808.00150, 2018.
dc.relation[107] Z. Huang, J. Fan, S. Cheng, S. Yi, X. Wang and H. Li, "HMS-Net: Hierar-chical Multi-Scale Sparsity-Invariant Network for Sparse Depth Completion,ïnIEEE Transactions on Image Processing, vol. 29, pp. 3429-3441, 2020, doi:10.1109/TIP.2019.2960589.
dc.relation[108] P. Hambarde and S. Murala, "S2DNet: Depth Estimation From Single Imageand Sparse Samples,ïn IEEE Transactions on Computational Imaging, vol. 6,pp. 806-817, 2020, doi: 10.1109/TCI.2020.2981761.
dc.relation[109] I. Laina, C. Rupprecht, V. Belagiannis, F. Tombari and N. Navab, "DeeperDepth Prediction with Fully Convolutional Residual Networks,"2016 FourthInternational Conference on 3D Vision (3DV), 2016, pp. 239-248, doi:10.1109/3DV.2016.32.
dc.relation[110] C. Mallet and C. Bretar, "Full waveform topographic lidar: State-of-the-art",ISPRS J. Photogramm. Remote Sens., vol. 64, no. 1, pp. 1-16, Jan. 2009.
dc.relation[111] R. Horaud, M. Hansard, G. Evangelidis and C. Ménier, .An overview of depthcameras and range scanners based on time-of-flight technologies", Mach. Vis.Appl., vol. 27, no. 7, pp. 1005-1020, Oct. 2016.
dc.relation[112] F. Ma and S. Karaman, "Sparse-to-Dense: Depth Prediction from Spar-se Depth Samples and a Single Image,"2018 IEEE International Con-ference on Robotics and Automation (ICRA), 2018, pp. 4796-4803, doi:10.1109/ICRA.2018.8460184.
dc.relation[113] C. Cadena, A. Dick and I. D. Reid, "Multi-modal auto-encoders as joint esti-mators for robotics scene understanding", Proc. Robot.: Sci. Syst. Conf., pp.377-386, 2016.
dc.relation[114] Y. Liao, L. Huang, Y. Wang, S. Kodagoda, Y. Yu and Y. Liu, "Parse geometryfrom a line: Monocular depth estimation with partial laser observation,"2017IEEE International Conference on Robotics and Automation (ICRA), 2017, pp.5059-5066, doi: 10.1109/ICRA.2017.7989590.72
dc.relation[115] C. Fu, C. Mertz and J. M. Dolan, "LIDAR and Monocular Camera Fu-sion: On-road Depth Completion for Autonomous Driving,"2019 IEEE Inte-lligent Transportation Systems Conference (ITSC), 2019, pp. 273-278, doi:10.1109/ITSC.2019.8917201.
dc.relation[116] F. Ma and S. Karaman, "Sparse-to-Dense: Depth Prediction from Spar-se Depth Samples and a Single Image,"2018 IEEE International Con-ference on Robotics and Automation (ICRA), 2018, pp. 4796-4803, doi:10.1109/ICRA.2018.8460184.
dc.relation[117] X. Cheng, P. Wang and R. Yang, "Depth estimation via affinity learned with con-volutional spatial propagation network", arXiv preprint arXiv:1808.00150, 2018.
dc.relation[118] P. Hambarde and S. Murala, "S2DNet: Depth Estimation From Single Imageand Sparse Samples,ïn IEEE Transactions on Computational Imaging, vol. 6,pp. 806-817, 2020, doi: 10.1109/TCI.2020.2981761.
dc.relation[119] B. Schoettle, "Sensor fusion: A comparison of sensing capabilities of humandrivers and highly automated vehicles", Aug. 2017.
dc.relation[120] A. Anas, "Methods of Point Cloud Alignment with Applications to 3D IndoorMapping and Localization", Mar. 2017.
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectMaestría en Ingeniería de Desarrollo de Productos
dc.titleDevelopment of a probabilistic perception system for camera-lidar sensor fusion
dc.typeTrabajo de grado - Maestría


Este ítem pertenece a la siguiente institución