Filters








485 Hits in 2.4 sec

Going beyond vision to improve bionic vision

Wai Ho Li, Titus Jia Jie Tang, Wen Lik Dennis Lui
2013 2013 IEEE International Conference on Image Processing  
Unfortunately, the resulting bionic vision has low spatial resolution and limited dynamic range. This dramatically reduces the usefulness of bionic vision in many real world scenarios.  ...  We explore another alternative: Combining multiple sensing modalities and robotic sensing algorithms. This paper gives a top level summary of ongoing research exploring this alternative.  ...  This is done by looking for non-planar local regions in the depth image.  ... 
doi:10.1109/icip.2013.6738320 dblp:conf/icip/LiTL13 fatcat:jhfqfznppvgl3ligwobnv3zye4

Estimating Vehicle Ego-Motion and Piecewise Planar Scene Structure from Optical Flow in a Continuous Framework [chapter]

Andreas Neufeld, Johannes Berger, Florian Becker, Frank Lenzen, Christoph Schnörr
2015 Lecture Notes in Computer Science  
We propose a variational approach for estimating egomotion and structure of a static scene from a pair of images recorded by a single moving camera.  ...  Our experiments demonstrate that our approach estimates egomotion and scene structure with a high quality, that reaches the accuracy of state-of-the-art stereo methods, but relies on a single sensor that  ...  scene and egomotion.  ... 
doi:10.1007/978-3-319-24947-6_4 fatcat:yb6zem6isjhyzloqkjzmwmgt6i

Using GNG to improve 3D feature extraction—Application to 6DoF egomotion

Diego Viejo, Jose Garcia, Miguel Cazorla, David Gil, Magnus Johnsson
2012 Neural Networks  
A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.  ...  The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data.  ...  -35, and Valencia's Government project GV/2011/034.  ... 
doi:10.1016/j.neunet.2012.02.014 pmid:22386789 fatcat:ou7fcbtyx5fh3no25nnkzghlbq

Recovery of Egomotion and Segmentation of Independent Object Motion Using the EM Algorithm

W. James MacLean, Allan D. Jepson, Richard C. Frecker
1994 Procedings of the British Machine Vision Conference 1994  
The input data are linear constraints on 3-D translational motion and bilinear constraints on 3-D translation and rotation, derived from computed optical flow using subspace methods.  ...  This paper examines the use of the EM algorithm to perform motion segmentation on image sequences that contain independent object motion.  ...  Conclusions We have described a method of segmenting images containing both egomotion and independent object motion based on 3-D motion constraints.  ... 
doi:10.5244/c.8.17 dblp:conf/bmvc/MacLeanJF94 fatcat:mw5r7hxkrndwjofhqeksf7rxqa

A study of a soft computing based method for 3D scenario reconstruction

Diego Viejo, Jose Garcia-Rodriguez, Miguel Cazorla
2012 Applied Soft Computing  
From this GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm.  ...  In this paper we detail an efficient approach to build complete 3D models using a soft computing method, the Growing Neural Gas (GNG).  ...  Figure 8 Figure 9 : 89 Planar based 6DoF egomotion results using planar patches after computing a GNG mesh.  ... 
doi:10.1016/j.asoc.2012.05.025 fatcat:dtwxtr2izraq3fliwndg37yzre

Online extrinsic multi-camera calibration using ground plane induced homographies

Moritz Knorr, Wolfgang Niehsen, Christoph Stiller
2013 2013 IEEE Intelligent Vehicles Symposium (IV)  
Results were obtained, using both, a planar and a general motion model with full six degrees of freedom.  ...  In contrast to other approaches, motion, relative camera poses, and the ground plane are estimated simultaneously using a single iterated extended Kalman filter.  ...  The egomotion estimation itself is based on the epipolar and trifocal constraint in combination with the minimization of the projection error of previously triangulated points.  ... 
doi:10.1109/ivs.2013.6629476 dblp:conf/ivs/KnorrNS13 fatcat:fuphtrsb7zcxdc556hwaegf7x4

Egomotion estimation of a range camera using the space envelope

A. Hoover, D. Goldgof, K. Bowyer
2003 IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)  
These correspondences are used to compute rotation and translation estimates of the egomotion. We demonstrate our methods on two image sequences containing 70 images.  ...  In this work we present a method to compute the egomotion of a range camera using the space envelope.  ...  In a range image, surface primitives can be computed from a single view and subsequently used for egomotion estimation.  ... 
doi:10.1109/tsmcb.2003.814297 pmid:18238222 fatcat:lojge6sd3rc6zjwkhkskyi4kgi

Hierarchical Model-Based Motion Estimation [chapter]

P. Anandan, J. R. Bergen, K. J. Hanna, Rajesh Hingorani
1993 Motion Analysis and Image Sequence Processing  
The key features of the resulting framework (or family of algorithms) a,re a global model that constrains the overall structure of the motion estimated, a local rnodel that is used in the estimation process  ...  Four specific motion models: affine flow, planar surface flow, rigid body motion, and general optical flow, are described along with their application to specific examPles.  ...  These include Peter Burt and Leonid Oliker from the David Sarnoff Research Center, and Shmuel Peleg from Hebrew University.  ... 
doi:10.1007/978-1-4615-3236-1_1 fatcat:fsglp7svrjhddi46v5lxeur434

Hierarchical model-based motion estimation [chapter]

James R. Bergen, P. Anandan, Keith J. Hanna, Rajesh Hingorani
1992 Lecture Notes in Computer Science  
The key features of the resulting framework (or family of algorithms) a,re a global model that constrains the overall structure of the motion estimated, a local rnodel that is used in the estimation process  ...  Four specific motion models: affine flow, planar surface flow, rigid body motion, and general optical flow, are described along with their application to specific examPles.  ...  These include Peter Burt and Leonid Oliker from the David Sarnoff Research Center, and Shmuel Peleg from Hebrew University.  ... 
doi:10.1007/3-540-55426-2_27 fatcat:jtq2oix4mrczzizdqoiqbp5cnm

Joint direct estimation of 3D geometry and 3D motion using spatio temporal gradients [article]

Francisco Barranco, Cornelia Fermüller, Yiannis Aloimonos, Eduardo Ros
2018 arXiv   pre-print
The 3D motion estimate is then refined and structure estimated adding a regularization based on depth.  ...  The main idea lies in a reformulation of the positive-depth constraint, which allows the use of well-known minimization techniques to solve for 3D motion.  ...  and CNS 1544797.  ... 
arXiv:1805.06641v1 fatcat:mbzq42eeyncwzi43htmmfmnbnq

Automatic monitoring and 3D reconstruction applied to cultural heritage

Federico Pedersini, Augusto Sarti, Stefano Tubaro
2000 Journal of Cultural Heritage  
In this article we present our global approach to the problem of accurate 3D measurement and reconstruction of 3D works of art using a calibrated multi-camera system.  ...  We also propose a general and robust approach to the problem of close-range partial 3D reconstruction of objects from stereo-correspondences.  ...  Furthermore we can use the same type of features for egomotion estimation as well.  ... 
doi:10.1016/s1296-2074(00)01082-7 fatcat:bcqelybf6ja6xeedgtgdlg3kyi

Inverse perspective mapping simplifies optical flow computation and obstacle detection

Hanspeter A. Mallot, H. H. Bülthoff, J. J. Little, S. Bohrer
1991 Biological cybernetics  
Psychophysical evidence for body-scaled obstacle detection and related neurophysiological results are discussed.  ...  Optical flow is established by a local "voting" (non-maximum suppression) over the outputs of correlation-type motion detectors similar to those found in the fly visual system.  ...  Further support for this work was provided by the German Federal Department of Research and Technology (BMFT), Grant. No. ITR8800/K4 and the NATO Scientific Affairs Division.  ... 
doi:10.1007/bf00201978 pmid:2004128 fatcat:an47vvigszec7lfsgpdljyf6te

Topological Mapping and Navigation Using a Developmental Learning Approach Based on Imitation through Sensory-Motor Maps [chapter]

Raquel Frizera, Hans Jorg Andreas Schneebeli, Jose Santos-Victor
2010 Mobile Robots Navigation  
Federal do Espírito Santo, Vitória -Brazil; and also by CNPq -Conselho Nacional de Desenvolvimento Científico e Tecnológico, Brazil, through the project 472727/2003-6.  ...  Acknowledgements This work is partly supported by CAPES -Coordenação de Aperfeiçoamento de Pessoal de Nível Superior via a cooperation between Instituto Superior Técnico, Lisbon -Portugal, and Universidade  ...  The reason for using omnidirectional images for egomotion estimation is that the problem becomes easier if a spherical motion field is used instead of a planar field obtained with perspective cameras  ... 
doi:10.5772/8992 fatcat:5mjnformyvai5fyi37lywdnia4

Multi-Camera Acquisitions for High-Accuracy 3D Reconstruction [chapter]

Federico Pedersini, Augusto Sarti, Stefano Tubaro
1998 Lecture Notes in Computer Science  
In particular, we illustrate a simple and effective adaptive technique for the self-calibration of CCD-based multi-camera acquisition systems.  ...  We also propose a general and robust approach to the problem of close-range partial 3D reconstruction of objects from stereo-correspondences.  ...  In order to be able to use edges for accurate egomotion estimation, however, we need to detect them with great accuracy.  ... 
doi:10.1007/3-540-49437-5_9 fatcat:6lth43ig65h5rblyvpa63pc36q

Entropy-based sim(3) calibration of 2D lidars to egomotion sensors

Jacob Lambert, Lee Clement, Matthew Giamou, Jonathan Kelly
2016 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)  
Given a non-degenerate trajectory and a sufficient number of lidar measurements, our calibration procedure achieves millimetre-scale and sub-degree accuracy.  ...  This paper explores the use of an entropy-based technique for point cloud reconstruction with the goal of calibrating a lidar to a sensor capable of providing egomotion information.  ...  The members of the Space and Terrestrial Autonomous Robotics (STARS) Laboratory and of the Dynamic Systems Laboratory (DSL) also deserve mention for creating a pleasant and fulfilling work environment.  ... 
doi:10.1109/mfi.2016.7849530 dblp:conf/mfi/LambertCGK16 fatcat:dtdhjkcitjawda7io6qg3rralq
« Previous Showing results 1 — 15 out of 485 results