Kinect 3D Reconstruction

Size: px
Start display at page:

Download "Kinect 3D Reconstruction"

Transcription

1 Kinect 3D Reconstruction Mahsa Mohammadkhani Computing Science University of Alberta Edmonton, Canada Abstract This report presents a Kinect-based framework that can reconstruct a scene and object in both real-time and offline processes according to the preference of a user. The user can capture images of the scene/object from different view-points to reconstruct it or he can capture the whole view-points like a video sequence and give it as an input to the framework in order to get the 3D model of the scene/object. By using a user-friendly and simple interface, a user can observe the scene/object RGB color and depth. Then he can start creating the 3D model of the desired scene/object. The resulting reconstruction is produced in a form of textured point cloud. Keywords:3D Reconstruction, Kinect, Scene Reconstruction, Object Reconstruction. I. INTRODUCTION Kinect [1, 2, 3] is a depth camera which has become an important 3D sensor. This devise has low cost, reliability and speed in measuring the depth has made it to one of the primary 3D measuring device for 3D scene reconstruction[4, 5, 6], and object recognition [7]. In computer vision, there are several well-studied methods for multi-view matching and reconstruction with the aim of reconstruction complicated real indoor and outdoor scenes and objects with accurate representation. However, the problem is still an open research problem. There are some methods which using a single image reconstruction commonly use cues such as shading, silhouette shapes, texture, and vanishing points. But, these schemes put some constraints on the features of the reconstructed objects and they restrict the allowable 3D modeling. Moreover, there are various approaches in computer vision and graphic which they uses active sensors [8], passive RGB cameras [9, 10], online images [11, 12], or image matching [13]. Also, these is a research about augmented reality and robotics community on Simultaneous Localization and Mapping (SLAM) which create a map from surroundings while the user or robot whirling around. In addition, some of the existing reconstruction systems support off-line tracking [13] and they try to detect images features and match them in a best way in order to find the corresponding features using some feature matching algorithms. In [5, 6], the new GPU-based implementation is introduced by Microsoft research group in They used Kinect to capture an indoor scene environment and their application is able to reconstruct it using the depth value gained by Kinect. Also, there is another software with the name of Reconstructme [14] which can reconstruct a 3D real model by moving Kinect around the desired object. The result of this application can be seen on Fig. 1. However, the available method are using GPU implementation which need a very powerful GPU graphic card. So, not all the computer can execute and test these programs. Also, they represent the model in mesh or surfel formats with no texture on it. Given this broad topic, I decided to implement a framework that can reconstruct a scene or object by using Kinect in a way that the program can run with all type of desktop computers. Also, the model can be textured because Kinect can capture both depth and RGB color of an image. In order to decrease the amount of processing of the reconstruction processes, I add a feature to the framework that one can choose some appropriate view-point from a scene and take a picture from them and then giving

2 them as an input to the framework to start reconstructing the scene or object. Figure 1. Reconstructme result. [15] This model is my 3D reconstruction. II. RELATED WORK Multi-view matching and reconstruction is a key element for acquisition of objects and scene models from several images or video sequences. This process is called image-based modeling. The multi-view matching algorithm can be categorized into four different groups depends on the way that they represent the final model. The first one is voxel-based approaches that many methods used it such as [15], [16] and [17]. The second group is using deformable polygonal meshes which need a good initialization such as visual hull model [18] for optimization process (This brings a limitation for these types of algorithms.) There are some approaches which are based on multiple depth maps such as [19], and the last category is those types of techniques which are based on patches such as [20] and [21]. These kinds of methods use small patches like surfels to demonstrate scene surfaces and they show the final resulting reconstructed model or scene in point clouds which need some postprocessing to convert the result to the mesh format. As most of the efforts for 3d reconstruction are based on images or video sequences, by emerging the new technology of the Kinect camera, which is a sensor-based devise, some of researchers decided to use the new depth data that Kinect can provide us. Kinect consists of one RGB camera and one infrared sensor which can produce the real depth information about the scene around. However, the depth is really noisy and it needs some filtering to provide us better information. There are some methods which try to use the depth information from the Kinect and make a 3D reconstruction of an object. One of the software which is doing the 3d reconstruction of the scene is KinectFusion [5, 6]. This software can capture a scene by moving around the Kinect. First, it applies some filter to the depth data which is producing in real time with the Kinect. Then, it finds vertex and normal for the surface of 3D model. The method uses iterative closest point (ICP) [22] algorithm in order to find the corresponding points between each frame from the incoming video sequence. Then it uses a ray casting process to get the new vertices and normal from the scene and provide new information for updating the scene. So, this algorithm is updated the result in each iteration to add more information to it. The implementation of this algorithm is based on GPU implementation which needs a very powerful CUDA GPU processors (such as an NVIDIA GeForce GTX 560 or higher) to work well. So, this limitation make this software limited to work on powerful systems which is not available everywhere. Although KinectFusion is real time application, its method is very expensive and complex. The methods which are refer to the multi view stereo (MVS) reconstruction uses multiple images, in order to reconstruct the 3D models. These methods use different techniques such as using the visual hull of the object, reproducing the photo-hull of the object and trying to find the optimized cost function over the surface shape [23]. Another reconstruction method is Visual Hull which is using the silhouette information of an object and produce intersected visual cones in order to apply that information for generating the 3D representation of the object. The method which is introduced in [24], is using the visual hull and multicamera environments and it is popular for its simplicity and efficiency. There are several methods which are based on this method, such as [25] which has parallel pipeline processing and uses fusion of multi-view silhouette cues, a space occupancy grid and recovers shape by means of rotating slicing planes.

3 Furthermore, space carving reconstruction [26] uses repeated sweeping plane in a scene volume. The algorithm starts testing the photo consistency of each voxel on the current plane. This method is dependent on a voxel, so if a voxel is removed by error, then the other voxels will be removed in cascading way. The resulting 3D reconstruction of this method has some holes on it which make its result not very acceptable. Using surface integral minimization, one can optimize the surface integral of a consistency function of a surface shape. Some level-set methods like [27] provide a way to minimize the cost function. By using both 2D images and 3D data and combining them together one can reconstruct a surface like the method in [28]. This approach is more robust that those methods which are using 2D information or 3D stereo information only. Another method for reconstruction is Marching Cubes Algorithms which creates a polygonal representation of surfaces from 3D data information [29]. This algorithm uses the conventional graphics-rendering algorithms in order to show its result which are implemented with software or hardware. Some reconstruction methods are feature based [30] and they use edge information. Those approaches which are based on constructing a mesh, in each iteration, they gradually refine the surface of the mesh until it represents the surface of the objects very well. One of the advantages of feature based surface reconstruction schemes is that they can represent the scene model in a more efficient way with compare to stereo matching algorithms which using images or quasi-dense reconstruction. III. METHOD In this section, I will describe how I implemented the framework for the project. The libraries that I have used in this framework are Point Cloud Library (PCL) [31], Nestk [32], and OpenCV. Nestk is a library which was mainly created for the RGBDemo [33] application which I started my framework based on this library. I changed the library code according to my need in order to achieve the final goal for this project. One of the main challenges in this project was installing these libraries on my laptop. First I tried to install them in Windows, however, I encountered with an error that I couldn t solve it. So, I tried to install them in Linux, Ubuntu 10.04, and finally I was successful in installing them. Unfortunately, some of these libraries don t have proper documentation, so I started to understand how to use them by looking through the code. A. Theory Description of the Method 1) Input: The input for this framework is prepare by using Kinect. The framework is designed in a way that the Kinect devise should be faced down to capture a scene or object from above. I made a ramp for this purpose Fig. 2. If one wants to cature a whole scene or object aspects, Kinect should face down. The program will produce acceptable results if the amount of shake in capturing the scene is not a lot. So, the user should move Kinect slowly with less vibration. Figure 2. The position of Kinect while we want to capture images or video. 2) Camera Calibration: As long as the Kinect camera and Kinect depth sensor are not in a same position (Fig. 3) [34], so we need to map and calibrate the depth data with rgb frame. For knowing the translation martix and rotation matrix, we can use the available information in OpenNI [35] for calibration. However, if one wants to do more pricise work such as robatic vision, they can calibrate their own Kinect. For this project, I used the calibration information in OpenNI. Figure 3. Kinect Elements

4 3) Extracting RGB Features: In this step the program will extract the features from the series of an images which is catured during the time and each time a new image receive, the program will do the same senario for the new image. For extracting features, first it uses a dector to detect the features within images, then it will use an algorithm as an describtor to find the best matches between two images. 4) Finding Closest View and Best Matches: By means of feature matching the program will find the closest view from all the collected images data up to now. 5) Optimization: After we find the closest view, we need to find the transformation matrix between the closest view and current view. So, we need to use the best optimizer in order to minimize the error between the two images. For this purpose, I compared two optimization algortithm below. The result of the optimization will be accepted if the error is less than threshold. Otherwise, the current image will be discarded. a) RANSAC (RANdom SAmple Consensus): This algorithm is useful for 2D RGB images and will iteratively find the corresponding points (feature in this project) and minimize the error between matching points. (Fig. 4) b) ICP(Iterative Closest Point): This algorithm is can be used for point clouds and it will find the corresponding points iteratively 6) Rendering 3D Points: By finding the transformation matrix between current view and closest view, the program will compute the normals for each point and some filtering processing will be executed in order to render the applicable points in the 3D viewer. (Fig. 5) B. Comparision In order to extract features, there are many algorithms that are introduced for detecting features. Algorithms that I have used to check whether they are useful for 3D reconstruction of a scene or object using Kinect or not. As long as the resolution of the Kinect camera is , the quality of images are not very high. Therefore, we should compare the available algorithm whether they are useful for extracting features from images. I used FAST (Features from Accelerated Segment Test)[36], SIFT (Scale-invariant feature transform) [37] and SURF (Speeded Up Robust Features) [38]. FAST is useful for corner detection. SIFT is useful for local features and SURF which is similar to SIFT algorithm but it is more robust to the different image transformation. After we detected our features from images, we need to find best matches between two images. So, as a descriptor I compared SIFT, SURF and BRIEF (Binary Robust Independent Elementary Features) [39]. In the Table 1, the results of this comparisons can be found. (Fig. 5) Table 1. Comparision of detector and descriptor for feature matching. Detector Descriptor Result FAST/SURF BRIEF Slow / Not complete reconstruction / Wrong matching SURF SURF Fast/ Good result SIFT/FAST SIFT/SURF Slow / Not complete reconstruction As you can see in the table 1, the SURF and SURF is the best option for this project. So, I used this combination for feature matching in scene and object reconstruction. Figure 4. RANSAC 3D representation C. Final Reconstrucion The program is able to reconstruct the 3D model of a scene or object by the preference of the user. 1) Scene Reconstruction: The program is able to reconstruct a point cloud representation of the scene using the method described earlier.

5 IV. EXPERIMENTAL RESULTS A. Final Results for Scene Reconstruction: The result for scene reconstruction can be seen in Fig. 6. B. Final Results for Object Reconstruction: The result for object reconstruction in Fig. 7. Figure 7. Object recontruction. Figure 5. The top image refer to the result of SIFT-SIFT. The second image refer to the wrong matching caused by BRIEF. 2) Object Reconstruction: The program will reconstruct an object by capturing the images from the object from different view-points and it will gradually reconstruct an object. The program will detect the object in 2D image and then I will detect the object in 3D space. So, the object will not reconstruct the points which is not related to the object. V. CONCLUSION AND FUTURE WORK In this project, we represented the method that uses Kinect and its depth data in order to reconstruct 3D model of a scene or object. The program will simply capture some images or get the whole view-points of the scene/object. As a future work, this framework can be extended in a way that the algorithm become more robust to the movement of the Kinect while obtaining the data from a scene or object. ACKNOWLEDGMENT I thank Dr. Martin Jagersand for his helpful advises for defining the correct course project. Figure 6. Scene Recustroction using ICP. REFERENCES [1] Microsoft: Kinect for X-BOX (2010) [2] Wikipedia: Kinect. [3] Freedman, B., Shpunt, A., Machline, M., Arieli, Y.: Depth mapping using projected patterns.us Patent (2010) [4] Henry, P., Krainin, M., Herbst, E., Ren, X., Fox, D.: RGB-D mapping: using Kinect-style depth cameras for dense 3d modeling of indoor environments. Int. J. Robot. Res. (2012). doi: / [5] Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux, Richard Newcombe, Pushmeet Kohli, Jamie hotton, Steve Hodges, Dustin Freeman, Andrew Davison, and Andrew Fitzgibbon KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In Proceedings of the 24th annual ACM symposium on User interface software

6 and technology (UIST '11). ACM, New York, NY, USA, [6] Newcombe, Richard A.; Davison, Andrew J.; Izadi, Shahram; Kohli, Pushmeet; Hilliges, Otmar; Shotton, Jamie; Molyneaux, David; Hodges, Steve; Kim, David; Fitzgibbon, Andrew; "KinectFusion: Real-time dense surface mapping and tracking," Mixed and Augmented Reality (ISMAR), th IEEE International Symposium on, vol., no., pp , Oct [7] Lai, K., Bo, L., Ren, X., Fox, D.: Sparse distance learning for object recognition combining RGB and depth information. In: IEEE International Conference on Robotics and Automation (2011) [8] M. Levoy et al. The digital Michelangelo Project: 3D scanning of large statues. ACM Trans. Graph., [9] R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, second edition, [10] P. Merrell et al. Real-time visibility-based fusion of depth maps. In Proc. of the Int. Conf. on Computer Vision (ICCV), [11] M. Kazhdan, M. Bolitho, and H. Hoppe. Poisson surface reconstruction. In Proc. of the Eurographics Symposium on Geometry Processing, [12] K. Zhou, M. Gong, X. Huang, and B. Guo. Dataparallel octrees for surface reconstruction. IEEE Trans. on Visualization and Computer Graphics, 17, [13] J. Frahm et al. Building Rome on a cloudless day. In Proc. Europ. Conf. on Computer Vision (ECCV), [14] [15] O. Faugeras and R. Keriven, Variational principles, surface evolution, PDE s, level set methods and the stereo problem, IEEE Trans. Im. Proc., vol. 7, no. 3, pp , [16] S. Paris, F. Sillion, and L. Quan, A surface reconstruction method using global graph cut optimization, in ACCV, January [Online]. Available: [17] J.-P. Pons, R. Keriven, and O. D. Faugeras, Multiview stereo reconstruction and scene flow estimation with a global image-based matching score, IJCV, vol. 72, no. 2, pp , [18] B. Baumgart, Geometric modeling for computer vision, Ph.D. dissertation, Stanford University, [19] D. Bradley, T. Boubekeur, and W. Heidrich, Accurate multi-view reconstruction using robust binocular stereo and surface meshing, in CVPR, [20] Y. Furukawa, and J. Ponce, Accurate, Dense, and Robust Multi-View Stereopsis, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, Issue 8, Pages , August [21] L. Kobbelt and M. Botsch, A survey of point-based techniques in computer graphics. Computers & Graphics, vol. 28, no. 6, pp , [22] BESL, P., AND MCKAY, N A method for registration of 3D shapes [23] Herrera C., Daniel; Kannala, Juho; Heikkilä, Janne, "Joint Depth and Color Camera Calibration with Distortion Correction," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.34, no.10, pp.2058,2064, Oct [24] Pons, J., Keriven, R., Faugeras, O. Multi-view stereo reconstruction and scene flow estimation with a global image-based matching score, IJCV, Springer, 72(2), (2007). [25] Grauman, K., Shakhnarovich, G., Darrell, T.: A Bayesian Approach to Image-Based Visual Hull Reconstruction. In CVPR, 187{194, (2003). [26] Franco, J., Boyer, E.: Fusion of multi-view silhouette cues using a space occupancy grid. In ICCV, 2, , (2005). [27] Kutulakos, K., Seitz, S.: A Theory of Shape by Space Carving. In International Journal of Computer Vision, 38(3), 199{218, (2000). [28] Osher, S., Sethian, J.: Fronts propagating with curvature-dependent speed: algorithms based on hamilton-jacobi equations. J. of Comp. Physics, 79, 12{49,(1988). [29] Lhuillier, M., Quan, L.: A Quasi-Dense Approach to Surface Reconstruction from Uncalibrated Images, TPAMI, 27(3), 418{433, (2005). [30] Lorensen, W.E,Cline, H.E.Marching cubes: A high resolution 3D surface construction algorithm. ACM [31] [32] senestk [33] [34] Herrera C., Daniel; Kannala, Juho; Heikkilä, Janne, "Joint Depth and Color Camera Calibration with Distortion Correction," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.34, no.10, pp.2058,2064, Oct [35] [36] E. Rosten and T. Drummond (May 2006). "Machine learning for high-speed corner detection,". European Conference on Computer Vision. [37] Lowe, David G. (1999). "Object recognition from local scale-invariant features". Proceedings of the International Conference on Computer Vision. 2. pp [38] Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding (CVIU), Vol. 110, No. 3, pp , [39] Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua BRIEF: binary robust independent elementary features. In Proceedings of the 11th European conference on Computer vision: Part IV (ECCV'10), Kostas Daniilidis, Petros Maragos, and Nikos Paragios (Eds.). Springer-Verlag, Berlin, Heidelberg,

Multi-view stereo. Many slides adapted from S. Seitz

Multi-view stereo. Many slides adapted from S. Seitz Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window

More information

Mobile Point Fusion. Real-time 3d surface reconstruction out of depth images on a mobile platform

Mobile Point Fusion. Real-time 3d surface reconstruction out of depth images on a mobile platform Mobile Point Fusion Real-time 3d surface reconstruction out of depth images on a mobile platform Aaron Wetzler Presenting: Daniel Ben-Hoda Supervisors: Prof. Ron Kimmel Gal Kamar Yaron Honen Supported

More information

A Real-Time RGB-D Registration and Mapping Approach by Heuristically Switching Between Photometric And Geometric Information

A Real-Time RGB-D Registration and Mapping Approach by Heuristically Switching Between Photometric And Geometric Information A Real-Time RGB-D Registration and Mapping Approach by Heuristically Switching Between Photometric And Geometric Information The 17th International Conference on Information Fusion (Fusion 2014) Khalid

More information

Some books on linear algebra

Some books on linear algebra Some books on linear algebra Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Linear Algebra, Serge Lang, 2004 Linear Algebra and its Applications, Gilbert Strang, 1988 Matrix Computation, Gene H.

More information

High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images

High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images MECATRONICS - REM 2016 June 15-17, 2016 High-speed Three-dimensional Mapping by Direct Estimation of a Small Motion Using Range Images Shinta Nozaki and Masashi Kimura School of Science and Engineering

More information

Geometric Reconstruction Dense reconstruction of scene geometry

Geometric Reconstruction Dense reconstruction of scene geometry Lecture 5. Dense Reconstruction and Tracking with Real-Time Applications Part 2: Geometric Reconstruction Dr Richard Newcombe and Dr Steven Lovegrove Slide content developed from: [Newcombe, Dense Visual

More information

Mesh from Depth Images Using GR 2 T

Mesh from Depth Images Using GR 2 T Mesh from Depth Images Using GR 2 T Mairead Grogan & Rozenn Dahyot School of Computer Science and Statistics Trinity College Dublin Dublin, Ireland mgrogan@tcd.ie, Rozenn.Dahyot@tcd.ie www.scss.tcd.ie/

More information

Image Based Reconstruction II

Image Based Reconstruction II Image Based Reconstruction II Qixing Huang Feb. 2 th 2017 Slide Credit: Yasutaka Furukawa Image-Based Geometry Reconstruction Pipeline Last Lecture: Multi-View SFM Multi-View SFM This Lecture: Multi-View

More information

Object Reconstruction

Object Reconstruction B. Scholz Object Reconstruction 1 / 39 MIN-Fakultät Fachbereich Informatik Object Reconstruction Benjamin Scholz Universität Hamburg Fakultät für Mathematik, Informatik und Naturwissenschaften Fachbereich

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem

More information

Dense 3D Reconstruction. Christiano Gava

Dense 3D Reconstruction. Christiano Gava Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction

More information

International Journal for Research in Applied Science & Engineering Technology (IJRASET) A Review: 3D Image Reconstruction From Multiple Images

International Journal for Research in Applied Science & Engineering Technology (IJRASET) A Review: 3D Image Reconstruction From Multiple Images A Review: 3D Image Reconstruction From Multiple Images Rahul Dangwal 1, Dr. Sukhwinder Singh 2 1 (ME Student) Department of E.C.E PEC University of TechnologyChandigarh, India-160012 2 (Supervisor)Department

More information

Prof. Trevor Darrell Lecture 18: Multiview and Photometric Stereo

Prof. Trevor Darrell Lecture 18: Multiview and Photometric Stereo C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 18: Multiview and Photometric Stereo Today Multiview stereo revisited Shape from large image collections Voxel Coloring Digital

More information

3D Environment Reconstruction

3D Environment Reconstruction 3D Environment Reconstruction Using Modified Color ICP Algorithm by Fusion of a Camera and a 3D Laser Range Finder The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems October 11-15,

More information

Local features and image matching. Prof. Xin Yang HUST

Local features and image matching. Prof. Xin Yang HUST Local features and image matching Prof. Xin Yang HUST Last time RANSAC for robust geometric transformation estimation Translation, Affine, Homography Image warping Given a 2D transformation T and a source

More information

Outline. 1 Why we re interested in Real-Time tracking and mapping. 3 Kinect Fusion System Overview. 4 Real-time Surface Mapping

Outline. 1 Why we re interested in Real-Time tracking and mapping. 3 Kinect Fusion System Overview. 4 Real-time Surface Mapping Outline CSE 576 KinectFusion: Real-Time Dense Surface Mapping and Tracking PhD. work from Imperial College, London Microsoft Research, Cambridge May 6, 2013 1 Why we re interested in Real-Time tracking

More information

Visualization of Temperature Change using RGB-D Camera and Thermal Camera

Visualization of Temperature Change using RGB-D Camera and Thermal Camera 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 Visualization of Temperature

More information

Lecture 8 Active stereo & Volumetric stereo

Lecture 8 Active stereo & Volumetric stereo Lecture 8 Active stereo & Volumetric stereo Active stereo Structured lighting Depth sensing Volumetric stereo: Space carving Shadow carving Voxel coloring Reading: [Szelisky] Chapter 11 Multi-view stereo

More information

3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation

3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation 3D Line Segment Based Model Generation by RGB-D Camera for Camera Pose Estimation Yusuke Nakayama, Hideo Saito, Masayoshi Shimizu, and Nobuyasu Yamaguchi Graduate School of Science and Technology, Keio

More information

Dual Back-to-Back Kinects for 3-D Reconstruction

Dual Back-to-Back Kinects for 3-D Reconstruction Ho Chuen Kam, Kin Hong Wong and Baiwu Zhang, Dual Back-to-Back Kinects for 3-D Reconstruction, ISVC'16 12th International Symposium on Visual Computing December 12-14, 2016, Las Vegas, Nevada, USA. Dual

More information

3D Surface Reconstruction from 2D Multiview Images using Voxel Mapping

3D Surface Reconstruction from 2D Multiview Images using Voxel Mapping 74 3D Surface Reconstruction from 2D Multiview Images using Voxel Mapping 1 Tushar Jadhav, 2 Kulbir Singh, 3 Aditya Abhyankar 1 Research scholar, 2 Professor, 3 Dean 1 Department of Electronics & Telecommunication,Thapar

More information

Multi-View 3D-Reconstruction

Multi-View 3D-Reconstruction Multi-View 3D-Reconstruction Cedric Cagniart Computer Aided Medical Procedures (CAMP) Technische Universität München, Germany 1 Problem Statement Given several calibrated views of an object... can we automatically

More information

An Evaluation of Volumetric Interest Points

An Evaluation of Volumetric Interest Points An Evaluation of Volumetric Interest Points Tsz-Ho YU Oliver WOODFORD Roberto CIPOLLA Machine Intelligence Lab Department of Engineering, University of Cambridge About this project We conducted the first

More information

3D map reconstruction with sensor Kinect

3D map reconstruction with sensor Kinect 3D map reconstruction with sensor Kinect Searching for solution applicable to small mobile robots Peter Beňo, František Duchoň, Michal Tölgyessy, Peter Hubinský, Martin Kajan Institute of Robotics and

More information

Image-based ICP Algorithm for Visual Odometry Using a RGB-D Sensor in a Dynamic Environment

Image-based ICP Algorithm for Visual Odometry Using a RGB-D Sensor in a Dynamic Environment Image-based ICP Algorithm for Visual Odometry Using a RGB-D Sensor in a Dynamic Environment Deok-Hwa Kim and Jong-Hwan Kim Department of Robotics Program, KAIST 335 Gwahangno, Yuseong-gu, Daejeon 305-701,

More information

3D Object Representations. COS 526, Fall 2016 Princeton University

3D Object Representations. COS 526, Fall 2016 Princeton University 3D Object Representations COS 526, Fall 2016 Princeton University 3D Object Representations How do we... Represent 3D objects in a computer? Acquire computer representations of 3D objects? Manipulate computer

More information

3D Photography: Stereo Matching

3D Photography: Stereo Matching 3D Photography: Stereo Matching Kevin Köser, Marc Pollefeys Spring 2012 http://cvg.ethz.ch/teaching/2012spring/3dphoto/ Stereo & Multi-View Stereo Tsukuba dataset http://cat.middlebury.edu/stereo/ Stereo

More information

Handheld scanning with ToF sensors and cameras

Handheld scanning with ToF sensors and cameras Handheld scanning with ToF sensors and cameras Enrico Cappelletto, Pietro Zanuttigh, Guido Maria Cortelazzo Dept. of Information Engineering, University of Padova enrico.cappelletto,zanuttigh,corte@dei.unipd.it

More information

An Image Based 3D Reconstruction System for Large Indoor Scenes

An Image Based 3D Reconstruction System for Large Indoor Scenes 36 5 Vol. 36, No. 5 2010 5 ACTA AUTOMATICA SINICA May, 2010 1 1 2 1,,,..,,,,. : 1), ; 2), ; 3),.,,. DOI,,, 10.3724/SP.J.1004.2010.00625 An Image Based 3D Reconstruction System for Large Indoor Scenes ZHANG

More information

A Statistical Consistency Check for the Space Carving Algorithm.

A Statistical Consistency Check for the Space Carving Algorithm. A Statistical Consistency Check for the Space Carving Algorithm. A. Broadhurst and R. Cipolla Dept. of Engineering, Univ. of Cambridge, Cambridge, CB2 1PZ aeb29 cipolla @eng.cam.ac.uk Abstract This paper

More information

3D Reconstruction from Multi-View Stereo: Implementation Verification via Oculus Virtual Reality

3D Reconstruction from Multi-View Stereo: Implementation Verification via Oculus Virtual Reality 3D Reconstruction from Multi-View Stereo: Implementation Verification via Oculus Virtual Reality Andrew Moran MIT, Class of 2014 andrewmo@mit.edu Ben Eysenbach MIT, Class of 2017 bce@mit.edu Abstract We

More information

Project Updates Short lecture Volumetric Modeling +2 papers

Project Updates Short lecture Volumetric Modeling +2 papers Volumetric Modeling Schedule (tentative) Feb 20 Feb 27 Mar 5 Introduction Lecture: Geometry, Camera Model, Calibration Lecture: Features, Tracking/Matching Mar 12 Mar 19 Mar 26 Apr 2 Apr 9 Apr 16 Apr 23

More information

Step-by-Step Model Buidling

Step-by-Step Model Buidling Step-by-Step Model Buidling Review Feature selection Feature selection Feature correspondence Camera Calibration Euclidean Reconstruction Landing Augmented Reality Vision Based Control Sparse Structure

More information

Volumetric Scene Reconstruction from Multiple Views

Volumetric Scene Reconstruction from Multiple Views Volumetric Scene Reconstruction from Multiple Views Chuck Dyer University of Wisconsin dyer@cs cs.wisc.edu www.cs cs.wisc.edu/~dyer Image-Based Scene Reconstruction Goal Automatic construction of photo-realistic

More information

LOCAL AND GLOBAL DESCRIPTORS FOR PLACE RECOGNITION IN ROBOTICS

LOCAL AND GLOBAL DESCRIPTORS FOR PLACE RECOGNITION IN ROBOTICS 8th International DAAAM Baltic Conference "INDUSTRIAL ENGINEERING - 19-21 April 2012, Tallinn, Estonia LOCAL AND GLOBAL DESCRIPTORS FOR PLACE RECOGNITION IN ROBOTICS Shvarts, D. & Tamre, M. Abstract: The

More information

Some books on linear algebra

Some books on linear algebra Some books on linear algebra Finite Dimensional Vector Spaces, Paul R. Halmos, 1947 Linear Algebra, Serge Lang, 2004 Linear Algebra and its Applications, Gilbert Strang, 1988 Matrix Computation, Gene H.

More information

Real-Time Video-Based Rendering from Multiple Cameras

Real-Time Video-Based Rendering from Multiple Cameras Real-Time Video-Based Rendering from Multiple Cameras Vincent Nozick Hideo Saito Graduate School of Science and Technology, Keio University, Japan E-mail: {nozick,saito}@ozawa.ics.keio.ac.jp Abstract In

More information

Rigid ICP registration with Kinect

Rigid ICP registration with Kinect Rigid ICP registration with Kinect Students: Yoni Choukroun, Elie Semmel Advisor: Yonathan Aflalo 1 Overview.p.3 Development of the project..p.3 Papers p.4 Project algorithm..p.6 Result of the whole body.p.7

More information

Robust Online 3D Reconstruction Combining a Depth Sensor and Sparse Feature Points

Robust Online 3D Reconstruction Combining a Depth Sensor and Sparse Feature Points 2016 23rd International Conference on Pattern Recognition (ICPR) Cancún Center, Cancún, México, December 4-8, 2016 Robust Online 3D Reconstruction Combining a Depth Sensor and Sparse Feature Points Erik

More information

URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES

URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES An Undergraduate Research Scholars Thesis by RUI LIU Submitted to Honors and Undergraduate Research Texas A&M University in partial fulfillment

More information

03 - Reconstruction. Acknowledgements: Olga Sorkine-Hornung. CSCI-GA Geometric Modeling - Spring 17 - Daniele Panozzo

03 - Reconstruction. Acknowledgements: Olga Sorkine-Hornung. CSCI-GA Geometric Modeling - Spring 17 - Daniele Panozzo 3 - Reconstruction Acknowledgements: Olga Sorkine-Hornung Geometry Acquisition Pipeline Scanning: results in range images Registration: bring all range images to one coordinate system Stitching/ reconstruction:

More information

A Flexible Scene Representation for 3D Reconstruction Using an RGB-D Camera

A Flexible Scene Representation for 3D Reconstruction Using an RGB-D Camera 2013 IEEE International Conference on Computer Vision A Flexible Scene Representation for 3D Reconstruction Using an RGB-D Camera Diego Thomas National Institute of Informatics Chiyoda, Tokyo, Japan diego

More information

Visualization of Temperature Change using RGB-D Camera and Thermal Camera

Visualization of Temperature Change using RGB-D Camera and Thermal Camera Visualization of Temperature Change using RGB-D Camera and Thermal Camera Wataru Nakagawa, Kazuki Matsumoto, Francois de Sorbier, Maki Sugimoto, Hideo Saito, Shuji Senda, Takashi Shibata, and Akihiko Iketani

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics 13.01.2015 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar in the summer semester

More information

AN INDOOR SLAM METHOD BASED ON KINECT AND MULTI-FEATURE EXTENDED INFORMATION FILTER

AN INDOOR SLAM METHOD BASED ON KINECT AND MULTI-FEATURE EXTENDED INFORMATION FILTER AN INDOOR SLAM METHOD BASED ON KINECT AND MULTI-FEATURE EXTENDED INFORMATION FILTER M. Chang a, b, Z. Kang a, a School of Land Science and Technology, China University of Geosciences, 29 Xueyuan Road,

More information

Memory Management Method for 3D Scanner Using GPGPU

Memory Management Method for 3D Scanner Using GPGPU GPGPU 3D 1 2 KinectFusion GPGPU 3D., GPU., GPGPU Octree. GPU,,. Memory Management Method for 3D Scanner Using GPGPU TATSUYA MATSUMOTO 1 SATORU FUJITA 2 This paper proposes an efficient memory management

More information

Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting

Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1

More information

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix

More information

Local Patch Descriptors

Local Patch Descriptors Local Patch Descriptors Slides courtesy of Steve Seitz and Larry Zitnick CSE 803 1 How do we describe an image patch? How do we describe an image patch? Patches with similar content should have similar

More information

Computer Vision Lecture 17

Computer Vision Lecture 17 Announcements Computer Vision Lecture 17 Epipolar Geometry & Stereo Basics Seminar in the summer semester Current Topics in Computer Vision and Machine Learning Block seminar, presentations in 1 st week

More information

When Can We Use KinectFusion for Ground Truth Acquisition?

When Can We Use KinectFusion for Ground Truth Acquisition? When Can We Use KinectFusion for Ground Truth Acquisition? Stephan Meister 1, Shahram Izadi 2, Pushmeet Kohli 3, Martin Hämmerle 4, Carsten Rother 5 and Daniel Kondermann 6 Abstract KinectFusion is a method

More information

Virtualized Reality Using Depth Camera Point Clouds

Virtualized Reality Using Depth Camera Point Clouds Virtualized Reality Using Depth Camera Point Clouds Jordan Cazamias Stanford University jaycaz@stanford.edu Abhilash Sunder Raj Stanford University abhisr@stanford.edu Abstract We explored various ways

More information

A New Approach For 3D Image Reconstruction From Multiple Images

A New Approach For 3D Image Reconstruction From Multiple Images International Journal of Electronics Engineering Research. ISSN 0975-6450 Volume 9, Number 4 (2017) pp. 569-574 Research India Publications http://www.ripublication.com A New Approach For 3D Image Reconstruction

More information

Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization

Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization Appearance-Based Place Recognition Using Whole-Image BRISK for Collaborative MultiRobot Localization Jung H. Oh, Gyuho Eoh, and Beom H. Lee Electrical and Computer Engineering, Seoul National University,

More information

Passive 3D Photography

Passive 3D Photography SIGGRAPH 2000 Course on 3D Photography Passive 3D Photography Steve Seitz Carnegie Mellon University University of Washington http://www.cs cs.cmu.edu/~ /~seitz Visual Cues Shading Merle Norman Cosmetics,

More information

Multi-View Reconstruction Preserving Weakly-Supported Surfaces

Multi-View Reconstruction Preserving Weakly-Supported Surfaces Multi-View Reconstruction Preserving Weakly-Supported Surfaces Michal Jancosek and Tomas Pajdla Center for Machine Perception, Department of Cybernetics Faculty of Elec. Eng., Czech Technical University

More information

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching

CS 4495 Computer Vision A. Bobick. Motion and Optic Flow. Stereo Matching Stereo Matching Fundamental matrix Let p be a point in left image, p in right image l l Epipolar relation p maps to epipolar line l p maps to epipolar line l p p Epipolar mapping described by a 3x3 matrix

More information

3D Editing System for Captured Real Scenes

3D Editing System for Captured Real Scenes 3D Editing System for Captured Real Scenes Inwoo Ha, Yong Beom Lee and James D.K. Kim Samsung Advanced Institute of Technology, Youngin, South Korea E-mail: {iw.ha, leey, jamesdk.kim}@samsung.com Tel:

More information

Multiple View Depth Generation Based on 3D Scene Reconstruction Using Heterogeneous Cameras

Multiple View Depth Generation Based on 3D Scene Reconstruction Using Heterogeneous Cameras https://doi.org/0.5/issn.70-7.07.7.coimg- 07, Society for Imaging Science and Technology Multiple View Generation Based on D Scene Reconstruction Using Heterogeneous Cameras Dong-Won Shin and Yo-Sung Ho

More information

Removing Moving Objects from Point Cloud Scenes

Removing Moving Objects from Point Cloud Scenes Removing Moving Objects from Point Cloud Scenes Krystof Litomisky and Bir Bhanu University of California, Riverside krystof@litomisky.com, bhanu@ee.ucr.edu Abstract. Three-dimensional simultaneous localization

More information

Large Scale 3D Reconstruction by Structure from Motion

Large Scale 3D Reconstruction by Structure from Motion Large Scale 3D Reconstruction by Structure from Motion Devin Guillory Ziang Xie CS 331B 7 October 2013 Overview Rome wasn t built in a day Overview of SfM Building Rome in a Day Building Rome on a Cloudless

More information

A Stable and Accurate Marker-less Augmented Reality Registration Method

A Stable and Accurate Marker-less Augmented Reality Registration Method A Stable and Accurate Marker-less Augmented Reality Registration Method Qing Hong Gao College of Electronic and Information Xian Polytechnic University, Xian, China Long Chen Faculty of Science and Technology

More information

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.

3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University. 3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,

More information

Quasi-Dense Wide Baseline Matching Using Match Propagation

Quasi-Dense Wide Baseline Matching Using Match Propagation Quasi-Dense Wide Baseline Matching Using Match Propagation Juho Kannala and Sami S. Brandt Machine Vision Group University of Oulu, Finland {jkannala,sbrandt}@ee.oulu.fi Abstract In this paper we propose

More information

Reconstruction of 3D Models Consisting of Line Segments

Reconstruction of 3D Models Consisting of Line Segments Reconstruction of 3D Models Consisting of Line Segments Naoto Ienaga (B) and Hideo Saito Department of Information and Computer Science, Keio University, Yokohama, Japan {ienaga,saito}@hvrl.ics.keio.ac.jp

More information

Multiple View Geometry

Multiple View Geometry Multiple View Geometry Martin Quinn with a lot of slides stolen from Steve Seitz and Jianbo Shi 15-463: Computational Photography Alexei Efros, CMU, Fall 2007 Our Goal The Plenoptic Function P(θ,φ,λ,t,V

More information

EECS 442 Computer vision. Announcements

EECS 442 Computer vision. Announcements EECS 442 Computer vision Announcements Midterm released after class (at 5pm) You ll have 46 hours to solve it. it s take home; you can use your notes and the books no internet must work on it individually

More information

A NEW AUTOMATIC SYSTEM CALIBRATION OF MULTI-CAMERAS AND LIDAR SENSORS

A NEW AUTOMATIC SYSTEM CALIBRATION OF MULTI-CAMERAS AND LIDAR SENSORS A NEW AUTOMATIC SYSTEM CALIBRATION OF MULTI-CAMERAS AND LIDAR SENSORS M. Hassanein a, *, A. Moussa a,b, N. El-Sheimy a a Department of Geomatics Engineering, University of Calgary, Calgary, Alberta, Canada

More information

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava

3D Computer Vision. Dense 3D Reconstruction II. Prof. Didier Stricker. Christiano Gava 3D Computer Vision Dense 3D Reconstruction II Prof. Didier Stricker Christiano Gava Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de

More information

Robot localization method based on visual features and their geometric relationship

Robot localization method based on visual features and their geometric relationship , pp.46-50 http://dx.doi.org/10.14257/astl.2015.85.11 Robot localization method based on visual features and their geometric relationship Sangyun Lee 1, Changkyung Eem 2, and Hyunki Hong 3 1 Department

More information

Shape from Silhouettes I CV book Szelisky

Shape from Silhouettes I CV book Szelisky Shape from Silhouettes I CV book Szelisky 11.6.2 Guido Gerig CS 6320, Spring 2012 (slides modified from Marc Pollefeys UNC Chapel Hill, some of the figures and slides are adapted from M. Pollefeys, J.S.

More information

Accurate and Dense Wide-Baseline Stereo Matching Using SW-POC

Accurate and Dense Wide-Baseline Stereo Matching Using SW-POC Accurate and Dense Wide-Baseline Stereo Matching Using SW-POC Shuji Sakai, Koichi Ito, Takafumi Aoki Graduate School of Information Sciences, Tohoku University, Sendai, 980 8579, Japan Email: sakai@aoki.ecei.tohoku.ac.jp

More information

Talk plan. 3d model. Applications: cultural heritage 5/9/ d shape reconstruction from photographs: a Multi-View Stereo approach

Talk plan. 3d model. Applications: cultural heritage 5/9/ d shape reconstruction from photographs: a Multi-View Stereo approach Talk plan 3d shape reconstruction from photographs: a Multi-View Stereo approach Introduction Multi-View Stereo pipeline Carlos Hernández George Vogiatzis Yasutaka Furukawa Google Aston University Google

More information

IMAGE RETRIEVAL USING VLAD WITH MULTIPLE FEATURES

IMAGE RETRIEVAL USING VLAD WITH MULTIPLE FEATURES IMAGE RETRIEVAL USING VLAD WITH MULTIPLE FEATURES Pin-Syuan Huang, Jing-Yi Tsai, Yu-Fang Wang, and Chun-Yi Tsai Department of Computer Science and Information Engineering, National Taitung University,

More information

A Comparison of SIFT, PCA-SIFT and SURF

A Comparison of SIFT, PCA-SIFT and SURF A Comparison of SIFT, PCA-SIFT and SURF Luo Juan Computer Graphics Lab, Chonbuk National University, Jeonju 561-756, South Korea qiuhehappy@hotmail.com Oubong Gwun Computer Graphics Lab, Chonbuk National

More information

arxiv: v1 [cs.cv] 1 Jan 2019

arxiv: v1 [cs.cv] 1 Jan 2019 Mapping Areas using Computer Vision Algorithms and Drones Bashar Alhafni Saulo Fernando Guedes Lays Cavalcante Ribeiro Juhyun Park Jeongkyu Lee University of Bridgeport. Bridgeport, CT, 06606. United States

More information

arxiv: v1 [cs.cv] 28 Sep 2018

arxiv: v1 [cs.cv] 28 Sep 2018 Extrinsic camera calibration method and its performance evaluation Jacek Komorowski 1 and Przemyslaw Rokita 2 arxiv:1809.11073v1 [cs.cv] 28 Sep 2018 1 Maria Curie Sklodowska University Lublin, Poland jacek.komorowski@gmail.com

More information

A Integrated Depth Fusion Algorithm for Multi-View Stereo

A Integrated Depth Fusion Algorithm for Multi-View Stereo A Integrated Depth Fusion Algorithm for Multi-View Stereo Yongjian Xi, Ye Duan University of Missouri at Columbia Abstract. In this paper, we propose a new integrated depth fusion algorithm for multi-view

More information

Patch Descriptors. CSE 455 Linda Shapiro

Patch Descriptors. CSE 455 Linda Shapiro Patch Descriptors CSE 455 Linda Shapiro How can we find corresponding points? How can we find correspondences? How do we describe an image patch? How do we describe an image patch? Patches with similar

More information

Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images

Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images Ebrahim Karami, Siva Prasad, and Mohamed Shehata Faculty of Engineering and Applied Sciences, Memorial University,

More information

Dense 3D Reconstruction from Autonomous Quadrocopters

Dense 3D Reconstruction from Autonomous Quadrocopters Dense 3D Reconstruction from Autonomous Quadrocopters Computer Science & Mathematics TU Munich Martin Oswald, Jakob Engel, Christian Kerl, Frank Steinbrücker, Jan Stühmer & Jürgen Sturm Autonomous Quadrocopters

More information

3D Colored Model Generation Based on Multiview Textures and Triangular Mesh

3D Colored Model Generation Based on Multiview Textures and Triangular Mesh 3D Colored Model Generation Based on Multiview Textures and Triangular Mesh Lingni Ma, Luat Do, Egor Bondarev and Peter H. N. de With Department of Electrical Engineering, Eindhoven University of Technology

More information

Local Image Features

Local Image Features Local Image Features Ali Borji UWM Many slides from James Hayes, Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Overview of Keypoint Matching 1. Find a set of distinctive key- points A 1 A 2 A 3 B 3

More information

Semantic 3D Reconstruction of Heads Supplementary Material

Semantic 3D Reconstruction of Heads Supplementary Material Semantic 3D Reconstruction of Heads Supplementary Material Fabio Maninchedda1, Christian Ha ne2,?, Bastien Jacquet3,?, Amae l Delaunoy?, Marc Pollefeys1,4 1 ETH Zurich 2 UC Berkeley 3 Kitware SAS 4 Microsoft

More information

Chaplin, Modern Times, 1936

Chaplin, Modern Times, 1936 Chaplin, Modern Times, 1936 [A Bucket of Water and a Glass Matte: Special Effects in Modern Times; bonus feature on The Criterion Collection set] Multi-view geometry problems Structure: Given projections

More information

Nonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H.

Nonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H. Nonrigid Surface Modelling and Fast Recovery Zhu Jianke Supervisor: Prof. Michael R. Lyu Committee: Prof. Leo J. Jia and Prof. K. H. Wong Department of Computer Science and Engineering May 11, 2007 1 2

More information

SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE

SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE S. Hirose R&D Center, TOPCON CORPORATION, 75-1, Hasunuma-cho, Itabashi-ku, Tokyo, Japan Commission

More information

Live Metric 3D Reconstruction on Mobile Phones ICCV 2013

Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 Main Contents 1. Target & Related Work 2. Main Features of This System 3. System Overview & Workflow 4. Detail of This System 5. Experiments 6.

More information

Shape from Silhouettes

Shape from Silhouettes Shape from Silhouettes Schedule (tentative) 2 # date topic 1 Sep.22 Introduction and geometry 2 Sep.29 Invariant features 3 Oct.6 Camera models and calibration 4 Oct.13 Multiple-view geometry 5 Oct.20

More information

Specular 3D Object Tracking by View Generative Learning

Specular 3D Object Tracking by View Generative Learning Specular 3D Object Tracking by View Generative Learning Yukiko Shinozuka, Francois de Sorbier and Hideo Saito Keio University 3-14-1 Hiyoshi, Kohoku-ku 223-8522 Yokohama, Japan shinozuka@hvrl.ics.keio.ac.jp

More information

ABSTRACT. KinectFusion is a surface reconstruction method to allow a user to rapidly

ABSTRACT. KinectFusion is a surface reconstruction method to allow a user to rapidly ABSTRACT Title of Thesis: A REAL TIME IMPLEMENTATION OF 3D SYMMETRIC OBJECT RECONSTRUCTION Liangchen Xi, Master of Science, 2017 Thesis Directed By: Professor Yiannis Aloimonos Department of Computer Science

More information

Review on Feature Detection and Matching Algorithms for 3D Object Reconstruction

Review on Feature Detection and Matching Algorithms for 3D Object Reconstruction Review on Feature Detection and Matching Algorithms for 3D Object Reconstruction Amit Banda 1,Rajesh Patil 2 1 M. Tech Scholar, 2 Associate Professor Electrical Engineering Dept.VJTI, Mumbai, India Abstract

More information

Computer Vision. I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University

Computer Vision. I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University Computer Vision I-Chen Lin, Assistant Professor Dept. of CS, National Chiao Tung University About the course Course title: Computer Vision Lectures: EC016, 10:10~12:00(Tues.); 15:30~16:20(Thurs.) Pre-requisites:

More information

3D PLANE-BASED MAPS SIMPLIFICATION FOR RGB-D SLAM SYSTEMS

3D PLANE-BASED MAPS SIMPLIFICATION FOR RGB-D SLAM SYSTEMS 3D PLANE-BASED MAPS SIMPLIFICATION FOR RGB-D SLAM SYSTEMS 1,2 Hakim ELCHAOUI ELGHOR, 1 David ROUSSEL, 1 Fakhreddine ABABSA and 2 El-Houssine BOUYAKHF 1 IBISC Lab, Evry Val d'essonne University, Evry, France

More information

Monocular Tracking and Reconstruction in Non-Rigid Environments

Monocular Tracking and Reconstruction in Non-Rigid Environments Monocular Tracking and Reconstruction in Non-Rigid Environments Kick-Off Presentation, M.Sc. Thesis Supervisors: Federico Tombari, Ph.D; Benjamin Busam, M.Sc. Patrick Ruhkamp 13.01.2017 Introduction Motivation:

More information

Acquisition and Visualization of Colored 3D Objects

Acquisition and Visualization of Colored 3D Objects Acquisition and Visualization of Colored 3D Objects Kari Pulli Stanford University Stanford, CA, U.S.A kapu@cs.stanford.edu Habib Abi-Rached, Tom Duchamp, Linda G. Shapiro and Werner Stuetzle University

More information

A consumer level 3D object scanning device using Kinect for web-based C2C business

A consumer level 3D object scanning device using Kinect for web-based C2C business A consumer level 3D object scanning device using Kinect for web-based C2C business Geoffrey Poon, Yu Yin Yeung and Wai-Man Pang Caritas Institute of Higher Education Introduction Internet shopping is popular

More information

Patch Descriptors. EE/CSE 576 Linda Shapiro

Patch Descriptors. EE/CSE 576 Linda Shapiro Patch Descriptors EE/CSE 576 Linda Shapiro 1 How can we find corresponding points? How can we find correspondences? How do we describe an image patch? How do we describe an image patch? Patches with similar

More information