Yao Wang, 2015 EL-GY 6123: Image and Video Processing 1. Stereo and Multiview. Yao Wang Polytechnic School of Engineering, New York University
|
|
- Brandon Fletcher
- 6 years ago
- Views:
Transcription
1 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 1 Stereo and Multiview Yao Wang Polytechnic School of Engineering, New York University
2 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 2 Outline Depth perception Depth from disparity Depth sensors View synthesis Stereo and multiview video display Stereo and multiview video compression MPEG2 multiview H264 multiview coding (MVC) extension HEVC multiview video + depth (MVD) extension
3 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 3 Perception of Depth Monocular cues: Shape/size Occlusion (one object blocks another) Shading and texture Linear perspective (think railroad tracks) Relative height (with respect to the horizon) Motion parallax Aerial haze (blueness on the horizon) Motion cues motion parallax Binocular cue: Stereopsis The use of two images (or their disparity) to form a sense of depth From Amy Reibman
4 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 4 Depth Perception by Stereopsis Human eye perceives depth by having two eyes with slightly shifted views The shift is called disparity Perceived depth depends on the the disparity Such depth perception is called stereopsis
5 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 5 A Visual Experiment Try to look at the left and right images using your left and right eyes separately while try to merge the two images into one. Can you tell which ball is closer? Pictures generated by ray-tracing. Courtesy of Rushang Wang
6 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 6 How do we deduce depth from stereo views? Depth from disparity
7 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 7 Perspective Projection Revisited Z y x Z Y F y Z X F x Z Y F y Z X F x are inversely related to,,, = = = = All points in this ray will have the same image
8 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 8 Parallel Camera Configuration i) Only horizontal disparity ii) Disparity is inversely proportional to Z iii) Range of disparity increases with B
9 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 9 Disparity and Depth Negative disparity: Object in front of the screen Positive disparity Object behind the screen From Amy Reibman
10 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 10 Convergent Camera Configuration See text both horizontal and vertical disparity
11 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 11 Example Images (Converging Camera) Notice the keystone effect Can get a better depth perception of objects closer to the camera than with the parallel set up But when displayed using a parallel projection system and viewed by the human eye, the vertical disparity causes perceptual discomfort. Geometric correction is needed before displaying these images.
12 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 12 Epipolar Geometry: Arbitrary Case P: Epipolar plane ep l,r : Epipolar lines [F]: fundamental matrix, Depends on camera setup Epipolar constraint: For any point that is on the left epipolar line in the left image, its corresponding point in the right image must be on the epipolar line, and vice versa.
13 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 13 Epipolar Geometry: Parallel Case Epipolar constraint: the corresponding left and right image points should be on the same horizontal line (only horizontal disparity exists) Rectification: creation of images as if acquired from parallel cameras
14 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 14 Disparity Estimation Disparity Estimation Problem: For each point in one (anchor) image, find its corresponding point in the other (target) image Similar to motion estimation problem Parallel configuration: only horizontal disparity needs to be estimated. Difficulty: disparity range may be very large for objects nearby (up to pixels); occlusion areas are prevalent (area appearing only in one view); depth discontinuity are prevalent (must apply smoothness criterion judiciously!); intensity matching does not work in flat surface area. Constraints for disparity estimation Dense disparity estimation Block-based disparity estimation Mesh-based disparity estimation Line-by-line estimation using dynamic programing 3D structure estimation
15 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 15 Constraints for Disparity Estimation Epipolar constraints: For parallel set up: two corresponding points are in the same line, only horizontal disparity need to be searched For an arbitrary camera set up: given x_r, possible x_l sits on a line (epipolar line) Ordering constrain (for points at the same depth)t: If two points in the right image are such that Then the corresponding two points in the left image satisfy Models for disparity functions
16 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 16 Models for Disparity Functions Affine model for plane surface, parallel set-up: If an imaged object has a plane surface then the disparity function for points on the surface satisfies affine model: (Proof: HW!) For an arbitrary scene, we can divide the reference (right) image into small blocks so that the object surface corresponding to each block is approximately flat. Then the disparity function over each block can be modeled as affine. Using similar approach, can derive models for curved surfaces (higher order polynomial)
17 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 17 Block-Based Disparity Estimation Following the method for block-based motion estimation Divide the anchor image (e.g. right image) into regular blocks Assume disparity function over each block is constant or an affine function Determine the constant or the affine parameters For parallel set up: Only1 horizontal disparity or 3 affine parameters Difference from motion estimation Constant disparity model is less effective than constant motion model even over small blocks Affine model is quite good Need a large search range to account for disparities in objects nearby Occlusion is more prevalent and need to be handled effectively
18 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 18 Dense Disparity Estimation Estimate the disparity at every pixel Can be solved by using block-based approach by putting a block surrounding each pixel
19 Challenges of disparity estimation Ground truth depth image White: flat texture Black: occluded region in another view White: depth discontinuity region Black: occluded region in another view Yao Wang, 2015 EL-GY 6123: Image and Video Processing 19
20 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 20 Imposing constraints between estimated disparity in adjacent blocks/pixels Independent estimation at each block/pixel may lead to conflicting estimates Smoothness constraint: similar to motion estimation, may add a penalty term to the cost function to discourage significant difference between disparity of nearby pixels To relax smooth constraint near image edges (where depth discontinuity is more likely):
21 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 21 Mesh-Based Disparity Estimation Estimate the disparity at each node (corner) by minimizing DCP error over 4 blocks attached on this node. The disparity within each block modeled by a affine or bilinear function Can use a non-regular mesh in the anchor frame to mach with object boundary
22 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 22
23 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 23 Intra-line edge matching using dynamic programing Each point in the graph corresponds to one pair of left edge and right edge, with a corresponding matching cost. The problem is to find a path that has the minimal total cost. Because of the ordering constraint, the path cannot go backwards. The minimal cost path can be determined using dynamic programming.
24 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 24 Considering Occlusion in the Dynamic Programming Approach M: matching L: appearing only in left R: appearing only in right From [Scharstein02]
25 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 25 Depth and Structure From Disparity One can deduce depth and correspondingly 3D positions (structure) of a point from its disparity Main application of stereo imaging Parallel case: Z B = ; F d Z Y = y F xl + X = 2 x r Z F
26 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 26 Joint Motion and Structure Estimation Structure estimation: Given nodes in one view, determine corresponding nodes in another view Based on the disparity at each node, determine the depth and consequently 3D coordinate of the corresponding 3D point Motion estimation Given nodes in a previous frame, find corresponding nodes in the current frame, in both views Joint structure and motion estimation in video Perform structure ad motion estimation jointly to minimize both MCP and DCP errors Still a challenging research problem
27 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 27 3D Camera / Depth Sensing Stereo camera Depth from disparity, possibly with built-in algorithm for depth estimation Depth camera Time-of-flight (ToF): Shine a pulsed or modulated laser beam (at ultraviolet, visible or infrared freq) to the imaged object and measure the total time the light travels for each pixel position. From round trip travel time, deduce the distance. LIDAR: a special ToF camera targeted for outdoor long distance observation (e.g. environment, urban mapping), typically by scanning the scene in raster order Microsoft Kinect: contain a depth sensor, a color camera, and a microphone array Uses structured light illumination to deduce depth
28 Stereo cameras in the old days Yao Wang, 2015 EL-GY 6123: Image and Video Processing 28
29 New 3D cameras: standalone, on laptop, smartphones Yao Wang, 2015 EL-GY 6123: Image and Video Processing 29
30 Intel, led by Brian Krzanich, says its RealSense technology is now small enough to fit in a smartphone, April 2015 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 30
31 Lidar in commercial applications Yao Wang, 2015 EL-GY 6123: Image and Video Processing 31
32 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 32 How Kinect Deduce Depth? Project a speckle pattern of infrared light onto the scene Capture the reflected pattern Compare the projected pattern and reflected pattern to deduce depth Information in following slides from [Hoiem-LectureNote] courses.engr.illinois.edu/cs498dh/fa2011/lectures/lecture%2025%20-%20how%20the %20Kinect%20Works%20-%20CP%20Fall% pdf
33 from [Hoiem-LectureNote] Yao Wang, 2015 EL-GY 6123: Image and Video Processing 33
34 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 34 Depth from Projector-Sensor from [Hoiem-LectureNote]
35 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 35 Same stereo triangulation method from [Hoiem-LectureNote] From corresponding points (p, p ), we can figure out the 3D position P.
36 Book vs. No Book: Depth by Matching Dots Yao Wang, 2015 EL-GY 6123: Image and Video Processing from [Hoiem-LectureNote] 36
37 Book vs. No Book: Depth by Matching Dots Yao Wang, 2015 EL-GY 6123: Image and Video Processing 37
38 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 38 Natural light vs. projected IR stereo From [Hoiem-Lecture]
39 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 39 Intermediate View Synthesis Problem: Interpolate intermediate views from given views Necessary for virtual reality applications Important for multi-view display systems Linear interpolation: can lead to blurred images Disparity-compensated interpolation
40 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 40 Disparity Compensated View Synthesis D cl D cr Baseline distances (distance between camera centers): Dcl and Dcr
41 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 41 How to determine disparity from the central (unknown) view? One approach: First determine disparity between left and right for every pixel in the left d_lr(x_l) Then determine disparity between left and central based on distance, d_lc(x_l)=b_cl/(b_cl+b_cr) d_lr(x_l) (B_cl and B_cr are camera center distances between center and left, and center and right cameras) For every point x_l in left, find corresponding point in central x_c=x_l +d_lc(x_l) But the central point may not be an integer pixel! Need to interpolate the integer pixel values from these non-integer pixels When using block-based method for estimating d_lr, there may be uncovered points in the central view or multiple-covered points; a dense depth field is better
42 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 42 Mesh-Based Interpolation of Disparity Field No uncovered or multiple covered pixels in central view!
43 Mesh-Based View Synthesis Result Yao Wang, 2015 EL-GY 6123: Image and Video Processing 43
44 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 44 Display of Stereo Images/Sequences Principle: Project images for the left and right eyes simultaneously in a way that the two images can be received separately by left and right eyes Separation mechanism in stereoscopic display Color filter (Cannot be used for display color stereo images) Polorization Interlace in time the left and right views (Stereographics, Inc.) Viewers need to wear special glasses Auto-stereoscopic display Present two or multiple views on the same screen simultaneously A viewer sees different view when looking from different angle Viewers do not need to wear glasses Autostereoscopic lenticular screens
45 Yao Wang, 2015 EL-GY 6123: Image and Video Processing Using glasses Anaglyph. Two-color separation of left/right view. Poor color rendition. Polarized. For viewing stereo pairs projected through suitable polarizing filters. Better image quality. Shutter glasses. Liquid crystal. Expensive. Require high refresh rate. Require synchronization of display and glasses From Amy Reibman
46 Yao Wang, 2015 EL-GY 6123: Image and Video Processing Autostereoscopic display principle the effective horizontal pixel count viewable for each eye is reduced by one half The viewer must be positioned in a welldefined spot to experience the 3D effect The effective horizontal pixel count viewable for each eye is reduced by one half From Amy Reibman
47 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 47 3D-ready consumer TVs Display stereo pairs in time-sequential manner Active shutter glasses Options 3D DLP technology from TI (Samsung & Mitsubishi) 3D plasma (Samsung) From Amy Reibman
48 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 48 Screen geometry Each technology has its own screen size and resolution IMAX 48-foot screen; 2048x1080: aspect ratio 1.4 Typically all seats are within one screen height Real-D XLS: 20-foot screen; 2048x858 per view; aspect ratio 1.85 Typically seats are within {single digit} screen heights Home TV Typically 8 feet viewing distance Screen parallax (i.e. disparity) is affected by the size of the display screen From Amy Reibman
49 Mismatch in screen sizes and viewing distances (movie theater vs. home) Real-life, and original intended screen size: Same screen angle, smaller disparity. Result: different object size and distance From Amy Reibman Objects appear to be in a puppet theater: small and close together Yao Wang, 2015 EL-GY 6123: Image and Video Processing 49
50 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 50 Adaptation of disparity for different screen sizes Real-life, and original screen size: One way to fix : Shift one image relative to the other From Amy Reibman Same screen angle, shifted disparity. Result: same object size Now, the object appears the correct size. However, objects are almost always behind the screen. Causing conflict of converging and accommodation
51 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 51 Depth-based adaptation of 3D content Perceived depth is affected by the screen size and and viewing distance To display for different screens, need to adjust stereo disparity Limit maximum disparity to avoid too much eye strain Shifting/offsetting one image has only limited success Ideally, for a given viewer distance and viewer location, generate an intermediate view for that viewer: Intermediate view synthesis From Amy Reibman
52 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 52 Coding of Stereo Sequences Simulcast: Code each view independently Extension from block-based hybrid code: Code one view using a standard video coder, using MCP between successive frames in this view Code the other view by using both DCP between views at the same frame and MCP in the same view MPEG-2 Multiview profile Mixed resolution Code one view at the desired spatial/temporal resolution Code another view with reduced spatial/temporal resolution More advanced, object-based approach
53 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 53 MPEG-2 Multiview Profile Left view: MCP only Right view: combination of MCP and DCP, using the bi-directional prediction mode Can be implemented using the temporal scalability tool: left view treated as the base-layer, right view treated as the enhancement layer Only limited gain over simulcast MCP is typically more effective than DCP Ineffectiveness of DCP due to inaccuracy of block-based constant disparity model
54 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 54 H.264 Multiview prediction structures H.264/MVC: multiview video coding extension of H.264
55 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 55 HEVC Multiview Video + Depth (MVD) Two or more views Assuming depth map at each view is available Depth coding enable virtual view generation between every two coded views Allow encoding/decoding of color frames only Coding of dependent views using DCP, inter-view motion prediction, and inter-view residual prediction Depth map coded using new intra-coding modes, modified motion compensation and motion vector coding, and motion parameter inheritance from the associated video component
56 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 56 MVD Block Diagram From [Muller2013]
57 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 57 Examples of depth maps l Brighter objects closer, dark objects further away JBoyce, 2011
58 Depth Map Coding Depth map are typically piecewise smooth, with sharp edges In addition to conventional intra-prediction, new modes are introduced which represent each block as two different regions each with a constant depth value From [Muller2013] Yao Wang, 2015 EL-GY 6123: Image and Video Processing 58
59 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 59 Barriers to mass market Data and delivery format Quality of 3D video production Content creators must be aware of 3D videography Re-purposing of 3D content from cinema into the homes 2D->3D conversion: converting old 2D movie to 3D Human factors Stereoscopic glasses are no fun Auto-stereoscopic has its own issues Avoid objectionable 3D effects From Amy Reibman
60 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 60 Additional perceptual issues Both too much depth and too many fast changes of depth cause visual fatigue Conflicting depth information causes visual fatigue Accommodation and vergence are linked when scanning the scene (but can be decoupled over time) Compression, aliasing, other impairments (like keystoning) can make fusing more difficult Screen or glasses scratch or dust Cross-talk Left eye sees some of what Right eye should see Stronger in high-contrast and large-disparity areas (But fusing is easier in high-contrast areas) From Amy Reibman
61 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 61 Summary Human perception of depth Principle in stereo imaging: Relation between depth and disparity for parallel set-up and other more general camera set-ups. Epipolar constraint for an arbitrary set-up Disparity estimation: Formulation as an optimization problem similar to motion estimation Block-based approach Mesh-based approach: regular mesh vs. adaptive mesh Dynamic programming: not required Joint motion and structure estimation: not required 3D cameras: difference ways of depth sensing Intermediate view synthesis Stereo/multiview sequence coding Extension from standard video coder: Joint MCP and DCP Multiview + Depth coding Stereo image/video display
62 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 62 Homework Review questions Describe briefly how the human being deduce depth from disparity. A far away object has small or large disparity? Describe how a stereo camera deduce depth Describe how Kinect camera deduce depth Describe 3 different ways of depth sensing for 3D imaging Describe the general principle of intermediate view synthesis Describe briefly how to code a stereo video using both motion compensated prediction and disparity compensated prediction Written Homework Prob Prob. 12.2
63 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 63 Computer Assignment (Optional) Write a program that can estimate the horizontal disparity map between two stereo images captured using parallel set up. To estimate the disparity at each pixel, apply EBMA over a block centered at this pixel. Apply your program to any stereo image pair you can download (e.g. from Middlebury stereo database). Prob Prob
64 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 64 Recommended Readings [Wang2002]: Chap 12 Depth estimation from stereo images: D. Scharstein and R. Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV (an excellent website) Y. Ohta and T. Kanade. Stereo by intra- and interscanline search using dynamic programming. IEEE TPAMI, 7(2): , Kinect Derek Hoiem, Lecture note on Kinect, courses.engr.illinois.edu/cs498dh/fa2011/lectures/lecture%2025%20-%20how %20the%20Kinect%20Works%20-%20CP%20Fall% pdf
65 Yao Wang, 2015 EL-GY 6123: Image and Video Processing 65 Recommended Readings Stereo and multiview coding A Vetro, T Wiegand, GJ Sullivan, Overview of the stereo and multiview video coding extensions of the H. 264/MPEG-4 AVC standard, Proceedings of the IEEE, 2011, 99 (4): Muller, K.; Schwarz, H.; Marpe, D.; Bartnik, C.; Bosse, S.; Brust, H.; Hinz, T.; Lakshman, H.; Merkle, P.; Rhee, F.H.; Tech, G.; Winken, M.; Wiegand, T., "3D High-Efficiency Video Coding for Multi-View Video and Depth Data," Image Processing, IEEE Transactions on, vol.22, no.9, pp.3366,3378, Sept Stereo and autostereoscopic display A. Woods, T. Docherty, and R. Koch, Image distortions in stereoscopic video systems, Proceedings SPIE Stereoscopic Displays and Applications IV, vol. 1915, San Jose, CA, Feb Dodgson, N.A., "Autostereoscopic 3D Displays," IEEE Computer Magazine, vol.38, no.8, pp.31,36, Aug Lecture note by Neil Dodgson, multi-view autostereoscopic display
Prof. Feng Liu. Spring /27/2014
Prof. Feng Liu Spring 2014 http://www.cs.pdx.edu/~fliu/courses/cs510/ 05/27/2014 Last Time Video Stabilization 2 Today Stereoscopic 3D Human depth perception 3D displays 3 Stereoscopic media Digital Visual
More informationVideo Communication Ecosystems. Research Challenges for Immersive. over Future Internet. Converged Networks & Services (CONES) Research Group
Research Challenges for Immersive Video Communication Ecosystems over Future Internet Tasos Dagiuklas, Ph.D., SMIEEE Assistant Professor Converged Networks & Services (CONES) Research Group Hellenic Open
More informationCS 563 Advanced Topics in Computer Graphics Stereoscopy. by Sam Song
CS 563 Advanced Topics in Computer Graphics Stereoscopy by Sam Song Stereoscopy Introduction Parallax Camera Displaying and Viewing Results Stereoscopy What is it? seeing in three dimensions creates the
More informationStereo. Shadows: Occlusions: 3D (Depth) from 2D. Depth Cues. Viewing Stereo Stereograms Autostereograms Depth from Stereo
Stereo Viewing Stereo Stereograms Autostereograms Depth from Stereo 3D (Depth) from 2D 3D information is lost by projection. How do we recover 3D information? Image 3D Model Depth Cues Shadows: Occlusions:
More information3D Computer Vision. Depth Cameras. Prof. Didier Stricker. Oliver Wasenmüller
3D Computer Vision Depth Cameras Prof. Didier Stricker Oliver Wasenmüller Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational
More informationThere are many cues in monocular vision which suggests that vision in stereo starts very early from two similar 2D images. Lets see a few...
STEREO VISION The slides are from several sources through James Hays (Brown); Srinivasa Narasimhan (CMU); Silvio Savarese (U. of Michigan); Bill Freeman and Antonio Torralba (MIT), including their own
More informationEECS 442 Computer vision. Stereo systems. Stereo vision Rectification Correspondence problem Active stereo vision systems
EECS 442 Computer vision Stereo systems Stereo vision Rectification Correspondence problem Active stereo vision systems Reading: [HZ] Chapter: 11 [FP] Chapter: 11 Stereo vision P p p O 1 O 2 Goal: estimate
More informationIntermediate view synthesis considering occluded and ambiguously referenced image regions 1. Carnegie Mellon University, Pittsburgh, PA 15213
1 Intermediate view synthesis considering occluded and ambiguously referenced image regions 1 Jeffrey S. McVeigh *, M. W. Siegel ** and Angel G. Jordan * * Department of Electrical and Computer Engineering
More informationNext-Generation 3D Formats with Depth Map Support
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Next-Generation 3D Formats with Depth Map Support Chen, Y.; Vetro, A. TR2014-016 April 2014 Abstract This article reviews the most recent extensions
More informationMultidimensional image retargeting
Multidimensional image retargeting 9:00: Introduction 9:10: Dynamic range retargeting Tone mapping Apparent contrast and brightness enhancement 10:45: Break 11:00: Color retargeting 11:30: LDR to HDR 12:20:
More informationFundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision
Fundamentals of Stereo Vision Michael Bleyer LVA Stereo Vision What Happened Last Time? Human 3D perception (3D cinema) Computational stereo Intuitive explanation of what is meant by disparity Stereo matching
More informationRobert Collins CSE486, Penn State Lecture 08: Introduction to Stereo
Lecture 08: Introduction to Stereo Reading: T&V Section 7.1 Stereo Vision Inferring depth from images taken at the same time by two or more cameras. Basic Perspective Projection Scene Point Perspective
More informationRealtime 3D Computer Graphics Virtual Reality
Realtime 3D Computer Graphics Virtual Reality Human Visual Perception The human visual system 2 eyes Optic nerve: 1.5 million fibers per eye (each fiber is the axon from a neuron) 125 million rods (achromatic
More informationRange Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation. Range Imaging Through Triangulation
Obviously, this is a very slow process and not suitable for dynamic scenes. To speed things up, we can use a laser that projects a vertical line of light onto the scene. This laser rotates around its vertical
More informationBinocular cues to depth PSY 310 Greg Francis. Lecture 21. Depth perception
Binocular cues to depth PSY 310 Greg Francis Lecture 21 How to find the hidden word. Depth perception You can see depth in static images with just one eye (monocular) Pictorial cues However, motion and
More informationBIL Computer Vision Apr 16, 2014
BIL 719 - Computer Vision Apr 16, 2014 Binocular Stereo (cont d.), Structure from Motion Aykut Erdem Dept. of Computer Engineering Hacettepe University Slide credit: S. Lazebnik Basic stereo matching algorithm
More informationStereo CSE 576. Ali Farhadi. Several slides from Larry Zitnick and Steve Seitz
Stereo CSE 576 Ali Farhadi Several slides from Larry Zitnick and Steve Seitz Why do we perceive depth? What do humans use as depth cues? Motion Convergence When watching an object close to us, our eyes
More informationColorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.
Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Stereo Vision 2 Inferring 3D from 2D Model based pose estimation single (calibrated) camera > Can
More informationView Synthesis for Multiview Video Compression
View Synthesis for Multiview Video Compression Emin Martinian, Alexander Behrens, Jun Xin, and Anthony Vetro email:{martinian,jxin,avetro}@merl.com, behrens@tnt.uni-hannover.de Mitsubishi Electric Research
More informationLecture 19: Depth Cameras. Visual Computing Systems CMU , Fall 2013
Lecture 19: Depth Cameras Visual Computing Systems Continuing theme: computational photography Cameras capture light, then extensive processing produces the desired image Today: - Capturing scene depth
More informationLecture 14, Video Coding Stereo Video Coding
Lecture 14, Video Coding Stereo Video Coding A further application of the tools we saw (particularly the motion compensation and prediction) is stereo video coding. Stereo video is used for creating a
More informationBasic distinctions. Definitions. Epstein (1965) familiar size experiment. Distance, depth, and 3D shape cues. Distance, depth, and 3D shape cues
Distance, depth, and 3D shape cues Pictorial depth cues: familiar size, relative size, brightness, occlusion, shading and shadows, aerial/ atmospheric perspective, linear perspective, height within image,
More information3366 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 22, NO. 9, SEPTEMBER 2013
3366 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 22, NO. 9, SEPTEMBER 2013 3D High-Efficiency Video Coding for Multi-View Video and Depth Data Karsten Müller, Senior Member, IEEE, Heiko Schwarz, Detlev
More informationColorado School of Mines. Computer Vision. Professor William Hoff Dept of Electrical Engineering &Computer Science.
Professor William Hoff Dept of Electrical Engineering &Computer Science http://inside.mines.edu/~whoff/ 1 Stereo Vision 2 Inferring 3D from 2D Model based pose estimation single (calibrated) camera Stereo
More informationPerception, Part 2 Gleitman et al. (2011), Chapter 5
Perception, Part 2 Gleitman et al. (2011), Chapter 5 Mike D Zmura Department of Cognitive Sciences, UCI Psych 9A / Psy Beh 11A February 27, 2014 T. M. D'Zmura 1 Visual Reconstruction of a Three-Dimensional
More informationWhat have we leaned so far?
What have we leaned so far? Camera structure Eye structure Project 1: High Dynamic Range Imaging What have we learned so far? Image Filtering Image Warping Camera Projection Model Project 2: Panoramic
More informationlecture 10 - depth from blur, binocular stereo
This lecture carries forward some of the topics from early in the course, namely defocus blur and binocular disparity. The main emphasis here will be on the information these cues carry about depth, rather
More informationOmni Stereo Vision of Cooperative Mobile Robots
Omni Stereo Vision of Cooperative Mobile Robots Zhigang Zhu*, Jizhong Xiao** *Department of Computer Science **Department of Electrical Engineering The City College of the City University of New York (CUNY)
More informationMultiple 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 informationCS 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 informationMahdi Amiri. May Sharif University of Technology
Course Presentation Multimedia Systems 3D Technologies Mahdi Amiri May 2014 Sharif University of Technology Binocular Vision (Two Eyes) Advantages A spare eye in case one is damaged. A wider field of view
More informationChaplin, 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 informationEpipolar Geometry CSE P576. Dr. Matthew Brown
Epipolar Geometry CSE P576 Dr. Matthew Brown Epipolar Geometry Epipolar Lines, Plane Constraint Fundamental Matrix, Linear solution + RANSAC Applications: Structure from Motion, Stereo [ Szeliski 11] 2
More informationMultiview Image Compression using Algebraic Constraints
Multiview Image Compression using Algebraic Constraints Chaitanya Kamisetty and C. V. Jawahar Centre for Visual Information Technology, International Institute of Information Technology, Hyderabad, INDIA-500019
More informationMultiple View Geometry
Multiple View Geometry CS 6320, Spring 2013 Guest Lecture Marcel Prastawa adapted from Pollefeys, Shah, and Zisserman Single view computer vision Projective actions of cameras Camera callibration Photometric
More informationView Synthesis for Multiview Video Compression
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com View Synthesis for Multiview Video Compression Emin Martinian, Alexander Behrens, Jun Xin, and Anthony Vetro TR2006-035 April 2006 Abstract
More informationStereo. 11/02/2012 CS129, Brown James Hays. Slides by Kristen Grauman
Stereo 11/02/2012 CS129, Brown James Hays Slides by Kristen Grauman Multiple views Multi-view geometry, matching, invariant features, stereo vision Lowe Hartley and Zisserman Why multiple views? Structure
More informationComputer 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 informationComputer 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 informationINTERNATIONAL ORGANISATION FOR STANDARDISATION ORGANISATION INTERNATIONALE DE NORMALISATION ISO/IEC JTC1/SC29/WG11 CODING OF MOVING PICTURES AND AUDIO
INTERNATIONAL ORGANISATION FOR STANDARDISATION ORGANISATION INTERNATIONALE DE NORMALISATION ISO/IEC JTC1/SC29/WG11 CODING OF MOVING PICTURES AND AUDIO ISO/IEC JTC1/SC29/WG11 MPEG2011/N12559 February 2012,
More informationDevices displaying 3D image. RNDr. Róbert Bohdal, PhD.
Devices displaying 3D image RNDr. Róbert Bohdal, PhD. 1 Types of devices displaying 3D image Stereoscopic Re-imaging Volumetric Autostereoscopic Holograms mounted displays, optical head-worn displays Pseudo
More informationSTEREOSCOPIC IMAGE PROCESSING
STEREOSCOPIC IMAGE PROCESSING Reginald L. Lagendijk, Ruggero E.H. Franich 1 and Emile A. Hendriks 2 Delft University of Technology Department of Electrical Engineering 4 Mekelweg, 2628 CD Delft, The Netherlands
More informationIn the name of Allah. the compassionate, the merciful
In the name of Allah the compassionate, the merciful Digital Video Systems S. Kasaei Room: CE 315 Department of Computer Engineering Sharif University of Technology E-Mail: skasaei@sharif.edu Webpage:
More informationDepth Estimation for View Synthesis in Multiview Video Coding
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Depth Estimation for View Synthesis in Multiview Video Coding Serdar Ince, Emin Martinian, Sehoon Yea, Anthony Vetro TR2007-025 June 2007 Abstract
More informationDepth. Common Classification Tasks. Example: AlexNet. Another Example: Inception. Another Example: Inception. Depth
Common Classification Tasks Recognition of individual objects/faces Analyze object-specific features (e.g., key points) Train with images from different viewing angles Recognition of object classes Analyze
More informationCOMS W4172 Perception, Displays, and Devices 3
COMS W4172 Perception, Displays, and Devices 3 Steven Feiner Department of Computer Science Columbia University New York, NY 10027 www.cs.columbia.edu/graphics/courses/csw4172 February 20, 2018 1 What
More information2014 Summer School on MPEG/VCEG Video. Video Coding Concept
2014 Summer School on MPEG/VCEG Video 1 Video Coding Concept Outline 2 Introduction Capture and representation of digital video Fundamentals of video coding Summary Outline 3 Introduction Capture and representation
More informationStereo imaging ideal geometry
Stereo imaging ideal geometry (X,Y,Z) Z f (x L,y L ) f (x R,y R ) Optical axes are parallel Optical axes separated by baseline, b. Line connecting lens centers is perpendicular to the optical axis, and
More informationStereo Graphics. Visual Rendering for VR. Passive stereoscopic projection. Active stereoscopic projection. Vergence-Accommodation Conflict
Stereo Graphics Visual Rendering for VR Hsueh-Chien Chen, Derek Juba, and Amitabh Varshney Our left and right eyes see two views, which are processed by our visual cortex to create a sense of depth Computer
More informationRendering. Converting a 3D scene to a 2D image. Camera. Light. Rendering. View Plane
Rendering Pipeline Rendering Converting a 3D scene to a 2D image Rendering Light Camera 3D Model View Plane Rendering Converting a 3D scene to a 2D image Basic rendering tasks: Modeling: creating the world
More informationShadows in the graphics pipeline
Shadows in the graphics pipeline Steve Marschner Cornell University CS 569 Spring 2008, 19 February There are a number of visual cues that help let the viewer know about the 3D relationships between objects
More informationAn Introduction to 3D Computer Graphics, Stereoscopic Image, and Animation in OpenGL and C/C++ Fore June
An Introduction to 3D Computer Graphics, Stereoscopic Image, and Animation in OpenGL and C/C++ Fore June Chapter 15 Stereoscopic Displays In chapters 8 through 10, we have discussed the principles and
More informationVisual Rendering for VR. Stereo Graphics
Visual Rendering for VR Hsueh-Chien Chen, Derek Juba, and Amitabh Varshney Stereo Graphics Our left and right eyes see two views, which are processed by our visual cortex to create a sense of depth Computer
More informationIntermediate View Generation for Perceived Depth Adjustment of Stereo Video
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Intermediate View Generation for Perceived Depth Adjustment of Stereo Video Zafer Arican, Sehoon Yea, Alan Sullivan, Anthony Vetro TR2009-052
More informationDepth Sensors Kinect V2 A. Fornaser
Depth Sensors Kinect V2 A. Fornaser alberto.fornaser@unitn.it Vision Depth data It is not a 3D data, It is a map of distances Not a 3D, not a 2D it is a 2.5D or Perspective 3D Complete 3D - Tomography
More informationUpcoming Video Standards. Madhukar Budagavi, Ph.D. DSPS R&D Center, Dallas Texas Instruments Inc.
Upcoming Video Standards Madhukar Budagavi, Ph.D. DSPS R&D Center, Dallas Texas Instruments Inc. Outline Brief history of Video Coding standards Scalable Video Coding (SVC) standard Multiview Video Coding
More informationLecture 14: Computer Vision
CS/b: Artificial Intelligence II Prof. Olga Veksler Lecture : Computer Vision D shape from Images Stereo Reconstruction Many Slides are from Steve Seitz (UW), S. Narasimhan Outline Cues for D shape perception
More informationCOMP 558 lecture 22 Dec. 1, 2010
Binocular correspondence problem Last class we discussed how to remap the pixels of two images so that corresponding points are in the same row. This is done by computing the fundamental matrix, defining
More informationAutomatic 2D-to-3D Video Conversion Techniques for 3DTV
Automatic 2D-to-3D Video Conversion Techniques for 3DTV Dr. Lai-Man Po Email: eelmpo@cityu.edu.hk Department of Electronic Engineering City University of Hong Kong Date: 13 April 2010 Content Why 2D-to-3D
More informationProject 2 due today Project 3 out today. Readings Szeliski, Chapter 10 (through 10.5)
Announcements Stereo Project 2 due today Project 3 out today Single image stereogram, by Niklas Een Readings Szeliski, Chapter 10 (through 10.5) Public Library, Stereoscopic Looking Room, Chicago, by Phillips,
More informationStereo Vision A simple system. Dr. Gerhard Roth Winter 2012
Stereo Vision A simple system Dr. Gerhard Roth Winter 2012 Stereo Stereo Ability to infer information on the 3-D structure and distance of a scene from two or more images taken from different viewpoints
More information3D Video Formats and Coding Standards
3D Video Formats and Coding Standards Fraunhofer Institute for Telecommunications Heinrich-Hertz-Institut Berlin Einsteinufer 37 10587 Berlin Germany +49 30 310 02 0 info@hhi.fraunhofer.de http://www.hhi.fraunhofer.de
More informationLecture 6 Stereo Systems Multi- view geometry Professor Silvio Savarese Computational Vision and Geometry Lab Silvio Savarese Lecture 6-24-Jan-15
Lecture 6 Stereo Systems Multi- view geometry Professor Silvio Savarese Computational Vision and Geometry Lab Silvio Savarese Lecture 6-24-Jan-15 Lecture 6 Stereo Systems Multi- view geometry Stereo systems
More informationOutdoor Scene Reconstruction from Multiple Image Sequences Captured by a Hand-held Video Camera
Outdoor Scene Reconstruction from Multiple Image Sequences Captured by a Hand-held Video Camera Tomokazu Sato, Masayuki Kanbara and Naokazu Yokoya Graduate School of Information Science, Nara Institute
More informationHow to Shoot Good 3D with The Stereocam 3D Camcorder Adapter
How to Shoot Good 3D with The Stereocam 3D Camcorder Adapter By How to Shoot Good 3D With The Stereocam 3D Camcorder Adapter Introduction The Stereocam 3D Camcorder Adapter is a "break-through" product.
More informationPipeline Operations. CS 4620 Lecture 10
Pipeline Operations CS 4620 Lecture 10 2008 Steve Marschner 1 Hidden surface elimination Goal is to figure out which color to make the pixels based on what s in front of what. Hidden surface elimination
More informationStereo Vision. MAN-522 Computer Vision
Stereo Vision MAN-522 Computer Vision What is the goal of stereo vision? The recovery of the 3D structure of a scene using two or more images of the 3D scene, each acquired from a different viewpoint in
More informationCS 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 informationNatural Viewing 3D Display
We will introduce a new category of Collaboration Projects, which will highlight DoCoMo s joint research activities with universities and other companies. DoCoMo carries out R&D to build up mobile communication,
More informationLecture 6 Stereo Systems Multi-view geometry
Lecture 6 Stereo Systems Multi-view geometry Professor Silvio Savarese Computational Vision and Geometry Lab Silvio Savarese Lecture 6-5-Feb-4 Lecture 6 Stereo Systems Multi-view geometry Stereo systems
More informationPERCEIVING DEPTH AND SIZE
PERCEIVING DEPTH AND SIZE DEPTH Cue Approach Identifies information on the retina Correlates it with the depth of the scene Different cues Previous knowledge Slide 3 Depth Cues Oculomotor Monocular Binocular
More informationProject 3 code & artifact due Tuesday Final project proposals due noon Wed (by ) Readings Szeliski, Chapter 10 (through 10.5)
Announcements Project 3 code & artifact due Tuesday Final project proposals due noon Wed (by email) One-page writeup (from project web page), specifying:» Your team members» Project goals. Be specific.
More informationCEng Computational Vision
CEng 583 - Computational Vision 2011-2012 Spring Week 4 18 th of March, 2011 Today 3D Vision Binocular (Multi-view) cues: Stereopsis Motion Monocular cues Shading Texture Familiar size etc. "God must
More informationDense 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 information3D Video services. Marco Cagnazzo
3D Video services Marco Cagnazzo Part III: Advanced services Overview 3D Video systems History Acquisition Transmission (coding) Rendering Future services Super Hi Vision systems High speed cameras High
More informationHigh-Fidelity Augmented Reality Interactions Hrvoje Benko Researcher, MSR Redmond
High-Fidelity Augmented Reality Interactions Hrvoje Benko Researcher, MSR Redmond New generation of interfaces Instead of interacting through indirect input devices (mice and keyboard), the user is interacting
More informationRecap from Previous Lecture
Recap from Previous Lecture Tone Mapping Preserve local contrast or detail at the expense of large scale contrast. Changing the brightness within objects or surfaces unequally leads to halos. We are now
More informationRecap: Features and filters. Recap: Grouping & fitting. Now: Multiple views 10/29/2008. Epipolar geometry & stereo vision. Why multiple views?
Recap: Features and filters Epipolar geometry & stereo vision Tuesday, Oct 21 Kristen Grauman UT-Austin Transforming and describing images; textures, colors, edges Recap: Grouping & fitting Now: Multiple
More information3D Autostereoscopic Display Image Generation Framework using Direct Light Field Rendering
3D Autostereoscopic Display Image Generation Framework using Direct Light Field Rendering Young Ju Jeong, Yang Ho Cho, Hyoseok Hwang, Hyun Sung Chang, Dongkyung Nam, and C. -C Jay Kuo; Samsung Advanced
More informationAssignment 2: Stereo and 3D Reconstruction from Disparity
CS 6320, 3D Computer Vision Spring 2013, Prof. Guido Gerig Assignment 2: Stereo and 3D Reconstruction from Disparity Out: Mon Feb-11-2013 Due: Mon Feb-25-2013, midnight (theoretical and practical parts,
More informationEL6123 Video Processing Midterm Summary Spring 09. Yao Wang Polytechnic Institute of NYU Brooklyn, NY 11201
EL6123 Video Processing Midterm Summary Spring 09 Yao Wang Polytechnic Institute of NYU Brooklyn, NY 11201 Basics of Video Color representation and perception Camera model: perspective projection Color
More informationImage 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 informationStereo vision. Many slides adapted from Steve Seitz
Stereo vision Many slides adapted from Steve Seitz What is stereo vision? Generic problem formulation: given several images of the same object or scene, compute a representation of its 3D shape What is
More informationDepth from two cameras: stereopsis
Depth from two cameras: stereopsis Epipolar Geometry Canonical Configuration Correspondence Matching School of Computer Science & Statistics Trinity College Dublin Dublin 2 Ireland www.scss.tcd.ie Lecture
More informationAnalysis of 3D and Multiview Extensions of the Emerging HEVC Standard
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Analysis of 3D and Multiview Extensions of the Emerging HEVC Standard Vetro, A.; Tian, D. TR2012-068 August 2012 Abstract Standardization of
More informationPipeline Operations. CS 4620 Lecture Steve Marschner. Cornell CS4620 Spring 2018 Lecture 11
Pipeline Operations CS 4620 Lecture 11 1 Pipeline you are here APPLICATION COMMAND STREAM 3D transformations; shading VERTEX PROCESSING TRANSFORMED GEOMETRY conversion of primitives to pixels RASTERIZATION
More informationPublic Library, Stereoscopic Looking Room, Chicago, by Phillips, 1923
Public Library, Stereoscopic Looking Room, Chicago, by Phillips, 1923 Teesta suspension bridge-darjeeling, India Mark Twain at Pool Table", no date, UCR Museum of Photography Woman getting eye exam during
More informationA virtual tour of free viewpoint rendering
A virtual tour of free viewpoint rendering Cédric Verleysen ICTEAM institute, Université catholique de Louvain, Belgium cedric.verleysen@uclouvain.be Organization of the presentation Context Acquisition
More informationDepth from two cameras: stereopsis
Depth from two cameras: stereopsis Epipolar Geometry Canonical Configuration Correspondence Matching School of Computer Science & Statistics Trinity College Dublin Dublin 2 Ireland www.scss.tcd.ie Lecture
More informationImportant concepts in binocular depth vision: Corresponding and non-corresponding points. Depth Perception 1. Depth Perception Part II
Depth Perception Part II Depth Perception 1 Binocular Cues to Depth Depth Information Oculomotor Visual Accomodation Convergence Binocular Monocular Static Cues Motion Parallax Perspective Size Interposition
More informationCSE 165: 3D User Interaction. Lecture #3: Displays
CSE 165: 3D User Interaction Lecture #3: Displays CSE 165 -Winter 2016 2 Announcements Homework Assignment #1 Due Friday at 2:00pm To be presented in CSE lab 220 Paper presentations Title/date due by entering
More informationAlgorithm for automated eye strain reduction in real stereoscopic images and sequences. Carnegie Mellon University, Pittsburgh, PA 15213
/afs/cs/project/sensor-5/jmcveigh/text/disparity/spie2657-35.doc Algorithm for automated eye strain reduction in real stereoscopic images and sequences J. S. McVeigh 1, M. W. Siegel 2 and A. G. Jordan
More informationAnnouncements. Stereo Vision Wrapup & Intro Recognition
Announcements Stereo Vision Wrapup & Intro Introduction to Computer Vision CSE 152 Lecture 17 HW3 due date postpone to Thursday HW4 to posted by Thursday, due next Friday. Order of material we ll first
More informationFinally: Motion and tracking. Motion 4/20/2011. CS 376 Lecture 24 Motion 1. Video. Uses of motion. Motion parallax. Motion field
Finally: Motion and tracking Tracking objects, video analysis, low level motion Motion Wed, April 20 Kristen Grauman UT-Austin Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys, and S. Lazebnik
More information5LSH0 Advanced Topics Video & Analysis
1 Multiview 3D video / Outline 2 Advanced Topics Multimedia Video (5LSH0), Module 02 3D Geometry, 3D Multiview Video Coding & Rendering Peter H.N. de With, Sveta Zinger & Y. Morvan ( p.h.n.de.with@tue.nl
More informationComplex Sensors: Cameras, Visual Sensing. The Robotics Primer (Ch. 9) ECE 497: Introduction to Mobile Robotics -Visual Sensors
Complex Sensors: Cameras, Visual Sensing The Robotics Primer (Ch. 9) Bring your laptop and robot everyday DO NOT unplug the network cables from the desktop computers or the walls Tuesday s Quiz is on Visual
More informationRange Sensors (time of flight) (1)
Range Sensors (time of flight) (1) Large range distance measurement -> called range sensors Range information: key element for localization and environment modeling Ultrasonic sensors, infra-red sensors
More informationStereovision. Binocular disparity
Stereovision Binocular disparity Retinal correspondence Uncrossed disparity Horoptor Crossed disparity Horoptor, crossed and uncrossed disparity Wheatsteone stereoscope (c. 1838) Red-green anaglyph How
More informationINTERNATIONAL ORGANISATION FOR STANDARISATION ORGANISATION INTERNATIONALE DE NORMALISATION ISO/IEC JTC1/SC29/WG11 CODING OF MOVING PICTURES AND AUDIO
INTERNATIONAL ORGANISATION FOR STANDARISATION ORGANISATION INTERNATIONALE DE NORMALISATION ISO/IEC JTC1/SC29/WG11 CODING OF MOVING PICTURES AND AUDIO ISO/IEC JTC1/SC29/WG11 MPEG/M15672 July 2008, Hannover,
More information