1 Computational Vision CSCI 363, Fall 2012 Lecture 16 Stereopsis.

Slides:



Advertisements
Similar presentations
The Primary Visual Cortex
Advertisements

COMPUTATIONAL NEUROSCIENCE FINAL PROJECT – DEPTH VISION Omri Perez 2013.
Low-Level Vision. Low Level Vision--outline Problem to be solved Example of one computation—lines How simple computations yield more complex information.
Chapter 6 Opener. Figure 6.1 The Euclidean geometry of the three-dimensional world turns into something quite different on the curved, two-dimensional.
What happens when no correspondence is possible? Highly mismatched stereo-pairs lead to ‘binocular rivalry’ TANGENT ALERT! Open question: Can rivalry and.
Binocular Disparity points (C) nearer than fixation (P) have crossed disparity points (F) farther than fixation have uncrossed disparity.
What is Stereopsis? The process in visual perception that leads to the sensation of depth due to the slightly different perspectives that our two eyes.
Read Pinker article for Thurs.. Seeing in Stereo.
Motion Depth Cues – Motion 1. Parallax. Motion Depth Cues – Parallax.
Stereopsis Mark Twain at Pool Table", no date, UCR Museum of Photography.
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC Lecture 8: Stereoscopic Vision 1 Computational Architectures in Biological.
Stereoscopic Depth Disparity between the two retinal images indicates an objects distance from the plane of fixation.
© 2004 by Davi GeigerComputer Vision March 2004 L1.1 Binocular Stereo Left Image Right Image.
Infinity of Interpretations There are an infinite number of interpretations of the 2D pattern of light on the retina.
The visual system Lecture 1: Structure of the eye
CSE473/573 – Stereo Correspondence
Project 4 Results Representation – SIFT and HoG are popular and successful. Data – Hugely varying results from hard mining. Learning – Non-linear classifier.
1B50 – Percepts and Concepts Daniel J Hulme. Outline Cognitive Vision –Why do we want computers to see? –Why can’t computers see? –Introducing percepts.
PSYC 330: Perception Depth Perception. The Puzzle The “Real” World and Euclidean Geometry The Retinal World and Projective Geometry Anamorphic art.
Careers for Psychology and Neuroscience Majors Oct. 19th5-7pm in SU 300 Ballroom B.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #15.
Another viewpoint: V1 cells are spatial frequency filters
1 Computational Vision CSCI 363, Fall 2012 Lecture 26 Review for Exam 2.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
Low Level Visual Processing. Information Maximization in the Retina Hypothesis: ganglion cells try to transmit as much information as possible about the.
1 Computational Vision CSCI 363, Fall 2012 Lecture 10 Spatial Frequency.
1 Computational Vision CSCI 363, Fall 2012 Lecture 3 Neurons Central Visual Pathways See Reading Assignment on "Assignments page"
December 4, 2014Computer Vision Lecture 22: Depth 1 Stereo Vision Comparing the similar triangles PMC l and p l LC l, we get: Similarly, for PNC r and.
Lecture 2b Readings: Kandell Schwartz et al Ch 27 Wolfe et al Chs 3 and 4.
1 Computational Vision CSCI 363, Fall 2012 Lecture 20 Stereo, Motion.
1 Perception, Illusion and VR HNRS 299, Spring 2008 Lecture 8 Seeing Depth.
Computer Vision, Robert Pless
CS332 Visual Processing Department of Computer Science Wellesley College Binocular Stereo Vision Region-based stereo matching algorithms Properties of.
1 Computational Vision CSCI 363, Fall 2012 Lecture 21 Motion II.
CSE 185 Introduction to Computer Vision Stereo. Taken at the same time or sequential in time stereo vision structure from motion optical flow Multiple.
1 Computational Vision CSCI 363, Fall 2012 Lecture 5 The Retina.
1 Computational Vision CSCI 363, Fall 2012 Lecture 24 Computing Motion.
1 Perception and VR MONT 104S, Fall 2008 Lecture 6 Seeing Motion.
Perception and VR MONT 104S, Fall 2008 Lecture 8 Seeing Depth
Correspondence and Stereopsis Original notes by W. Correa. Figures from [Forsyth & Ponce] and [Trucco & Verri]
Outline Of Today’s Discussion 1.Some Disparities are Not Retinal: Pulfrich Effect 2.Random-Dot Stereograms 3.Binocular Rivalry 4.Motion Parallax.
Grenoble Images Parole Signal Automatique Modeling of visual cortical processing to estimate binocular disparity Introduction - The objective is to estimate.
1 Computational Vision CSCI 363, Fall 2012 Lecture 18 Stereopsis III.
Computational Vision CSCI 363, Fall 2012 Lecture 17 Stereopsis II
Independent Component Analysis features of Color & Stereo images Authors: Patrik O. Hoyer Aapo Hyvarinen CIS 526: Neural Computation Presented by: Ajay.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
Exploring Spatial Frequency Channels in Stereopsis
Depth Perception, with Emphasis on Stereoscopic Vision
Computational Vision CSCI 363, Fall 2016 Lecture 15 Stereopsis
STEREOPSIS The Stereopsis Problem: Fusion and Reconstruction
STEREOPSIS The Stereopsis Problem: Fusion and Reconstruction
Common Classification Tasks
Space Perception and Binocular Vision
Early Processing in Biological Vision
Binocular Stereo Vision
Stereopsis: How the brain sees depth
“What Not” Detectors Help the Brain See in Depth
Binocular Stereo Vision
Binocular Stereo Vision
Binocular Stereo Vision
Stereopsis Current Biology
Binocular Disparity and the Perception of Depth
Detecting image intensity changes
Nicholas J. Priebe, David Ferster  Neuron 
Binocular Stereo Vision
The Normalization Model of Attention
Chapter 11: Stereopsis Stereopsis: Fusing the pictures taken by two cameras and exploiting the difference (or disparity) between them to obtain the depth.
Receptive Fields of Disparity-Tuned Simple Cells in Macaque V1
Binocular Stereo Vision
Visual Perception: One World from Two Eyes
Presentation transcript:

1 Computational Vision CSCI 363, Fall 2012 Lecture 16 Stereopsis

2 Random Dot Stereogram

3 Transformed

4 Linear Systems Linear functions: F(x 1 + x 2 ) = F(x 1 ) + F(x 2 ) F(ax) = aF(x) Linear systems are nice to work with because you can predict (or compute) the responses of the system relatively easily. For example, if you double the input, the output doubles. Fourier Transforms are linear operations. (The Fourier transform of the sum of two images is the sum of the Fourier transforms of each image). Gabor filters are linear filters. Neurons are not linear.

5 Threshold and Saturation Threshold non-linearity: Neurons do not respond until the input reaches a minimum level (threshold). Saturation non-linearity: Neurons have a maximum firing rate. The response saturates after they reach this maximum. Response Input strength ThresholdSaturation Linear response region

6 Phase and Half-wave Rectification Phase non-linearity: Complex cells are insensitive to the phase (position) of a grating within the receptive field. Complex cells do not sum inputs within the receptive field. Half-wave Rectification: Cortical cells have a low spontaneous firing rate. There cannot be as large a negative response as a positive response. The bottom half of the waveform is clipped off. Response time This can be alleviated with pairs of matched cells that are 180 deg out of phase with one another. The difference in responses acts like a linear response.

7 Lateral Inhibition There is evidence that a spatial frequency channel is inhibited by other channels tuned to nearby frequencies. (Also true for orientation tuning). This is accomplished by lateral inhibitory connections within the cortex, known as lateral inhibition. This can cause interesting effects, such as repulsion of perceived orientation when 2 lines of similar orientation are shown close together. If you adapt 1 spatial frequency, there is an increased sensitivity at other nearby frequencies. Inhibitory interactions can help to make tuning curves narrower.

8 Random Dot Stereogram

9 Binocular Stereo The image in each of our two eyes is slightly different. Images in the plane of fixation fall on corresponding locations on the retina. Images in front of the plane of fixation are shifted outward on each retina. They have crossed disparity. Images behind the plane of fixation are shifted inward on the retina. They have uncrossed disparity.

10 Crossed and uncrossed disparity crossed (positive) disparity uncrossed (negative) disparity plane of fixation 1 2

11 Stereo processing To determine depth from stereo disparity: 1)Extract the "features" from the left and right images 2)For each feature in the left image, find the corresponding feature in the right image. 3)Measure the disparity between the two images of the feature. 4)Use the disparity to compute the 3D location of the feature.

12 The Correspondence problem How do you determine which features from one image match features in the other image? (This problem is known as the correspondence problem). This could be accomplished if each image has well defined shapes or colors that can be matched. Problem: Random dot stereograms. Left ImageRight ImageMaking a stereogram

13 Random Dot Stereogram

14 Problem with Random Dot Stereograms In 1980's Bela Julesz developed the random dot stereogram. The stereogram consists of 2 fields of random dots, identical except for a region in one of the images in which the dots are shifted by a small amount. When one image is viewed by the left eye and the other by the right eye, the shifted region is seen at a different depth. No cues such as color, shape, texture, shading, etc. to use for matching. How do you know which dot from left image matches which dot from the right image?

15 Using Constraints to Solve the Problem To solve the correspondence problem, we need to make some assumptions (constraints) about how the matching is accomplished. Constraints used by many computer vision stereo algorithms: 1)Uniqueness: Each point has at most one match in the other image. 2)Similarity: Each feature matches a similar feature in the other image (i.e. you cannot match a white dot with a black dot). 3)Continuity: Disparity tends to vary slowly across a surface. (Note: this is violated at depth edges). 4)Epipolar constraint: Given a point in the image of one eye, the matching point in the image for the other eye must lie along a single line.

16 The epipolar constraint Feature in left image Possible matches in right image

17 It matters where you look If the observer is fixating a point along a horizontal plane through the middle of the eyes, the possible positions of a matching point in the other image lie along a horizontal line. If the observer is looking upward or downward, the line will be tilted. Most stereo algorithms for machine vision assume the epipolar lines are horizontal. For biological systems, the stereo computation must take into account where the eyes are looking (e.g. upward or downward).