December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.

Slides:



Advertisements
Similar presentations
Andrew Cosand ECE CVRR CSE
Advertisements

November 12, 2013Computer Vision Lecture 12: Texture 1Signature Another popular method of representing shape is called the signature. In order to compute.
Dynamic Occlusion Analysis in Optical Flow Fields
October 2, 2014Computer Vision Lecture 8: Edge Detection I 1 Edge Detection.
December 5, 2013Computer Vision Lecture 20: Hidden Markov Models/Depth 1 Stereo Vision Due to the limited resolution of images, increasing the baseline.
Computer Vision Optical Flow
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
Motion Detection And Analysis Michael Knowles Tuesday 13 th January 2004.
Optical Flow Methods 2007/8/9.
May 2004Motion/Optic Flow1 Motion Field and Optical Flow Ack, for the slides: Professor Yuan-Fang Wang Professor Octavia Camps.
Probabilistic video stabilization using Kalman filtering and mosaicking.
E.G.M. PetrakisDynamic Vision1 Dynamic vision copes with –Moving or changing objects (size, structure, shape) –Changing illumination –Changing viewpoints.
Segmentation Divide the image into segments. Each segment:
CSc83029 – 3-D Computer Vision/ Ioannis Stamos 3-D Computational Vision CSc Optical Flow & Motion The Factorization Method.
CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.
Motion Computing in Image Analysis
Optical Flow Estimation using Variational Techniques Darya Frolova.
Motion Estimation Today’s Readings Trucco & Verri, 8.3 – 8.4 (skip 8.3.3, read only top half of p. 199) Numerical Recipes (Newton-Raphson), 9.4 (first.
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
Matching Compare region of image to region of image. –We talked about this for stereo. –Important for motion. Epipolar constraint unknown. But motion small.
October 7, 2010Neural Networks Lecture 10: Setting Backpropagation Parameters 1 Creating Data Representations On the other hand, sets of orthogonal vectors.
Motion from normal flow. Optical flow difficulties The aperture problemDepth discontinuities.
Optical flow (motion vector) computation Course: Computer Graphics and Image Processing Semester:Fall 2002 Presenter:Nilesh Ghubade
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
Lecture 12 Stereo Reconstruction II Lecture 12 Stereo Reconstruction II Mata kuliah: T Computer Vision Tahun: 2010.
October 14, 2014Computer Vision Lecture 11: Image Segmentation I 1Contours How should we represent contours? A good contour representation should meet.
CSSE463: Image Recognition Day 30 This week This week Today: motion vectors and tracking Today: motion vectors and tracking Friday: Project workday. First.
Optical Flow Donald Tanguay June 12, Outline Description of optical flow General techniques Specific methods –Horn and Schunck (regularization)
1-1 Measuring image motion velocity field “local” motion detectors only measure component of motion perpendicular to moving edge “aperture problem” 2D.
Computer Vision, Robert Pless Lecture 11 our goal is to understand the process of multi-camera vision. Last time, we studies the “Essential” and “Fundamental”
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.
September 23, 2014Computer Vision Lecture 5: Binary Image Processing 1 Binary Images Binary images are grayscale images with only two possible levels of.
Motion Segmentation By Hadas Shahar (and John Y.A.Wang, and Edward H. Adelson, and Wikipedia and YouTube) 1.
Image Processing Jitendra Malik. Different kinds of images Radiance images, where a pixel value corresponds to the radiance from some point in the scene.
Course 11 Optical Flow. 1. Concept Observe the scene by moving viewer Optical flow provides a clue to recover the motion. 2. Constraint equation.
1 Computational Vision CSCI 363, Fall 2012 Lecture 21 Motion II.
Motion Analysis using Optical flow CIS750 Presentation Student: Wan Wang Prof: Longin Jan Latecki Spring 2003 CIS Dept of Temple.
CS332 Visual Processing Department of Computer Science Wellesley College Analysis of Motion Measuring image motion.
3D Imaging Motion.
Optical Flow. Distribution of apparent velocities of movement of brightness pattern in an image.
1 Motion Analysis using Optical flow CIS601 Longin Jan Latecki Fall 2003 CIS Dept of Temple University.
Autonomous Robots Vision © Manfred Huber 2014.
Course14 Dynamic Vision. Biological vision can cope with changing world Moving and changing objects Change illumination Change View-point.
Motion Estimation using Markov Random Fields Hrvoje Bogunović Image Processing Group Faculty of Electrical Engineering and Computing University of Zagreb.
October 1, 2013Computer Vision Lecture 9: From Edges to Contours 1 Canny Edge Detector However, usually there will still be noise in the array E[i, j],
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
Determining 3D Structure and Motion of Man-made Objects from Corners.
November 5, 2013Computer Vision Lecture 15: Region Detection 1 Basic Steps for Filtering in the Frequency Domain.
Motion / Optical Flow II Estimation of Motion Field Avneesh Sud.
September 26, 2013Computer Vision Lecture 8: Edge Detection II 1Gradient In the one-dimensional case, a step edge corresponds to a local peak in the first.
MASKS © 2004 Invitation to 3D vision Lecture 3 Image Primitives andCorrespondence.
COMP 9517 Computer Vision Motion 7/21/2018 COMP 9517 S2, 2012.
Motion Detection And Analysis
Mean Shift Segmentation
Computer Vision Lecture 12: Image Segmentation II
Fourier Transform: Real-World Images
Common Classification Tasks
Range Imaging Through Triangulation
Presented by: Cindy Yan EE6358 Computer Vision
Computer Vision Lecture 16: Texture II
Object Recognition Today we will move on to… April 12, 2018
CSSE463: Image Recognition Day 30
Announcements Questions on the project? New turn-in info online
Coupled Horn-Schunck and Lukas-Kanade for image processing
Measuring image motion
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 30
Introduction to Artificial Intelligence Lecture 22: Computer Vision II
Detecting Motion Pattern in Optical Flow Fields
Presentation transcript:

December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis

December 9, 2014Computer Vision Lecture 23: Motion Analysis 2 Motion analysis Motion analysis is dealing with three main groups of motion- related problems: Motion detection Moving object detection and location. Derivation of 3D object properties. Motion analysis and object tracking combine two separate but inter-related components: Localization and representation of the object of interest (target). Trajectory filtering and data association. One or the other may be more important based on the nature of the motion application.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 3 Motion analysis

December 9, 2014Computer Vision Lecture 23: Motion Analysis 4 Differential Motion Analysis A simple method for motion detection is the subtraction of two or more images in a given image sequence. Usually, this method results in a difference image d(i, j), in which non-zero values indicate areas with motion. For given images f 1 and f 2, d(i, j) can be computed as follows: d(i, j) = 0 if | f 1 (i, j) – f 2 (i, j) |   = 1 otherwise

December 9, 2014Computer Vision Lecture 23: Motion Analysis 5 Differential Motion Analysis

December 9, 2014Computer Vision Lecture 23: Motion Analysis 6 Difference Pictures Another example of a difference picture that indicates the motion of objects (  = 25).

December 9, 2014Computer Vision Lecture 23: Motion Analysis 7 Difference Pictures Applying a size filter (size 10) to remove noise from a difference picture.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 8 Difference Pictures The differential method can rather easily be “tricked”. Here, the indicated changes were induced by changes in the illumination instead of object or camera motion (again,  = 25).

December 9, 2014Computer Vision Lecture 23: Motion Analysis 9 Differential Motion Analysis In order to determine the direction of motion, we can compute the cumulative difference image for a sequence f 1, …, f n of more than two images: Here, f 1 is used as the reference image, and the weight coefficients a k can be used to give greater weight to more recent frames and thereby highlight the current object positions.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 10 Cumulative Difference Image Example: Sequence of 4 images: a 2 = a 3 = 2a 4 = 4 Result:

December 9, 2014Computer Vision Lecture 23: Motion Analysis 11 Differential Motion Analysis Generally speaking, while differential motion analysis is well-suited for motion detection, it is not ideal for the analysis of motion characteristics.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 12 Optical flow Optical flow reflects the image changes due to motion during a time interval dt which must be short enough to guarantee small inter-frame motion changes. The optical flow field is the velocity field that represents the three-dimensional motion of object points across a two- dimensional image. Optical flow computation is based on two assumptions: The observed brightness of any object point is constant over time. Nearby points in the image plane move in a similar manner (the velocity smoothness constraint).

December 9, 2014Computer Vision Lecture 23: Motion Analysis 13 Optical flow

December 9, 2014Computer Vision Lecture 23: Motion Analysis 14 Optical Flow The basic idea underlying most algorithms for optical flow computation: Regard image sequence as three-dimensional (x, y, t) space Determine x- and y-slopes of equal-brightness pixels along t-axis The computation of actual 3D gradients is usually quite complex and requires substantial computational power for real-time applications.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 15 Optical Flow Let us consider the two-dimensional case (one spatial dimension x and the temporal dimension t), with an object moving to the right: x t

December 9, 2014Computer Vision Lecture 23: Motion Analysis 16 Optical Flow Instead of using the gradient methods, one can simply determine those straight lines with a minimum of variation (standard deviation) in intensity along them: x t Flow undefined in these areas

December 9, 2014Computer Vision Lecture 23: Motion Analysis 17 Optical flow Optical flow computation will be in error if the constant brightness and velocity smoothness assumptions are violated. In real imagery, their violation is quite common. Typically, the optical flow changes dramatically in highly textured regions, around moving boundaries, at depth discontinuities, etc. Resulting errors propagate across the entire optical flow solution.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 18 Optical flow Global error propagation is the biggest problem of global optical flow computation schemes, and local optical flow estimation helps overcome the difficulties. However, local flow estimation can introduce large errors for homogeneous areas, i.e., regions of constant intensity. One solution of this problem is to assign confidence values to local flow estimations and consider those when integrating local and global optical flow.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 19 Optical flow

December 9, 2014Computer Vision Lecture 23: Motion Analysis 20 Optical flow

December 9, 2014Computer Vision Lecture 23: Motion Analysis 21 Detecting Motion Pattern in Optical Flow Fields We can compute the local speed gradient to detect certain basic motion patterns. The speed gradient is defined as the direction of the steepest speed increase, regardless of the direction of motion.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 22 Detecting Motion Pattern in Optical Flow Fields There are four different basic motion patterns: counterclockwise and clockwise rotation, contraction, and expansion. They can be combined to form spiral motion. counterclockwiseclockwisecontractionexpansion movement speed gradient Idea: A consistent angle between the direction of movement and the orientation of the speed gradient indicates a specific motion pattern.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 23 Detecting Motion Pattern in Optical Flow Fields direction of movement orientation of speed gradient Angles other than 0, 90, 180, and 270 degrees correspond to spiral motion patterns.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 24 Feature Point Correspondence Feature point correspondence is another method for motion field construction. Velocity vectors are determined only for corresponding feature points. Object motion parameters can be derived from computed motion field vectors. Motion assumptions can help to localize moving objects. Frequently used assumptions include, like discussed above: Maximum velocity Small acceleration Common motion

December 9, 2014Computer Vision Lecture 23: Motion Analysis 25 Feature Point Correspondence The idea is to find significant points (interest points, feature points) in all images of the sequence—points least similar to their surroundings, representing object corners, borders, or any other characteristic features in an image that can be tracked over time. Basically the same measures as for stereo matching can be used. Point detection is followed by a matching procedure, which looks for correspondences between these points in time. The main difference to stereo matching is that now we cannot simply search along an epipolar line, but the search area is defined by our motion assumptions. The process results in a sparse velocity field. Motion detection based on correspondence works even for relatively long interframe time intervals.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 26 Feature Point Correspondence

December 9, 2014Computer Vision Lecture 23: Motion Analysis 27 And this is… The End