Caught in Motion By: Eric Hunt-Schroeder EE275 – Final Project - Spring 2012.

Slides:



Advertisements
Similar presentations
CBA #1 Review Graphing Motion 1-D Kinematics Projectile Motion Circular Motion Gravity Graphing Motion 1-D Kinematics Projectile Motion Circular.
Advertisements

Formation et Analyse d’Images Session 8
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Tracking a maneuvering object in a noisy environment using IMMPDAF By: Igor Tolchinsky Alexander Levin Supervisor: Daniel Sigalov Spring 2006.
© 2003 by Davi GeigerComputer Vision November 2003 L1.1 Tracking We are given a contour   with coordinates   ={x 1, x 2, …, x N } at the initial frame.
Novel approach to nonlinear/non- Gaussian Bayesian state estimation N.J Gordon, D.J. Salmond and A.F.M. Smith Presenter: Tri Tran
Tracking with Linear Dynamic Models. Introduction Tracking is the problem of generating an inference about the motion of an object given a sequence of.
Analysis of a position vs. time graph Analysis of a velocity vs. time graph What can be determined from a position vs. time graph? What can be determined.
Kinematics Graphs One-Dimensional Motion Graphs provide an easy tool for understanding and communicating how objects move. Objectives to learn how to interpret.
1 Formation et Analyse d’Images Session 7 Daniela Hall 7 November 2005.
Kinematics in Two Dimensions Chapter 3. Expectations After Chapter 3, students will:  generalize the concepts of displacement, velocity, and acceleration.
Adding Vectors, Rules When two vectors are added, the sum is independent of the order of the addition. This is the Commutative Law of Addition.
BraMBLe: The Bayesian Multiple-BLob Tracker By Michael Isard and John MacCormick Presented by Kristin Branson CSE 252C, Fall 2003.
Colorado Center for Astrodynamics Research The University of Colorado 1 STATISTICAL ORBIT DETERMINATION Satellite Tracking Example of SNC and DMC ASEN.
CSSE463: Image Recognition Day 30 This week This week Today: motion vectors and tracking Today: motion vectors and tracking Friday: Project workday. First.
Real-time object tracking using Kalman filter Siddharth Verma P.hD. Candidate Mechanical Engineering.
1. Introduction Motion Segmentation The Affine Motion Model Contour Extraction & Shape Estimation Recursive Shape Estimation & Motion Estimation Occlusion.
CH-01-3: Predicting Position. Predicting Position - first time step +y +x t = 0 t =  t The position of the object at t=  t is its initial position plus.
Describing Motion: Kinematics in One Dimension
3D SLAM for Omni-directional Camera
Displacement, Velocity, and Acceleration Equations of Kinematics in 2 Dimensions Projectile Motion Relative Velocity.
Complete Pose Determination for Low Altitude Unmanned Aerial Vehicle Using Stereo Vision Luke K. Wang, Shan-Chih Hsieh, Eden C.-W. Hsueh 1 Fei-Bin Hsaio.
Kinematics in One Dimension We will focus today on problem- solving. Note: some problems are hard, some are not so hard. Part of the learning is recognizing.
X is the magnitude of a position v is the magnitude of the velocity, sometimes speed a is the magnitude of acceleration t is time Δ represents a change,
Karman filter and attitude estimation Lin Zhong ELEC424, Fall 2010.
One Dimensional Kinematics: Problem Solving Kinematics in Two-Dimensions: Law of Addition of Velocities Projectile Motion 8.01 W02D1.
Projectile Motion Previously, we studied motion in one direction (linear motion) Projectiles follow a curved path (nonlinear motion) The velocity of a.
Submitted by: Giorgio Tabarani, Christian Galinski Supervised by: Amir Geva CIS and ISL Laboratory, Technion.
Chapter 2: Kinematics in one Dimension Displacement Velocity Acceleration HW2: Chap. 2: pb.3,pb.8,pb.12,pb.22,pb.27,pb.29,pb.46 DUE on Wednesday, Sept.
December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.
Stable Multi-Target Tracking in Real-Time Surveillance Video
Expectation-Maximization (EM) Case Studies
Real-Time Simultaneous Localization and Mapping with a Single Camera (Mono SLAM) Young Ki Baik Computer Vision Lab. Seoul National University.
Chapter 4 Two-Dimensional Kinematics. Units of Chapter 4 Motion in Two Dimensions Projectile Motion: Basic Equations Zero Launch Angle General Launch.
Kinematics in Two Dimensions AP Physics 1. Cartesian Coordinates When we describe motion, we commonly use the Cartesian plane in order to identify an.
PROJECTILE MOTION. Relevant Physics: The Independence of the Vertical and Horizontal directions means that a projectile motion problem consists of two.
Segmentation of Vehicles in Traffic Video Tun-Yu Chiang Wilson Lau.
Let’s Bounce! or Physics of Collisions Part 1 Games Fundamentals © by Jarek Francik Kingston University, London
An Introduction To The Kalman Filter By, Santhosh Kumar.
By Naveen kumar Badam. Contents INTRODUCTION ARCHITECTURE OF THE PROPOSED MODEL MODULES INVOLVED IN THE MODEL FUTURE WORKS CONCLUSION.
Unit Two: Dynamics Section 1: Forces. What Do I Already Know? Take 10 minutes to discuss with the person next to you. You can use your textbook and/or.
Mechanics Topic 2.1 Kinematics. Kinematic Concepts: Displacement Is a measured distance in a given direction It is a vector quantity It tells us not only.
By: Aaron Dyreson Supervising Professor: Dr. Ioannis Schizas
CSSE463: Image Recognition Day 29 This week This week Today: Surveillance and finding motion vectors Today: Surveillance and finding motion vectors Tomorrow:
Kinematics The branch of mechanics that studies the motion of a body without caring about what caused the motion.
Visual Tracking by Cluster Analysis Arthur Pece Department of Computer Science University of Copenhagen
l The study of HOW objects move: è Graphs è Equations è Motion maps è Verbal descriptions Kinematics-1.
1/29/03 Physics 103, Spring 2004, U. Wisconsin 1 Physics 103: Lecture 3 Position & Velocity with constant Acceleration l Today’s lecture will be on kinematic.
KINEMATICS OF PARTICLES RELATIVE MOTION WITH RESPECT TO TRANSLATING AXES.
Force and Motion. Prior Concepts Related to Forces PreK-2 Forces are pushes and pulls that change the motion of an object. Forces are required to change.
Kalman Filter and Data Streaming Presented By :- Ankur Jain Department of Computer Science 7/21/03.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
Grade 9 Review Kinematics (motion) – Velocity and Acceleration Reference Frames and Displacement Average Velocity Instantaneous Velocity Acceleration Motion.
SPACE MOUSE. INTRODUCTION  It is a human computer interaction technology  Helps in movement of manipulator in 6 degree of freedom * 3 translation degree.
Tracking We are given a contour G1 with coordinates G1={x1 , x2 , … , xN} at the initial frame t=1, were the image is It=1 . We are interested in tracking.
Mechanics 1 : Kinematics
Chapter 2 Motion Along a Straight Line
Chap. 2: Kinematics in one Dimension
KINEMATICS: LESSON 2.
Vehicle Segmentation and Tracking from a Low-Angle Off-Axis Camera
Kinematics Acceleration
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 30
CSSE463: Image Recognition Day 30
PROJECTILE MOTION.
The Discrete Kalman Filter
Presentation transcript:

Caught in Motion By: Eric Hunt-Schroeder EE275 – Final Project - Spring 2012

Kalman Filter

Kalman Filter Equations Summary

U n – Control Vector, magnitude of any control system’s or user’s control on situation Z n – Measurement Vector, real-world measurement received X n – newest estimate of current true state X n – newest estimate of current true state P n – newest estimate of the average error A – State Transition Matrix B – Control Matrix H – Observation Matrix Q – Estimated process error covariance R – Estimated Measurement error covariance

Example Lets suppose we fire a tennis ball at a 45˚ angle with a velocity of 100 m/s. We take measurements from a camera inside the tennis ball. This camera acts as our sensor taking measurements of position at the same time step (∆t). The camera adds error to our position measurements. Velocity in the x and y directions are known exact throughout the example. We then have error in position but no error in velocity.

Expected Results using Newtons Kinematic Equations

Kinematic Equations x(t) = x 0 + V 0x t x direction position V x (t) = V 0x velocity in x direction, Assumed Constant y (t) = y 0 + V 0y t - (1/2)gt 2 y direction position V y (t) = V 0y – gt velocity in y direction Where: x 0 is the initial displacement and g is the acceleration due to gravity (i.e. ≈ 9.81m/s 2 ) ∆t represents a time step of 1

Converting to a Recurrence Relation, discrete time x n = x n-1 + V xn-1 ∆t x direction position V xn = V xn-1 velocity in x direction y n = y n-1 + V yn-1 ∆t - (1/2)g∆t 2 y direction position V yn = V yn-1 - g∆t velocity in y direction g is the acceleration due to gravity (i.e. ≈ 9.81m/s 2 ) ∆t represents a time step of 1

Putting into Matrix form

Giving our Kalman Filter some initial information:

Simulation Results

Introduction – Why do we want to do Motion Tracking? Track and detect objects moving across a given space Location and Identification of an object - detection of a robbery in bank, car crash in intersection Want to know behavior of an animal being tested on in the lab

Object Detection - Process We must differentiate between what is the foreground and background image. We assign each pixel of an image a distribution of typical values -> our background image. The background should be constantly updated over subsequent frames.

Problems with Outlier-Detection & algorithm Drastic changes to our background – no easy fix Gradual changes to the background on the other hand can be fixed. We let our background be an accumulation of previous backgrounds. This allows for minor changes to take place such as a change from sunlight to dusk. Time for an example!

Example – Background VS Foreground Background image: with a pedestrian passing through (outlier) Foreground Image: Pedestrian detected On the left we see our frame with a background image already developed. We also notice an object, in this case a pedestrian, has entered the frame. This pedestrian causes a drastic change in the pixels we expected and we notice that the frame on the right has detected this change, shown vividly in white (foreground image). This process is completed by lumping large connected foreground regions into blobs, allowing one to detect an object.

object detected incorrectly Background image: with a pedestrian passing through (outlier) Foreground Image: Pedestrian detected – Unwanted blob shown We notice an unwanted blob is shown in the foreground image. When we evaluate the original image we see that this was a street light and may have been caused by excessive winds producing an outlier to be detected incorrectly. With minor errors in object detection our main goal still remains MOTION TRACKING -> this involves creating a series of object blobs together across successive image frames, this is commonly referred to as blob tracking.

Step 2: Object Tracking We are able to track an object with a bounding box by estimating the trajectory of two (x,y) coordinates at opposite corners using the Kalman Filter This is quite similar to the example of tracking a tennis ball except we now keep track of two points

Another problem…Occlusion Another difficulty faced with this motion tracking algorithm is that of occlusion. When two objects pass each other we lose track of the object. Future algorithms and research may learn how to better deal with this common problem.

Sources/References man.html man.html /kalman.html /kalman.html