Persistent Surveillance

Slides:



Advertisements
Similar presentations
P L A Y Materials and Processes Module An introduction to Sculpture and Video Video- first steps.
Advertisements

Foreground Modeling The Shape of Things that Came Nathan Jacobs Advisor: Robert Pless Computer Science Washington University in St. Louis.
Presenter: Yufan Liu November 17th,
Kalman’s Beautiful Filter (an introduction) George Kantor presented to Sensor Based Planning Lab Carnegie Mellon University December 8, 2000.
Probabilistic video stabilization using Kalman filtering and mosaicking.
Background Estimation with Gaussian Distribution for Image Segmentation, a fast approach Gianluca Bailo, Massimo Bariani, Paivi Ijas, Marco Raggio IEEE.
Adaptive Rao-Blackwellized Particle Filter and It’s Evaluation for Tracking in Surveillance Xinyu Xu and Baoxin Li, Senior Member, IEEE.
Object Detection and Tracking Mike Knowles 11 th January 2005
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Multi-camera Video Surveillance: Detection, Occlusion Handling, Tracking and Event Recognition Oytun Akman.
Geometric Approaches to Reconstructing Time Series Data Final Presentation 10 May 2007 CSC/Math 870 Computational Discrete Geometry Connie Phong.
Tracking with Linear Dynamic Models. Introduction Tracking is the problem of generating an inference about the motion of an object given a sequence of.
Overview and Mathematics Bjoern Griesbach
                      Digital Video 1.
Kalman filter and SLAM problem
Muhammad Moeen YaqoobPage 1 Moment-Matching Trackers for Difficult Targets Muhammad Moeen Yaqoob Supervisor: Professor Richard Vinter.
Path-Based Constraints for Accurate Scene Reconstruction from Aerial Video Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth I. Joy 3 Abstract - This.
Sequential Reconstruction Segment-Wise Feature Track and Structure Updating Based on Parallax Paths Mauricio Hess-Flores 1, Mark A. Duchaineau 2, Kenneth.
Real-time object tracking using Kalman filter Siddharth Verma P.hD. Candidate Mechanical Engineering.
GESTURE ANALYSIS SHESHADRI M. (07MCMC02) JAGADEESHWAR CH. (07MCMC07) Under the guidance of Prof. Bapi Raju.
Intro to Computers By Alex Pu Computational Thinking: Overview Making Information Available to the World with HTML an d Web Pages Desktop Publishing with.
ECE 172A SIMPLE OBJECT DETECTOR WITH INDICATOR WHEN A NEW OBJECT HAS BEEN ADDED TO OR MISSING IN A ROOM Presented by by Hugo Groening.
Stable Multi-Target Tracking in Real-Time Surveillance Video
Reference: The Game Loop Animation / Game loop 1. Update variables 2. [Get input from the user] (GameLoop only) 3. Draw (using variables)
Crowd Analysis at Mass Transit Sites Prahlad Kilambi, Osama Masound, and Nikolaos Papanikolopoulos University of Minnesota Proceedings of IEEE ITSC 2006.
Expectation-Maximization (EM) Case Studies
Simulation software Definition of simulation software Purpose of simulation software Characteristics of simulation software Criteria for good simulation.
1 Motion estimation from image and inertial measurements Dennis Strelow and Sanjiv Singh Carnegie Mellon University.
Linearization and Newton’s Method. I. Linearization A.) Def. – If f is differentiable at x = a, then the approximating function is the LINEARIZATION of.
Introduction to Image Processing Our first look at image processing will be through the use of Paint Shop Pro, a bitmap editing program available as shareware.
An Introduction To The Kalman Filter By, Santhosh Kumar.
Object Tracking - Slide 1 Object Tracking Computer Vision Course Presentation by Wei-Chao Chen April 05, 2000.
Final Year Project. Project Title Kalman Tracking For Image Processing Applications.
Cameron Rowe.  Introduction  Purpose  Implementation  Simple Example Problem  Extended Kalman Filters  Conclusion  Real World Examples.
Arizona’s First University. Scenario, Demo and New Application In collaboration with Vanderbilt University, and the University of California, Berkeley.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Project and Project Formulation and Management
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
V4 – Video Tracker for Extremely Hard Night Conditions
Rotoscoping Senior Capstone Project | Ted Trisco
3.3 Fundamentals of data representation
Tracking Objects with Dynamics
COMPONENTS OF A COMPUTER
Introduction CSE 1310 – Introduction to Computers and Programming
Intelligent Information System Lab
Mauricio Hess-Flores1, Mark A. Duchaineau2, Kenneth I. Joy3
Completing the tasks for A452 with….
ISOMAP TRACKING WITH PARTICLE FILTERING
Presenter: Xudong Zhu Authors: Xudong Zhu, etc.
Segmentation of Images By Color
Global Challenge Walking for Water Lesson 2.
Persistent Surveillance
Global Challenge Walking for Water Lesson 2.
Global Challenge Walking for Water Lesson 2.
SIMPLE ONLINE AND REALTIME TRACKING WITH A DEEP ASSOCIATION METRIC
By Soham Chakraborty, Joey Huntley, and Susan Xie
Global Challenge Walking for Water Lesson 2.
Graph Review Skills Needed Identify the relationship in the graph
Global Challenge Walking for Water Lesson 2.
Global Challenge Walking for Water Lesson 2.
Global Challenge Walking for Water Lesson 2.
Hashing Hash are the auxiliary values that are used in cryptography.
Power save and routing use case examination
Global Challenge Walking for Water Lesson 2.
Application of Facial Recognition in Biometric Security
Modeling the Spread of a Virus in a Modern Environment
Global Challenge Walking for Water Lesson 2.
Global Challenge Walking for Water Lesson 2.
Tracking Many slides adapted from Kristen Grauman, Deva Ramanan.
Nome Sobrenome. Time time time time time time..
Presentation transcript:

Persistent Surveillance Tracking In Persistent Surveillance Adam Mounts Computer Systems Lab 2009-2010

Abstract Crucial development in security and/or surveillance systems. Useful in the event of a crisis situation to follow potential suspects or targets All based on aerial imagery. Has an advantage over human analysts in efficiency and feasibility

Introduction The goal of this project is to create and compare trackers that can follow a certain object, whether it be a human, a vehicle, or some other moving target, and trace its path through a series of images. http://www.stdb-seesamples.com/seesamples_pdfs/Aerial%20Image.jpg

Background Project Chloe www.homelandsecurity.org/StakeholdersMay07/Br45_Wilson.pdf

The first aspect of this project was the creation of a “movie maker” that creates and saves a sequence of images that can be used as data for a quick test of the tracking algorithms. A small black circle moves across the screen randomly, and frames are saved into files. Testing Software

The first algorithm I use to track a target is the use of pixel subtraction. This essentially takes a series of linear images, and compares them pixel by pixel and highlights the differences between them. Pixel Subtraction

Pros and Cons Relatively easy to code Effective and quick in simple situations Slow and inaccurate in complex scenarios Not as accurate as other algorithms

In Action

Kalman Filter A Kalman Filter is a recursive algorithm that repetitively minimizes the square of the error, after making a slight random adjustment to the data. By doing this, its estimate gradually approaches the actual answer. By using variables such as location and velocity, it can be applied to tracking.

As shown in some of my previous slides, these are the current outputs of my programs Results