Search for tag: "science"

Advanced Vision: Course overview

We start with an introduction to the set of videos, summarizing the six prototype computer vision systems.

From  Joanna Malgorzata Równicka 3 Weeks ago 1   77    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Coordinate geometry transformation review

We review coordinate geometry reference frame transformations and how to represent these.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   2    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Polycurve models

We introduce a simple polycurve model that will be used to represent flat shapes and later extended for 3D shapes.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   1    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: 2D pose estimation

With the model to data correspondences, we can estimate the 2D transformation that maps the model onto the data.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   18    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: 2D match verification

Because the matching and pose estimation phases can produce spurious matches and poses, we introduce a verification step that eliminates bad hypotheses.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   16    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Straight line finding

We next turn the boundary edge points into a more compact set of straight line segments.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   41    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Part boundary finding

First we find the edge points that surround the part, by analyzing a binary image.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   52    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: 2D model matching

Then we match those straight line segments to a rigid geometric model using the Interpretation Tree model matching algorithm.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   25    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Adaptive change detection

When the background is changing due to lighting or leave motion, etc, simple subtraction is inadequate.We introduce a non-parametric statistical approach to modeling the background and then detect…

From  Joanna Malgorzata Równicka 3 Weeks ago 0   5    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Rigid flat part recognition introduction

We introduce a simple flat rigid part recognition system that is based on matching part edges to a geometric model. This will also require estimating the reference frame transformation that maps the…

From  Joanna Malgorzata Równicka 3 Weeks ago 0   67    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Ball tracking with the Kalman filter

The Kalman filter is applied to the falling ball tracking problem.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   1    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Ball tracking with Condensation Tracking

We extend the ball tracking example to use Condensation tracking, which allows tracking of the ball through bounces and stopping.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   2    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Condensation Tracking

When a target can change state, tracking can lose the target. If you have a model of different possible successor states, then the Condensation tracking algorithm can explore these…

From  Joanna Malgorzata Równicka 3 Weeks ago 0   2    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Example of adaptive change detection

We demonstrate the adaptive change detection algorithm on an indoor scene where the lighting is slowly changing, and where there are compression artifacts in the video.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   1    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Kalman filter

We introduce the Kalman Filter, which is an important algorithm for estimation of variables given data that arrives periodically. Here it is used to track the ball, predict its position and refine…

From  Joanna Malgorzata Równicka 3 Weeks ago 0   2    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016

Advanced Vision: Mathematical morphology for noise removal

We present several heuristics from removing small detections that arise because of noise, compression artifacts and camera jitter.

From  Joanna Malgorzata Równicka 3 Weeks ago 0   2    0  
Course Code
INFR11127
Publisher
Robert Fisher
Licence Type
Creative Commons - Attribution Non Commercial Share A Like
Language
English
Date Created
01/01/2016