Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
24 Cards in this Set
- Front
- Back
- 3rd side (hint)
What is a parametric model? |
A model that represent a class ofinstances where each is defined by a value ofthe parameters. Examples include lines, or circles, or even aparameterized template. |
2B-L1 |
|
How can line fitting be difficult? |
There can be noise in edge points. Only parts of the line can be detected. There can be extra edge points. |
2B-L1 |
|
How does voting help detect features? |
Cycle through features, each casting a vote for model parameters. Look for the most popular votes. |
2B-L1 |
|
Why is voting effective? |
Noise will not cast enough votes to be detected as a feature. |
2B-L1 |
|
What is the main idea behind a Hough transform? |
1. Each edge point votes forcompatible lines. 2. Look for lines that get manyvotes. |
2B-L1 |
|
What is Hough space? |
|
2B-L1 |
|
What is the equation to transform a point in Hough space to a line? |
|
2B-L1 |
|
How does the Hough algorithm work? |
|
2B-L1 |
|
What is the polar representation of a line? |
x * cos(theta) + y * sin(theta) = 0 |
2B-L1 |
|
How is a polar Hough array constructed? |
|
2B-L1 |
|
What is the Hough transform algorithm for polar coordinates? |
|
2B-L1 |
|
How does noise impact a Hough transform? |
Long segments will still get a high amount of points, but votes might end up being split across buckets. |
2B-L1 |
|
What is the advantage of using the gradient of an edge point with Hough voting? |
Instead of computing each possible line for an edge point, the gradient reduces it down to one possible line, which dramatically reduces computational complexity. |
2B-L1 |
|
What is Hough space for a circle with known radius? |
Each edge point creates a circle based on the circle center. |
2B-L2 |
|
What is the Hough space for a circle with unknown radius? |
Each point creates a cone in Hough space. |
2B-L2 |
|
What is the Hough space for a circle with unknown radius, and a gradient? |
Each point creates a three dimensional line. |
2B-L2 |
|
What is the algorithm for Hough voting for circles? |
There is a typo in this slide... a = x + r * cos( theta ) |
2B-L2 |
|
What are some pros of parameterized Hough space? |
1. All points are processed independently, so can copewith occlusion 2. Some robustness to noise: noise points unlikely tocontribute consistently to any single bin 3. Can detect multiple instances of a model in a singlepass |
2B-L2 |
|
What are some cons of parameterized Hough space? |
1. Complexity of search time increases exponentiallywith the number of model parameters 2. Non-target shapes can produce spurious peaks inparameter space 3. Quantization: hard to pick a good grid size |
2B-L2 |
|
How is a generalized Hough Transform Table created? |
1. At each boundary point,compute displacementvector: r = c – pi 2. Measure the gradientangle θ at the boundarypoint. 3. Store that displacement ina table indexed by θ. |
2B-L3 |
|
What is the pseudo code of a Hough Transform of a template with known orientation and scale? |
For each edge point: Compute gradient direction θRetrieve displacement vectors r to vote for reference point. |
2B-L3 |
|
What is the pseudo code of a Hough Transform of a template with unknown scale S? |
For each edge point: For each possible master scale S:Compute gradient direction θFor θ’ retrieve displacement vectors rVote r scaled by S for reference point. |
2B-L3 |
|
What is the pseudo code of a Hough Transform of a template with unknown orientation? |
For each edge point: For each possible master θ*: Compute gradient direction θNew θ’ = θ - θ*For θ’ retrieve displacement vectors r to vote forreference point. |
2B-L3 |
|
What is a Code book? |
Clustering used on patches around an interest points. By storing displacements relative to an objects center, for each codebook entry, can "learn" to locate an object in an image. |
2B-L3 |