capture cells¶

object_recognition_capture¶

MatchRefinementHSvd¶

Brief doc

A feature descriptor match refiner, using Homography and svd estimation.

Parameters

inlier_thresh type: float not required default: 25.0

The inlier threshold of pose found.
min_inliers type: unsigned int not required default: 100

minimum number of inliers
n_iters type: unsigned int not required default: 200

number of ransac iterations
reprojection_error type: float not required default: 43.5

error threshold

Inputs

matches type: std::vector<cv::DMatch, std::allocator<cv::DMatch> >

The descriptor matches.
test_2d type: cv::Mat

The 2d test points.
test_3d type: cv::Mat

The 3d test points.
train_2d type: cv::Mat

The 2d training points.
train_3d type: cv::Mat

The 3d training points.

Outputs

R type: cv::Mat
T type: cv::Mat
found type: bool
matches type: std::vector<cv::DMatch, std::allocator<cv::DMatch> >

The verified matches.
matches_mask type: cv::Mat

The matches mask, same size as the output matches.

PoseDrawer¶

Brief doc

Draw pose

Inputs

K type: cv::Mat

The camera projection matrix.
R type: cv::Mat

3x3 Rotation matrix.
T type: cv::Mat

3x1 Translation vector.
image type: cv::Mat

The original image to draw the pose onto.
trigger type: bool

Should i draw.

Outputs

output type: cv::Mat

The pose of the fiducial, drawn on an image

LSHMatcher¶

Brief doc

Given descriptors, find matches.

Parameters

key_size type: unsigned int not required default: 8
multi_probe_level type: unsigned int not required default: 1
n_tables type: unsigned int not required default: 4
radius type: unsigned int not required default: 55

Inputs

test type: cv::Mat

Train descriptors.
train type: cv::Mat

Test descriptors.
update type: bool

If set to true, update the descriptors.

Outputs

matches type: std::vector<cv::DMatch, std::allocator<cv::DMatch> >

The descriptor matches.

DeltaRT¶

Brief doc

Uses the R|T of the camera to determine when a frame in novel.

Parameters

angle_thresh type: double not required default: 0.0872664625997

The angle thresh hold.
n_desired type: unsigned int not required default: 4294967295

The number of desired views
reset type: bool not required default: False

Reset observations.

Inputs

R type: cv::Mat

The orientation.
T type: cv::Mat

The translation.
found type: bool

Whether or not the R|T is good.

Outputs

novel type: bool

Whether or not the R|T is novel relative to previous novel R|T poses.

FPSDrawer¶

Brief doc

Draw the Hz on an image.

Inputs

image type: cv::Mat

The original image to draw the pose onto.

Outputs

image type: cv::Mat

The image with fps drawn on it.

Matcher¶

Brief doc

A feature descriptor matcher.

Inputs

test type: cv::Mat

Train descriptors.
train type: cv::Mat

Test descriptors.

Outputs

matches type: std::vector<cv::DMatch, std::allocator<cv::DMatch> >

The descriptor matches.

DrawMatches¶

Brief doc

Draws matches.

Inputs

matches type: std::vector<cv::DMatch, std::allocator<cv::DMatch> >

The descriptor matches.
matches_mask type: cv::Mat

The descriptor matches mask.
test type: cv::Mat

Test keypoints.
test_image type: cv::Mat

Test image.
train type: cv::Mat

Train keypoints
train_image type: cv::Mat

Test image.

Outputs

output type: cv::Mat

An output image.

imshow¶

Brief doc

Displays an image. If a dictionary is defined in triggers, each key is defined as an output, the value being a bool of whether it’s been pressed

Parameters

autoSize type: bool not required default: True

Autosize the window.
maximize type: bool not required default: False

Fullscreen the window, takes precedence over autoSize.
name type: std::string not required default: image

The window name
triggers type: boost::python::api::object not required no default value

A dict of trigger keys, e.g. {‘x_key’:ord(‘x’)}
waitKey type: int not required default: -1

Number of millis to wait, -1 for not at all, 0 for infinity.

Inputs

image type: cv::Mat

The image to show

MatReader¶

Brief doc

Read a cv::Mat from a yaml or xml file.

Parameters

filename type: std::string required default:

Name of mat to read.

Outputs

mat type: cv::Mat

A mat to print.

imread¶

Brief doc

Reads a single image, const cell.

Parameters

image_file type: std::string not required default: lena.jpg

The path to the image to read.
lock_name type: std::string not required default:

If set to something, an flock will be created for that file
mode type: ecto_opencv::Image::Modes not required default: COLOR
Legal Values: GRAYSCALE (0) COLOR (1) ANYDEPTH (2) ANYCOLOR (4) UNCHANGED (-1)

The image read mode.
refresh type: bool not required default: False

If true, the image is re-read every time

Outputs

image type: cv::Mat

The image in full color.

OrbPoseEstimator¶

Brief doc

Parameters

directory type: boost::python::api::object not required default: .

The template directory.
inlier_thresh type: float not required default: 25.0

The inlier threshold of pose found.
key_size type: unsigned int not required default: 8
min_inliers type: unsigned int not required default: 100

minimum number of inliers
multi_probe_level type: unsigned int not required default: 1
n_features type: int not required default: 1000

The number of desired features
n_iters type: unsigned int not required default: 200

number of ransac iterations
n_levels type: int not required default: 3

The number of scales
n_tables type: unsigned int not required default: 4
nonmax type: bool not required default: True

Use the FAST nonmax suppression.
radius type: unsigned int not required default: 55
reprojection_error type: float not required default: 43.5

error threshold
scale_factor type: float not required default: 1.20000004768

The factor between scales
show_matches type: boost::python::api::object not required default: False

Display the matches.
thresh type: int not required default: 20

The FAST threshold. 20 is a decent value.
use_fast type: boost::python::api::object not required default: False

Use fast or not.
use_lsh type: boost::python::api::object not required default: True

Use lsh for matching instead of brute force.

Inputs

K type: ecto::tendril::none

Any type
color_image type: ecto::tendril::none

Any type
image type: ecto::tendril::none

Any type
mask type: ecto::tendril::none

Any type
points3d type: ecto::tendril::none

Any type

Outputs

R type: cv::Mat

3x3 Rotation matrix.
T type: cv::Mat

3x1 Translation vector.
debug_image type: cv::Mat

The image with fps drawn on it.
found type: bool

PlaneFilter¶

Brief doc

Takes a set of planes and returns the one overlaping most with the center of the image

Parameters

do_center type: bool not required default: False

If set to true, the plane origin will be at the center of the image.
size type: int not required default: 100

The edge of the central square in which to look for the plane.

Inputs

K type: cv::Mat

The calibration matrix.
R type: cv::Mat

The currently estimated plane rotation.
T type: cv::Mat

The currently estimated plane origin.
masks type: cv::Mat

The masks for each plane.
planes type: std::vector<cv::Vec<float, 4>, std::allocator<cv::Vec<float, 4> > >

The different found planes (a,b,c,d) of equation ax+by+cz+d=0.

Outputs

R type: cv::Mat

The rotation component of the plane pose
T type: cv::Mat

The translation component of the plane pose
coeffs type: cv::Vec<float, 4>

The coefficients of the plane.
found type: bool

Whether or not the R|T is good.

TemplateLoader¶

Brief doc

Parameters

directory type: boost::python::api::object not required default: .

The directory of the template.

Outputs

R type: cv::Mat

A mat to print.
T type: cv::Mat

A mat to print.
descriptors type: cv::Mat

A mat to print.
image type: cv::Mat

The image in full color.
points type: cv::Mat

A mat to print.
points3d type: cv::Mat

A mat to print.

OpposingDotPoseEstimator¶

Brief doc

Parameters

cols type: boost::python::api::object not required default: 7

Number of cols in the pattern.
debug type: boost::python::api::object not required default: True

Debug the detector.
pattern_type type: boost::python::api::object not required default: ASYMMETRIC_CIRCLES_GRID
Legal Values: CHESSBOARD (0) CIRCLES_GRID (1) ASYMMETRIC_CIRCLES_GRID (2)

Type of pattern
rows type: boost::python::api::object not required default: 11

Number of rows in the pattern.
square_size type: boost::python::api::object not required default: 0.1

The pattern spacing

Inputs

K type: ecto::tendril::none

Any type
color_image type: ecto::tendril::none

Any type
image type: ecto::tendril::none

Any type

Outputs

R type: cv::Mat

3x3 Rotation matrix.
T type: cv::Mat

3x1 Translation vector.
debug_image type: cv::Mat

The image with fps drawn on it.
found type: bool

Found some points.

FASTFeature¶

Brief doc

A FAST feature detector.

Parameters

nonmax type: bool not required default: True

Use the FAST nonmax suppression.
thresh type: int not required default: 20

The FAST threshold. 20 is a decent value.

Outputs

image type: cv::Mat

An input image.
keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints.
mask type: cv::Mat

An mask, same size as image.

TransformCompose¶

Brief doc

Compose to transforms.

Inputs

R1 type: cv::Mat

3x3 Rotation matrix.
R2 type: cv::Mat

3x3 Rotation matrix.
T1 type: cv::Mat

3x1 Translation vector.
T2 type: cv::Mat

3x1 Translation vector.

Outputs

R type: cv::Mat

3x3 Rotation matrix.
T type: cv::Mat

3x1 Translation vector.

KeypointsToMat¶

Brief doc

Take key points and return an array of the x,y coordinates.

Inputs

keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints

Outputs

points type: cv::Mat

The array of x,y coordinates

Select3d¶

Brief doc

Select 3D points given 2D locations.

Inputs

points type: cv::Mat

The 2d coordinates (matrix with 2 channels)
points3d type: cv::Mat

The 3d points to select from.

Outputs

points3d type: cv::Mat

The 3d points, same dimensions as the input, 3 channels (x, y and z).

Select3dRegion¶

Brief doc

Select 3D points given a radius in the center of the image.

Parameters

radius type: float not required default: 0.0

A radius, in pixel with which to select a plane, from the center.

Inputs

image type: cv::Mat

To base the size off of.
points3d type: cv::Mat

The 3d points to select from.

Outputs

points3d type: cv::Mat

The 3d points, same dimensions as the input, 3 channels (x, y and z).

FeatureFinder¶

Brief doc

Parameters

n_features type: int not required default: 1000

The number of desired features
n_levels type: int not required default: 3

The number of scales
nonmax type: bool not required default: True

Use the FAST nonmax suppression.
scale_factor type: float not required default: 1.20000004768

The factor between scales
thresh type: int not required default: 20

The FAST threshold. 20 is a decent value.
use_fast type: boost::python::api::object not required default: False

Use fast or not.

Inputs

image type: cv::Mat

An input image.
keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints.
mask type: cv::Mat

An mask, same size as image.
points type: cv::Mat

2d points.
points3d type: cv::Mat

The 3d points to select from.

Outputs

descriptors type: cv::Mat

The descriptors per keypoints
keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints.
points type: cv::Mat

The array of x,y coordinates
points3d type: cv::Mat

The 3d points, same dimensions as the input, 3 channels (x, y and z).

ORB¶

Brief doc

An ORB detector. Takes a image and a mask, and computes keypoints and descriptors(32 byte binary).

Parameters

n_features type: int not required default: 1000

The number of desired features
n_levels type: int not required default: 3

The number of scales
scale_factor type: float not required default: 1.20000004768

The factor between scales

Inputs

image type: cv::Mat

An input image.
keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints.
mask type: cv::Mat

An mask, same size as image.
points type: cv::Mat

2d points.

Outputs

descriptors type: cv::Mat

The descriptors per keypoints
keypoints type: std::vector<cv::KeyPoint, std::allocator<cv::KeyPoint> >

The keypoints.

Previous topic

This Page

capture cells¶

object_recognition_capture¶

MatchRefinementHSvd¶

PoseDrawer¶

LSHMatcher¶

DeltaRT¶

FPSDrawer¶

Matcher¶

DrawMatches¶

imshow¶

MatReader¶

imread¶

OrbPoseEstimator¶

PlaneFilter¶

TemplateLoader¶

OpposingDotPoseEstimator¶

FASTFeature¶

TransformCompose¶

KeypointsToMat¶

Select3d¶

Select3dRegion¶

FeatureFinder¶

ORB¶

Navigation

Previous topic

This Page

Quick search

capture cells¶

object_recognition_capture¶

MatchRefinementHSvd¶

PoseDrawer¶

LSHMatcher¶

DeltaRT¶

FPSDrawer¶

Matcher¶

DrawMatches¶

imshow¶

MatReader¶

imread¶

OrbPoseEstimator¶

PlaneFilter¶

TemplateLoader¶

OpposingDotPoseEstimator¶

FASTFeature¶

TransformCompose¶

KeypointsToMat¶

Select3d¶

Select3dRegion¶

FeatureFinder¶

ORB¶

Navigation