what :
Home > Search > jit.op

Objectspage : 1
cv.jit.flow.draw Abstraction Visualize optical flow.
This object displays the output of cv.jit.LKflow, cv.jit.HSflow and cv.jit.opticalflow, mapping direction to hue and distance to saturation.
cv.jit.open External An "open" operation is simply an "erode" followed by a "dilate".
An "open" operation is simply an "erode" followed by a "dilate". This results in a slight widening of holes and openings, hence the name. It gets rid of smaller specks of noise while retaining the general size of the input objects, unlike "erode" alone.
cv.jit.opticalflow External Calculate optical flow using a variety of techniques.
Optical flow is a measure of the velocity of each pixel between two consecutive frames. In other words, displacing the pixels in the first image by the optical flow should produce the second image.

Optical flow can unfortunately only be estimated, not precisely calculated. For this reason, there are several optical flow estimation algorithms. cv.jit.lkflow and cv.jit.hsflow implement two of the most famous approaches, but because the output format and its meaning are the same, cv.jit.opticalflow encapsulates several algorithms, allowing you to easily switch between them to find the one that best suits your needs.

Appart from the Lucas-Kanade and Horn-Schunk techniques, cv.jit.opticalflow currently implements the "block matching" algorithm and an algorithm by Gunnar Farnebäck.
cv.jit.stddev External Computes the standard deviation of the incoming matrices.
Computes the standard deviation of the incoming matrices. The standard deviation is simply the square root of the variance, so the same result can be obtained with cv.jit.variance and a jit.op object. The standard deviation is a measure of how much sample values vary from the mean, or in other words, how wide the distribution on either side of the mean is. About 65% of sample values fall within one standard deviation of the mean, whereas 95% are within twice that value. This measurement is very useful when it comes to setting bounds or threshold values, for instance in a background subtraction operation. If the mean value of a background pixel is 50, and the standard deviation is 10, then a pixel valued at 80 would be considered foreground. However, if the standard deviation is around 30, there is a good chance that it belongs to the background.
ike.mix_op_smooth Abstraction Creates smooth transitions between jit.op modes
Creates smooth transitions between jit.op modes; maintains operating efficiency by turning off unused jit.op; handles restriction that the "left" jit.op/movie stream must always be running to produce output.
jit.expr External evaluate expressions of matrix operators, functors, and other jitter objects
The jit.expr object evaluates expressions to fill an output matrix. The expression can contain any operator available from within jit.op, any functor available from within jit.bfg, and many jitter MOPs.
jit.la.mult External True matrix multiplication
The jit.la.mult object calculates the matrix product of two input matrices (as opposed to multiplication performed by the jit.op object, which ispointwise multiplication). The input matrices must have type float32 or float64, and may have planecount 1 or 2. If the input matrix has a planecount of 2, it is assumed that the data is from the set of complex numbers.
jit.op External Apply binary or unary operators
The jit.op object applies either a binary operator to two input matrices, or a unary operator to the left input matrix. A different operator may be specified for each plane, or a scalar may be specified via the val attribute as an alternate to using a second matrix.
jit.op External Apply binary or unary operators
The jit.op object applies either a binary operator to two input matrices, or a unary operator to the left input matrix. A different operator may be specified for each plane, or a scalar may be specified via the val attribute as an alternate to using a second matrix.
jit.openexr External Load or save HDR image data in OpenEXR format.
read and write OpenEXR format images (includes floating point HDR, and arbitrary color channels)
jit.openni External Max Jitter external for OpenNI middleware, supports Kinect and any other OpenNI compliant device
Rich support of OpenNI features using devices like Kinect. Currently supports:

* Configuration of OpenNI by an OpenNI XML configuration file; see OpenNI documentation for format
* ImageMap image output of RGB24 output in a 4-plane char jitter matrix
* DepthMap depth output in a 1-plan long, float32, or float64 jitter matrix
* IrMap Infrared IR output in a 1-plan long, float32, or float64 jitter matrix
* UserPixelMap user tagging/identification output in a 1-plan long, float32, or float64 jitter matrix
* Skeleton joints in an OSC, native max route, or legacy OSCeleton format
* Skeleton events in an OSC, native max route, or legacy OSCeleton format (e.g. user seen, user lost, calibration success, etc.)
* User centers of mass
* Values for user centers of mass and joints in OpenNI native, projective coordinate, or OSCeleton legacy “normalized” values
* Attributes to filtering data based on position or orientation confidence, display or not the orientation data, and smooth skeleton data using OpenNI’s smoothing API
* Compiled as a Win32 max/jitter external
page : 1

4813 objects and 135 libraries within the database Last entries : August 20th, 2014 Last comments : 0 RSS
Site under GNU Free Documentation License page generated in : 0.0823 s