Class BackgroundMovingGaussian<T extends ImageBase<T>,​Motion extends InvertibleTransform<Motion>>

java.lang.Object
boofcv.alg.background.BackgroundModel<T>
boofcv.alg.background.BackgroundModelMoving<T,​Motion>
boofcv.alg.background.moving.BackgroundMovingGaussian<T,​Motion>
All Implemented Interfaces:
BackgroundAlgorithmGaussian
Direct Known Subclasses:
BackgroundMovingGaussian_IL, BackgroundMovingGaussian_IL_MT, BackgroundMovingGaussian_PL, BackgroundMovingGaussian_PL_MT, BackgroundMovingGaussian_SB, BackgroundMovingGaussian_SB_MT

public abstract class BackgroundMovingGaussian<T extends ImageBase<T>,​Motion extends InvertibleTransform<Motion>>
extends BackgroundModelMoving<T,​Motion>
implements BackgroundAlgorithmGaussian

Implementation of BackgroundAlgorithmGaussian for moving images.

See Also:
BackgroundAlgorithmGaussian, BackgroundModelMoving
  • Field Details

    • learnRate

      protected float learnRate
      Specifies how fast it will adapt. 0 to 1, inclusive. 0 = static 1.0 = instant.
    • threshold

      protected float threshold
      Threshold for classifying a pixel as background or not. This threshold is applied to the computed Mahalanobis from the distribution.
    • initialVariance

      protected float initialVariance
      The initial variance assigned to a new pixel. Larger values to reduce false positives due to under sampling
    • minimumDifference

      protected float minimumDifference
  • Constructor Details

    • BackgroundMovingGaussian

      protected BackgroundMovingGaussian​(float learnRate, float threshold, Point2Transform2Model_F32<Motion> transform, ImageType<T> imageType)
      See class documentation for parameters definitions.
      Parameters:
      learnRate - Specifies how quickly the background is updated Try 0.05
      threshold - Threshold for background. ≥ 0. Try 10
      transform - Used to convert pixel coordinates
      imageType - Type of input image