Package org.opencv.bioinspired

Class RetinaFastToneMapping

  • public class RetinaFastToneMapping
extends Algorithm
    a wrapper class which allows the tone mapping algorithm of Meylan&al(2007) to be used with OpenCV. This algorithm is already implemented in thre Retina class (retina::applyFastToneMapping) but used it does not require all the retina model to be allocated. This allows a light memory use for low memory devices (smartphones, etc. As a summary, these are the model properties:
    • 2 stages of local luminance adaptation with a different local neighborhood for each.
    • first stage models the retina photorecetors local luminance adaptation
    • second stage models th ganglion cells local information adaptation
    • compared to the initial publication, this class uses spatio-temporal low pass filters instead of spatial only filters. this can help noise robustness and temporal stability for video sequence use cases.
    for more information, read to the following papers : Meylan L., Alleysson D., and Susstrunk S., A Model of Retinal Local Adaptation for the Tone Mapping of Color Filter Array Images, Journal of Optical Society of America, A, Vol. 24, N 9, September, 1st, 2007, pp. 2807-2816Benoit A., Caplier A., Durette B., Herault, J., "USING HUMAN VISUAL SYSTEM MODELING FOR BIO-INSPIRED LOW LEVEL IMAGE PROCESSING", Elsevier, Computer Vision and Image Understanding 114 (2010), pp. 758-773, DOI: http://dx.doi.org/10.1016/j.cviu.2010.01.011 regarding spatio-temporal filter and the bigger retina model : Vision: Images, Signals and Neural Networks: Models of Neural Processing in Visual Perception (Progress in Neural Processing),By: Jeanny Herault, ISBN: 9814273686. WAPI (Tower ID): 113266891.

    • Constructor Summary

      Constructors 
      Modifier Constructor Description
      protected RetinaFastToneMapping​(long addr)  

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      static RetinaFastToneMapping __fromPtr__​(long addr)  
      void applyFastToneMapping​(Mat inputImage, Mat outputToneMappedImage)
      applies a luminance correction (initially High Dynamic Range (HDR) tone mapping) using only the 2 local adaptation stages of the retina parvocellular channel : photoreceptors level and ganlion cells level.
      static RetinaFastToneMapping create​(Size inputSize)  
      protected void finalize()  
      void setup()
      updates tone mapping behaviors by adjusing the local luminance computation area (default is 1, see reference paper)
      void setup​(float photoreceptorsNeighborhoodRadius)
      updates tone mapping behaviors by adjusing the local luminance computation area
      void setup​(float photoreceptorsNeighborhoodRadius, float ganglioncellsNeighborhoodRadius)
      updates tone mapping behaviors by adjusing the local luminance computation area
      void setup​(float photoreceptorsNeighborhoodRadius, float ganglioncellsNeighborhoodRadius, float meanLuminanceModulatorK)
      updates tone mapping behaviors by adjusing the local luminance computation area

      • Methods inherited from class java.lang.Object

        clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    • Constructor Detail

      • RetinaFastToneMapping

        protected RetinaFastToneMapping​(long addr)

    • Method Detail

      • applyFastToneMapping

        public void applyFastToneMapping​(Mat inputImage,
                                 Mat outputToneMappedImage)
        applies a luminance correction (initially High Dynamic Range (HDR) tone mapping) using only the 2 local adaptation stages of the retina parvocellular channel : photoreceptors level and ganlion cells level. Spatio temporal filtering is applied but limited to temporal smoothing and eventually high frequencies attenuation. This is a lighter method than the one available using the regular retina::run method. It is then faster but it does not include complete temporal filtering nor retina spectral whitening. Then, it can have a more limited effect on images with a very high dynamic range. This is an adptation of the original still image HDR tone mapping algorithm of David Alleyson, Sabine Susstruck and Laurence Meylan's work, please cite: -> Meylan L., Alleysson D., and Susstrunk S., A Model of Retinal Local Adaptation for the Tone Mapping of Color Filter Array Images, Journal of Optical Society of America, A, Vol. 24, N 9, September, 1st, 2007, pp. 2807-2816
        Parameters:
        inputImage - the input image to process RGB or gray levels
        outputToneMappedImage - the output tone mapped image

      • setup

        public void setup​(float photoreceptorsNeighborhoodRadius,
                  float ganglioncellsNeighborhoodRadius,
                  float meanLuminanceModulatorK)
        updates tone mapping behaviors by adjusing the local luminance computation area
        Parameters:
        photoreceptorsNeighborhoodRadius - the first stage local adaptation area
        ganglioncellsNeighborhoodRadius - the second stage local adaptation area
        meanLuminanceModulatorK - the factor applied to modulate the meanLuminance information (default is 1, see reference paper)

      • setup

        public void setup​(float photoreceptorsNeighborhoodRadius,
                  float ganglioncellsNeighborhoodRadius)
        updates tone mapping behaviors by adjusing the local luminance computation area
        Parameters:
        photoreceptorsNeighborhoodRadius - the first stage local adaptation area
        ganglioncellsNeighborhoodRadius - the second stage local adaptation area (default is 1, see reference paper)

      • setup

        public void setup​(float photoreceptorsNeighborhoodRadius)
        updates tone mapping behaviors by adjusing the local luminance computation area
        Parameters:
        photoreceptorsNeighborhoodRadius - the first stage local adaptation area (default is 1, see reference paper)

      • setup

        public void setup()
        updates tone mapping behaviors by adjusing the local luminance computation area (default is 1, see reference paper)

      • finalize

        protected void finalize()
                 throws java.lang.Throwable
        Overrides:
        finalize in class Algorithm
        Throws:
        java.lang.Throwable