| 摘要 |
A depth estimation method based on light field data distribution, the method including the following steps: S1, adjusting the pixel distribution of image inputted into a light field, and generating a plurality of refocused light field images with different focal lengths; S2, for the plurality of refocused light field images, respectively extracting the intensity range of the same macro-pixel, thereby selecting the refocused light field image corresponding to the smallest intensity range, the focal length of the refocused light field image serves as the scene depth of the macro-pixel; the macro-pixel is corresponding to one point in an actual scene, and the intensity range of the macro-pixel is the variation range of the intensity values of all points in the macro-pixel; and repeating the step S2, obtaining the scene depths of all macro-pixels. The method of the present invention can make full use of the scene textures and spatial information collected by a light field camera such as Lytro, and obtains the estimation of scene depths with abundant details, clear characteristics and high accuracy and consistency. |
