Resolving focal plane ambiguity in depth map creation from defocus blur using chromatic aberration

Abstract

Focal plane ambiguity in depth map creation from defocus blur has remained an challenging problem. In this paper, we present a method to resolve this issue with the help of Chromatic Aberration(CA). CA is a distortion referred to focal length variation of the lens with wavelength of light. When light, a mixture of various monochromatic components, passes through a lens, multiple focal planes are generated due to CA. There also exists an inherent ordering in the defocus blur of the object for different RGB components depending on whether the object lies in the near or far focus region. The ordering reverses as soon as focal planes are crossed. By using this difference in ordering of the defocus amount for different RGB components of an object, we can deduce whether the object is present in front of or behind the image plane, hence using this information, a more reliable depth map can be obtained.

Blur parameter locus curve and its applications

“…Negative value of is not possible and denotes serious errors in estimation process. These two types of focusing condition give rise to Focal Plane Ambiguity and can be removed using method such as [57, 58]. Generally, images of the scene with focus at nearest object are taken for full defocus map quality evaluation.…”

Monocular 3D metric scale reconstruction using depth from defocus and image velocity

“…The focal plane ambiguity results from the fact that DfD from a single image cannot differentiate on which side of the focal plane the objects are placed [8]. Kumar et al [16] demonstrated that chromatic aberration provides an effective indicator to solve the focal plane ambiguity. Second, the motion blur influences the defocus estimation.…”

Eliminating Scale Drift in Monocular SLAM Using Depth From Defocus

“…First, objects placed in front and behind the focal plane may be viewed with exactly the same amount of defocus blur [23]. Kumar et al [24] used the chromatic aberration as a clue to solve the focal plane ambiguity. Second, in dynamic scenes both depth and motion contribute to the blur.…”

“…Manuscript received: September, 9, 2017; Accepted October, 24,2017 We begin with ORB-SLAM [1], which is one of the best monocular SLAM systems currently available. This system uses ORB features to represent the environment and select a set of frames (keyframes) for representing the camera poses.…”