All-in-focus synthetic aperture imaging method based on automatic target extraction

Abstract

The invention discloses an all-in-focus synthetic aperture imaging method based on automatic target extraction, which is used to solve the technical problem that the existing all-in-focus synthetic aperture imaging method is of poor imaging precision. According to the technical scheme, all-in-focus synthetic aperture imaging is taken as a problem of joint imaging of a focusing target and a non-focusing plane, a target is naturally embedded into an estimated non-focusing area through estimation of the non-focusing area and the focusing target and by use of a target extraction method to realize all-in-focus synthetic aperture imaging without defocus blur, and the technical problem that error in iterative calculation of visible pixels is easy to transmit and results in poor precision is solved. According to the invention, multi-view information is fully utilized, all-in-focus synthetic aperture imaging is taken as a problem of joint imaging of a focusing target and a non-focusing plane, a target is naturally embedded into a background through estimation of the non-focusing area and the focusing target and by use of a target extraction technology, and therefore, all-in-focus synthetic aperture imaging without defocus blur is realized, and the imaging precision is high.

Description

technical field [0001] The invention relates to an all-focus synthetic aperture imaging method, in particular to an all-focus synthetic aperture imaging method based on automatic target extraction. Background technique [0002] The literature ", All-in-focus Synthetic Aperture Imaging, ECCV, p1–15, 2014" discloses an all-in-focus synthetic aperture imaging method, which is used to solve the problem of blurring of objects on non-focus planes caused by focusing on a certain focal plane during synthetic aperture imaging. Focus blur problem. This method is based on the idea of ​​layer-by-layer visible pixel marking. Firstly, a certain camera angle of view is selected as a reference angle of view. By calculating the maximum color discrimination of pixels corresponding to each angle of view, the unobstructed visible pixels of the current layer are marked, and then used in the next layer. Iterative operation of visible pixels. After repeated iterative operations layer by layer, a...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of poor imaging accuracy of existing all-focus synthetic aperture imaging methods, the present invention provides a full-focus synthetic aperture imaging method based on automatic target extraction

The all-focus synthetic aperture imaging is regarded as a joint imaging problem of the focused target and the non-focused plane. Through the estimation of the non-focused area and the focused target, the target and the estimated non-focused area are naturally mosaiced by using the target extraction method to achieve no dispersion. Focus blurred all-focus synthetic aperture imaging, solving the technical problem of poor precision caused by iterative calculation of visual pixel errors that are easy to transfer

Images