Abstract
A new method for generating 3D images using both disparity parameters due to the color filtered aperture (CFA) and depth alignment of the multi-plane images for an acquired 2D image using a novel computational imaging system is presented. A CFA is created using add-on red, green, and blue color filters in front of the objective lens for a conventional 2D camera system. The multiple plane images are computed using various image regions identified by 2.1D sketch and the corresponding inter-region depth information with the aid of color disparities caused in the acquired 2D image. Our emphasis is to handle possible occlusions in single 2D image regions due to various object features for the acquired scene using ordered multiple plane images and to generate a 3D image by exploiting the order existing in the computed multiple plane images and compositing the region with aligned inter-image region depth information. The simulation and analysis demonstrate the elegance of the 3D image generation. Ultimately, the proposed computational imaging system is not only cost-effective but also an alternative to the stereo-based imaging system, which is not suited for ophthalmic or endoscopic imaging applications.
Highlights
T HE necessity of 3D image generation and its analysis plays a major role in the field of both computer vision and many imaging-based applications such as quick medical diagnosis, robot navigation, perception of a scene, industrial automation, surveillance, object recognition, animations and 3D modeling, virtual / mixed reality in health diagnostic and surgical studies
Large number of literature exist for depth estimation and 3D image generation using more than two images and only a few are based on single image
Related to regions/organs such as colors, texture, Tjunctions, boundaries and salient regions. 4) 3D image generation is carried by fusing depth estimated from color disparities and ordering arrangement of multiple plane images from 2.1D sketch to distinguish the overlapped regions
Summary
T HE necessity of 3D image generation and its analysis plays a major role in the field of both computer vision and many imaging-based applications such as quick medical diagnosis, robot navigation, perception of a scene, industrial automation, surveillance, object recognition, animations and 3D modeling, virtual / mixed reality in health diagnostic and surgical studies. It estimates the degree of defocus blur, by which the depth of scene can be recovered providing the camera setting. In this article we focus on 3D image based on visible information for single view camera. The latter has led to the study related to non-line of sight image, which is not scope of our research.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
