Depth perception in single camera system using focus blur and aperture number

• Published in: Multimedia tools and applications Vol. 82; no. 26; pp. 41405 - 41431
• Main Authors: Keshri, Divakar, Sriharsha, K.V., Alphonse, P.J.A
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2023; Springer Nature B.V
• Subjects: Apertures; Cameras; Computation; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Digital imaging; Estimates; Estimation; Lenses; Multimedia Information Systems; Pictures; Prediction models; Scene analysis; Single lens reflex; Space perception; Special Purpose and Application-Based Systems; Track 6: Computer Vision for Multimedia Applications; Triangulation; Aperture number fstop; Exposure time; Film speed; Defocus; Auto focusing mode; Focal length
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-14528-5

This article discusses a depth prediction model that takes advantage of rich interpretations. Profundity assessment is a basic interest for scene understanding and exact 3D reproduction. Latest methodologies with profound learning exploit mathematical designs of standard sharp pictures to foresee profundity maps. In any case, cameras can likewise deliver pictures with defocus obscure contingent upon the profundity of the articles and camera settings. Subsequently, these highlights might address a significant clue for figuring out how to foresee profundity. In this article, we postulate a full framework for single-picture profundity expectation by estimating the level of obscure w.r.t real profundity by bringing the picture in to concentrate just on pre-characterized focal point numbers. As a result, these characteristics may provide a crucial clue for studying to predict depth. These lens numbers indicate the distance at which the lens is currently focused. We also intend to know the influence of lens aperture numbers on the depth estimated. For this stated goal,We introduce a new data set that has 477 images taken in real-time using a DSLR (Digital Single-Lens Reflex). For indoor pictures, a lens is coupled with ground truth depth data provided with a laser distance meter.On this new platform, the strategy has been a framework that supports new data set and is proved that the predicted depth estimates correlate with ground truth by 98.7 percent with an 8.647 Std Error estimate. When compared to recent research on stereo vision and other non-triangulation techniques proposed so far, the depth estimations derived from the proposed model approximates the ground truth with RMSE of 0.05 and display around 98.7 percent correlation wrt ground truth data. Depth estimation strategy using a Single RGB cameras are proved efficient in computing depth estimates from blur with 99 percent accuracy, which is not in an earlier case. Our proposed model evidently works well with both sharp and blur images in computing depth estimates up to 3.3 meters range irrespective of whether an image is in focus or out of focus.