Abstract:
Binocular stereo vision (SV) is widely used to reconstruct depth information, but strong occlusions make it vulnerable. Light-field (LF) imaging, an emerging computational photography technology, records multiple angular views in a single exposure to solve passive depth perception.
Binocular SV and LF imaging form the binocular-LF imaging system in this paper. Modeling the imaging process and analyzing disparity properties using geometrical optics yields an imaging theory.
Using multi-baseline stereo matching and defocus cues, an accurate occlusion-robust depth estimation algorithm is proposed. Binocular SV/LF imaging occlusions are detected and handled to eliminate matching ambiguities and outliers.
To test accuracy and robustness, we create a binocular-LF database and capture real-world scenes with our system. The experimental results show that the proposed algorithm recovers high-quality depth maps with smooth surfaces and precise geometric shapes, overcoming the drawbacks of binocular SV and LF imaging simultaneously.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
