3D integral imaging depth estimation of partially occluded objects using mutual information and Bayesian optimization

Integral imaging (InIm) is useful for passive ranging , 3D visualization of partially -occluded objects. We consider 3D object localization within a scene and in occlusions. 2D localization can be achieved using machine learning and non-machine learning-based techniques. These techniques aim to provide a 2D bounding box around each one of the objects of interest. A recent study uses InIm for the 3D reconstruction of the scene with occlusions and utilizes mutual information (MI) between the bounding box in this 3D reconstructed scene and the corresponding bounding box in the central elemental image to achieve passive depth estimation of partially occluded objects. Here, we improve upon this InIm method by using Bayesian optimization to minimize the number of required 3D scene reconstructions. We evaluate the performance of the proposed approach by analyzing different kernel functions, acquisition functions , parameter estimation algorithms for Bayesian optimization-based inference for simultaneous depth estimation of objects and occlusion. In our optical experiments, mutual-information-based depth estimation with Bayesian optimization achieves depth estimation with a handful of 3D reconstructions. To the best of our knowledge, this is the first report to use Bayesian optimization for mutual information-based InIm depth estimation.& COPY; 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

Automated summary

Integral imaging (InIm) is a useful technique for passive ranging and 3D visualization of partially-occluded objects. This study improves upon an existing InIm method by using Bayesian optimization to minimize the number of 3D scene reconstructions required for depth estimation. The proposed approach achieves depth estimation with a few 3D reconstructions and is the first to use Bayesian optimization for mutual information-based InIm depth estimation.