Multi-view shape estimation of transparent containers
This addresses a domain-specific problem for robotics or computer vision applications involving transparent objects, but it is incremental as it builds on existing assumptions and methods.
The paper tackles the problem of 3D localization and dimension estimation of transparent containers under varying lighting conditions by proposing a method using two RGB cameras, circular symmetry, and iterative shape fitting, achieving higher localization success and accuracy than a deep-learning approach using depth maps.
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising container-like objects and estimating their dimensions using two wide-baseline, calibrated RGB cameras. Under the assumption of circular symmetry along the vertical axis, we estimate the dimensions of an object with a generative 3D sampling model of sparse circumferences, iterative shape fitting and image re-projection to verify the sampling hypotheses in each camera using semantic segmentation masks. We evaluate the proposed method on a novel dataset of objects with different degrees of transparency and captured under different backgrounds and illumination conditions. Our method, which is based on RGB images only, outperforms in terms of localisation success and dimension estimation accuracy a deep-learning based approach that uses depth maps.