DeepAI
Log In Sign Up

Multi-view shape estimation of transparent containers

11/27/2019
by   Alessio Xompero, et al.
0

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 vertical circular symmetry, we estimate the dimensions of an object by sampling at different heights a set of sparse circumferences with 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.

READ FULL TEXT

page 2

page 3

page 4

09/21/2021

StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimation

We present a large-scale stereo RGB image object pose estimation dataset...
03/23/2021

Adaptive Illumination based Depth Sensing using Deep Learning

Dense depth map capture is challenging in existing active sparse illumin...
05/30/2022

MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation

We present MVMO (Multi-View, Multi-Object dataset): a synthetic dataset ...
04/19/2022

4D-MultispectralNet: Multispectral Stereoscopic Disparity Estimation using Human Masks

Multispectral stereoscopy is an emerging field. A lot of work has been d...
05/28/2022

Estimation of 3D Body Shape and Clothing Measurements from Frontal- and Side-view Images

The estimation of 3D human body shape and clothing measurements is cruci...
03/08/2021

Localization and Mapping using Instance-specific Mesh Models

This paper focuses on building semantic maps, containing object poses an...
03/07/2019

Locating Transparent Objects to Millimetre Accuracy

Transparent surfaces, such as glass, transmit most of the visible light ...