Enhancing Transparent Object Pose Estimation: A Fusion of GDR-Net and Edge Detection

TL;DR

This paper improves transparent object pose estimation by integrating edge detection as a pre-processing step, enhancing the performance of existing pipelines like GDR-Net and YOLOX on challenging transparent objects.

Contribution

It introduces a novel pre-processing approach using edge detection to boost pose estimation accuracy for transparent objects, validated on a new dataset.

Findings

Edge detection improves pose estimation for certain transparent objects.

Different edge detectors have varying effects on performance.

Pre-processing with edge detection can stabilize features for transparent object recognition.

Abstract

Object pose estimation of transparent objects remains a challenging task in the field of robot vision due to the immense influence of lighting, background, and reflections. However, the edges of clear objects have the highest contrast, which leads to stable and prominent features. We propose a novel approach by incorporating edge detection in a pre-processing step for the tasks of object detection and object pose estimation. We conducted experiments to investigate the effect of edge detectors on transparent objects. We examine the performance of the state-of-the-art 6D object pose estimation pipeline GDR-Net and the object detector YOLOX when applying different edge detectors as pre-processing steps (i.e., Canny edge detection with and without color information, and holistically-nested edges (HED)). We evaluate the physically-based rendered dataset Trans6D-32 K of transparent objects with parameters proposed by the BOP Challenge. Our results indicate that applying edge detection as a pre-processing enhances performance for certain objects.