Semi-supervised learning approach for localization and pose estimation of texture-less objects in cluttered scenes

Lugo, Gabriel; Hajari, Nasim; Cheng, Irene

doi:10.1016/j.array.2022.100247

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, misalignment during assembly processes can result in component damage. Consequently, addressing the problem of pose estimation for textureless objects in industrial production scenarios remains a critical concern in this field [8].…”

Section: Introductionmentioning

confidence: 99%

DCSPose: A Dual-Channel Siamese Framework for Unseen Textureless Object Pose Estimation

Yue,

Han,

Yang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The demand for object pose estimation is steadily increasing, and deep learning has propelled the advancement of this field. However, the majority of research endeavors face challenges in their applicability to industrial production. This is primarily due to the high cost of annotating 3D data, which places higher demands on the generalization capabilities of neural network models. Additionally, existing methods struggle to handle the abundance of textureless objects commonly found in industrial settings. Finally, there is a strong demand for real-time processing capabilities in industrial production processes. Therefore, in this study, we introduced a dual-channel Siamese framework to address these challenges in industrial applications. The architecture employs a Siamese structure for template matching, enabling it to learn the matching capability between the templates constructed from high-fidelity simulated data and real-world scenes. This capacity satisfies the requirements for generalization to unseen objects. Building upon this, we utilized two feature extraction channels to separately process RGB and depth information, addressing the limited feature issue associated with textureless objects. Through our experiments, we demonstrated that this architecture effectively estimates the three-dimensional pose of objects, achieving a 6.0% to 10.9% improvement compared to the state-of-the-art methods, while exhibiting robust generalization and real-time processing capabilities.

show abstract

Section: Introductionmentioning

confidence: 99%