Towards Deep Learning-based 6D Bin Pose Estimation in 3D Scan

Gajdošech, Lukáš; Kocur, Viktor; Stuchlík, Martin; Hudec, Lukas; Madaras, Martin

doi:10.5220/0010878200003124

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gajdošech et al (2021) concentrated on a single problem, which is the 6D pose estimate of a bin in 3D scans. As a result, they presented a high‐quality dataset made up of both artificial data and actual scans that were recorded by a structured‐light scanner and annotated precisely.…”

Section: Pose Estimation Typesmentioning

confidence: 99%

“…With the current RGB-D observation, a synthetic image conditioned on the prior best estimate, and the object's model, their work aims to find the optimum relative position. A unique NN design that effectively decouples the feature encoding to lessen domain shift and provides a useful 3D orientation representation is the key contribution Gajdošech et al (2021). concentrated on a single problem, which is the 6D pose estimate of a bin in 3D scans.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Ultimate pose estimation: A comparative study

Hassan,

Hossain,

Elmuogy

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Pose estimation is a computer vision task used to detect and estimate the pose of a person or an object in images or videos. It has some challenges that can leverage advances in computer vision research and others that require efficient solutions. In this paper, we provide a preliminary review of the state‐of‐the‐art in pose estimation, including both traditional and deep learning approaches. Also, we implement and compare the performance of Hand Pose Estimation (HandPE), which uses PoseNet architecture for hand sign problems, for an ASL dataset by using different optimizers based on 10 common evaluation metrics on different datasets. Also, we discuss some related future research directions in the field of pose estimation and explore new architectures for pose estimation types. After applying the PoseNet model, the experiment results showed that the accuracy achieved was 99.9%, 89%, 97%, 79%, and 99% for the ASL alphabet, HARPET, Yoga, Animal, and Head datasets, comparing those with common optimizers and evaluation metrics on different dataset.

show abstract

Section: Pose Estimation Typesmentioning

confidence: 99%

mentioning

confidence: 99%