Andris Lapins, Janis Arents and Modris Greitans. Augmenting a Pretrained Object Detection Model with Planar Pose Estimation Capability. Automatic Control and Computer Sciences, 57(5), 459-468 pp. Pleiades Publishing, 2023.
Bibtex citāts:
Bibtex citāts:
@article{15697_2023,
author = {Andris Lapins and Janis Arents and Modris Greitans},
title = {Augmenting a Pretrained Object Detection Model with Planar Pose Estimation Capability},
journal = {Automatic Control and Computer Sciences},
volume = {57},
issue = {5},
pages = {459-468},
publisher = {Pleiades Publishing},
year = {2023}
}
author = {Andris Lapins and Janis Arents and Modris Greitans},
title = {Augmenting a Pretrained Object Detection Model with Planar Pose Estimation Capability},
journal = {Automatic Control and Computer Sciences},
volume = {57},
issue = {5},
pages = {459-468},
publisher = {Pleiades Publishing},
year = {2023}
}
Anotācija: This paper presents a 2D pose estimation solution to the bin-picking problem for robotic grasping systems. By extending a pretrained object detection model, namely DETR, with pose and visibility prediction heads we obtain classification, center, 2D rotation and occlusion scores for every detected object. The augmented model is trained and evaluated on synthetically generated images representing the real environment for faster and more flexible acquisition of data. The results show an average angle error of 3.23 deg for cylindrical and cuboid shape objects.
Žurnāla kvartile: Q3
Pilnais teksts: ACCS459