AttentionPose: Attention-driven end-to-end model for precise 6D pose estimation
Abstract: Addressing the complex problem of 6D pose estimation from single RGB images is essential for robotics, augmented reality, and autonomous driving applications. The aim of this study is to overcome limitations in handling scenes with high object occlusion and clutter. We introduce an attention-driven end-to-end model that builds upon existing methods employing pixel-wise unit vectors and voting for object keypoints. Integrating attention mechanisms allows the model to focus computational resources on salient features, enhancing accuracy. Experimental results using the LINEMOD benchmark dataset demonstrate an accuracy rate of 99.73%, outperforming state-of-the-art approaches. The model also exhibits strong generalization capabilities, achieving an average accuracy of 97.36% on objects not included in the dataset. This work concludes that the attention mechanism significantly elevates the performance and robustness of 6D pose estimation, particularly in challenging environments, and opens new avenues for real-world applications.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
AttentionPose: Attention-driven end-to-end model for precise 6D pose estimation ; volume:32 ; number:1 ; year:2023 ; extent:16
Journal of intelligent systems ; 32, Heft 1 (2023) (gesamt 16)
- Urheber
-
Rasheed, Mayada Abdalsalam
Farhan, Rabah Nori
Jasim, Wesam M.
- DOI
-
10.1515/jisys-2023-0153
- URN
-
urn:nbn:de:101:1-2023122113095702210548
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:25 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Rasheed, Mayada Abdalsalam
- Farhan, Rabah Nori
- Jasim, Wesam M.
Ähnliche Objekte (12)
Improved training of end-to-end attention models for speech recognition
Segment boundary detection directed attention for online end-to-end speech recognition
Integrating Motion Priors For End-To-End Attention-Based Multi-Object Tracking
INTEGRATING MOTION PRIORS FOR END-TO-END ATTENTION-BASED MULTI-OBJECT TRACKING
Explaining autonomous driving with visual attention and end-to-end trainable region proposals
Attention-augmented end-to-end multi-task learning for emotion prediction from speech
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation
Pay attention to raw traces: a deep learning architecture for end-to-end profiling attacks
A hybrid CTC+Attention model based on end-to-end framework for multilingual speech recognition
Exploring Hybrid CTC/Attention End-to-End Speech Recognition: Adversarial Robustness, Sinc Convolutions, and CTC Segmentation
Sub-convolutional U-Net with transformer attention network for end-to-end single-channel speech enhancement
Improved training of end-to-end attention models for speech recognition
Segment boundary detection directed attention for online end-to-end speech recognition
Integrating Motion Priors For End-To-End Attention-Based Multi-Object Tracking
INTEGRATING MOTION PRIORS FOR END-TO-END ATTENTION-BASED MULTI-OBJECT TRACKING
Explaining autonomous driving with visual attention and end-to-end trainable region proposals
Attention-augmented end-to-end multi-task learning for emotion prediction from speech
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation
Pay attention to raw traces: a deep learning architecture for end-to-end profiling attacks
A hybrid CTC+Attention model based on end-to-end framework for multilingual speech recognition
Exploring Hybrid CTC/Attention End-to-End Speech Recognition: Adversarial Robustness, Sinc Convolutions, and CTC Segmentation
Sub-convolutional U-Net with transformer attention network for end-to-end single-channel speech enhancement
Improved training of end-to-end attention models for speech recognition
Segment boundary detection directed attention for online end-to-end speech recognition
Integrating Motion Priors For End-To-End Attention-Based Multi-Object Tracking
INTEGRATING MOTION PRIORS FOR END-TO-END ATTENTION-BASED MULTI-OBJECT TRACKING
Explaining autonomous driving with visual attention and end-to-end trainable region proposals
Attention-augmented end-to-end multi-task learning for emotion prediction from speech
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation
Pay attention to raw traces: a deep learning architecture for end-to-end profiling attacks
A hybrid CTC+Attention model based on end-to-end framework for multilingual speech recognition
Exploring Hybrid CTC/Attention End-to-End Speech Recognition: Adversarial Robustness, Sinc Convolutions, and CTC Segmentation