Pose-Guided Tracking-by-Detection: Robust Multi-Person Pose Tracking

2021 ◽  
Vol 23 ◽  
pp. 161-175 ◽  
Author(s):  
Qian Bao ◽  
Wu Liu ◽  
Yuhao Cheng ◽  
Boyan Zhou ◽  
Tao Mei
2021 ◽  
Vol 102 (2) ◽  
Author(s):  
Nuno Pessanha Santos ◽  
Victor Lobo ◽  
Alexandre Bernardino

Author(s):  
Kejie Gong ◽  
Ying Liao ◽  
Yafei Mei

This article proposed an extended state observer (ESO)–based output feedback control scheme for rigid spacecraft pose tracking without velocity feedback, which accounts for inertial uncertainties, external disturbances, and control input constraints. In this research, the 6-DOF tracking error dynamics is described by the exponential coordinates on SE(3). A novel continuous finite-time ESO is proposed to estimate the velocity information and the compound disturbance, and the estimations are utilized in the control law design. The ESO ensures a finite-time uniform ultimately bounded stability of the observation states, which is proved utilizing the homogeneity method. A non-singular finite-time terminal sliding mode controller based on super-twisting technology is proposed, which would drive spacecraft tracking the desired states. The other two observer-based controllers are also proposed for comparison. The superiorities of the proposed control scheme are demonstrated by theory analyses and numerical simulations.


2021 ◽  
pp. 1-15
Author(s):  
Xinke Deng ◽  
Arsalan Mousavian ◽  
Yu Xiang ◽  
Fei Xia ◽  
Timothy Bretl ◽  
...  

Author(s):  
Li Yuan ◽  
Shuning Chang ◽  
Ziyuan Huang ◽  
Yichen Zhou ◽  
Yupeng Chen ◽  
...  
Keyword(s):  

Machines ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 112
Author(s):  
Loukas Bampis ◽  
Spyridon G. Mouroutsos ◽  
Antonios Gasteratos

The paper at hand presents a novel and versatile method for tracking the pose of varying products during their manufacturing procedure. By using modern Deep Neural Network techniques based on Attention models, the most representative points to track an object can be automatically identified using its drawing. Then, during manufacturing, the body of the product is processed with Aluminum Oxide on those points, which is unobtrusive in the visible spectrum, but easily distinguishable from infrared cameras. Our proposal allows for the inclusion of Artificial Intelligence in Computer-Aided Manufacturing to assist the autonomous control of robotic handlers.


Sign in / Sign up

Export Citation Format

Share Document