- 47 views
- 48 downloads
Joint Detection and Pose Estimation Based on Images
-
- Author / Creator
- Wen, Shuchun
-
Pose estimation is widely used in our daily lives and there exist many algorithms that are applied for bringing convenience and improving efficiency in various fields. While images are the most common input for feature detection and matching, it is necessary to study their knowledge background and mathematical representations for conducting implementations. Techniques of joint extraction and classification have been introduced in detail with conducted simulations for each algorithm and they are applied together for joint detection and classification of a robotic arm.
Several common object tracking algorithms have been introduced and implemented, including their mandatory background and mathematical representations. Multiple filter-based algorithms are simulated and discussed for object tracking purposes, including the Kalman Filter (KF), Extended Kalman Filter (EKF), and Particle Filter. Reinforcement Learning (RL) has been implemented together with EKF working towards a trajectory tracking and motion planning problem for robotic arm
accomplishing a pick-and-place task. Enhanced methods are tested in the thesis. -
- Subjects / Keywords
-
- Graduation date
- Fall 2024
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Library with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.