TY - GEN
T1 - Proposing Camera Calibration Method Using PPO (Proximal Policy Optimization) for Improving Camera Pose Estimations
AU - Al-Jabri, Haitham
AU - Matsumaru, Takafumi
PY - 2019/3/11
Y1 - 2019/3/11
N2 - This paper highlights camera orientation estimation accuracy and precision, as well as proposing a new camera calibration technique using a reinforcement learning method named PPO (Proximal Policy Optimization) in offline mode. The offline mode is used just for extracting the camera geometry parameters that are used for improving accuracy in real-time camera pose estimation techniques. We experiment and compare two popular techniques using 2D vision feedbacks and evaluate their accuracy beside other considerations related to real applications such as disturbance cases from surrounding environment and pose data stability. First, we use feature points detection ORB (Oriented FAST and Rotated BRIEF) and BF (Brute-Force) matcher to detect and match points in different frames, respectively. Second, we use FAST (Features from Accelerated Segment Test) corners and LK (Lucas-Kanade) optical flow methods to detect corners and track their flow in different frames. Those points and corners are then used for the pose estimation through optimization process with the: (a) calibration method of Zhang using chessboard pattern and (b) our proposed method using PPO. The results using our proposed calibration method show significant accuracy improvements and easier deployment for end-user compared to the pre-used methods.
AB - This paper highlights camera orientation estimation accuracy and precision, as well as proposing a new camera calibration technique using a reinforcement learning method named PPO (Proximal Policy Optimization) in offline mode. The offline mode is used just for extracting the camera geometry parameters that are used for improving accuracy in real-time camera pose estimation techniques. We experiment and compare two popular techniques using 2D vision feedbacks and evaluate their accuracy beside other considerations related to real applications such as disturbance cases from surrounding environment and pose data stability. First, we use feature points detection ORB (Oriented FAST and Rotated BRIEF) and BF (Brute-Force) matcher to detect and match points in different frames, respectively. Second, we use FAST (Features from Accelerated Segment Test) corners and LK (Lucas-Kanade) optical flow methods to detect corners and track their flow in different frames. Those points and corners are then used for the pose estimation through optimization process with the: (a) calibration method of Zhang using chessboard pattern and (b) our proposed method using PPO. The results using our proposed calibration method show significant accuracy improvements and easier deployment for end-user compared to the pre-used methods.
UR - http://www.scopus.com/inward/record.url?scp=85064120902&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064120902&partnerID=8YFLogxK
U2 - 10.1109/ROBIO.2018.8665088
DO - 10.1109/ROBIO.2018.8665088
M3 - Conference contribution
AN - SCOPUS:85064120902
T3 - 2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018
SP - 790
EP - 795
BT - 2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Robotics and Biomimetics, ROBIO 2018
Y2 - 12 December 2018 through 15 December 2018
ER -