Date of Publication

4-23-2024

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Electronics and Communications Engineering

Subject Categories

Controls and Control Theory | Electrical and Computer Engineering | Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics And Communications Engg

Honor/Award

N/A

Thesis Advisor

Elmer Jose P. Dadios

Defense Panel Chair

Argel A. Bandala

Defense Panel Member

Edwin Sybingco
Ryan Rhay P. Vicerra
Laurence A. Gan Lim
Raouf Naguib

Abstract/Summary

Aligning a mobile X-ray system in challenging environments, such as bomb-surrounded areas, poses difficulties due to safety concerns and occlusion. This study introduces a novel approach employing 6D object pose estimation and pose correction by integrating DeepLabV3 and iterative dense fusion into the visual servoing mechanism. The robotic system exhibits enhanced accuracy in detecting and aligning the occluded known 3D object model x-ray source to film. Evaluation metrics, including intersection-over-union and mean average, demonstrate high accuracy percentages for detecting the body (98.91%), handle (96.57%), and aperture (89.54%). The mean IoU for each part of the 3D model portable X-ray source ranges from 65.69% to 76.42%. Pose estimation accuracy, assessed through the ADD metric, indicates superior performance for static pose estimation closer to the camera. Dynamic pose estimation exhibits higher average ADD metrics in scenes with total occlusion. The robustness metric reveals lower lost tracking counts in scenes without occlusion, emphasizing the algorithm's challenges in fully occluded scenarios. The film handler alignment system, characterized by kinematic formulation and actuator calibration data, shows minimal errors in X and Y actuation (

Abstract Format

html

Language

English

Format

Electronic

Keywords

Robotics; Servomechanisms; Automatic control

Upload Full Text

wf_yes

Embargo Period

4-23-2024

Download

Share

COinS