Underwater Vehicle Gesture Control Aided by Air Bubble Motion Observation in a Water Flow
Date Issued
2016
Date
2016
Author(s)
Lee, Chih-Wei
Abstract
This thesis describes the gesture control of a Biomimetic Autonomous Underwater Vehicle (BAUV) in a water flow by utilizing information derived from on board sensors of stereo cameras, a compass, and an accelerometer. In an alternating water flow, the BAUV suffers from drag forces and consumes more energy when it advances. The relationship between air bubbles and water flow is first discussed. The air bubble is detected by Harris corner. The relative position between air bubble and BAUV is estimated based on the calibrated stereo cameras and the bubble is tracked by using Lucas-Kanade method and image pyramid algorithm. By integrating observation information from air bubbles, heading angles and 3-axis accelerations from compass and the accelerometer, the BAUV adjusts its heading angle to optimize the gesture of control in the water flow. Finally, the control algorithm based on the computer vision algorithm is verified by experimental data. The control power consumed in the driving motors are calculated to compare the energy used in a water flow with and without gesture control. Keywords: BAUV, water current, air bubbles, harris corner, camera calibration, stereo vision, Lucas-Kanade tracking algorithm, image pyramid
Subjects
BAUV
water current
air bubbles
harris corner
camera calibration
stereo vision
Lucas-Kanade tracking algorithm
image pyramid
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-105-R02525028-1.pdf
Size
23.54 KB
Format
Adobe PDF
Checksum
(MD5):8fb9ad9c1d7e79cb2045b5893455929f