Image processing module of an underwater robot agent for remote data collection

• Main Author: Chau, Yuen Ling
• Other Authors: Hu, Guoqiang
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/145175
• Institution: Nanyang Technological University

Vision system plays a crucial role in the field of underwater robotics and Oceanography, such as marine investigation and object detection. However, the quality of the underwater images captured is greatly impacted due to water turbidity, light scattering and absorption in the water. This issue will affect the quality of data collected which leads to inefficient extraction of information. Hence, this report presents and discusses the proposed methods of Canny Edge Detector, Dark Channel Prior(DCP) and Contrast Limited Adaptive Histogram Equalization(CLAHE) to tackle the underwater haze and noise filter and enhancement of the underwater images to lead to a more efficient extraction of information. Algorithms and software modules such as Convolutional Neural Network (CNN) and Python will be used to process the underwater images.