Deep learning-based underwater metal object detection using input image data and corrosion protection of mild steel used in underwater study: A case study: Part A: Deep learning-based underwater metal object detection using input image data

Abstract

Due to the importance of underwater exploration in the development and utilization of deep-sea resources, underwater autonomous operation is more and more important to avoid the dangerous high-pressure deep-sea environment. For underwater autonomous operation, intelligent computer vision is the most important technology. In an underwater environment, weak illumination and low-quality image enhancement, as a pre-processing procedure, is necessary for underwater vision. In this paper, introduced Deep learning-based Underwater Metal object detection using input Image data by using several step to improve the model performance. In this experimentation we are using TURBID dataset 100 images to validate the performance. And also we compare the performance result by given the input images in different validation level. In first input image is initially preprocessed and that images is given to the KFCM-Segmentation. The segmented images are given to the DWT Extraction to extract the features from those images. And finally the Convolution Neural Network (CNN) is used to classify the images to detect the objects. Also this proposed model attained the classification accuracy of 98.83%. This method is much suitable for detect the objects in underwater robotically. Metallic parts of machines of ships or airplanes may submerge in sea water. They may undergo corrosion when they come in contact with sea water which contains 3.5% sodium chloride. This is most commonly responsible for the corrosive nature of the seawater. The robots made of materials such as mild steel may also undergo corrosion when they come in contact with sea water, while is search. If a paint coating is given, it will control the corrosion of these proposed materials. Hence this work is undertaken. Mild steel is coated with Asian guard red paint. Corrosion resistance of mild in 3.5% sodium chloride solution is measured before coating and after coating by electrochemical studies such as polarization study and AC impedance spectra. The corrosion inhibition efficiency offered by red paint to mild steel in 3.5% sodium chloride is 99.98%.