Underwater Computer Vision: Exploring the Depths of Computer Vision Beneath the Waves

By Fouad Sabry

What is Underwater Computer Vision

Underwater computer vision is a subfield of computer vision. In recent years, with the development of underwater vehicles, the need to be able to record and process huge amounts of information has become increasingly important. Applications range from inspection of underwater structures for the offshore industry to the identification and counting of fishes for biological research. However, no matter how big the impact of this technology can be to industry and research, it still is in a very early stage of development compared to traditional computer vision. One reason for this is that, the moment the camera goes into the water, a whole new set of challenges appear. On one hand, cameras have to be made waterproof, marine corrosion deteriorates materials quickly and access and modifications to experimental setups are costly, both in time and resources. On the other hand, the physical properties of the water make light behave differently, changing the appearance of a same object with variations of depth, organic material, currents, temperature etc.

How you will benefit

(I) Insights, and validations about the following topics:

Chapter 1: Underwater computer vision

Chapter 2: Computer vision

Chapter 3: Hydrographic survey

Chapter 4: Autonomous underwater vehicle

Chapter 5: Monterey Bay Aquarium Research Institute

Chapter 6: Unmanned underwater vehicle

Chapter 7: Noise reduction

Chapter 8: Underwater vision

Chapter 9: Video post-processing

Chapter 10: Image quality

(II) Answering the public top questions about underwater computer vision.

(III) Real world examples for the usage of underwater computer vision in many fields.

Who this book is for

Professionals, undergraduate and graduate students, enthusiasts, hobbyists, and those who want to go beyond basic knowledge or information for any kind of Underwater Computer Vision.

• Language: English
• Publisher: One Billion Knowledgeable
• Release date: Apr 28, 2024

Book preview

Chapter 1: Underwater computer vision

The subset of computer vision that focuses on underwater imagery. The necessity to gather and interpret massive volumes of data has become increasingly critical in recent years due to the rise of underwater vehicles (ROV, AUV, gliders). There are a wide variety of uses for this technology, from underwater structure inspection for the offshore business to fish identification and population counting in the name of science. Despite the potential for this technology to revolutionize industries and scientific fields, it is still in its infancy when compared to more established forms of computer vision. This is because taking a camera into the water introduces a whole other set of difficulties. However, it can be expensive in terms of both time and money to get access to and make adjustments to experimental installations, and cameras must be waterproofed. However, the depth, organic material, currents, temperature, and other physical qualities of the water alter how light interacts with an object, altering its appearance.

Seafloor survey

Satellite-based Positioning and Navigation

Biological monitoring

Video mosaics as aids to orientation and navigation

Pipeline inspection

Wreckage visualization

Repairs of Submarine Structures

Prevention of drowning with means such as pool alarms

On overcast days, light travels through the atmosphere from all directions, but the sun is the dominant source. Light in water is emitted from a bounded cone in the sky. Snell's window is the name given to this phenomena.

Water has an enormously greater attenuation of light than air. The end result is low-contrast, fuzzy images. Absorption (where energy is lost from the light) and scattering (where the direction of the light is changed) are the primary causes of light attenuation. Forward scattering causes an increase in blurriness, whereas backward scattering reduces contrast and is to blame for the veil that permeates underwater photographs. The presence of dissolved or suspended organic matter has a significant impact on both scattering and attenuation in water.

Water's attenuation of light is also wavelength dependent, which is problematic. This means that color deterioration occurs at varying rates depending on the hue. Attenuation begins with red and orange light and progresses through yellow and green. Visually, the least attenuated color is blue.

Human structures are commonly employed as image features for picture matching in high-level computer vision. The lack of topographical characteristics at the ocean below, however, makes it challenging to discover similarities between photos.

A watertight housing is necessary for underwater photography. However, due to density variations, refraction will occur at the water-glass and glass-air interfaces. This causes a non-linear shift in the shape of the image.

Another unique difficulty is the vehicle's motion. Due to currents and other factors, underwater vehicles are in constant motion. This adds a new layer of uncertainty to algorithms, increasing the possibility that minor fluctuations could arise in any direction. For video tracking, this can be especially useful. Algorithms for improving image stability could be used to mitigate this issue.

The goal of picture restoration is to solve for the original image by modeling its degradation and then inverting the process. It's typically a complicated method that calls for a wide range of parameters that dramatically change depending on the type of water being analyzed.

Image enhancement primarily focuses on making the image look better visually, without considering how an image is actually formed. These procedures are typically less complicated and computationally demanding.

Several automatic color correcting algorithms exist. To give just one example, the UCM (Unsupervised Color Correction Method) follows these steps: In the first place, it restores color accuracy by balancing out color values. Then, it optimizes the saturation and intensity components after increasing contrast by stretching the red histogram to its maximum.

The geometry and radiometry of stereo cameras are presumed to have been calibrated beforehand. Therefore, it's safe to assume that adjacent pixels should share the same hue. This, however, cannot be ensured in an underwater scene due to dispersion and backscatter. However, this phenomenon can be computationally modeled, and a virtual image with the impacts eliminated can be produced.

These days, sonar imaging systems

{End Chapter 1}

Chapter 2: Computer vision

The study of how computers can derive high-level knowledge from digital pictures or videos is the focus of the multidisciplinary scientific area of computer vision. From a technological point of view, it investigates and attempts to automate activities that are within the capabilities of the human visual system.

Tasks associated with computer vision include techniques for obtaining, processing, analyzing, and comprehending digital pictures, as well as the extraction of high-dimensional data from the physical environment in order to create numeric or symbolic information, such as judgments.

Computer vision is a subfield of computer science that investigates the theoretical underpinnings of artificial systems designed to derive information from pictures. The visual data may be presented in a variety of formats, including video sequences, images obtained from several cameras, multi-dimensional data obtained from a 3D scanner or medical scanning equipment, and so on. The goal of the technical field known as computer vision is to implement the ideas and models it has developed in the process of building computer vision systems.

The fields of scene reconstruction, object detection, event detection, video tracking, object recognition, 3D pose estimation, learning, indexing, motion estimation, visual servoing, 3D scene modeling, and image restoration are all sub-domains of computer vision. Other sub-domains of computer vision include 3D scene modeling.

Computer vision is a multidisciplinary study that examines how computers can be programmed to extract high-level knowledge from digital pictures or movies. This area focuses on how computers can be taught to comprehend what is being shown to them. From the point of view of engineering, the goal is to find ways to automate operations that can already be done by the human visual system. Computer vision is a field of study in the field of information technology that focuses on applying existing theories and models to the process of building computer vision systems.

In the late 1960s, colleges that were on the cutting edge of artificial intelligence were the first to experiment with computer vision. Its purpose was to function in a manner similar to that of the human visual system, with the ultimate goal of