Robust scene interpretation of underwater image sequences

Fairweather, A.J.R.; Hodgetts, Mark; Greig, Alistair

doi:10.1049/cp:19970977

Cited by 13 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the depth of 10m, the orange colour is lost. Thirdly most of the yellow goes off at the depth of 20 m and finally the green and purple disappear at further depth [17]. This is shown diagrammatically in Figure 2.…”

Section: B Color Change Effectmentioning

confidence: 85%

Underwater Image Enhancement Techniques: A Review

Madhumatke¹

2017

IJRASET

View full text Add to dashboard Cite

Underwater images mainly suffer from the problem of poor color contrast and poor visibility. These problems occurred due to the scattering of light and refraction of light while entering from rarer to denser medium. Scattering causes the blurring of light and reduces the color contrast. These effects of water on underwater images are only not due the nature water but also because of the organisms and other material present in the water. Image enhancement is the process of improving the quality of the input image so that it would be easily understood by viewers in the future. Image enhancement improves the information content of the image and alters the visual impact of the image on the observer. Image enhancement intensifies the features of images. It accentuates the image features like edges, contrast to build display of photographs more useful for examination and study. Active range of the chosen features of images is amplified by enhancement so that they can be detected simply. Many techniques and methods are established by researchers to solve the problem of underwater image enhancement. In this work different underwater image enhancing techniques have been studied. Keywords: Homomorphic Filtering, Histogram Equalization, Bilateral filtering, Contrast Stretching, CLAHE I. INTRODUCTIONFrom last few years, underwater image processing area has received a great attention of researchers to explore the mysterious underwater world. Underwater surveys have numerous scientific applications in the field of archaeology, geology and biology, involving tasks such as ancient shipwreck prospection, environmental damage assessment etc. To capture a clear underwater image has a crucial importance in oceanic engineering [1]. Clear underwater images have a great importance in scientific operations like taking a census of sea population, include the discovery of objects in liquids or the image analysis needed to identify targets submerged in a liquid. There have also been studied that attempted to identify targets suspended in a solution. These studies could be useful for defense applications. For capturing a clear visible underwater image, water must be a limpid or clear, but naturally all the water is turbid with particles such as sand, planktonsor , minerals. As outdoor images are distorted because of particles present in the air, like that underwater images also get distorted because of particles present in the water. Underwater Images becomes more and more hazy or less visible as water depth increases. Generally underwater images get distorted because of two reasons. One is light scattering effect and second is color change effect. Therefore, the processing of underwater image captured is necessary because the quality of underwater images affect and these image leads due to low contrast, poor visibility conditions (absorption of natural light), non uniform lighting and little color variations, pepper noise and blur effect in the underwater images because of all these reasons number of methods are existing to cure...

show abstract

Section: B Color Change Effectmentioning

confidence: 85%

Underwater Image Enhancement Techniques: A Review

Madhumatke¹

2017

IJRASET

View full text Add to dashboard Cite

show abstract

“…After mixture, the left over noise is removed using multi-scale de-noising algorithm based on complex valued Log Gabor wavelets [2]. Similarly Fair weather [3] have used techniques such as contrast stretching and Markov Random field. They apply the bimodal histogram form to the images in order to increase the underwater image, firstly they use contrast stretching method.…”

Section: Fig 2: Basic Block Diagram Of Image Enhancementmentioning

confidence: 99%

A Survey on Underwater Image Enhancement Techniques

Sahu¹,

Gupta²,

Sharma³

2014

IJCA

View full text Add to dashboard Cite

This review paper deals with the methods to improve underwater image enhancement techniques, the processing of underwater image captured is necessary because the quality of underwater images affect and these image leads some serious problems when compared to images from a clearer environment. A lot of noise occurs due to low contrast, poor visibility conditions (absorption of natural light), non uniform lighting and little color variations, pepper noise and blur effect in the underwater images because of all these reasons number of methods are existing to cure these underwater images different filtering techniques are also available in the literature for processing and enhancement of underwater images one of them is image enhancement using median filter which enhances the image and help to estimate the depth map and improve quality by removing noise particles with the help of different techniques, and the other is RGB Color Level Stretching have used. Forward USM technique can also be used for image enhancement.

show abstract

“…Fairweather 13 and Hodgetts, 14 also concerned with underwater robotics, extend Markov dependency such that the local neighbourhood surrounding any particular pixel also includes a contribution from the corresponding pixel in a predicted image (figure 2). The predicted image is projected using a 3D model of the object being tracked and an estimate of camera position based on a Kalman filtered model of the robot trajectory.…”

Section: Extending Markov Dependencymentioning

confidence: 99%

“…Equations (2) to (5) describe a conventional MRF image model in which pixel class labels are considered to be spatially dependent. However, Markov dependency is now extended to include a contribution from a predicted class label,Ĉ i,j , derived from a previous frame, 9,10 a predicted image, 13,14 or a corresponding image from a different kind of imaging device. 11,12 Now:…”

Section: Extending Markov Dependencymentioning

confidence: 99%

Extended Markov Random Fields for Predictive Image Segmentation

Hodgetts¹,

Greig²,

Gilby³

2006

Advances in Pattern Recognition

View full text Add to dashboard Cite

Since the 1970s, there has been increasing interest in the use of Markov Random Fields (MRFs) as models to aid in the segmentation of noisy or degraded digital images. MRFs can make up for deficiencies in observed information by adding a-priori knowledge to the image interpretation process in the form of models of spatial interaction between neighbouring pixels. In data fusion problems, interaction might also be assumed between corresponding pixels in two different kinds of image of the same scene. Alternatively, temporal interaction might be assumed between corresponding pixels in consecutive frames of a video sequence. In object tracking or robotic navigation problems, a similar relationship may exist between pixels of an observed image and those of a predicted image, derived from models of the motion and scene. In all of these cases the MRF model can be extended to incorporate this additional knowledge. This paper explains the theory of Extended-Markov Random Field (E-MRF) segmentation techniques, surveys the research which has been crucial to their development and presents results from new work in this area with an application to robotic vision in conditions of extremely poor visibility.

show abstract

Robust scene interpretation of underwater image sequences

Cited by 13 publications

References 0 publications

Underwater Image Enhancement Techniques: A Review

Underwater Image Enhancement Techniques: A Review

A Survey on Underwater Image Enhancement Techniques

Extended Markov Random Fields for Predictive Image Segmentation

Contact Info

Product

Resources

About