Non-uniform de-Scattering and de-Blurring of Underwater Images

Li, Yujie; Lu, Huimin; Li, Kuan-Ching; Kim, Hyoungseop; Serikawa, Seiichi

doi:10.1007/s11036-017-0933-7

Cited by 42 publications

(13 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In hazy conditions, this veiling effect appears with a whitish hue. This veiling effect may be dominant in some local areas and the pixel intensity becomes saturated, occluding image details [9].…”

Section: Image Appearancementioning

confidence: 99%

See 1 more Smart Citation

3D Information from Scattering Media Images

Rahadianti

2021

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

Scattering media environments are real-world conditions that occur often, in daily life. Some examples of scattering media are haze, fog, and other bad weather conditions. In these environments, micro-particles in the surrounding media interfere with light propagation and image formation. Thus, images that are captured in these scattering media environments will suffer from low contrast and loss of intensity. This becomes an issue for computer vision methods that employ features found in the scene. To solve this issue, many approaches must estimate the corresponding clear scene prior to further processing. However, the image formation model in scattering media shows potential 3D distance information about the scene encoded implicitly in image intensities. In this paper, we investigate the potential information that can be extracted directly from the scattering media images. We demonstrate the possibility of extracting relative depth in the form of transmission as well as explicit depth maps from single images.

show abstract

Section: Image Appearancementioning

confidence: 99%

“…(4) and(5), it is possible to estimate transmission of underwater images using UDCP and RCP following Eq. (8) and (9).…”

Section: The Special Case Of Underwater Imagesmentioning

confidence: 99%

3D Information from Scattering Media Images

Rahadianti

2021

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

show abstract

“…It performs some filtering processing on the transformed coefficients in a certain transformation domain of the image, and then inversely transforms them to the spatial domain to achieve the enhanced image. According to the characteristics of underwater images, in recent years, scholars have proposed many typical underwater image enhancement methods, for example, based on the quaternion attenuation coefficient inversion recovery processing algorithm [53], integration, RGB and HSI color model enhancement algorithm [54], color correction method based on the ACE model [55] point spread function (PSF), processing algorithm [56], underwater image based on wavelength compensation to “atomization” enhancement methods [57], etc. Some other methods mainly improve the underwater image enhancement algorithm, such as the underwater image enhancement method based on RETINEX [58].…”

Section: Related Work In Tactile Theory and Underwater Image Restomentioning

confidence: 99%

Development of Tactile Imaging for Underwater Structural Damage Detection

Chen

Hou

et al. 2019

Sensors

View full text Add to dashboard Cite

Underwater structural damage inspection has mainly relied on diver-based visual inspection, and emerging technologies include the use of remotely operated vehicles (ROVs) for improved efficiency. With the goal of performing an autonomous and robotic underwater inspection, a novel Tactile Imaging System for Underwater Inspection (TISUE) is designed, prototyped, and tested in this paper. The system has two major components, including the imaging subsystem and the manipulation subsystem. The novelty lies in the imaging subsystem, which consists of an elastomer-enabled contact-based optical sensor with specifically designed artificial lighting. The completed TISUE system, including optical imaging, data storage, display analytics, and a mechanical support subsystem, is further tested in a laboratory experiment. The experiment demonstrates that high-resolution and high-quality images of structural surface damage can be obtained using tactile ‘touch-and-sense’ imaging, even in a turbid water environment. A deep learning-based damage detection framework is developed and trained. The detection results demonstrate the similar detectability of five damage types in the obtained tactile images to images obtained from regular (land-based) structural inspection.

show abstract

“…Imaging in an underwater environment is difficult particularly in turbid media due to backscattering and absorption effects. Various researches have been done aiming to capture the images of objects in underwater environments [1], [2] and underwater imaging enhancement [3], [4]. Due to the presence of faster, more dynamic computers and strong fundamental spatial light mapping mechanisms such as Spatial Light Modulator (SLM) and Digital Micromirror…”

Section: Introductionmentioning

confidence: 99%

Active Mode Single Pixel Imaging in the Highly Turbid Water Environment Using Compressive Sensing

et al. 2019

View full text Add to dashboard Cite

Underwater imaging has always been a challenge due to limitations imposed by scattering and absorption nature of the underwater environment. The light would be highly degraded after reflection and propagation in the water medium. Being an advanced imaging technique, Single-pixel Imaging (SPI) is applicable to acquire object spatial information in low light, severe backscattering, and high absorption conditions. Combination of Compressive Sensing (CS) and SPI can overcome the limitation of SPI algorithms such as long data-acquisition time, low reconstruction efficiency and poor reconstruction quality. In the current research, an underwater SPI system based on CS is established to reconstruct our two-dimensional (2D) transparent object. We have systematically investigated the influence of water turbid degree, measurement pattern types and number of measurements on image reconstruction performance. The proposed system is capable to reconstruct the object even when the turbidity reaches up to 80 Nephelometric Turbidity Unit (NTU), where the conventional imaging systems are unusable. Proposed reconstruction method in our research can save more than 70% data acquisition time, compared to SPI algorithm. Our experimental setup has been compared to a conventional imaging system and an underwater ghost imaging system to show its efficiency in obtaining accurate results from turbid water conditions. Furthermore, various algorithm comparison and imaging enhancement studies demonstrates that our algorithm is superior in bringing highly convex optimization at a faster rate with a smaller number of measurements. This work creates new insight into the SPI application and generates a guideline for researchers to improve their applications.INDEX TERMS Single pixel imaging, compressive sensing, gated techniques, imaging through turbid media.

show abstract

Non-uniform de-Scattering and de-Blurring of Underwater Images

Cited by 42 publications

References 25 publications

3D Information from Scattering Media Images

3D Information from Scattering Media Images

Development of Tactile Imaging for Underwater Structural Damage Detection

Active Mode Single Pixel Imaging in the Highly Turbid Water Environment Using Compressive Sensing

Contact Info

Product

Resources

About