An Underwater Image Enhancement Method for Simultaneous Localization and Mapping of Autonomous Underwater Vehicle

Huang, Zhaojie; Wan, Lei; Sheng, Mingwei; Zou, Jing; Song, Jun

doi:10.1109/icras.2019.8809014

Cited by 10 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…‘Dehaze’ algorithms have also been used to overcome the light scattering problem in air [ 36 , 37 , 38 ] and in water [ 39 ]. In [ 40 ], a method for enhancing images against low contrast and color distortion based on guided filer and color space conversion is introduced.…”

Section: Underwater Monocular Imagesmentioning

confidence: 99%

Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM

Hidalgo

Bräunl

2020

Sensors

View full text Add to dashboard Cite

Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, but not extensively for underwater scenarios. In this paper (I) we characterize underwater images where light and suspended particles alter considerably the images captured, (II) evaluate the performance of common interest points detectors and descriptors in a variety of underwater scenes and conditions towards vSLAM in terms of the number of features matched in subsequent video frames, the precision of the descriptors and the processing time. This research justifies the usage of feature detectors in vSLAM for underwater scenarios and present its challenges and limitations.

show abstract

Section: Underwater Monocular Imagesmentioning

confidence: 99%

Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM

Hidalgo

Bräunl

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Final tests are run to determine the efficiency of the suggested approach, and the results display that their approach results in superior structural restoration, more natural-looking color modification, and quicker turnaround times. Huang et al, (2019) The proposed study implements visual SLAM using the positioning of autonomous underwater vehicles (AUVs) as background information. This technique involved converting the image from RGB to HSV color area, following which the value element underwent guided filing to produce the irradiation image.…”

Section: Related Workmentioning

confidence: 99%

Review of Underwater Image Enhancement Using CNN and U-net

Teli,

Shelke

2023

JoAII

View full text Add to dashboard Cite

Due to environmental scattering, images taken in the underwater environment still exhibit color distortion, loss of resolution, and decreased contrast. The suggested study presents a method for enhancing the aesthetic appeal of underwater photography. Yet, because of unwanted staining, decreased contrast, and detail loss brought on by light scattering and absorption, photos that are directly taken in the marine environment are still highly damaged, drastically limiting the amount of information that can be extracted from the image. Thus, acquiring precise and clear photographs is a crucial requirement for aiding scientists in their understanding of the underwater environment. The CNN algorithms are employed in many different applications, including Identification of the object, tracking, recognition, and navigation. Separating the water component from the other component is the most important step here. To get rid of water from a color image, we're suggesting a practical technique.

show abstract

“…To address this issue, Cho et al Cho and Kim (2017) combined Contrast-limited Adaptive Histogram Equalization (CLAHE) Reza (2004) to conduct real-time underwater image enhancement to promote the underwater SLAM performance. Furthermore, Huang et al Huang et al (2019) performed underwater image enhancement by converting RGB images to HSV space and then performing color correction based on Retinex theory. Then the enhanced outputs were applied for downstream underwater SLAM.…”

Section: Introductionmentioning

confidence: 99%

“…Generative adversarial networks (GANs) Goodfellow et al (2014) had been adopted for underwater image enhancement Anwar and Li (2020); Islam et al (2020a) to boost underwater vision perception. Compared 48 with the model-free enhancement methods Drews et al (2013); Huang et al (2019), GAN-based image-to image (I2I) translation algorithms could enhance textile and content representations and generate realistic images with clear and plausible features Ledig et al (2017), especially in highly turbid conditions Han et al (2020); Islam et al (2020c). This line of research has mostly taken place in the computer vision fields, with the main focus on underwater single image restoration Akkaynak and Treibitz (2019); Islam et al (2020b).…”

Section: Introductionmentioning

confidence: 99%

Real-time GAN-based image enhancement for robust underwater monocular SLAM

Zheng

Zhou

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Underwater monocular visual simultaneous localization and mapping (SLAM) plays a vital role in underwater computer vision and robotic perception fields. Unlike the autonomous driving or aerial environment, performing robust and accurate underwater monocular SLAM is tough and challenging due to the complex aquatic environment and the collected critically degraded image quality. The underwater images’ poor visibility, low contrast, and color distortion result in ineffective and insufficient feature matching, leading to the poor or even failure of the existing SLAM algorithms. To address this issue, we propose introducing the generative adversarial network (GAN) to perform effective underwater image enhancement before conducting SLAM. Considering the inherent real-time requirement of SLAM, we conduct knowledge distillation to achieve GAN compression to reduce the inference cost, while achieving high-fidelity underwater image enhancement and real-time inference. The real-time underwater image enhancement acts as the image pre-processing to build a robust and accurate underwater monocular SLAM system. With the introduction of real-time underwater image enhancement, we can significantly promote underwater SLAM performance. The proposed method is a generic framework, which could be extended to various SLAM systems and achieve various scales of performance gain.

show abstract

An Underwater Image Enhancement Method for Simultaneous Localization and Mapping of Autonomous Underwater Vehicle

Cited by 10 publications

References 13 publications

Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM

Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM

Review of Underwater Image Enhancement Using CNN and U-net

Real-time GAN-based image enhancement for robust underwater monocular SLAM

Contact Info

Product

Resources

About