Search

Image processing-based methods, capable of detecting and quantifying cracks, surface defects or recovering 3D shape information are increasingly being recognised as a valuable tool for inspecting underwater structures. It is of great practical importance for inspectors to know the effectiveness of such techniques when applied in conditions. This paper considers an underwater environment characterised by poor visibility chiefly governed by the lighting and turbidity levels, along with a range of geometry and damage conditions of calibrated specimens. The paper addresses the relationship between underwater visibility and the performance of image-based methods through the development and calibration of a first open-source underwater lighting and turbidity image repository (ULTIR). ULTIR contains a large collection of images of submerged specimens that have been photographed under controlled lighting and turbidity levels featuring various forms of geometry and damage. ULTIR aims to facilitate inspectors when rationalising the use of image processing methods as part of an underwater inspection campaign and to enable researchers to efficiently evaluate the performance of image-based methods under realistic operating conditions. Stakeholders in underwater infrastructure can benefit through this first large, standardised, well-annotated, and freely available database of images and associated metadata. [ABSTRACT FROM AUTHOR]

The training of a deep learning model requires a large amount of data. In case of sidescan sonar images, the number of snippets from objects of interest is limited. Generative adversarial networks (GAN) have shown to be able to generate photo-realistic images. Hence, we use a GAN to augment a baseline sidescan image dataset with synthetic snippets. Although the training of a GAN with few data samples is likely to cause mode collapse, a combination of pre-training using simple simulated images and fine-tuning with real data reduces this problem. However, for sonar data, we show that this approach of transfer-learning a GAN is sensitive to the pre-training step, meaning that the vanishing of the gradients of the GAN's discriminator becomes a critical problem. Here, we demonstrate how to overcome this problem, and thus how to apply transfer-learning to GANs for generating synthetic sidescan snippets in a more robust way. Additionally, in order to further investigate the GAN's ability to augment a sidescan image dataset, the generated images are analyzed in the image and the frequency domain. The work helps other researchers in the field of sonar image processing to augment their dataset with additional synthetic samples. [ABSTRACT FROM AUTHOR]

Fishing net cleanliness plays a critical role for aquaculture industry as bio-fouled nets restrict the flow of water through the net leading to a build-up of toxins and reduced oxygen levels within the pen, thereby putting the fish under increased stress. In this paper, we proposed an underwater fishing Net Health State Estimation (NHSE) method, which can automatically analyze the degree of fouling on the net through underwater image analysis using remotely operated vehicles (ROV) images, and calculate a blocking percentage metric of each net opening. The level of fouling estimated through this method help the operators decide on the need of cleaning or maintenance schedule. There are mainly six modules in the proposed NHSE method, namely user interaction, distortion correction, underwater image dehazing, marine growth segmentation, net-opening structure analysis, and blocked percentage estimation. To evaluate the proposed NHSE method, we collected and labeled several underwater images in Mulroy Bay, Ireland with pixel-wise annotations. In order to verify the universality and robustness of the algorithm, we simulated and built a virtual fishing farm, and, on this basis, collected and labeled fishing net images under different environmental conditions. Seven evaluation metrics are introduced to demonstrate the effectiveness and advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Recent breakthroughs in the computer vision community have led to the emergence of efficient deep learning techniques for end-to-end segmentation of natural scenes. Underwater imaging stands to gain from these advances, however, deep learning methods require large annotated datasets for model training and these are typically unavailable for underwater imaging applications. This paper proposes the use of photorealistic synthetic imagery for training deep models that can be applied to interpret real-world underwater imagery. To demonstrate this concept, we look at the specific problem of biofouling detection on marine structures. A contemporary deep encoder–decoder network, termed SegNet, is trained using 2500 annotated synthetic images of size 960 × 540 pixels. The images were rendered in a virtual underwater environment under a wide variety of conditions and feature biofouling of various size, shape, and colour. Each rendered image has a corresponding ground truth per-pixel label map. Once trained on the synthetic imagery, SegNet is applied to segment new real-world images. The initial segmentation is refined using an iterative support vector machine (SVM) based post-processing algorithm. The proposed approach achieves a mean Intersection over Union (IoU) of 87% and a mean accuracy of 94% when tested on 32 frames extracted from two distinct real-world subsea inspection videos. Inference takes several seconds for a typical image. [ABSTRACT FROM AUTHOR]

In India, video monitoring of urban roads in order to estimate traffic condition parameters (volume, speed and density) is difficult due to the heterogeneous nature of the traffic and poor lane discipline. As an alternative, a methodology to estimate levels of traffic congestion on urban roads using image processing of monitored video recordings was developed. Four levels of congestion, from completely congested to free-flow conditions, were identified utilising surrogates such as area occupancy or average velocity along with additional attributes such as the number of corner features extracted using image processing. The algorithm was adjusted for changes in lighting and camera angles. The performance of the framework was evaluated on videos recorded from a major road in Chennai, India. The findings indicated that the proposed framework is well-suited for real-time identification of traffic states and has potential as a cost-effective tool for updating traveller information systems in similar road transport networks. [ABSTRACT FROM AUTHOR]