-A major obstacle to processing images of the ocean floor comes from the absorption and scattering effects of the light in the aquatic environment. Due to the absorption of natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion, and, as the vehicle moves, induce shadows in the scene. For this reason, the first step towards application of standard computer vision techniques to underwater imaging requires dealing first with these lighting problems. This paper analyses and compares existing methodologies to deal with lowcontrast, nonuniform illumination in underwater image sequences. The reviewed techniques include: (i) study of the illumination-reflectance model, (ii) local histogram equalization, (iii) homomorphic filtering and (iv) subtraction of the illumination field. Several experiments on real data have been conducted to compare the different approaches.

Scene modeling has a key role in applications ranging from visual mapping to augmented reality. This paper presents an end-to-end solution for creating accurate three-dimensional (3D) textured models using monocular video sequences. The methods are developed within the framework of sequential structure from motion, in which a 3D model of the environment is maintained and updated as new visual information becomes available. The proposed approach contains contributions at different levels. The camera pose is recovered by directly associating the 3D scene model with local image observations, using a dual-registration approach. Compared to the standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures, while allowing 3D reconstructions for any type of scene. Motivated by the need to map large areas, a novel 3D vertex selection mechanism is proposed, which takes into account the geometry of the scene. Vertices are selected not only to have high reconstruction accuracy but also to be representative of the local shape of the scene. This results in a reduction in the complexity of the final 3D model, with minimal loss of precision. is generated. We present a method for blending image textures using 3D geometric information and photometric differences between registered textures. The method allows high-quality mosaicing over 3D surfaces by reducing the effects of the distortions induced by camera viewpoint and illumination changes. The results are presented for four scene modeling scenarios, including a comparison with ground truth under a realistic scenario and a challenging underwater data set. Although developed primarily for underwater mapping applications, the methods are general and applicable to other domains, such as aerial and land-based mapping. C 2009 Wiley Periodicals, Inc.

Detecting already-visited regions based on their visual appearance helps reduce drift and position uncertainties in robot navigation and mapping. Inspired from content-based image retrieval, an efficient approach is the use of visual vocabularies to measure similarities between images. This way, images corresponding to the same scene region can be associated. State-of-theart proposals that address this topic use prebuilt vocabularies that generally require a priori knowledge of the environment. We propose a novel method for appearance-based navigation and mapping where the visual vocabularies are built online, thus eliminating the need for prebuilt data. We also show that the proposed technique allows efficient loop-closure detection, even at small vocabulary sizes, resulting in a higher computational efficiencyThis work was supported in part by European Union Project FP7-ICT-2011-288704 and the Spanish Ministry of Science and Innovation under Grant CTM2010-1521

No abstract

AbstracI-This paper presents a vision-based localization approach for an underwater robot in a ~t~e t u r r d environment. The system is based on a coded pattern placed on the bottom of a water tank and an onhoard downlooking camera. Main features are, absolute and map-based localization, landmark detection and tracking, and real-time computation (12.5 Hz). The proposed system provides threedimensional position and orientation of the vehicle along with its velocity. Accuracy of the drift-free estimates is very high, allowing them to he used as feedback measures of a velocity-based low level controller. The paper details the localization algorithm, by showing some graphical results, and the accuracy of the system.

. Unlike previous proposals that focus the classification on the sensors involved in the fusion, we propose a synthetic approach that is focused on the techniques involved in the fusion and their applications in ULIV navigation. We believe that our approach is better oriented towards the development of sensor fusion systems, since a sensor fusion architecture should be first of all focused on its goals and then on the fused sensors.

Abstract-This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential Structure from Motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures.The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene.

Fisheries acoustics surveys are effective tools in marine resource assessment and marine ecology. Significant advances have occurred in recent years with the application of multiple and broadband frequencies to enable remote species identification. There is, however, still the need to obtain additional evidence for identification, and the estimation of the size and tilt angle distribution of fish, which influences their acoustic target strength. The former two requirements are usually met by obtaining simultaneous net samples: there are limited, if any, recognized successful techniques for the latter. Here, two alternative tools for obtaining evidence for all three requirements are examined: angling gear and small video cameras. These tools were deployed during surveys of Atlantic mackerel (Scomber scombrus). In 2014, angling was actually more efficient than pelagic trawling (the standard technique) and over two survey periods (2012 and 2014) provided length frequency distributions that were not significantly different. A small video camera was deployed into mackerel schools, providing species identification and fish orientation. Image analysis was then applied, producing tilt-angle distributions of free swimming wild mackerel for the first time. Mean tilt angles from three deployments were very variable with 95% of observations falling between −70° and 39° with evidence of a multinomial frequency distribution. A video equipped lander was also deployed onto the type of rocky seabed where deployment of a trawl would be impossible: this confirmed the presence of Norway pout and suggested it was the dominant scatterer on this type of seabed. These techniques are complementary to traditional trawling methods, but provide additional insights into fish behaviour whilst satisfying standard requirements of identification and supplying biological samples. Crucially, the small cameras deployed approximate the size of the animals under observation and allow for measurement of behaviour (specifically tilt) that are more likely to represent those conditions encountered during surveying.