Search

This work presents a novel approach for monocular dense Simultaneous Localization and Mapping. The surface to be estimated is represented as a piecewise planar surface, defined as a group of surfels each having as parameters its position and normal. These parameters are then directly estimated from the raw camera pixels measurements, by a Gauss-Newton iterative process. The representation of the surface as a group of surfels has several advantages. It allows the recovery of robust and accurate pixel depths, without the need to use a computationally demanding depth regularization schema. This has the further advantage of avoiding the use of a physically unlikely surface smoothness prior. New surfels can be correctly initialized from the information present in nearby surfels, avoiding also the need to use an expensive initialization routine commonly needed in Gauss-Newton methods. The method was written in the GLSL shading language, allowing the usage of GPU thus achieving real-time. The method was tested against several datasets, showing both its depth and normal estimation correctness, and its scene reconstruction quality. The results presented here showcase the usefulness of the more physically grounded piecewise planar scene depth prior, instead of the more commonly pixel depth independence and smoothness prior.

This work deals with the design of a real-time approach for automatic parameter tuning in a deflickering process of videos of a moving landscape scene underwater perturbed with sunlight waves. The tuner performs a continuous parameter optimization inside a basic filter, which employes feedback in order to improve the performance. Also it is able to adapt the optimum to eventual changing of the scenario conditions. Moreover, issues like the parameter sensitivity and loop stability are addressed equally. The results have been illustrated by means of a worked-out case-study employing real film material of a scenario underwater. The approach was motivated by the SLAM applications with monocamera vision-based vehicles underwater and simple hardware implementations in FPGA structures.

A multi stage visual odometry system with a failure detection mechanism is developed to measure movement and correct unreliable estimations in poorly textured underwater environments. The system has only one camera as the sensor, and is composed of a primary movement estimation based of features presented in the scene and two backup system. The first backup is based on phase correlation to estimate the AUV movement. The second backup movement estimation mechanism is based on a high order prediction of the movement using the last good movement estimations. Failure detection mechanism are constructed to detect unreliable measurements in each of the stages and appropriate responses are developed in all cases. A full SLAM implementation is developed and a real case study is presented in which the good properties of the system are shown.

This work deals with the development of a node-based monocular visual methodology for autonomous vehicle navigation which has the goal of exploring unknown regions of the sea bottom with a posterior safe revisiting of them. The work accentuates characteristics of the seabed like self-similarity and backscattering. In a stepwise fashion, a visual guidance system constructs a shape similar to a narrow corridor by optimally creating a heading function on the basis of keypoints threads, which ensures future revisits. The corridor is composed of nodes and paths in between. Each path is composed of a visual-odometry-based trail which is generated in feature-poor environments, in combination with a feature-based trail which emerges in feature-rich regions. A probabilistic analysis of the uncertainties and their impact in the success rate on loop closings is carried out. We work out two case studies, the first employing an ad-hoc benchmark and the second a series of experiments in the real world. From here qualitative conclusions can be drawn out that enable us to anticipate potential applications of the approach in the field of autonomous navigation underwater. Fil: Trabes, Emanuel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto Argentino de Oceanografía. Universidad Nacional del Sur. Instituto Argentino de Oceanografía; Argentina Fil: Jordan, Mario Alberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto Argentino de Oceanografía. Universidad Nacional del Sur. Instituto Argentino de Oceanografía; Argentina