Francisco Bonnin-Pascual

Emilio Garcia-Fidalgo, Joan P. Company-Corcoles, Francisco Bonnin-Pascual et al.

In the last decades, Light Detection And Ranging (LiDAR) technology has been extensively explored as a robust alternative for self-localization and mapping. These approaches typically state ego-motion estimation as a non-linear optimization problem dependent on the correspondences established between the current point cloud and a map, whatever its scope, local or global. This paper proposes LiODOM, a novel LiDAR-only ODOmetry and Mapping approach for pose estimation and map-building, based on minimizing a loss function derived from a set of weighted point-to-line correspondences with a local map abstracted from the set of available point clouds. Furthermore, this work places a particular emphasis on map representation given its relevance for quick data association. To efficiently represent the environment, we propose a data structure that combined with a hashing scheme allows for fast access to any section of the map. LiODOM is validated by means of a set of experiments on public datasets, for which it compares favourably against other solutions. Its performance on-board an aerial platform is also reported.

Kai Yao, Alberto Ortiz, Francisco Bonnin-Pascual

Following the success of machine vision systems for on-line automated quality control and inspection processes, an object recognition solution is presented in this work for two different specific applications, i.e., the detection of quality control items in surgery toolboxes prepared for sterilizing in a hospital, as well as the detection of defects in vessel hulls to prevent potential structural failures. The solution has two stages. First, a feature pyramid architecture based on Single Shot MultiBox Detector (SSD) is used to improve the detection performance, and a statistical analysis based on ground truth is employed to select parameters of a range of default boxes. Second, a lightweight neural network is exploited to achieve oriented detection results using a regression method. The first stage of the proposed method is capable of detecting the small targets considered in the two scenarios. In the second stage, despite the simplicity, it is efficient to detect elongated targets while maintaining high running efficiency.

Kai Yao, Alberto Ortiz, Francisco Bonnin-Pascual

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is particularly difficult for semantic segmentation tasks since the annotation must be ideally generated at the pixel level. Weakly-supervised semantic segmentation aims at reducing this cost by employing simpler annotations that, hence, are easier, cheaper and quicker to produce. In this paper, we propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function whose goal is to counteract the effects of weak annotations. To this end, this loss function comprises several terms based on partial cross-entropy losses, being one of them the Centroid Loss. This term induces a clustering of the image pixels in the object classes under consideration, whose aim is to improve the training of the segmentation network by guiding the optimization. The performance of the approach is evaluated against datasets from two different industry-related case studies: while one involves the detection of instances of a number of different object classes in the context of a quality control application, the other stems from the visual inspection domain and deals with the localization of images areas whose pixels correspond to scene surface points affected by a specific sort of defect. The detection results that are reported for both cases show that, despite the differences among them and the particular challenges, the use of weak annotations do not prevent from achieving a competitive performance level for both.

Emilio Garcia-Fidalgo, Francisco Bonnin-Pascual, Joan P. Company-Corcoles et al.

The periodic inspection of vessels is a fundamental task to ensure their integrity and avoid maritime accidents. Currently, these inspections represent a high cost for the ship owner, in addition to the danger that this kind of hostile environment entails for the surveyors. In these situations, robotic platforms turn out to be useful not only for safety reasons, but also to reduce vessel downtimes and simplify the inspection procedures. Under this context, in this paper we report on the evaluation of a new control architecture devised to drive an aerial platform during these inspection procedures. The control architecture, based on an extensive use of behaviour-based high-level control, implements visual inspection-oriented functionalities, while releases the operator from the complexities of inspection flights and ensures the integrity of the platform. Apart from the control software, the full system comprises a multi-rotor platform equipped with a suitable set of sensors to permit teleporting the surveyor to the areas that need inspection. The paper provides an extensive set of testing results in different scenarios, under different operational conditions and over real vessels, in order to demonstrate the suitability of the platform for this kind of tasks.