Large scale SLAM with visual features

Comunicación presentada en el X Workshop of Physical Agents, Cáceres, 10-11 septiembre 2009.

A study of 2D features for 3D visual SLAM

Paper submitted to the 43rd International Symposium on Robotics (ISR), Taipei, Taiwan, August 29-31, 2012.

Hand gesture recognition based on morphologic features

Comunicación presentada en el IX Simposium Nacional de Reconocimiento de Formas y Análisis de Imágenes, Benicàssim, Mayo, 2001.

Event-based visual servoing with features’ prediction

Event-based visual servoing is a recently presented approach that performs the positioning of a robot using visual information only when it is required. From the basis of the classical image-based visual servoing control law, the scheme proposed in this paper can reduce the processing time at each loop iteration in some specific conditions. The proposed control method enters in action when an event deactivates the classical image-based controller (i.e. when there is no image available to perform the tracking of the visual features). A virtual camera is then moved through a straight line path towards the desired position. The virtual path used to guide the robot improves the behavior of the previous event-based visual servoing proposal.

The role of statistical and semantic features in single-document extractive summarization

This paper reports on the further results of the ongoing research analyzing the impact of a range of commonly used statistical and semantic features in the context of extractive text summarization. The features experimented with include word frequency, inverse sentence and term frequencies, stopwords filtering, word senses, resolved anaphora and textual entailment. The obtained results demonstrate the relative importance of each feature and the limitations of the tools available. It has been shown that the inverse sentence frequency combined with the term frequency yields almost the same results as the latter combined with stopwords filtering that in its turn proved to be a highly competitive baseline. To improve the suboptimal results of anaphora resolution, the system was extended with the second anaphora resolution module. The present paper also describes the first attempts of the internal document data representation.

Combining visual features and Growing Neural Gas networks for robotic 3D SLAM

The use of 3D data in mobile robotics provides valuable information about the robot’s environment. Traditionally, stereo cameras have been used as a low-cost 3D sensor. However, the lack of precision and texture for some surfaces suggests that the use of other 3D sensors could be more suitable. In this work, we examine the use of two sensors: an infrared SR4000 and a Kinect camera. We use a combination of 3D data obtained by these cameras, along with features obtained from 2D images acquired from these cameras, using a Growing Neural Gas (GNG) network applied to the 3D data. The goal is to obtain a robust egomotion technique. The GNG network is used to reduce the camera error. To calculate the egomotion, we test two methods for 3D registration. One is based on an iterative closest points algorithm, and the other employs random sample consensus. Finally, a simultaneous localization and mapping method is applied to the complete sequence to reduce the global error. The error from each sensor and the mapping results from the proposed method are examined.

Electrochemical features of Pt(S)[n(110) × (100)] surfaces in acidic media

Experiments have been carried out in sulfuric and perchloric acid solutions on Pt(S)[n(110) × (100)] electrodes. The comparison between the two different electrolytic media reveals an important influence of the anion in the voltammetric features. Total charge curves have been obtained with the CO charge displacement method in combination with voltammetric measurements. From these curves, the dependence of the pztc with the step density and the strength of the anion adsorption have been analyzed. The problem of the so-called third peak is treated for a series of electrodes that contain (110) terraces, revealing the requirement of (110) domains for occurrence of this adsorption state.

Spectral features in isolated neutron stars induced by inhomogeneous surface temperatures

The thermal X-ray spectra of several isolated neutron stars display deviations from a pure blackbody. The accurate physical interpretation of these spectral features bears profound implications for our understanding of the atmospheric composition, magnetic field strength and topology, and equation of state of dense matter. With specific details varying from source to source, common explanations for the features have ranged from atomic transitions in the magnetized atmospheres or condensed surface, to cyclotron lines generated in a hot ionized layer near the surface. Here, we quantitatively evaluate the X-ray spectral distortions induced by inhomogeneous temperature distributions of the neutron star surface. To this aim, we explore several surface temperature distributions, we simulate their corresponding general relativistic X-ray spectra (assuming an isotropic, blackbody emission), and fit the latter with a single blackbody model. We find that, in some cases, the presence of a spurious ‘spectral line’ is required at a high significance level in order to obtain statistically acceptable fits, with central energy and equivalent width similar to the values typically observed. We also perform a fit to a specific object, RX J0806.4−4123, finding several surface temperature distributions able to model the observed spectrum. The explored effect is unlikely to work in all sources with detected lines, but in some cases it can indeed be responsible for the appearance of such lines. Our results enforce the idea that surface temperature anisotropy can be an important factor that should be considered and explored also in combination with more sophisticated emission models like atmospheres.

Learning Probabilistic Features for Robotic Navigation Using Laser Sensors

SLAM is a popular task used by robots and autonomous vehicles to build a map of an unknown environment and, at the same time, to determine their location within the map. This paper describes a SLAM-based, probabilistic robotic system able to learn the essential features of different parts of its environment. Some previous SLAM implementations had computational complexities ranging from O(Nlog(N)) to O(N2), where N is the number of map features. Unlike these methods, our approach reduces the computational complexity to O(N) by using a model to fuse the information from the sensors after applying the Bayesian paradigm. Once the training process is completed, the robot identifies and locates those areas that potentially match the sections that have been previously learned. After the training, the robot navigates and extracts a three-dimensional map of the environment using a single laser sensor. Thus, it perceives different sections of its world. In addition, in order to make our system able to be used in a low-cost robot, low-complexity algorithms that can be easily implemented on embedded processors or microcontrollers are used.

Active Visual Features Based on Events to Guide Robot Manipulators in Tracking Tasks

Traditional visual servoing systems do not deal with the topic of moving objects tracking. When these systems are employed to track a moving object, depending on the object velocity, visual features can go out of the image, causing the fail of the tracking task. This occurs specially when the object and the robot are both stopped and then the object starts the movement. In this work, we have employed a retina camera based on Address Event Representation (AER) in order to use events as input in the visual servoing system. The events launched by the camera indicate a pixel movement. Event visual information is processed only at the moment it occurs, reducing the response time of visual servoing systems when they are used to track moving objects.

An improvement of a SLAM RGB-D method with movement prediction derived from a study of visual features

This paper presents a method for the fast calculation of a robot’s egomotion using visual features. The method is part of a complete system for automatic map building and Simultaneous Location and Mapping (SLAM). The method uses optical flow to determine whether the robot has undergone a movement. If so, some visual features that do not satisfy several criteria are deleted, and then egomotion is calculated. Thus, the proposed method improves the efficiency of the whole process because not all the data is processed. We use a state-of-the-art algorithm (TORO) to rectify the map and solve the SLAM problem. Additionally, a study of different visual detectors and descriptors has been conducted to identify which of them are more suitable for the SLAM problem. Finally, a navigation method is described using the map obtained from the SLAM solution.

What can physical, biotic and chemical features of a tree hollow tell us about their associated diversity?

Tree hollows are keystone structures for saproxylic fauna and host numerous endangered species. However, not all tree hollows are equal. Many variables including physical, biotic and chemical ones, can characterise a tree hollow, however, the information that these could provide about the saproxylic diversity they harbour has been poorly explored. We studied the beetle assemblages of 111 Quercus species tree hollows in four protected areas of the Iberian Peninsula. Three physical variables related to tree hollow structure, and two biotic ones (presence of Cetoniidae and Cerambyx species recognised as ecosystem engineers) were measured in each hollow to explore their relative effect on beetle assemblages. Moreover, we analysed the chemical composition of the wood mould in 34 of the hollows, in order to relate beetle diversity with hollow quality. All the environmental variables analysed (physical and biological) showed a significant influence on saproxylic beetle assemblages that varied depending on the species. Furthermore, the presence of ecosystem engineers affected both physical and chemical features. Although wood mould volume, and both biotic variables could act as beetle diversity surrogate, we enhance the presence of Cetoniidae and Cerambyx activity (both easily observable in the field) as indicator variables, even more if both co-occur as each affect to different assemblages. Finally, assimilable carbon and phosphorous contents could act as indicator for past and present beetle activity inside the cavity that could become a useful tool in functional diversity studies. However, an extension of this work to other taxonomic groups would be desirable.

Phraseological features in conversational routines: An integrative model of autonomy

This paper deals with the analysis of routine formulas according to their degree of independence in discourse, with the aim of establishing a gradual line which restructures Sphere III (Corpas 1996, Alvarado 2015) — where phraseological utterances belong. The system developed by Briz and the Val.Es.Co. Group (2003, 2014) will help us segment conversation and check that phraseological utterances show various degrees of independence, both in Peninsular Spanish and in Latin American Spanish, which will make it possible to restructure Sphere III. The methodology utilized corresponds to the phraseological and pragmatic approach, and the examples were extracted from the Corpus de Conversaciones Coloquiales of Briz and the Val.Es.Co. Group (2002), and from the Corpus Preseea (2014).