Antonio Bandera

Pyramid segmentation algorithms revisited

The main goal of this work is to compare pyramidal structures proposed to solve segmentation tasks. Segmentation algorithms based on regular and irregular pyramids are described, together with the data structures and decimation procedures which encode and manage the information in the pyramid. In order to compare the different segmentation algorithms, we have employed three types of quality measurements: the shift variance measure, the F function and the Q function.

Natural landmark extraction for mobile robot navigation based on an adaptive curvature estimation

This paper proposes a geometrical feature detection system which is to be used with conventional 2D laser range finders. It consists of three main modules: data acquisition and pre-processing, segmentation and landmark extraction and characterisation. The novelty of this system is a new approach for laser data segmentation based on an adaptive curvature estimation. Contrary to other works, this approach divides the laser scan into line and curve segments. Then, these items are used to directly extract several types of landmarks associated with real and virtual features of the environment (corners, center of tree-like objects, line segments and edges). For each landmark, characterisation provides not only the parameter vector, but also complete statistical information, suitable to be used in a localization and mapping algorithm. Experimental results show that the proposed approach is efficient to detect landmarks for structured and semi-structured environments.

Feature extraction from laser scan data based on curvature estimation for mobile robotics

This paper presents a geometrical feature detection system to use with conventional 2D laser rangefinders. This system consists of three main modules: data acquisition and pre-processing, rupture and breakpoint detection and feature extraction. The novelty of this system is a new efficient approach for natural feature extraction based on curvature estimation. This approach permits to extract and characterise line segments, corners and curve segments from the laser scan. Experimental results show that the proposed approach is very fast and permit to verify its effectiveness in indoor and outdoor environments

Mean shift based clustering of Hough domain for fast line segment detection

This paper proposes a new algorithm for extracting line segments from edge images. Basically, the method performs two consecutive stages. In the first stage, the algorithm follows a line segment random window randomized Hough transform (RWRHT) based approach. This approach provides a mechanism for finding more favorable line segments from a global point of view. In our case, the RWRHT based approach is used to actualise an accurate Hough parameter space. In the second stage, items of this parameter space are unsupervisedly clustered in a set of classes using a variable bandwidth mean shift algorithm. Cluster modes provided by this algorithm constitute a set of base lines. Thus, clustering process allows using accurate Hough parameters and, however, detecting only one line when pixels along it are not exactly collinear. Edge pixels lying on the lines grouped to generate each base line are projected onto this base line. A fast and purely local grouping algorithm is employed to merge points along each base line into line segments. We have performed several experiments to compare the performance of our method with that of other methods. Experimental results show that the performance of the proposed method is very high in terms of line segment detection ability and execution time.

Non-parametric planar shape representation based on adaptive curvature functions

This paper presents a non-parametric method to extract a very short feature vector from the curvature function of a planar shape. Curvature is adaptively calculated using a new procedure that removes noise from the contour without missing relevant points. Then, its Fourier transform is projected onto a set of vectors, which have been chosen to be as representative as possible, to obtain the similarity between the input object and each vector of the set. These similarity values are the elements of the feature vector. The proposed method is very fast and classification has proven that the representation is good.

2D object recognition based on curvature functions obtained from local histograms of the contour chain code

Abstract In this paper a real time 2D object recognition algorithm is proposed. Contours are represented by their curvature functions, decomposed in the Fourier domain as linear combination of a set of representative objects. Finally, objects are identified by multilevel clustering.

Curvature-Based Environment Description for Robot Navigation Using Laser Range Sensors

This work proposes a new feature detection and description approach for mobile robot navigation using 2D laser range sensors. The whole process consists of two main modules: a sensor data segmentation module and a feature detection and characterization module. The segmentation module is divided in two consecutive stages: First, the segmentation stage divides the laser scan into clusters of consecutive range readings using a distance-based criterion. Then, the second stage estimates the curvature function associated to each cluster and uses it to split it into a set of straight-line and curve segments. The curvature is calculated using a triangle-area representation where, contrary to previous approaches, the triangle side lengths at each range reading are adapted to the local variations of the laser scan, removing noise without missing relevant points. This representation remains unchanged in translation or rotation, and it is also robust against noise. Thus, it is able to provide the same segmentation results although the scene will be perceived from different viewpoints. Therefore, segmentation results are used to characterize the environment using line and curve segments, real and virtual corners and edges. Real scan data collected from different environments by using different platforms are used in the experiments in order to evaluate the proposed environment description algorithm.

A SURVEY OF VISION-BASED ARCHITECTURES FOR ROBOT LEARNING BY IMITATION

Learning by imitation is a natural and intuitive way to teach social robots new behaviors. While these learning systems can use different sensory inputs, vision is often their main or even their only source of input data. However, while many vision-based robot learning by imitation (RLbI) architectures have been proposed in the last decade, they may be difficult to compare due to the absence of a common, structured description. The first contribution of this survey is the definition of a set of standard components that can be used to describe any RLbI architecture. Once these components have been defined, the second contribution of the survey is an analysis of how different vision-based architectures implement and connect them. This bottom–up, structural analysis of architectures allows to compare different solutions, highlighting their main advantages and drawbacks, from a more flexible perspective than the comparison of monolithic systems.

Hierarchical planning in a mobile robot for map learning and navigation

This chapter focuses on autonomous navigation for mobile robots. We propose a hybrid layered architecture, which is used to navigate in totally or partially explored environments using sonar sensors. Our architecture relies on a hierarchical representation of the environment, which has both a metric and a topological level, which is based on the metric level. High level planning layers work at the topological level deliberatively, while low level navigation layers operate at the metric level reactively. The main advantage of the proposed scheme is that it can operate in both known and unknown environments rapidly and efficiently.

Efficient integration of metric and topological maps for directed exploration of unknown environments

Recent research in mobile robot navigation is focused on integrating the metric and topological paradigms to unsupervisedly construct representations of indoor environments. While metric methods produce accurate environment representations, these representations present a huge data volume and they are consequently difficult to process in real time. On the other hand, topological maps can be processed in a more efficient way, but they are typically difficult to disambiguate and update. This paper describes an exploration algorithm for totally or partially unexplored environments. The algorithm is based on a representation that integrates the metric and topological paradigms. Exploration planning is performed at two levels: global planning is performed at topological level and local planning is performed at metric level. The main advantage of the proposed algorithm is that exploration can be performed in a fast and efficient way by using the presented representation. The method has been successfully tested for a Pioneer P2AT mobile robot in indoor environments.