Rebeca Marfil

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.

Fast gesture recognition based on a two-level representation

Towards developing an interface for human-robot interaction, this paper proposes a two-level approach to recognise gestures which are composed of trajectories followed by different body parts. In a first level, individual trajectories are described by a set of key-points. These points are chosen as the corners of the curvature function associated to the trajectory, which will be estimated using and adaptive, non-iterative scheme. This adaptive representation allows removing noise while preserving detail in curvature at different scales. In a second level, gestures are characterised through global properties of the trajectories that compose them. Gesture recognition is performed using a confidence value that integrates both levels. Experimental results show that the performance of the proposed method is high in terms of computational cost and memory consumption, and gesture recognition ability.

Bounded irregular pyramid: a new structure for color image segmentation

This paper presents a new segmentation technique for color images. It relies on building an irregular pyramid into a regular one, presenting only nodes associated to homogeneous color regions. Hence, the size of the irregular pyramid is bounded. Segmentation is performed by rearranging the set of links among pyramid nodes. Unlike other hierarchical methods based on relinking procedures, our algorithm does not operate in an iterative way and it preserves region connectivity.

Real-time human motion analysis for human-robot interaction

This paper introduces a novel real-time human motion analysis system based on hierarchical tracking and inverse kinematics. This work constitutes a first step towards our goal of implementing a mechanism of human-machine interaction that allows a robot to provide feedback to a teacher in an imitation learning framework. In particular, we have developed a computer-vision based, upper-body motion analysis system that works without special devices or markers. Since such system is unstable and can only acquire partial information because of self-occlusions and depth ambiguity, we have employed a model-based pose estimation method based on inverse kinematics. The resulting system can estimate upper-body human postures with limited perceptual cues, such as centroid coordinates and disparity of head and hands.

Real-time object tracking using bounded irregular pyramids

Target representation and localization is a central component in visual object tracking. In this paper a new approach for target representation and localization is presented. This approach tackles two of the most important causes of failure in object tracking: changes of object appearance and occlusions. We propose a modified template matching approach which does not require a priori learning of object views. This method allows to track non-rigid objects in real-time by employing a weighted template which is dynamically updated, and a hierarchical framework that integrates all the components of the tracker. Our hierarchical tracker allows tracking of multiple objects with low increase of computational time. The capability of the tracking system to handle occlusions and target distortions is demonstrated for several video sequences.

A novel approach for salient image regions detection and description

This paper proposes a new algorithm for visual landmarks detection and description. The detection is achieved using a hierarchical grouping mechanism, which combines a color contrast measure defined between regions with internal region descriptors and with attributes of the shared boundary. This detector reliably finds the same salient regions under different viewing conditions. Then, geometrically and photometrically normalized regions are characterized by a kernel-based descriptor. This descriptor is rotation-invariant and robust against noise. Several tests are conducted in order to compare the proposed approach with other similar approaches. Experimental results prove that the performance of our proposal is high in terms of computational consuming and visual landmark detection and description abilities.

The construction of bounded irregular pyramids with a union-find decimation process

The Bounded Irregular Pyramid (BIP) is a mixture of regular and irregular pyramids whose goal is to combine their advantages. Thus, its data structure combines a regular decimation process with a union-find strategy to build the successive levels of the structure. The irregular part of the BIP allows to solve the main problems of regular structures: their inability to preserve connectivity or to represent elongated objects. On the other hand, the BIP is computationally efficient because its height is constrained by its regular part. In this paper the features of the Bounded Irregular Pyramid are discussed, presenting a comparison with the main pyramids present in the literature when applied to a colour segmentation task.

Real-time template-based tracking of non-rigid objects using bounded irregular pyramids

In object tracking, change of objects aspect is the most important cause of failure. This paper proposes a modified template matching approach to solve this problem without a priori learning of object views. This method permits to track non-rigid objects in real-time by employing a weighted template, which is dynamically updated, and a hierarchical framework that integrates all the components of the tracker. The capability of the tracking system to handle partial occlusions and target distortions is demonstrated for several video sequences.

Graph-Based Representations in Pattern Recognition and Computational Intelligence

Graph theory, which used to be a purely academic discipline, is now increasingly becoming an essential part in different areas of research. This paper briefly present new perspectives in graph---based representations applied in emerging fields, such as computer vision and image processing, robotics, network analysis, web mining, chemistry, bioinformatics, sensor networks, biomedical engineering or evolutionary computation.

Part-based object detection into a hierarchy of image segmentations combining color and topology

Object detection is one of the key components in computer vision systems. Current research on this topic has shifted from holistic approaches to representations of individual object parts linked by structural information. Along this line of research, this paper presents a novel part-based approach for automatic object detection using 2D images. The approach encodes the visual structures of the object to be detected and the image by a 2D combinatorial map and a combinatorial pyramid, respectively. Within this framework, we propose to perform the searching of the object as an error-tolerant submap isomorphism that will be conducted at the different layers of the pyramid. The approach has been applied to the detection of visual landmarks for mobile robotics self-localization. Experimental results show the good performance and robustness of the approach in the presence of partial occlusions, uneven illumination and 3-dimensional rotations.