F. Arrebola

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.

Corner detection and curve segmentation by multiresolution chain-code linking

In this paper, we propose a new method to characterise a curve by means of the hierarchical computation of a multiresolution structure. This structure, consisting of successive lower resolution versions of the same object, is processed using the linked pyramid approach. We adapt the multiresolution pixel linking algorithm to the processing of curve contours which are described by their chain-code. We also introduce a selective class selection process which allows application of the algorithm to segmentation and detection of contour features. The resulting framework presents good performance for a wide range of object sizes without the need of any parameter tweaking, and allows detection of shape detail at different scales.

Shifted fovea multiresolution geometries

This paper describes reconfigurable geometries for image sensors based on a concentric cartesian multiresolution lattice modified by four configuration parameters. They allow one, without moving the image sensor, to examine any region of the field of view with the highest available resolution, as well as to select the acuity profile for the regions surrounding the fovea. The efficient processing of the multiresolution images obtained requires discrete shifts of fovea and rings whose magnitudes are calculated. Real time foveal images have been preprocessed and examples are given.

Adaptive Fovea Structures for Space-Variant Sensors

In this paper we describe the architecture and data structure of space-variant sensors with reconfigurable cartesian geometries. The ability of these sensors to change the position and size of their high resolution regions or electronic foveas, makes them suitable to compensate the limited performance or coarse fixation characteristics of the mechanical systems utilized for gaze tasks in active vision applications where size, weight or cost could be conditioning factors to the performance or feasibility of the whole system. An alternative to the implementation of these sensors is based on off-the-shelf CCD cameras and devices with reconfiguration capabilities, such as FPGAs. In this way, besides the multiresolution data output, sensor reconfiguration systems let generate additional data adapted to the functions of the higher level modules of the active vision systems. As a result of this computing capability at the sensor level, it is possible to unload the processing stages of certain tasks without penalty in time or significant addition of hardware. An approach to selective foveation tasks and motion detection is presented.

Multiresolution sensors with adaptive structure

This paper describes the architecture of adaptive space-variant sensors with Cartesian topologies. Besides their multiresolution output, reconfigurable sensors can be upgraded to generate additional data to be processed at higher level modules of the vision systems, making it possible to unload the processing stages of certain tasks, without penalty in time or significant addition of hardware. A synthesizable implementation of these sensors, based on off-the-shelf FPGAs and CCD cameras is also described.

Generalization of Shifted Fovea Multiresolution Geometries Applied to Object Detection

This work describes a foveal vision system applied to object detection. The novelty of this system consists of carrying the detections using a generalization of the multiresolution shifted fovea images. The main advantage introduced is the great increase of the number of fovea positions allowed in shifted-fovea systems already implemented: this means that the maximum error of placement is reduced to one pixel, implying that any object could be examined at the highest resolution available regardless of its coordinates. The concept is based on increasing the degrees of freedom and the related number of configuration parameters and the application of a new shifting algorithm which allows a higher number of fixation points on the scene and, therefore, reduces the error of fovea positioning on the region of interest and aproaches closer to the required scene details. Besides, we introduce the multiresolution data structure to manipulate and process this type of foveal geometries, as well as the results obtained after applying hierarchical algorithms for segmentation and detection of objects within this type of multiresolution images.

VLSI implementation of a foveal polygon segmentation algorithm

Conventional vision systems with uniform resolution sensors contain a huge amount of information, a great part of it not necessary for the tasks they are intended. This fact makes processing difficult at speeds that may be desirable for many applications. Opposed to this option, foveal vision offers a wide visual field and high resolution in a small area of the image with a reduced data set, allowing us to do real-time image processing in many applications. In this field have emerged a great deal of algorithms and hierarchical structures to support the processing of this type of image. In this paper we present a VLSI architecture that implements a level sequential segmentation algorithm in one of these hierarchical structures (a polygon) generated using a Cartesian symmetric lattice topology. This structure is designed to work at real time (20-30 frames/s).

Merging Attention and Segmentation: Active Foveal Image Representation

Research on the brain information processing has focused on the interrelationships among cognitive processes. Thus, it is currently well-established that the units of attention on human vision are not merely spatial but closely related to perceptual objects. This implies a strong relationship between segmentation and attention processes. This interaction is bi-directional: if the segmentation process constraints attention, the way an image is segmented may depend on the specific question asked to an observer, i.e. what she ‘attend’ in this sense. When the focus of attention is deployed from one visual unit to another, the rest of the scene is perceived but at a lower resolution that the focused object. The result is a multi-resolution visual perception in which the fovea, a dimple on the central retina, provides the highest resolution vision. While much work has recently been focused on computational models for object-based attention, the design and development of multi-resolution structures that can segment the input image according to the focused perceptual unit is largely unexplored. This paper proposes a novel structure for multi-resolution image segmentation that extends the encoding provided by the Bounded Irregular Pyramid. Bottom-up attention is enclosed in the same structure, allowing to set the fovea over the most salient image region. Preliminary results obtained from the segmentation of natural images show that the performance of the approach is good in terms of speed and accuracy.

Multiresolution vision in autonomous systems

The performance of many autonomous systems based on artificial vision depends mainly on the speed of response and the field of view of the vision systems. The many tasks to be carried out, such as object detection, recognition, tracking, etc., the complexity of reliable algorithms and tasks to be done in real time, and the huge data volumes involved with stereo vision systems, imply processing times and resources that, in some cases, are incompatible with or unsuitable for acceptable system operation. Multiresolution systems are one alternative to cover wide fields of view without involving high data volumes and, therefore, considerably reduce the constraints imposed by off-the-shelf uniresolution vision systems.Our work is related to adaptive space-variant sensors, able to supply any number of resolution levels with reconfigurable resolution profiles around regions or objects of interest, and to the specific algorithms and hierarchical data structures related to processing multiresolution data involved in tasks of image segmentation, object detection, etc. required for operation in dynamic environments.