P. Camacho

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.

Vision system based on shifted fovea multiresolution retinotopologies

In this paper, the authors present a foveal active vision system. It is capable of moving and fixating the fovea to any region of a scene, detecting its most relevant areas to extract certain features of these regions of interest. The system conducts a segmentation of the image, detects the possible existing objects in the scene, obtains hierarchically a set of features for each detected object-centroid, area, bounding box and grey level and extracts the corners of the object contained in the fovea. This system is going to be integrated in an autonomous mobile agent, so it is important to process each object in the optimal resolution level to minimise computational load and time requirements. The most important novelty of the system is the use of reconfigurable shifted fovea retinotopologies, also including a new algorithm capable of obtaining a curvature function by means of local histograms of the contour chain code to reliably calculate the stable corners of the contour of the objects.

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).

Hardware platform for regions extraction in foveal images

Foveal sensors can substantially increase the performance of active vision systems because of their ability to handle wide field of view and simultaneously reducing the data/bandwidth with space variant sensing. In order to process the multiresolution images and associated data structures, a new hierarchical processing has been applied to minimize data communications and retrieval. In the paper we present a hardware platform implementing a level sequential segmentation algorithm in one of these hierarchical structures generated using a Cartesian lattice topology. This platform is designed to work at 33 frame/s using as an input the levels obtained after preprocessing the uniform resolution images from digital cameras.

Hardware architecture for hierarchical segmentation in foveal images

Foveal sensors can substantially increase the performance of active vision systems because of their ability to handle wide field of view and simultaneously reduce the data/bandwidth with space variant sensing. To process the multiresolution images and associated data structures, a new hierarchical processing has been applied to minimize data communications and retrieval. In this article, we present a hardware platform that implements a level sequential segmentation algorithm in one of these hierarchical structures based on a Cartesian lattice topology. The platform operates in real time, at speeds in the range of 25 to 85 frames/s, using a digital uniform‐resolution camera as the source to generate and process the multiresolution images.

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.

Adaptive multifovea sensors for mobile tracking

This paper presents an implementation of adaptive multifovea sensors with reconfigurable structures based on multiresolution topologies and hierarchical data structures related to vision pyramids. These sensors are particularly useful for applications where fast data processing is a requirement together with low cost, volume, weight and power consumption. One of those applications, detection and tracking of several moving objects, as well as the algorithm used for the application is described.