José Luis Lázaro

Integral system for assisted mobility

Abstract This paper presents the results of a research work carried out in the Electronics Department of the University of Alcala in the field of electronic systems for the guidance of wheelchairs for the disabled and/or the elderly. These electronic systems have been designed to meet a wide range of needs experienced by users of this type of wheelchair. One of their most important features is their modularity, thereby making them adaptable to the particular needs of each user according to the type and degree of handicap involved. The overall system includes a complete user–machine interface, motor control modules and safety and autonomous guidance systems. The project is called: “Sistema Integral de Ayuda a la Movilidad (SIAMO)” (integral system for assisted mobility).

Wheelchair for physically disabled people with voice, ultrasonic and infrared sensor control

This paper describes a wheelchair for physically disabled people developed within the UMIDAM Project. A dependent-user recognition voice system and ultrasonic and infrared sensor systems has been integrated in this wheelchair. In this way we have obtained a wheelchair which can be driven with using voice commands and with the possibility of avoiding obstacles and downstairs or hole detection. The wheelchair has also been developed to allow autonomous driving (for example, following walls). The project, in which two prototypes have been produced, has been carried out totally in the Electronics Department of the University of Alcalá (Spain). It has been financed by the ONCE. Electronic system configuration, a sensor system, a mechanical model, control (low level control, control by voice commands), voice recognition and autonomous control are considered. The results of the experiments carried out on the two prototypes are also given.

Directional People Counter Based on Head Tracking

This paper presents an application for counting people through a single fixed camera. This system performs the count distinction between input and output of people moving through the supervised area. The counter requires two steps: detection and tracking. The detection is based on finding peoples heads through preprocessed image correlation with several circular patterns. Tracking is made through the application of a Kalman filter to determine the trajectory of the candidates. Finally, the system updates the counters based on the direction of the trajectories. Different tests using a set of real video sequences taken from different indoor areas give results ranging between 87% and 98% accuracies depending on the volume of flow of people crossing the counting zone. Problematic situations, such as occlusions, people grouped in different ways, scene luminance changes, etc., were used to validate the performance of the system.

Electronic control of a wheelchair guided by voice commands

Abstract This paper describes the control of an electric wheel chair with voice commands. This chair has been developed and built at the U.A.H. Electronic Department and financed by the ONCE Foundation (Spain). The first prototype consists of voice recognition, motor control, user interface and central processor modules. The electronic system allows the chair user a safe, easy ride, and guarantees the concordance between user commands and actual trajectories. Furthermore, the system has been designed to allow the addition of future features, like obstacle and stair detection and the tele-commanding of electrical household appliances from the chair.

Guidance of a mobile robot using an array of static cameras located in the environment

Abstract This paper presents a new proposal for positioning and guiding mobile robots in indoor environments. The proposal is based on the information provided by static cameras located in the movement environment. This proposal falls within the scope of what are known as intelligent environments; in this case, the environment is provided with cameras that, once calibrated, allow the position of the robots to be obtained. Based on this information, control orders for the robots can be generated using a radio frequency link. In order to facilitate identification of the robots, even under extremely adverse ambient lighting conditions, a beacon consisting of four circular elements constructed from infrared diodes is mounted on board the robots. In order to identify the beacon, an edge detection process is carried out. This is followed by a process that, based on the algebraic distance, obtains the estimated ellipses associated with each element of the beacon. Once the beacon has been identified, the coordinates of the centroids for the elements that make up the beacon are obtained on the various image planes. Based on these coordinates, an algorithm is proposed that takes into account the standard deviation of the error produced in the various cameras in ascertaining the coordinates of the beacon’s elements. An odometric system is also used in guidance that, in conjunction with a Kalman Filter, allows the position of the robot to be estimated during the time intervals required to process the visual information provided by the cameras.

Calibration of Line-Scan Cameras

This paper presents a novel method for calibrating line-scan cameras using a calibration pattern comprising two parallel planes with lines that can be described using known equations. Using pattern geometry and a line that is captured by a line-scan camera, we calculate the 3-D coordinates of the points corresponding to the straight lines of a pattern that is captured by the line-scan camera. These coordinates are used to obtain the intrinsic and extrinsic parameters of the line scan using a standard calibration procedure that is based on a recursive least squares method. In this paper, the procedure of calibration and the results obtained for a specific line scan will be shown; specifically, the obtained median residual error is 0.28 pixel. Also, the repetitiveness of the calibration process was verified for a sequence of 500 times.

Implementation in Fpgas of Jacobi Method to Solve the Eigenvalue and Eigenvector Problem

This work shows a modular architecture based on FPGAs to solve the eigenvalue problem according to the Jacobi method. This method is able to solve the eigenvalues and eigenvectors concurrently. The main contribution of this work is the low execution time compared with other sequential algorithms, and minimal internal FPGA consumed resources, mainly due to the fact of using the CORDIC algorithm. Two CORDIC modules have been designed to solve the trigonometric operations involved. A parallel CORDIC architecture is proposed as it is the best option to compute the eigenvalues with this method. Both CORDIC modules can work in rotation and vector mode. The whole system has been done in VHDL language, attempting to optimize the design.

Novel HW Architecture Based on FPGAs Oriented to Solve the Eigen Problem

A hardware solution is presented to obtain the eigenvalues and eigenvectors of a real and symmetrical matrix using field-programmable gate arrays (FPGAs). Currently, this system is used to compute the eigenvalues and eigenvectors in covariance matrices for applications in digital image processing that make use of the principal component analysis (PCA) technique. The proposed solution in this paper is based on the Jacobi method, but in comparison with other related works, it presents a different architecture that remarkably improves execution time, while reducing the number of consumed resources of the FPGA.

Detection of moving objects in railway using vision

In this paper, a new strategy to detect motion object in railway is presented, using vision and principal components analysis (PCA). For this purpose, a set of images of the railway static environment is first captured to obtain the transformation matrix that used in PCA. By means of this matrix, the successive images are projected in the transformation space and recovered. The motion detection is performed, evaluating the Euclidean distance between the original and recovered images. The image regions whose Euclidean distance are greater than a threshold, are considered like belonging to motion objects. The new of our system is the utilization of a method to obtain an adaptive threshold that allows to classify, within an image, zones without motion (background) and motion objects. A system with dynamic adjustment of this threshold is proposed, which it compensates to a great extent, illumination and others environmental conditions variations founded in outdoor spaces. Anyway, to show the validity and robustness of this method, the system has been implemented practically.

An Intelligent Architecture Based on Field Programmable Gate Arrays Designed to Detect Moving Objects by Using Principal Component Analysis

This paper presents a complete implementation of the Principal Component Analysis (PCA) algorithm in Field Programmable Gate Array (FPGA) devices applied to high rate background segmentation of images. The classical sequential execution of different parts of the PCA algorithm has been parallelized. This parallelization has led to the specific development and implementation in hardware of the different stages of PCA, such as computation of the correlation matrix, matrix diagonalization using the Jacobi method and subspace projections of images. On the application side, the paper presents a motion detection algorithm, also entirely implemented on the FPGA, and based on the developed PCA core. This consists of dynamically thresholding the differences between the input image and the one obtained by expressing the input image using the PCA linear subspace previously obtained as a background model. The proposal achieves a high ratio of processed images (up to 120 frames per second) and high quality segmentation results, with a completely embedded and reliable hardware architecture based on commercial CMOS sensors and FPGA devices.