José Antonio Cerrada

Improved Method for Object Recognition in Complex Scenes by Fusioning 3-D Information and RFID Technology

This work analyzes a new method for object recognition in complex scenes combining vision-based techniques applied to the 3-D data obtained using range sensors and object identification coming from radio frequency tags (radio frequency identification (RFID) technology). Three-dimensional vision-based algorithms for object recognition have many restrictions in practical applications, i.e., uncertainty, incapability for real-time tasks, etc., but they work well for pose determination once the object is recognized. On the other hand, RFID technology allows us to detect the presence of specific objects in a scene, but it cannot provide their localization, at least not with the accuracy required in applications such as ours. In this paper, we present a new and powerful recognition method obtained by fusing both techniques. The phases of the method are described, and abundant experimentation results are included. An in-depth performance analysis has been carried out to demonstrate the recognition improvements achieved by the algorithm when RFID assistance is considered. It helps to confirm the robustness of this fusion approach and prove its effectiveness. A final discussion is included, concerning what should be the most adequate size of the object database for optimal algorithm exploitation.

A method to design multirate controllers for plants sampled at a low rate

Classical discrete control systems allow control of the output of a plant at sampling instants. If control of the output between sampling instants is required, a multirate controller can be used. An analytical procedure is developed that allows feedforward control of the output at multirate instants and feedback control at sampling instants. The method proposed is a practical approach to the model-matching problem and takes into account the intersampling dynamics of the system. >

A New Control Scheme of Single-link Flexible Manipulators Robust to Payload Changes

A new scheme is presented in this paper to control single-link flexiblemanipulators. The objective is to control the tip position of the flexiblearm in the presence of joint friction and payload changes. The controlscheme is based on two nested loops: an inner feedback loop to control themotor position which is robust to joint friction, and an outer loop tocontrol the tip position which is robust to payload changes. This outer loopis composed of a feedforward term and a feedback term. This results in asimple control law that needs minimal computing effort and, thus, can beused for real time control of flexible arms. The proposed method is generalin the sense that it can be applied to very different arm structures anddiverse sensor systems configurations. Results corresponding to twodifferent arm setups are presented.

Managing RFID Sensors Networks with a General Purpose RFID Middleware

RFID middleware is anticipated to one of the main research areas in the field of RFID applications in the near future. The Data EPC Acquisition System (DEPCAS) is an original proposal designed by our group to transfer and apply fundamental ideas from System and Data Acquisition (SCADA) systems into the areas of RFID acquisition, processing and distribution systems. In this paper we focus on how to organize and manage generic RFID sensors (edge readers, readers, PLCs, etc…) inside the DEPCAS middleware. We denote by RFID Sensors Networks Management (RSNM) this part of DEPCAS, which is built on top of two new concepts introduced and developed in this work: MARC (Minimum Access Reader Command) and RRTL (RFID Reader Topology Language). MARC is an abstraction layer used to hide heterogeneous devices inside a homogeneous acquisition network. RRTL is a language to define RFID Reader networks and to describe the relationship between them (concentrator, peer to peer, master/submaster).

Fusion of 3D Vision Techniques and RFID Technology for Object Recognition in Complex Scenes

This work presents a new method for object recognition in complex scenes combining vision-based techniques applied to the 3D data obtained using range sensors, and object identification coming from Radio Frequency tags (RFID technology). Vision based algorithms for 3D recognition have many restrictions in practical applications: uncertainty, incapability for real time tasks; but they work well for pose determination once the object is recognized. On the other hand, RFID technology allows detecting the presence of specific objects in a scene but it cannot provide their localization. In this paper, we show the powerful recognition tool obtained by fusioning both techniques. The phases of the proposed procedure are described and an in depth experimental demonstration is included. A performance analysis of the method is made by comparing the recognition algorithm with and without the RFID phase. Obtained results, concerning to success rate increasing and computational cost reduction, confirm the robustness of this fusion approach and prove its effectiveness.

Indoor Positioning System Using Depth Maps and Wireless Networks

This work presents a new Indoor Positioning System (IPS) based on the combination of WiFi Positioning System (WPS) and depth maps, for estimating the location of people. The combination of both technologies improves the efficiency of existing methods, based uniquely on wireless positioning techniques. While other positioning systems force users to wear special devices, the system proposed in this paper just requires the use of smartphones, besides the installation of RGB-D sensors in the sensing area. Furthermore, the system is not intrusive, being not necessary to know people’s identity. The paper exposes the method developed for putting together and exploiting both types of sensory information with positioning purposes: the measurements of the level of the signal received from different access points (APs) of the wireless network and the depth maps provided by the RGB-D cameras. The obtained results show a significant improvement in terms of positioning with respect to common WiFi-based systems.

Dynamic control of a reconfigurable stair-climbing mobility system

Electric-powered wheelchairs improve the mobility of people with physical disabilities, but the problem to deal with certain architectural barriers has not been resolved satisfactorily. In order to solve this problem, a stair-climbing mobility system SCMS was developed. This paper presents a practical dynamic control system that allows the SCMS to exhibit a successful climbing process when faced with typical architectural barriers such as curbs, ramps, or staircases. The implemented control system depicts high simplicity, computational efficiency, and the possibility of an easy implementation in a microprocessor-/microcontroller-based system. Finally, experiments are included to support theoretical results.

A LITERATURE REVIEW ON FEATURE DIAGRAM PRODUCT COUNTING AND ITS USAGE IN SOFTWARE PRODUCT LINE ECONOMIC MODELS

In software product line engineering, feature diagrams are a popular means to represent the similarities and differences within a family of related systems. In addition, feature diagrams implicitly model valuable information that can be used in economic models to estimate the cost savings of a product line. In particular, this paper reviews existing proposals on computing the total number of products modeled with a feature diagram and, given a feature, the number of products that implement it. The paper also reviews the economic information that can be estimated when such numbers are known. Thus, this paper contributes by bringing together previously-disparate streams of work: the automated analysis of feature diagrams and economic models for product lines.

An Improved Indoor Positioning System Using RGB-D Cameras and Wireless Networks for Use in Complex Environments

This work presents an Indoor Positioning System to estimate the location of people navigating in complex indoor environments. The developed technique combines WiFi Positioning Systems and depth maps, delivering promising results in complex inhabited environments, consisting of various connected rooms, where people are freely moving. This is a non-intrusive system in which personal information about subjects is not needed and, although RGB-D cameras are installed in the sensing area, users are only required to carry their smart-phones. In this article, the methods developed to combine the above-mentioned technologies and the experiments performed to test the system are detailed. The obtained results show a significant improvement in terms of accuracy and performance with respect to previous WiFi-based solutions as well as an extension in the range of operation.

A Scalable Approach to Exact Model and Commonality Counting for Extended Feature Models

A software product line is an engineering approach to efficient development of software product portfolios. Key to the success of the approach is to identify the common and variable features of the products and the interdependencies between them, which are usually modeled using feature models. Implicitly, such models also include valuable information that can be used by economic models to estimate the payoffs of a product line. Unfortunately, as product lines grow, analyzing large feature models manually becomes impracticable. This paper proposes an algorithm to compute the total number of products that a feature model represents and, for each feature, the number of products that implement it. The inference of both parameters is helpful to describe the standardization/parameterization balance of a product line, detect scope flaws, assess the product line incremental development, and improve the accuracy of economic models. The paper reports experimental evidence that our algorithm has better runtime performance than existing alternative approaches.