Francisco Javier Ferrández-Pastor

A vision-based system for intelligent monitoring: human behaviour analysis and privacy by context.

Due to progress and demographic change, society is facing a crucial challenge related to increased life expectancy and a higher number of people in situations of dependency. As a consequence, there exists a significant demand for support systems for personal autonomy. This article outlines the vision@home project, whose goal is to extend independent living at home for elderly and impaired people, providing care and safety services by means of vision-based monitoring. Different kinds of ambient-assisted living services are supported, from the detection of home accidents, to telecare services. In this contribution, the specification of the system is presented, and novel contributions are made regarding human behaviour analysis and privacy protection. By means of a multi-view setup of cameras, peoples behaviour is recognised based on human action recognition. For this purpose, a weighted feature fusion scheme is proposed to learn from multiple views. In order to protect the right to privacy of the inhabitants when a remote connection occurs, a privacy-by-context method is proposed. The experimental results of the behaviour recognition method show an outstanding performance, as well as support for multi-view scenarios and real-time execution, which are required in order to provide the proposed services.

Developing Ubiquitous Sensor Network Platform Using Internet of Things: Application in Precision Agriculture

The application of Information Technologies into Precision Agriculture methods has clear benefits. Precision Agriculture optimises production efficiency, increases quality, minimises environmental impact and reduces the use of resources (energy, water); however, there are different barriers that have delayed its wide development. Some of these main barriers are expensive equipment, the difficulty to operate and maintain and the standard for sensor networks are still under development. Nowadays, new technological development in embedded devices (hardware and communication protocols), the evolution of Internet technologies (Internet of Things) and ubiquitous computing (Ubiquitous Sensor Networks) allow developing less expensive systems, easier to control, install and maintain, using standard protocols with low-power consumption. This work develops and test a low-cost sensor/actuator network platform, based in Internet of Things, integrating machine-to-machine and human-machine-interface protocols. Edge computing uses this multi-protocol approach to develop control processes on Precision Agriculture scenarios. A greenhouse with hydroponic crop production was developed and tested using Ubiquitous Sensor Network monitoring and edge control on Internet of Things paradigm. The experimental results showed that the Internet technologies and Smart Object Communication Patterns can be combined to encourage development of Precision Agriculture. They demonstrated added benefits (cost, energy, smart developing, acceptance by agricultural specialists) when a project is launched.

Vision Based Extraction of Dynamic Gait Features Focused on Feet Movement Using RGB Camera

Bipedal gait involves the entire body but some subsystems are decisive for gait while other parts of the body play complementary roles (dynamic balance, harmony of movement, etc.). We have proposed a functional specification of gait. It is based on logical expression format and takes into account only observational kinematic aspects. The specification is open enough that it can be used in other gait analysis problems (rehabilitation, sport, children, etc.).

A Proposal for a Distributed Computational Framework in IoT Context

The new internet of things paradigm allows for small devices with sensing, processing and communication capabilities to be designed, which enable the development of sensors, embedded devices and other ‘things’ ready to understand the environment. In this paper, a distributed model and an architecture for internet of things paradigm is proposed to perform complex computational tasks and run advanced applications. This novel computing system defines a network design with different levels which combines sensing and processing capabilities based on the Mobile Cloud Computing paradigm.

Vision Based Gait Analysis for Frontal View Gait Sequences Using RGB Camera

In this paper we propose a vision based gait analysis approach to work with frontal view sequences. The main issue of sagittal view gait sequences is the physical space required to record them. We propose two different approaches to obtain heel strike and toe off with frontal gait, both of them are based in the time series of the difference of component y of both feet. In the former, the zero crosses are used to determine the range in which heel strike and toe off occurs. In the latter, the maxima and minima are used instead. Testing our approach with our own dataset show that it is possible to obtain heel strike and toe off events using only frontal view gait sequences recorded with an RGB camera. Results show as well that it is possible to classify between normal and abnormal gait using frontal view.

A Vision System for Intelligent Monitoring of Activities of Daily Living at Home

Social progress and demographic changes favor increased life expectancy and the number of people in situations of dependency. As a consequence, the demand for support systems for personal autonomy is increasing. This article outlines the vision @ home project, whose goal is the development of vision-based services for monitoring and recognition of the activity carried out by individuals in the home. Incorporating vision devices in private settings is justified by its power to extract large amounts of data with low cost but must safeguard the privacy of individuals. The vision system we have designed incorporates a knowledge base containing information from the environment, parameters of different cameras used, human behavior modeling and recognition, and information about people and objects. By analyzing the scene, we infer its context, and provide a privacy filter which is able to return textual information, as well as synthetic and real images.

Distributed Optimization of Finite Resource Planning for Asincronous and Non-linear Systems: Application to Power Management

This paper introduces a Multiagent System (MAS) for optimal resource planning in non-linear systems. The distributed planning strategy, which is based on interaction of agents, is composed by two phases. The first one uses an iterative double auction based protocol and allows requesting for getting back the previously allocated resources in order to establish a better planning. The second phase takes the previous resource allocation for finding better alternative paths. The proposal has been applied into our house-lab power system for optimize the use of renewable power supplies. Power production and requirements are simulated using the average of power consumption measures of each component.

Gait Analysis Using Computer Vision Based on Cloud Platform and Mobile Device

Frailty and senility are syndromes that affect elderly people. The ageing process involves a decay of cognitive and motor functions which often produce an impact on the quality of life of elderly people. Some studies have linked this deterioration of cognitive and motor function to gait patterns. Thus, gait analysis can be a powerful tool to assess frailty and senility syndromes. In this paper, we propose a vision-based gait analysis approach performed on a smartphone with cloud computing assistance. Gait sequences recorded by a smartphone camera are processed by the smartphone itself to obtain spatiotemporal features. These features are uploaded onto the cloud in order to analyse and compare them to a stored database to render a diagnostic. The feature extraction method presented can work with both frontal and sagittal gait sequences although the sagittal view provides a better classification since an accuracy of 95% can be obtained.

Scheduler for Automatic Management of Maintenance Jobs in Large-Size Systems: A Case Study Applied to Smart City

Maintenance of systems such as infrastructure, services and equipment on city context requires a complex management process in order to provide quality services, comply with regulations and extend lifespan of urban equipment and infrastructure without neglecting the proper use of resources to execute maintenance jobs. Cities can generate hundreds or thousands of maintenance jobs during a particular time period. These jobs can be generated automatically by equipment or can be reported by citizens/users. This work introduces a scheduling architecture for automatic management of maintenance jobs. The proposal is able to handle preventive and corrective maintenance jobs looking for available human and instrumental resources during the common time period required by the job to be executed. The scheduler uses intelligent strategies to satisfy constraints of each job in order to get a scheduling according to the criterion of the manager of maintenance. A case study is applied to smart city.

Electromagnetic Multi-frequency Model and Differential Measuring in Remote Sensing Applications

The interaction between electromagnetic waves and matter has led to the development of applications to detect and characterise them. The conventional systems use the emission, transmission and reception of waves at a specific frequency range to detect medium parameters (constant dielectric, permittivity, conductivity or permeability) of an analysed area. The interaction between the electromagnetic wave and the analysed medium depends on the range of frequency used. This phenomenon is used in different disciplines and working environments, geoscience or medical disciplines are examples where the use of electromagnetic waves provides non-intrusive applications with clear benefits. Each frequency of signal transmitted and received is analysed to determine the interaction produced in absolute measurements. In this work a method based in differential measurement technique is proposed as a novel way of detecting and characterizing electromagnetic matter characteristics. The theoretical results show that it is possible to obtain benefits from the behaviour of the wave-medium interaction using differential measurement on reception of electromagnetic waves at different frequencies. Differential measures introduce advantages in detection processes and increase development possibilities of new non-intrusive applications.