Towards a real-time 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors

In this project, we propose the implementation of a 3D object recognition system which will be optimized to operate under demanding time constraints. The system must be robust so that objects can be recognized properly in poor light conditions and cluttered scenes with significant levels of occlusion. An important requirement must be met: the system must exhibit a reasonable performance running on a low power consumption mobile GPU computing platform (NVIDIA Jetson TK1) so that it can be integrated in mobile robotics systems, ambient intelligence or ambient assisted living applications. The acquisition system is based on the use of color and depth (RGB-D) data streams provided by low-cost 3D sensors like Microsoft Kinect or PrimeSense Carmine. The range of algorithms and applications to be implemented and integrated will be quite broad, ranging from the acquisition, outlier removal or filtering of the input data and the segmentation or characterization of regions of interest in the scene to the very object recognition and pose estimation. Furthermore, in order to validate the proposed system, we will create a 3D object dataset. It will be composed by a set of 3D models, reconstructed from common household objects, as well as a handful of test scenes in which those objects appear. The scenes will be characterized by different levels of occlusion, diverse distances from the elements to the sensor and variations on the pose of the target objects. The creation of this dataset implies the additional development of 3D data acquisition and 3D object reconstruction applications. The resulting system has many possible applications, ranging from mobile robot navigation and semantic scene labeling to human-computer interaction (HCI) systems based on visual information.

Advances in camera trap data management tools: Towards collaborative development and integration with GIS

Camera traps have become a widely used technique for conducting biological inventories, generating a large number of database records of great interest. The main aim of this paper is to describe a new free and open source software (FOSS), developed to facilitate the management of camera-trapped data which originated from a protected Mediterranean area (SE Spain). In the last decade, some other useful alternatives have been proposed, but ours focuses especially on a collaborative undertaking and on the importance of spatial information underpinning common camera trap studies. This FOSS application, namely, “Camera Trap Manager” (CTM), has been designed to expedite the processing of pictures on the .NET platform. CTM has a very intuitive user interface, automatic extraction of some image metadata (date, time, moon phase, location, temperature, atmospheric pressure, among others), analytical (Geographical Information Systems, statistics, charts, among others), and reporting capabilities (ESRI Shapefiles, Microsoft Excel Spreadsheets, PDF reports, among others). Using this application, we have achieved a very simple management, fast analysis, and a significant reduction of costs. While we were able to classify an average of 55 pictures per hour manually, CTM has made it possible to process over 1000 photographs per hour, consequently retrieving a greater amount of data.

Comunicación y salud: el ejemplo histórico de la revista HIGIA (1935-1938)

Antecedentes: El trabajo de investigación que se desarrolla a continuación, se suma a otras investigaciones que se han ocupado de la divulgación higiénico-sanitaria en España durante el período de entreguerras al aprovechar el interés historiográfico que ofrece el de una revista como HIGIA. Objetivo: Analizar la revista de divulgación higiénico-sanitaria HIGIA (1935-1938) desde una perspectiva bibliométrica y documental. Metodología: El material de estudio está conformado por todos los números de la revista Higia. Tras una primera valoración de los contenidos se establecieron las áreas temáticas abordadas en las diferentes secciones y se clasificaron en 24 categorías. Se hizo un estudio de la productividad de los colaboradores que aportaron documentos a la revista. Para su análisis se confeccionó una base de datos gestionada por la aplicación Microsoft Excell del paquete ofimático Office 2010. Resultados: El período de publicación de Higia comprendido entre enero de 1935 y junio de 1938, totaliza 42 meses y 31 ejemplares, con una periodicidad de veintiún números mensuales, nueve bimensuales y uno trimestral. La secciones estudiadas aportaron un resultado de 31 Portadas, 11 Editoriales, 324 Colaboraciones, 16 textos de Ejercicio físico y consejos higiénico dietéticos, 1105 Anuncios, 110 contenidos que conforman la Correspondencia, 16 Publicaciones recibidas en la redacción de la revista, 5 Programaciones de eventos, 1 Concurso, 522 Consejos sanitarios, y 5 dibujos, un obituario y una página de Humor que se incluían en “Otras secciones”. Participaron en su producción 112 autores; de ellos un máximo productor con 29 colaboraciones. Las temáticas más abordadas acumulando un 55 % del total, fueron la Higiene General (13%), la Puericultura e Higiene Infantil ( 11%), la Higiene Nerviosa y Psíquica y las Relaciones de Pareja ( 9,2%) y la Higiene digestiva ( 7%). Conclusiones: La revista Higia constituye un compendio amplio de todos los aspectos que tenían que ver con la salud, la higiene, la maternidad, la crianza de los niños, las relaciones de pareja, la alimentación, las repercusiones inmediatas de la guerra, las tendencias en mobiliario, la estética femenina, la introducción de nuevas estrategias de salud en cuanto a prevención y vacunas.