Resumen: La inseguridad es un problema que afecta en mayor o menor medida a todas las ciudades del mundo. Las ciudades más informatizadas hacen uso de la video-vigilancia para combatirla, montando en muchos de los casos centros de monitoreo con cientos de cámaras. En su mayoría, estos centros cuentan con grupos de personas para realizar la tarea de observación, sin embargo, este método no es suficiente y los organismos públicos deben lidiar un reclamo social por mayor transparencia y eficiencia en el accionar ante un delito. En este contexto, es que surge el presente proyecto, una plataforma de administración de cámaras y sensores, para apoyar a la gestión integral de la seguridad. Esta plataforma complementa técnicas de análisis automatizado de video, junto con una API para registrar eventos de tipo alarmas o alertas por parte de la ciudadanía y permitir el acceso a otras entidades (policía, bomberos, organizaciones vecinales) a ciertos recursos (los videos). Toda la información se centraliza en un sistema georreferenciado, en una arquitectura abierta y escalable, organizado en diferentes capas de información, con un sistema de organización de roles de accesos. Se presenta una discusión de la estructura ideada, de los algoritmos utilizados para el seguimiento, problemas propios que se suceden en este tipo de sistemas y los resultados preliminares obtenidos.Palabras-clave: Seguridad, Survillance, Plataforma abierta, Gobierno Digital. Open platform managing IP cameras and mobile applications for civil securityAbstract: Insecurity is a problem affecting many cities in the world. Most developed cities are using video surveillance systems to fight crime, mounting huge monitoring centers with hundreds of cameras. Many of these centers have people observing cameras in order to detect suspicious situations. However, this is not enough and public governments must deal with a social demand for more transparency and efficiency in actions against crime. In this context, a camera and

No abstract

No abstract

No abstract

Video surveillance systems are employed to prevent crime, mounting hundreds of cameras and sensors monitoring activities during the whole day. Due to the huge amount of video information generated in real time, these surveillance centers are requiring more technology and intelligence to support human operators in many complex situations. There are important analyses that could be realized with this video-data: from criminalistics event detection to particular object recognition. One important tool is License Plate Recognition (LPR) that helps detecting vehicles that could have been robbed. Although corporative solutions exist, these techniques require a lot of processing power and special located cameras, that not always could be afford by the local government. In this context, the proposed project is based on applying open-source LPR algorithms that runs on already existent surveillance cameras. These cameras are observing a complete scene (not just a line as it is commonly used), so LPR algorithms are rather slow, processing only 1 image per second. For this reason, the objective is to improve the performance combining a parallel LPR running on graphic processor units (GPU) and object tracking algorithms. This work describes the ongoing implementation, the techniques currently used for object tracking and LPR implementation, and exposes results regarding the efficiency of the solution.