Adaptive Multi-Camera System for Real Time Object Detection

In this paper we present an adaptive multi-camera system for real time object detection able to efficiently adjust the computational requirements of video processing blocks to the available processing power and the activity of the scene. The system is based on a two level adaptation strategy that works at local and at global level. Object detection is based on a Gaussian mixtures model background subtraction algorithm. Results show that the system can efficiently adapt the algorithm parameters without a significant loss in the detection accuracy.

Video Prioritization for Unequal Error Protection

We analyze the effect of packet losses in video sequences and propose a lightweight Unequal Error Protection strategy which, by choosing which packet is discarded, reduces strongly the Mean Square Error of the received sequence

High-Definition Video Distribution in 802.11g Home Wireless Networks

Multimedia distribution through wireless networks in the home environment presents a number of advantages which have fueled the interest of industry in recent years, such as simple connectivity and data delivery to a variety of devices. Together with High-Definition (HD) contents, multimedia wireless networks have been proposed for several applications, such as IPTV and Digital TV distribution for multiple devices in the home environment. For these scenarios, we propose a multicast distribution system for High-Definition video over 802.11 wireless networks based on rate-limited packet retransmission. We develop a limited rate ARQ system that retransmits packets according to the importance of their content (prioritization scheme) and according to their delay limitations (delay control). The performance of our proposed ARQ system is evaluated and compared with a similarly rate-limited ARQ algorithm. The results show a higher packet recovery rate and improvements in video quality for our proposed system.

A dual-band priority assignment algorithm for dynamic QoS resource management

Future high-quality consumer electronics will contain a number of applications running in a highly dynamic environment, and their execution will need to be efficiently arbitrated by the underlying platform software. The multimedia applications that currently execute in such similar contexts face frequent run-time variations in their resource demands, originated by the greedy nature of the multimedia processing itself. Changes in resource demands are triggered by numerous reasons (e.g. a switch in the input media compression format). Such situations require real-time adaptation mechanisms to adjust the system operation to the new requirements, and this must be done seamlessly to satisfy the user experience. One solution for efficiently managing application execution is to apply quality of service resource management techniques, based on assigning and enforcing resource contracts to applications. Most resource management solutions provide temporal isolation by enforcing resource assignments and avoiding any resource overruns. However, this has a clear limitation over the cost-effective resource usage. This paper presents a simple priority assignment scheme based on uniform priority bands to allow that greedy multimedia tasks incur in safe overruns that increase resource usage and do not threaten the timely execution of non-overrunning tasks. Experimental results show that the proposed priority assignment scheme in combination with a resource accounting mechanism preserves timely multimedia execution and delivery, achieves a higher cost-effective processor usage, and guarantees the execution isolation of non-overrunning tasks.

High-quality real-time temporal segmentation tool for video editing software

The increasing use of video editing software has resulted in a necessity for faster and more efficient editing tools. Here, we propose a lightweight high-quality video indexing tool that is suitable for video editing software.

Low-cost efficient interactive whiteboard

In this paper we present a low-cost efficient Interactive Whiteboard that, by fusing depth and video information provided by a low-cost depth camera, is able to detect and track user movements.

3D Videoconferencing system using spatial scalability

An implementation of a real-time 3D videoconferencing system using the currently available technology is presented. This appr oach is based on the side by side spatial compression of the stereoscopic images . The encoder and the decoder have b een implemented in a standard personal computer and a conventional 3D comp atible TV has been used to present the frames. Moreover, the users without 3D technology can use the system because 2D compatibility mode has been implemented in the decoder. The performance res ults show that a conventional computer can be used for encod ing/decoding audio and video streams and the delay in the transmission is lower than 200 ms.

Systematic analysis of the decoding delay on MVC decoders

We present a framework for the analysis of the decoding delay and communication latency in Multiview Video Coding. The application of this framework on MVC decoders allows minimizing the overall delay in immersive video-conference systems.

Monitoring packet loss impact in IPTV and 3DTV receivers

Considering a scalable video quality monitoring architecture to detect transmission errors at households, we propose a technique to detect packet losses in IPTV and Side-by-Side 3DTV and evaluate their impact on the perceived quality.

Low latency LDGM code for multimedia-packet stream in bursty packet loss networks

In this paper we present a FEC scheme based on simple LDGM codes to protect packetized multimedia streams. We demonstrate that simple LDGM codes working with a limited number of packets (small values of k) obtain recovery capabilities, against bursty packet losses, that are similar to those of other more complex FEC-based schemes designed for this type of channels.

Temporal segmentation tool for high-quality real time video editing software

The increasing use of video editing software requires faster and more efficient editing tools. As a first step, these tools perform a temporal segmentation in shots that allows a later building of indexes describing the video content. Here, we propose a novel real-time high-quality shot detection strategy, suitable for the last generation of video editing software requiring both low computational cost and high quality results. While abrupt transitions are detected through a very fast pixel-based analysis, gradual transitions are obtained from an efficient edge-based analysis. Both analyses are reinforced with a motion analysis that helps to detect and discard false detections. This motion analysis is carried out exclusively over a reduced set of candidate transitions, thus maintaining the computational requirements demanded by new applications to fulfill user needs.

Moving object detection for real-time augmented reality applications in a GPGPU

The last generation of consumer electronic devices is endowed with Augmented Reality (AR) tools. These tools require moving object detection strategies, which should be fast and efficient, to carry out higher level object analysis tasks. We propose a lightweight spatio-temporal-based non-parametric background-foreground modeling strategy in a General Purpose Graphics Processing Unit (GPGPU), which provides real-time high-quality results in a great variety of scenarios and is suitable for AR applications.

Desarrollo de sistema de medida del consumo de energía para la tarjeta BeagleBoard

En la actualidad existen cada vez más dispositivos móviles que utilizamos diariamente. Estos dispositivos usan las nuevas tecnologías inalámbricas, ya sean redes de telefonía, Wifi o Bluetooth, lo que conlleva un consumo de energía elevado. Estos dispositivos además tienen una limitación que es la capacidad de la batería. Un ejemplo claro son los smartphones, los usamos a diario y la batería dura un día o poco más. Dada esta problemática del alto consumo de energía el mundo de la electrónica de consumo se ve obligado a desarrollar aplicaciones y sistemas operativos que realicen un consumo de potencia más eficientes, baterías de otro tipo de composiciones, etc. Para lo que es necesario que exista una forma eficaz de medir el consumo de energía. En la actualidad, en el laboratorio del GDEM (Grupo de Diseño Electrónico y Microeletrónico) existen varias corrientes de acción a la hora de resolver o paliar esta problemática. Aquí podemos dividirlo en dos grupos: trabajos que se dediquen a conseguir que el sistema realice un consumo más eficiente de la energía y trabajos dedicados a realizar medidas más precisas de este consumo para que, a su vez, sean utilizadas por el propio sistema para decidir formas de actuar. Con estas motivaciones se ha diseñado una tarjeta capaz de medir la potencia consumida por la BeagleBoard usando un método de medida novedoso. Los resultados obtenidos validan el diseño y el presupuesto total de la fabricación ha sido inferior a diez euros. Por lo tanto, los objetivos se han cumplido fabricando una tarjeta caracterizada por su sencillez y su bajo coste, además de abrir la puerta a que, junto con un trabajo futuro, se consiga que la BeagleBoard sea capaz de conocer el consumo de potencia en tiempo real. ABSTRACT. At present, the number of mobile devices that we use normally are increasing. These devices use the new wireless technologies, whether telephone network, wireless or Bluetooth, which carries a large power consumption. These devices also have a limitation which is the battery capacity. One clear example is the smartphones, we use them daily and the battery is spent in a day. With this problem of high energy consumption the world of consumer electronics is forced to develop applications and operating systems with more efficient power consumption or a battery of other compositions. For that purposese it is necessary to have an effective way to measure energy consumption. In the GDEM (Microelectronic and Electronic Design Group) lab there are several streams action for solving or alleviating this problem. Here we can divide into two groups: jobs that are dedicated to getting the system that perform more efficient consumption of energy and works dedicated to doing more precise measures of this consumption. With these motivations we designed a board which was able to measure the power consumed by the BeagleBoard using a innovative measurement method. The results validate the design and the price of the board is less than 10 euros. Therefore, the goals have been accomplished by making a board which is characterized by its simplicity and low cost. It has also opened the door to, in a future work, the BeagleBoard be able to know the power consumption in real time by adding the necessary software.

Real-time Surveillance Application by Multiple Detectors and Compressive Trackers

A real-time surveillance system for IP network cameras is presented. Motion, part-body, and whole-body detectors are efficiently combined to generate robust and fast detections, which feed multiple compressive trackers. The generated trajectories are then improved using a reidentification strategy for long term operation.

Region-based moving object detection using spatially conditioned nonparametric models in a GPU

A novel GPU-based nonparametric moving object detection strategy for computer vision tools requiring real-time processing is proposed. An alternative and efficient Bayesian classifier to combine nonparametric background and foreground models allows increasing correct detections while avoiding false detections. Additionally, an efficient region of interest analysis significantly reduces the computational cost of the detections.