Efficient hybrid monocular-stereo approach to on-board, video-based traffic sign detection and tracking

In this paper we propose an innovative method for the automatic detection and tracking of road traffic signs using an onboard stereo camera. It involves a combination of monocular and stereo analysis strategies to increase the reliability of the detections such that it can boost the performance of any traffic sign recognition scheme. Firstly, an adaptive color and appearance based detection is applied at single camera level to generate a set of traffic sign hypotheses. In turn, stereo information allows for sparse 3D reconstruction of potential traffic signs through a SURF-based matching strategy. Namely, the plane that best fits the cloud of 3D points traced back from feature matches is estimated using a RANSAC based approach to improve robustness to outliers. Temporal consistency of the 3D information is ensured through a Kalman-based tracking stage. This also allows for the generation of a predicted 3D traffic sign model, which is in turn used to enhance the previously mentioned color-based detector through a feedback loop, thus improving detection accuracy. The proposed solution has been tested with real sequences under several illumination conditions and in both urban areas and highways, achieving very high detection rates in challenging environments, including rapid motion and significant perspective distortion

Analysis of pixel-mapping rounding on geometric distortion as a prediction for view synthesis distortion

We analyze the performance of the geometric distortion, incurred when coding depth maps in 3D Video, as an estimator of the distortion of synthesized views. Our analysis is motivated by the need of reducing the computational complexity required for the computation of synthesis distortion in 3D video encoders. We propose several geometric distortion models that capture (i) the geometric distortion caused by the depth coding error, and (ii) the pixel-mapping precision in view synthesis. Our analysis starts with the evaluation of the correlation of geometric distortion values obtained with these models and the actual distortion on synthesized views. Then, the different geometric distortion models are employed in the rate-distortion optimization cycle of depth map coding, in order to assess the results obtained by the correlation analysis. Results show that one of the geometric distortion models is performing consistently better than the other models in all tests. Therefore, it can be used as a reasonable estimator of the synthesis distortion in low complexity depth encoders.

Comparación de desempeño de una cámara de profundidad comercial y un LIDAR en explotaciones agrícolas.

Este estudio presenta una comparativa entre un LIDAR modelo LMS-111 (Sick Ltd.) y una cámara de profundidad de uso doméstico: Kinect (Microsoft Corporation), orientada a determinar las condiciones de uso de uno y otro sensor, así como sus ventajas e inconvenientes cuando son empleados en condiciones de campo, en una explotación agrícola. Para ello se realizaron diversos ensayos en una parcela experimental del CSIC-CAR de Arganda del Rey, España. Para los ensayos ambos sensores fueron instalados en un tractor operado remotamente diseñado y construido en el marco del proyecto europeo RHEA. Dicho tractor realizó dos recorridos diferentes: el primero se efectuó en paralelo a un muro y el segundo paralelo a una hilera de olivos. El primer ensayo se realizó con el propósito de cuantificar la uniformidad de las mediciones de ambos sensores y el segundo para validar los resultados en un cultivo real. Los recorridos se realizaron empleando cuatro marchas diferentes, con el objetivo de determinar si los diferentes regímenes de operación del motor influyen sobre la precisión de los sensores. Los resultados muestran que el LIDAR posee un mayor alcance máximo de medición, pero una resolución menor frente a Kinect, muestran además que el LIDAR puede ser operado a cualquier hora del día y condición meteorológica, mientras que Kinect, no puede operar en exteriores, salvo en horas del día con baja intensidad lumínica. Por otra parte la gran desventaja del LIDAR es su coste, 30 veces más alto que Kinect.

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.

Bounded non-deterministic planning for multimedia adaptation

This paper proposes a novel combination of artificial intelligence planning and other techniques for improving decision-making in the context of multi-step multimedia content adaptation. In particular, it describes a method that allows decision-making (selecting the adaptation to perform) in situations where third-party pluggable multimedia conversion modules are involved and the multimedia adaptation planner does not know their exact adaptation capabilities. In this approach, the multimedia adaptation planner module is only responsible for a part of the required decisions; the pluggable modules make additional decisions based on different criteria. We demonstrate that partial decision-making is not only attainable, but also introduces advantages with respect to a system in which these conversion modules are not capable of providing additional decisions. This means that transferring decisions from the multi-step multimedia adaptation planner to the pluggable conversion modules increases the flexibility of the adaptation. Moreover, by allowing conversion modules to be only partially described, the range of problems that these modules can address increases, while significantly decreasing both the description length of the adaptation capabilities and the planning decision time. Finally, we specify the conditions under which knowing the partial adaptation capabilities of a set of conversion modules will be enough to compute a proper adaptation plan.

Adaptable Bayesian classifier for spatiotemporal nonparametric moving object detection strategies

Electronic devices endowed with camera platforms require new and powerful machine vision applications, which commonly include moving object detection strategies. To obtain high-quality results, the most recent strategies estimate nonparametrically background and foreground models and combine them by means of a Bayesian classifier. However, typical classifiers are limited by the use of constant prior values and they do not allow the inclusion of additional spatiodependent prior information. In this Letter, we propose an alternative Bayesian classifier that, unlike those reported before, allows the use of additional prior information obtained from any source and depending on the spatial position of each pixel.

A framework for the analysis and optimization of encoding latency for multiview video

We present a novel framework for the analysis and optimization of encoding latency for multiview video. Firstly, we characterize the elements that have an influence in the encoding latency performance: (i) the multiview prediction structure and (ii) the hardware encoder model. Then, we provide algorithms to find the encoding latency of any arbitrary multiview prediction structure. The proposed framework relies on the directed acyclic graph encoder latency (DAGEL) model, which provides an abstraction of the processing capacity of the encoder by considering an unbounded number of processors. Using graph theoretic algorithms, the DAGEL model allows us to compute the encoding latency of a given prediction structure, and determine the contribution of the prediction dependencies to it. As an example of DAGEL application, we propose an algorithm to reduce the encoding latency of a given multiview prediction structure up to a target value. In our approach, a minimum number of frame dependencies are pruned, until the latency target value is achieved, thus minimizing the degradation of the rate-distortion performance due to the removal of the prediction dependencies. Finally, we analyze the latency performance of the DAGEL derived prediction structures in multiview encoders with limited processing capacity.

Refined facial disparity maps for automatic creation of 3D avatars

We propose a new method to automatically refine a facial disparity map obtained with standard cameras and under conventional illumination conditions by using a smart combination of traditional computer vision and 3D graphics techniques. Our system inputs two stereo images acquired with standard (calibrated) cameras and uses dense disparity estimation strategies to obtain a coarse initial disparity map, and SIFT to detect and match several feature points in the subjects face. We then use these points as anchors to modify the disparity in the facial area by building a Delaunay triangulation of their convex hull and interpolating their disparity values inside each triangle. We thus obtain a refined disparity map providing a much more accurate representation of the the subjects facial features. This refined facial disparity map may be easily transformed, through the camera calibration parameters, into a depth map to be used, also automatically, to improve the facial mesh of a 3D avatar to match the subjects real human features.

Experimental investigation of radio signal propagation in scientific facilities for telerobotic applications

Understanding the radio signal transmission characteristics in the environment where the telerobotic application is sought is a key part of achieving a reliable wireless communication link between a telerobot and a control station. In this paper, wireless communication requirements and a case study of a typical telerobotic application in an underground facility at CERN are presented. Then, the theoretical and experimental characteristics of radio propagation are investigated with respect to time, distance, location and surrounding objects. Based on analysis of the experimental findings, we show how a commercial wireless system, such as Wi-Fi, can be made suitable for a case study application at CERN.

Energy Management Module for Mobile Robots in Hostile Environments

In hostile environments at CERN and other similar scientific facilities, having a reliable mobile robot system is essential for successful execution of robotic missions and to avoid situations of manual recovery of the robots in the event that the robot runs out of energy. Because of environmental constraints, such mobile robots are usually battery-powered and hence energy management and optimization is one of the key challenges in this field. The ability to know beforehand the energy consumed by various elements of the robot (such as locomotion, sensors, controllers, computers and communication) will allow flexibility in planning or managing the tasks to be performed by the robot.

Model Based On-Line Energy Prediction System for Semi-Autonomous Mobile Robots

Maximizing energy autonomy is a consistent challenge when deploying mobile robots in ionizing radiation or other hazardous environments. Having a reliable robot system is essential for successful execution of missions and to avoid manual recovery of the robots in environments that are harmful to human beings. For deployment of robots missions at short notice, the ability to know beforehand the energy required for performing the task is essential. This paper presents a on-line method for predicting energy requirements based on the pre-determined power models for a mobile robot. A small mobile robot, Khepera III is used for the experimental study and the results are promising with high prediction accuracy. The applications of the energy prediction models in energy optimization and simulations are also discussed along with examples of significant energy savings.

Haptic teleoperation of mobile robots for augmentation of operator perception in environments with low-wireless signal

Wireless teleoperation of field robots for maintenance, inspection and rescue missions is often performed in environments with low wireless connectivity, caused by signal losses from the environment and distance from the wireless transmitters. Various studies from the literature have addressed these problems with time-delay robust control systems and multi-hop wireless relay networks. However, such approaches do not solve the issue of how to present wireless data to the operator to avoid losing control of the robot. Despite the fact that teleoperation for maintenance often already involves haptic devices, no studies look at the possibility of using this existing feedback to aid operators in navigating within areas of variable wireless connectivity. We propose a method to incorporate haptic information into the velocity control of an omnidirectional robot to augment the operators perception of wireless signal strength in the remote environment. In this paper we introduce a mapping between wireless signal strength from multiple receivers to the force feedback of a 6 Degree of Freedom haptic master and evaluate the proposed approach using experimental data and randomly generated wireless maps

Spatial sampling methods for improved communication for wireless relay robots

Having reliable wireless communication in a network of mobile robots is an ongoing challenge, especially when the mobile robots are given tasks in hostile or harmful environments such as radiation environments in scientific facilities, tunnels with large metallic components and complicated geometries as found at CERN. In this paper, we propose a decentralised method for improving the wireless network throughput by optimizing the wireless relay robot position to receive the best wireless signal strength using implicit spatial diversity concepts and gradient-search algorithms. We experimentally demonstrate the effectiveness of the proposed solutions with a KUKA Youbot omni-directional mobile robot. The performance of the algorithms is compared under various scenarios in an underground scientific facility at CERN.

Efecto del tamaño de la ventana de promediado y la histéresis variable en algoritmos de handover horizontal en redes convergentes

En las redes convergentes inalámbricas, el traspaso horizontal entre distintos puntos de acceso de la red WLAN es una gran fuente de degradación de la calidad de la VoIP y otros servicios conversacionales en tiempo real. Esto es debido a que este tipo de redes no fueron concebidas originalmente para soportar este tipo de servicios, y los traspasos siguen un protocolo ¿cortar antes de realizar¿, produciéndose interrupciones en la comunicación motivadas por el tiempo que necesitan los terminales en volver a asociarse a la red. En este artículo se estudia el efecto que tienen el tamaño de la ventana de promediado de la señal, la histéresis variable y el retardo del handover por parecido entre potencia de puntos de acceso de destino sobre el número de traspasos y las caídas de la potencia de señal por debajo del valor de sensibilidad del terminal, causantes principales de las interrupciones en la comunicación, y, con ello, de la degradación de la calidad de las comunicaciones.

Despliegues de femtoceldas LTE en interiores comparación con otras tecnologías inalámbricas

Long Term Evolution (LTE) has appeared with the aim of improving the performance of 3G networks, increasing spectral efficiency and peak rates both at downlink and uplink, reducing latency and increasing flexibility of frequency allocation. Therefore, LTE is expected to have a key role in the development of wireless networks and services in the next years, and, of course, in specific dedicated in-building solutions. Due to that fact, an analysis of LTE performance in indoor scenarios in terms of capacity and grade of service is essential, as well as its comparison with other indoor solutions, pointing out the technical challenges derived, and describing and proposing performance assessment rules to be used in LTE deployments.