Pasar al contenido principal

ANALISIS MULTIMODAL DE ESCENAS PARA APLICACIONES DE MONITORIZACION

PGC2018-098817-A-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de Generación de Conocimiento y Fortalecimiento Científico y Tecnológico del Sistema de I+D+i
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D (Excelencia / Generación de Conocimiento)
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ZARAGOZA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Control inteligente mediante escalado dinámico voltaje-frecuencia (DVFS) de la temperatura en procesadores embebidos, Intelligent control of temperature with dynamic voltage-frequency scaling (DVFS) in embedded processors

  • Hernández-Almudi, P.
  • Suárez, D.
  • Montijano, E.
  • Merino, J.
[EN] The increment in computing power of embedded processors has fueled a revolution in many application domains such as mobile computing or robotics. Dissipating the energy consumed by those processors on a very small area has made power management a first-order constraint. On one hand, it is impossible to directly apply active dissipation techniques. On the other hand, design requirements prevent the correct behaviour of known passive detection techniques. To alleviate this problem, we present a new control approach to keep the temperature of the system controlled through the Dynamic Voltage and Frequency Scaling (DVFS) system. The solution includes a feedback control scheme together with a supervisor that adjusts the control parameters based on the system load. To ease experimentation without compromising real use, the code can run in user space and as a Linux kernel driver. The experiments in a real platform prove that, compared to the current control methodology, our approach handles the processor’s temperature with more precision, keeping similar performance levels in the execution of well known benchmarks., [ES] El aumento de la capacidad de cálculo de los procesadores embebidos ha generado una revolución en numerosos dominios de aplicación como la computación móvil o la robótica. La disipación del consumo producido por estos cálculos en una superficie tan pequeña hace que la disipación de energía suponga un problema de primer orden. Por un lado, no es posible aplicar técnicas de disipación activas y, por otro, las exigencias de diseño impiden una correcta disipación pasiva. Para resolver este problema, este trabajo presenta una metodología de control para el mantenimiento de una temperatura bajo control mediante el uso de escalado dinámico de la frecuencia del procesador (DVFS, Dynamic Voltage Frequency Scaling). La solución incluye un esquema de control de temperatura basado en realimentación junto con un supervisor que ajusta los parámetros del controlador en base al tipo de carga del trabajo. La estrategia de control propuesta se ha implementado tanto en espacio de usuario como driver dentro del kernel de Linux. Los experimentos realizados en una plataforma real demuestran que, comparado con el control existente en la actualidad, nuestra propuesta es capaz de gestionar la temperatura del procesador con más precisión, manteniendo niveles similares de eficiencia en la ejecución de benchmarks conocidos., Este artículo ha sido financiado parcialmente por los proyectos PGC2018-098817-A-I00 (MCIU/AEI/FEDER, UE), MIG20201006, PID2019-105660RB-C21 ( MINECO/AEI/FEDER), Grupos T58 20R y T45 20R ( Gobierno de Aragón) y FEDER 2014-2020 “Construyendo Europa desde Aragón”. Los autores agradecen el apoyo recibido.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Planificación de trayectorias en sistemas multirobot utilizando redes de Petri. Resultados y problemas abiertos, Path planning of multirobot systems using Petri net models. Results and open problems

  • Mahulea, C.
  • González, R.
  • Montijano, E.
  • Silva, M.
[EN] This paper presents a trajectory planning approach in multirobot systems based on Petri net models. This type of models is very useful for high-level specifications since, in this case, the classical planning methods (potential functions, RRT algorithms, RRT*) cannot be used being dicult to determine a priori the sequence of configurations for each robot. This work presents the formal definition of the Robot Motion Petri net t hat i s obtained from a partition of the environment in cells. Using the s tructure of the Petri net, in case of specifications defined as Boolean or Linear Temporal Logic (LTL) formulas, dierent optimization problems are presented that can be used to obtain trajectories for robots. The main advantage of models based on Petri nets is their scalability with respect to the number of robots. This makes it possible to reciently solve planning problems with a large number of robots. In the second part of the paper, some extensions and new results for distributed planning in unknown environments and with partial communications between robots are presented., [ES] Este trabajo presenta una estrategia de planificacón de trayectorias en equipos de robots moviles basada en el uso de modelos definidos con redes de Petri. Estos tipos de modelos son muy útiles para especificaciones de alto nivel ya que, en este caso, los métodos clásicos de planificación (funciones potenciales, algoritmos RRT, RRT*) no se pueden utilizar, siendo difícil determinar a priori la secuencia de configuraciones para cada robot. Este trabajo presenta la definición formal de la Red de Petri de Movimiento de Robots que se obtiene a partir de una partición del entorno en celdas. Utilizando la estructura de la red de Petri, en caso de especificaciones definidas como fórmulas Booleanas o fórmulas en lógica temporal lineal (LTL), se presentan diferentes problemas de optimización que se pueden utilizar para obtener trayectorias para los robots. La principal ventaja de los modelos basados en redes de Petri es su escalabilidad con respecto al número de robots. Ello permite resolver con eficiencia problemas de planificación de equipos con un número grande de robots. En la segunda parte del trabajo, se presentan algunas extensiones y resultados nuevos para la planificación distribuida en entornos desconocidos y con comunicaciones parciales entre los robots., Los resultados de esta línea de investigación son fruto de la participación de varios compañeros, investigadores de la Universidad de Zaragoza y de otras Universidades extranjeras. Queremos agradecer la participación de todos ellos, mencionando muy especialmente a Marius Kloetzer (profesor de la Universidad Técnica de Iasi, Rumanía). Este trabajo ha sido financiado parcialmente por los proyectos PGC2018-098719-B-I00 and PGC2018-098817-A-I00 (MCIU/AEI/FEDER, UE) y la ONR Global NICOP grant N62909-19-1-2027.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Consensus-based Distributed 3D Pose Estimation with Noisy Relative Measurements

  • Cristofalo, E.
  • Montijano, E.
  • Schwager, M.
In this paper we study consensus-based tributed estimation algorithms for estimating the global translation and rotation of each agent in a multi-agent system. We consider the case in which agents measure the noisy relative pose of their neighbors and communicate their estimates to agree upon the global poses in an arbitrary reference frame. The main contribution of this paper is a formal analysis that provides necessary and sufficient conditions to guarantee stability (in a Lyapunov sense) of the estimation system''s equilibria. We prove that consensus-based algorithms will diverge, even with arbitrarily small inconsistencies on the relative pose, unless the measurements satisfy minimum consistency conditions. We determine these consistency conditions for translation-only, rotation-only, and combined 3D pose estimation using the axis-angle rotation representation over undirected graphs. We then propose an initialization method based on these conditions that guarantees consistency and stability of the estimator''s equilibria. Additionally, we show that existing distributed estimation methods in literature exploit these conditions to guarantee convergence of their algorithms. Lastly, we perform simulations that show convergence when consistency conditions hold and divergence when they do not.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Distributed Dynamic Sensor Assignment of Multiple Mobile Targets

  • Montijano, E.
  • Tardioli, D.
  • Mosteo, A.R.
Distributed scalable algorithms are sought in many multi-robot contexts. In this work we address the dynamic optimal linear assignment problem, exemplified as a target tracking mission in which mobile robots visually track mobile targets in a one-to-one capacity. We adapt our previous work on formation achievement by means of a distributed simplex variant, which results in a conceptually simple consensus solution, asynchronous in nature and requiring only local broadcast communications. This approach seamlessly tackles dynamic changes in both costs and network topology. Improvements designed to accelerate the global convergence in the face of dynamically evolving task rewards are described and evaluated with simulations that highlight the efficiency and scalability of the proposal. Experiments with a team of three Turtlebot robots are finally shown to validate the applicability of the algorithm.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications

  • Alonso, Íñigo
  • Riazuelo, Luis
  • Murillo, Ana C.
Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this analysis, we have developed a novel architecture, MiniNet-v2, an enhanced version of MiniNet. MiniNet-v2 is built considering the best option depending on CPU or GPU availability. It reaches comparable accuracy to the state-of-the-art models but uses less memory and computational resources. We validate and analyze the details of our architecture through a comprehensive set of experiments on public benchmarks (Cityscapes, Camvid, and COCO-Text datasets), showing its benefits over relevant prior work. Our experiments include a sample application where these models can boost existing robotic applications.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Repeatable semantic reef-mapping through photogrammetry and label-augmentation

  • Yuval, M.
  • Alonso, I.
  • Eyal, G.
  • Tchernov, D.
  • Loya, Y.
  • Murillo, A.C.
  • Treibitz, T.
In an endeavor to study natural systems at multiple spatial and taxonomic resolutions, there is an urgent need for automated, high-throughput frameworks that can handle plethora of information. The coalescence of remote-sensing, computer-vision, and deep-learning elicits a new era in ecological research. However, in complex systems, such as marine-benthic habitats, key ecological processes still remain enigmatic due to the lack of cross-scale automated approaches (mms to kms) for community structure analysis. We address this gap by working towards scalable and comprehensive photogrammetric surveys, tackling the profound challenges of full semantic segmentation and 3D grid definition. Full semantic segmentation (where every pixel is classified) is extremely labour-intensive and difficult to achieve using manual labeling. We propose using label-augmentation, i.e., propagation of sparse manual labels, to accelerate the task of full segmentation of photomosaics. Photomosaics are synthetic images generated from a projected point-of-view of a 3D model. In the lack of navigation sensors (e.g., a diver-held camera), it is difficult to repeatably determine the slope-angle of a 3D map. We show this is especially important in complex topographical settings, prevalent in coral-reefs. Specifically, we evaluate our approach on benthic habitats, in three different environments in the challenging underwater domain. Our approach for label-augmentation shows human-level accuracy in full segmentation of photomosaics using labeling as sparse as 0.1%, evaluated on several ecological measures. Moreover, we found that grid definition using a leveler improves the consistency in community-metrics obtained due to occlusions and topology (angle and distance between objects), and that we were able to standardise the 3D transformation with two percent error in size measurements. By significantly easing the annotation process for full segmentation and standardizing the 3D grid definition we present a semantic mapping methodology enabling change-detection, which is practical, swift, and cost-effective. Our workflow enables repeatable surveys without permanent markers and specialized mapping gear, useful for research and monitoring, and our code is available online. Additionally, we release the Benthos data-set, fully manually labeled photomosaics from three oceanic environments with over 4500 segmented objects useful for research in computer-vision and marine ecology.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fine grained pointing recognition for natural drone guidance

  • Barbed, O.L.
  • Azagra, P.
  • Teixeira, L.
  • Chli, M.
  • Civera, J.
  • Murillo, A.C.
Human action recognition systems are typically focused on identifying different actions, rather than fine grained variations of the same action. This work explores strategies to identify different pointing directions in order to build a natural interaction system to guide autonomous systems such as drones. Commanding a drone with hand-held panels or tablets is common practice but intuitive user-drone interfaces might have significant benefits. The system proposed in this work just requires the user to provide occasional high-level navigation commands by pointing the drone towards the desired motion direction. Due to the lack of data on these settings, we present a new benchmarking video dataset to validate our framework and facilitate future research on the area. Our results show good accuracy for pointing direction recognition, while running at interactive rates and exhibiting robustness to variability in user appearance, viewpoint, camera distance and scenery.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

  • Alonso, Iñigo
  • Sabater, Alberto
  • Ferstl, David
  • Montesano, Luis
  • Murillo, Ana Cristina
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Path planning of multirobot systems using Petri net models. Results and open problems

  • Mahulea, C
  • Gonzalez, R
  • Montijano, E
  • Silva, M
This paper presents a trajectory planning approach in multirobot systems based on Petri net models. This type of models is very useful for high-level specifications since, in this case, the classical planning methods (potential functions, RRT algorithms, RRT*) cannot be used being difficult to determine a priori the sequence of configurations for each robot. This work presents the formal definition of the Robot Motion Petri net that is obtained from a partition of the environment in cells. Using the structure of the Petri net, in case of specifications defined as Boolean or Linear Temporal Logic (LTL) formulas, different optimization problems are presented that can be used to obtain trajectories for robots. The main advantage of models based on Petri nets is their scalability with respect to the number of robots. This makes it possible to efficiently solve planning problems with a large number of robots. In the second part of the paper, some extensions and new results for distributed planning in unknown environments and with partial communications between robots are presented.ntial functions, RRT algorithms, RRT*) cannot be used being difficult to determine a priori the sequence of configurations for each robot. This work presents the formal definition of the Robot Motion Petri net that is obtained from a partition of the environment in cells. Using the structure of the Petri net, in case of specifications defined as Boolean or Linear Temporal Logic (LTL) formulas, different optimization problems are presented that can be used to obtain trajectories for robots. The main advantage of models based on Petri nets is their scalability with respect to the number of robots. This makes it possible to efficiently solve planning problems with a large number of robots. In the second part of the paper, some extensions and new results for distributed planning in unknown environments and with partial communications between robots are presented.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

  • Alonso, I.
  • Riazuelo, L.
  • Montesano, L.
  • Murillo, A.C.
LIDAR semantic segmentation is an essential task that provides 3D semantic information about the environment to robots. Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many real-world robotic applications. This work presents 3D-MiniNet, a novel approach for LIDAR semantic segmentation that combines 3D and 2D learning layers. It first learns a 2D representation from the raw points through a novel projection which extracts local and global information from the 3D data. This representation is fed to an efficient 2D Fully Convolutional Neural Network (FCNN) that produces a 2D semantic segmentation. These 2D semantic labels are re-projected back to the 3D space and enhanced through a post-processing module. The main novelty in our strategy relies on the projection learning module. Our detailed ablation study shows how each component contributes to the final performance of 3D-MiniNet. We validate our approach on well known public benchmarks (SemanticKITTI and KITTI), where 3D-MiniNet gets state-of-the-art results while being faster and more parameter-efficient than previous methods.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Domain and View-Point Agnostic Hand Action Recognition

  • Sabater, A.
  • Alonso, I.
  • Montesano, L.
  • Murillo, A.C.
Hand action recognition is a special case of action recognition with applications in human-robot interaction, virtual reality or life-logging systems. Building action classifiers able to work for such heterogeneous action domains is very challenging. There are very subtle changes across different actions from a given application but also large variations across domains (e.g. virtual reality vs life-logging). This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. When working on a single domain (intra-domain action classification) our approach performs better or similar to current state-of-the-art methods on well-known hand action recognition benchmarks. And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods. These experiments show the robustness and generalization capabilities of our framework.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Event Transformer. A sparse-aware solution for efficient event data processing

  • Sabater, Alberto
  • Montesano, Luis
  • Murillo, Ana C.
Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption. However, top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms. Efforts toward efficient solutions usually do not achieve top-accuracy results for complex tasks. This work proposes a novel framework, Event Transformer (EvT) 1 , that effectively takes advantage of event-data properties to be highly efficient and accurate. We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition. Evaluation results show better or comparable accuracy to the state-of-the-art while requiring significantly less computation resources, which makes EvT able to work with minimal latency both on GPU and CPU.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Robust and efficient post-processing for video object detection

  • Sabater, Alberto
  • Montesano, Luis
  • Murillo, Ana C.
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks. Object recognition using video data is more challenging than using still images due to blur, occlusions or rare object poses. Specific video detectors with high computational cost or standard image detectors together with a fast post-processing algorithm achieve the current state-of-the-art. This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods by introducing a learning-based similarity evaluation between detections across frames. Our method improves the results of stat-of-the-art specific video detectors, specially regarding fast moving objects, and presents low resource requirements. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.