Multiple eyes in the skies - Architecture and perception issues in the comets unmanned air vehicles project

Ollero, A.; Lacroix, Simon; Merino, Luís; Gancet, Jérémi; Wiklund, Johan; Remuß, Volker; Perez, Ismael; Gutiérrez, Leopoldo; Viegas, Domingos X.; Benitez, Margarita; Mallet, Anthony; Alami, Rachid; Chatila, Raja; Hommel, G.; Lechuga, F.J.C.; Arrue, Begoña C.; Ferruz, J.; Dios, J.R. Martínez-de; Caballero, Fernando

doi:10.1109/mra.2005.1458323

Cited by 98 publications

(36 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The evaluation dataset includes videos with objects of different classes that undergo deformations, occlusions, scale and appearance changes. The test video sequences come from the following datasets: ETH Walking Pedestrians (EWAP) [26], Pedestrian dataset [27], Comets project [28] and the Aerial Action Dataset [29]. In total, we used 13 sequences for evaluation.…”

Section: Methodsmentioning

confidence: 99%

Segmentation Based Particle Filtering for Real-Time 2D Object Tracking

Belagiannis

Schubert²,

Navab

et al. 2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. We address the problem of visual tracking of arbitrary objects that undergo significant scale and appearance changes. The classical tracking methods rely on the bounding box surrounding the target object. Regardless of the tracking approach, the use of bounding box quite often introduces background information. This information propagates in time and its accumulation quite often results in drift and tracking failure. This is particularly the case with the particle filtering approach that is often used for visual tracking. However, it always uses a bounding box around the object to compute features of the particle samples. Since this causes the drift, we propose to use segmentation for sampling. Relying on segmentation and computing the colour and gradient orientation histograms from these segmented particle samples allows the tracker to easily adapt to the object's deformations, occlusions, orientation, scale and appearance changes. We propose two particle sampling strategies based on segmentation. In the first, segmentation is done for every propagated particle sample, while in the second only the strongest particle sample is segmented. Depending on this decision there is obviously a trade-off between speed and performance. We perform an exhaustive quantitative evaluation on a number of challenging sequences and compare our method with the number of stateof-the-art methods previously evaluated on those sequences. The results we obtain outperform majority of the related work, both in terms of the performance and speed.

show abstract

Section: Methodsmentioning

confidence: 99%

Segmentation Based Particle Filtering for Real-Time 2D Object Tracking

Belagiannis

Schubert²,

Navab

et al. 2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

show abstract

“…It deals with task requests/status and data transmissions, such as images or robot telemetry. It should be noted that the robots currently integrated in the architecture are using the BBCS (BlackBoard Communication System) developed by the Technical University of Berlin [15] and tested in the COMETS Project [16] funded by the IST Programme of the European Commission. It is a robust communication system implemented via a distributed shared memory, the blackboard (BB), in which each network node has a local copy of the BB portion it is accessing.…”

Section: Multi-robot Architecture Overviewmentioning

confidence: 99%

Distributed Service-Based Cooperation in Aerial/Ground Robot Teams Applied to Fire Detection and Extinguishing Missions

2010

View full text Add to dashboard Cite

This paper presents a system for the coordination of aerial and ground robots for applications such as surveillance and intervention in emergency management. The overall system architecture is described. An important part for the coordination between robots is the task allocation strategy. A distributed market-based algorithm, called S + T, has been developed to solve the multi-robot task allocation problem in applications that require cooperation among the robots to accomplish all the tasks. Using this algorithm, robots can provide transport and communication relay services dynamically to other robots during the missions. Moreover, the paper presents a demonstration with a team of heterogeneous robots (aerial and ground) cooperating in a mission of fire detection and extinguishing.

show abstract

“…The first works related to formations date from early 2000s and most authors focused on maintaining the set distance between UAVs of the formation (Giulietti, Pollini, & Innocenti, 2000). Then more complex multi-UAV systems were considered, for example composed of different types of UAVs such as helicopters and airships (Ollero et al, 2005). However, the swarm approach to cooperation between UAVs is definitely the most popular.…”

Section: Introductionmentioning

confidence: 99%

A framework for a hierarchical model of cooperation between unmanned airplanes

Rotter

Chmiel

2018

European Journal of Remote Sensing

View full text Add to dashboard Cite

In this article we propose a framework for a hierarchical model for cooperation between unmanned airplanes in large groups. We argue that the swarm approach to cooperation between a large number of mobile robots is ineffective when robots can be equipped with efficient communication, precise location hardware and with complex control algorithms. The proposed model, analogous to the organisation of a team of people, is an intermediate solution, between the swarm approach and central control. The bottom layer of the model includes unmanned airplanes that perform tasks related to the mission goals, such as capturing images, looking for objects through image analysis, etc. These airplanes are organised in teams, and each team is controlled by the superior airplane. Two top layers are ground-based: the central computer and the human operator, and their functions are mostly defining the goals, planning and optimisation of the mission. We present two examples of response to events, related to failure or loss of an airplane. We discuss how the proposed model can manage possible interruptions of communication and security issues, and how collision avoidance can be implemented. Finally, we point out that, although the control structure is different than in the swarm approach, swarm intelligence can still be used to optimise missions. ARTICLE HISTORY

show abstract

Multiple eyes in the skies - Architecture and perception issues in the comets unmanned air vehicles project

Cited by 98 publications

References 16 publications

Segmentation Based Particle Filtering for Real-Time 2D Object Tracking

Segmentation Based Particle Filtering for Real-Time 2D Object Tracking

Distributed Service-Based Cooperation in Aerial/Ground Robot Teams Applied to Fire Detection and Extinguishing Missions

A framework for a hierarchical model of cooperation between unmanned airplanes

Contact Info

Product

Resources

About