We describe a system under development for the 3D fusion of multi-sensor surface surveillance imagery, including electro-optical (EO), IR, SAR, multispectral and hyperspectral sources. Our approach is founded on biolo...
详细信息
Current needs in tactical situational awareness require a new type of infrastructure to encode, transmit, store, fuse, and display vastly heterogeneous data that may include "hard" sensor types including vid...
详细信息
ISBN:
(纸本)9780819486363
Current needs in tactical situational awareness require a new type of infrastructure to encode, transmit, store, fuse, and display vastly heterogeneous data that may include "hard" sensor types including video, radar, multispectral, acoustic sensor array, 3D flash LIDAR, and "soft" sensor inputs such as textual reports from trained and untrained personnel, unsolicited and solicited open source web information, and hybrid "hard/soft" data such as human-annotated image or video data - which can be highly useful, but difficult to categorize and exploit. While the demand for scalability, rapid deployment, and decentralized access to data and services grows, the need for data security and integrity is as critical as ever. Methods for handling the conflicting needs between access and security are addressed. Furthermore, the evolving role of humans in data fusion systems must be addressed by the infrastructure. In addition to systems enhancing human data analysis capabilities through advanced visualization and sonification techniques, the data itself is more likely to contain information about humans - which is not always a task well suited to conventional data storage and retrieval methods. This paper describes a multi-agent approach to designing a secure, distributed, service-oriented infrastructure to support human-centric hard and soft information fusion.
We present a new concept (named DA vinCi) of distributedagents, sensor networks and an intelligent server catered to the home environment. Instead of a single multi-tasking human-like robot, we propose a team of netw...
详细信息
ISBN:
(纸本)9781605584041
We present a new concept (named DA vinCi) of distributedagents, sensor networks and an intelligent server catered to the home environment. Instead of a single multi-tasking human-like robot, we propose a team of networked task-specific roboticagents that interface with each other and the environment through a spatial map built by the server. We also highlight how our server will be a proxy for all the human-robot interactions (HRI) in the system and discuss the challenges involved. The paper's title captures the jist of our system where even a tea table can be inexpensively mobilized and interacted with via the DA vinCi *** is held by the author/owner(s).
In this paper, we investigate data fusion techniques for target tracking using distributedsensors. Specifically, we are interested in how pairs of bearing or range sensors can be best assigned to targets in order to ...
详细信息
In this paper, we investigate data fusion techniques for target tracking using distributedsensors. Specifically, we are interested in how pairs of bearing or range sensors can be best assigned to targets in order to minimize the expected error in the estimates. We refer to this as the focus of attention (FOA) problem. In its general form, FOA is NP-hard and not well approximable. However, for specific geometries we obtain significant approximation results: a 2-approximation algorithm for stereo cameras on a line, a PTAS for when the cameras are equidistant, and a 1.42 approximation for equally spaced range sensors on a circle. By reposing as a maximization problem - where the goal is to maximize the number of tracks with bounded error - we are able to leverage results from maximum set-packing to render the problem approximable. We demonstrate the results in simulation for a target tracking task, and for localizing a team of mobile agents in a sensor network. These results provide insights into sensor/target assignment strategies, as well as sensor placement in a distributed network.
In this contribution a Multi-Agent System architecture is proposed to deal with the management of spatially distributed heterogeneous nets of sensors, specially is described the problem of Pan-Tilt-Zoom or active came...
详细信息
The coverage control problem for robotic networks focuses on distributively coordinating the positioning of multiple dynamic agents to provide sensor coverage across a bounded region in two dimensional space. The asso...
详细信息
ISBN:
(纸本)9783907144008
The coverage control problem for robotic networks focuses on distributively coordinating the positioning of multiple dynamic agents to provide sensor coverage across a bounded region in two dimensional space. The associated optimal coverage problem seeks to position these agents so as to minimize an associated coverage cost. This coverage cost is typically defined with respect to a density function that is used to bias the network towards desired configurations. Previous approaches to this optimal coverage problem have addressed both static and dynamic environments through the choice of density function;however, stability guarantees for time-varying densities are restricted by significant technical assumptions that simplify the underlying proofs at the expense of limited applicability. In this paper, a generalized algorithm is presented that guarantees practical stability under relaxed technical assumptions. The algorithm, and its convergence, is illustrated via simulation examples.
agents acting in physical space use perception in combination with their own world models and shared context models. The shared context models have to be adapted permanently to the conditions of the real world. If a m...
详细信息
ISBN:
(纸本)9781586038878
agents acting in physical space use perception in combination with their own world models and shared context models. The shared context models have to be adapted permanently to the conditions of the real world. If a measurement of an agent's sensor does not fit to the corresponding data in the shared context model the system contains an inconsistency. In this case it is necessary to decide whether the reason for the discrepancy is a change in the real world or a measurement error. A solution has to be based on only a limited number of measurements from different agents and a reduction of noise in the sensor data. The study reported in this paper evaluates procedures that combine a multitude of measurements to a single result that can be integrated in the shared context model. The statistically optimized procedure based on ratings of the participating agents is enhanced using scaled weighted arithmetic means which prevents the system from running into singularities caused by the feedback from the ratings. The method is combined with an additional preprocessing based on fuzzy clustering that detects aberrant measurements which can be excluded from further processing.
Network-centric warfare (NCW) and the interoperability of joint and coalition forces lie among the future warfighting concepts that have been identified by defence. The purpose behind the introduction of such concepts...
详细信息
ISBN:
(纸本)917056115X
Network-centric warfare (NCW) and the interoperability of joint and coalition forces lie among the future warfighting concepts that have been identified by defence. The purpose behind the introduction of such concepts is to "link sensors, engagement systems and decision-makers into an effective and responsive whole, through shared situation awareness, clear procedures and the information connectivity needed to synchronise the actions of the defence farce to meet the commander's intent [1]." To realise the goal of shared situation awareness for NCW, it has long been acknowledged that decentralised data fusion is a key enabling technology, and to this end it has been investigated in terms of distributed target tracking and identification, and the development of distributedagents and ontologies. However, the aspects of interoperability relating to the fusion of disparate types of uncertain (local) data from joint and coalition data fusion systems for shared situation awareness do not appear to have been reported on in the open literature;fusion of disparate types of uncertain data has only been considered for centralised fusion systems. In this paper, these facets of data fusion are considered in tandem for the automatic target identification problem. In particular, a novel Bayesian technique is described and demonstrated for fusing estimates of target identity generated by local data fusion systems which employ a mix of Bayesian probability and Dempster-Shafer formalisms.
The proceedings contain 96 papers. The topics discussed include: personal data management with secure hardware: how to keep your data at hand;crowdsourcing for mobile data management;visual analysis of mobility data;u...
The proceedings contain 96 papers. The topics discussed include: personal data management with secure hardware: how to keep your data at hand;crowdsourcing for mobile data management;visual analysis of mobility data;using mobile agents in vehicular networks for data processing;smartphone-assisted mobility in urban environments for visually impaired users through computer vision and sensorfusion;location privacy management and protection in geo-social networks;distributed complex event processing in sensor networks;collaborative mobile application and advanced services for smart parking;building accurate 3D spatial networks to enable next generation intelligent transportation systems;efficient spatio-temporal information fusion in sensor networks;exploiting foursquare and cellular data to infer user activity in urban environments;and continuous query processing for actual and predicted object flow in symbolic space.
The proceedings contain 96 papers. The topics discussed include: personal data management with secure hardware: how to keep your data at hand;crowdsourcing for mobile data management;visual analysis of mobility data;u...
The proceedings contain 96 papers. The topics discussed include: personal data management with secure hardware: how to keep your data at hand;crowdsourcing for mobile data management;visual analysis of mobility data;using mobile agents in vehicular networks for data processing;smartphone-assisted mobility in urban environments for visually impaired users through computer vision and sensorfusion;location privacy management and protection in geo-social networks;distributed complex event processing in sensor networks;collaborative mobile application and advanced services for smart parking;building accurate 3D spatial networks to enable next generation intelligent transportation systems;efficient spatio-temporal information fusion in sensor networks;exploiting foursquare and cellular data to infer user activity in urban environments;and continuous query processing for actual and predicted object flow in symbolic space.
暂无评论