We study the problem of aggregating data from a sparse set of nodes in a wireless sensor network. This is a common situation when a sensor network is deployed to detect relatively rare events. In such situations, each...
详细信息
We study the problem of aggregating data from a sparse set of nodes in a wireless sensor network. This is a common situation when a sensor network is deployed to detect relatively rare events. In such situations, each node that should participate in the aggregation knows this fact based on its own sensor readings, but there is no global knowledge in the network of where all these interesting nodes are located. Instead of blindly querying all nodes in the network, we show how the interesting nodes can autonomously discover each other in a distributed fashion and form an ad hoc aggregation structure that can be used to compute cumulants, moments, or other statistical summaries. Key to our approach is the capability for two nodes that wish to communicate at roughly the same time to discover each other at a cost that is proportional to their network distance. We show how to build nearly optimal aggregation structures that can further deal with network volatility and compensate for the loss or duplication of data by exploiting probabilistic techniques.
In this paper we present our preliminary results in the automatic analysis of colonoscopy video using eye-tracking. We propose that eye-tracking can be successfully applied to solve different problems in computer assi...
详细信息
In this paper we present our preliminary results in the automatic analysis of colonoscopy video using eye-tracking. We propose that eye-tracking can be successfully applied to solve different problems in computer assisted colonoscopy, such as database labelling, expertise assessment and abnormality detection. We provide results in these three areas, including a machine learning-based system for colon cancer detection using data generated with eye-tracking.
This paper presents algorithms for vision-based classification of vehicles based on vehicle logo in monocular image of traffic scenes recorded by a stationary camera. The intended application is automatic recognition ...
详细信息
This paper presents algorithms for vision-based classification of vehicles based on vehicle logo in monocular image of traffic scenes recorded by a stationary camera. The intended application is automatic recognition of vehicle type for secure access and traffic monitoring applications, a problem not hitherto considered at such a level of accuracy. In recognition of vehicle type, differing with other researchers who attend to the recognition of shape, size of vehicle, we pay attention to the location and recognition of vehicle logo. The vehicle logo is unique mark of vehicle type (both make and model). We demonstrate that a relatively simple vehicle logo recognition method from front images can be used to obtain high performance verification and recognition of vehicle type. Firstly, the vehicle logo can be rough detected by prior knowledge, such as license, and then logo can be exactly detected by edge feature. Finally, the logo can be recognized using template matching and edge orientation histograms. Experimental results show the effectiveness of the proposed method.
Institutions of higher education are self-governing bodies of which participating members must serve on various committees from time to time. To this end, nominations and elections of schoolwide committees are the vit...
详细信息
We consider the problem of approximating a family of isocontours in a sensor field with a topologically-equivalent family of simple polygons. Our algorithm is simple and distributed, it gracefully adapts to any user-s...
详细信息
We consider the problem of approximating a family of isocontours in a sensor field with a topologically-equivalent family of simple polygons. Our algorithm is simple and distributed, it gracefully adapts to any user-specified representation size k, and it delivers a worst-case guarantee for the quality of approximation. In particular, we prove that the topology-respecting Hausdorff error in our k-vertex approximation is within a small constant factor of the optimal error possible with Theta(k/log m) vertices, where m is the number of contours. Evaluation of the algorithm on real data suggests that the size increase factor in practice is a constant near 2.6, and shows no error increase. Our simulation results using a variety of synthetic and real data show that the algorithm smoothly handles complex isocontours, even for representation sizes as small as 32 or 48. Because isocontours are widely used to represent and communicate bi-variate signals, our technique is broadly applicable to in- network aggregation and summarization of spatial data in sensor networks.
We prove superlinear lower bounds for some shortest path problems in directed graphs, where no such bounds were previously known. The central problem in our study is the replacement paths problem: Given a directed gra...
详细信息
An increasing number of conferences, symposia, workshops, journals and books address the subject of emotions and their role in Human-computer Interaction, including workshops at the last two HCI conferences. The need ...
详细信息
One issue hindering the deployment of integrated ubicomp environments is the lack of a shared model for applications to utilize resources across administrative and network domains. Through the use of concrete examples...
详细信息
One issue hindering the deployment of integrated ubicomp environments is the lack of a shared model for applications to utilize resources across administrative and network domains. Through the use of concrete examples, we describe our proposed common model for ubicomp environments to address this issue. We then present use cases and additional examples for how our ubicomp common model (UCM) is used by our integration framework. The ubicomp integration framework (UIF) uses an ontology driven architecture (ODA) (P. Tetlow et al., 2001) and enterprise application integration (EAI) techniques to integrate existing ubiquitous computing middleware to the common model. The use cases illustrate how the integrated model and reasoning is used to maintain a dynamic integrated model of an environment
Object selection is a primary interaction technique which must be supported by any interactive three-dimensional virtual reality application. Although numerous techniques exist, few have been designed to support the s...
详细信息
Object selection is a primary interaction technique which must be supported by any interactive three-dimensional virtual reality application. Although numerous techniques exist, few have been designed to support the selection of objects in dense target environments, or the selection of objects which are occluded from the user's viewpoint. There is, thus, a limited understanding on how these important factors will affect selection performance. In this paper, we present a set of design guidelines and strategies to aid the development of selection techniques which can compensate for environment density and target visibility. Based on these guidelines, we present two techniques, the depth ray and the 3D bubble cursor, both augmented to allow for the selection of fully occluded targets. In a formal experiment, we evaluate the relative performance of these techniques, varying both the environment density and target visibility. The results found that both of these techniques outperformed a baseline point cursor technique, with the depth ray performing best overall.
暂无评论