Thousands of cameras are connected to the Internet providing streaming data (videos or periodic images). The images contain information that can be used to determine the scene contents such as traffic, weather, and the environment. Analyzing the data from these cameras presents many challenges, such as (i) retrieving data from geographically distributed and heterogeneous cameras, (ii) providing a software environment for users to simultaneously analyze large amounts of data from the cameras, (iii) allocating and managing computation and storage resources. This paper presents a system designed to address these challenges. The system enables users to execute image analysis and computer vision techniques on a large scale with only slight changes to the existing methods. It currently includes more than 65,000 cameras deployed worldwide. Users can select cameras for the types of analysis they can do. The system allocates Amazon EC2 and Windows Azure cloud instances for executing the analysis. Our experiments demonstrate that this system can be used for a variety of image analysis techniques (e.g. motion analysis and human detection) using 2.7 million images from 1274 cameras for three hours using 15 cloud instances to analyze 141 GB of images (at 107 Mbps).
The majority of web-pages are unsuitable for viewing on PDAs, WAP phones and similar devices without first being adapted. However, little empirical work has been done on what actually constitutes a good PDA or WAP web-page. This paper ranks a number of PDA web-pages from different categories empirically and correlates the result against the design metrics present. The findings are then compared against a similar set of experiments for PC web-pages. The results of this comparison suggest that, as well as omitting, summarizing and converting individual multimedia objects in the web-page to a less resource intensive form, the design metrics need to be changed during adaptation to enhance the presentation of web-content on non-PC devices. The paper concludes by investigating the effect of applying some suitable changes to the design metrics on web=page content chunks, which form the basic units in automatic content adaptation systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.