An advanced research arm of the U.S. government's intelligence community is looking to develop AI capable of tracking people across a vast surveillance network. As reported by Nextgov, the Intelligence Advanced Research Projects Activity (IARPA) has put out a call for more information on developing an algorithm that can be trained to identify targets by visually analyzing swaths of security camera footage. The goal, says the request, is to be able to identify and track subjects across areas as large as six miles in an effort to reconstruct crime scenes, protect military operations, and monitor critical infrastructure facilities. To develop the technology, IARPA will collect nearly 1,000 hours of video surveillance from at least 20 camera networks and then, using that sample, test various algorithms effectiveness. The agency's interest in AI-based surveillance technology mirrors a broader movement from governments and intelligence communities around the globe, many of whom have ramped up efforts to develop and scale systems.
A team of researchers at JD AI Research and Beijing University have recently developed a progressive vehicle search system for video surveillance networks, called PVSS. Their system, presented in a paper pre-published on arXiv, can effectively search for a specific vehicle that appeared in surveillance footage. Vehicle search systems could have many useful applications, including enabling smarter transportation and automated surveillance. Such systems could, for instance, allow users to input a query vehicle, search area and time interval to find out where the vehicle was located at different times during the day. Existing vehicle search methods typically assume that all vehicle images are cropped well from surveillance videos, using visual attributes or license plate numbers to identify the target vehicle within these images.
New data predicts the market for AI-driven healthcare technologies will exceed $6 billion in just three years. The surge is being driven largely by growing demand and acceptance among consumers for electronic, data-driven and virtual-based care, and the desire for more convenient, accessible, and affordable care. While it's entertaining to speculate on the future of these applications to healthcare, there are several use cases underway today which promise to change the way we think about and deliver care at the individual and population levels. These three areas highlight where AI is already making an impact in the delivery, treatment, and reimbursement of care. Tracking disease prevalence, treatment methods, and patient response through widespread systematic data collection, analysis, and dissemination has the potential to help us fine tune treatment protocols based on clear evidence of what's working and what's not across various disease states and populations.
China has been building what it calls "the world's biggest camera surveillance network". Across the country, 170 million CCTV cameras are already in place and an estimated 400 million new ones will be installed in the next three years. Many of the cameras are fitted with artificial intelligence, including facial recognition technology. The BBC's John Sudworth has been given rare access to one of the new hi-tech police control rooms.
Twitter provides the freshest source of data about what is happening in the lives people across the world. The publicly available streams of status updates available on Twitter have been used to track earthquakes, forest fires and most especially flu outbreaks. Current techniques for tracking flu outbreaks rely on count data for a number of keywords. However, count data alone on the noisy Twitter streams is not reliable enough for health officials to make critical decisions. We propose a semi-automatic outbreak detection system. Rather than providing only alarms backed by count data, we propose a summarization system that will allow health officials to quickly verify outbreak alarms. This will lead to higher levels of trust in the system and allow the system to be used by health organizations around the world. We experimentally verify our summarization system and have found system users to have an accuracy of 0.86 when identifying multi-tweet summaries.
We describe a method to improve detection of disease outbreaks in pre-diagnostic time series data. The method uses multiple forecasters and learns the linear combination to minimize the expected squared error of the next day's forecast. This combination adaptively changes over time. This adaptive ensemble combination is used to generate a disease alert score for each day, using a separate multi-day combination method learned from examples of different disease outbreak patterns. These scores are used to generate an alert for the epidemiologist practitioner. Several variants are also proposed and compared. Results from the International Society for Disease Surveillance (ISDS) technical contest are given, evaluating this method on three syndromic series with representative outbreaks.