Pictures and video have long been effective weapons in the fight for national security. The information conveyed in a simple image – a freeze-frame of a suspect captured on video, the license plate of a car, the words on a street sign or on the side of a building – are an increasingly important part of research, security, and investigations at all levels of government. But the sheer volume of content makes it nearly impossible for analysts to review images and develop keywords for every frame to make analysis possible.
The ability to locate and analyze all types of images in databases based on their visual content is something the artificial intelligence community has been working on for the past 40 years. It requires teaching a machine how to see and understand images in the same ways a person views and comprehends using both their eyes and brain.
Machine Intelligence and Smart Image Tagging Lead to More Productivity
That has been the goal all along – to create software that’s capable of analyzing and searching pictures, video, and satellite images based on their visual content, much like an actual person would. piXlogic has built a commercial software product, piXserve, with these types of capabilities. The software can separate man-made items from natural things in the landscape, understand context within an image, distinguish faces and facial features, identify, recognize and automatically label objects, detect and recognize text in several languages, and create descriptions on the fly for everything it sees.
piXserve makes it possible to recognize, locate, and count objects such as planes on a tarmac, or cars on a road, or, in a military supply chain context for instance, parts and equipment on shelves in a warehouse. All of this generates powerful data that can be mined for a variety of purposes, putting some very interesting image-understanding capabilities in the hands of general users.
Computer vision, machine learning, and artificial intelligence, are all very difficult concepts and programs to develop and deploy. At piXlogic, we have worked hard to make these technologies work for the user in a transparent way so that they can interact with the system intuitively. Because the software can recognize multiple objects, faces, etc. in a picture, users can express not only simple queries (find this person or this object) but also more sophisticated ones.
End-users can upload a snapshot of a person and a picture of a car, for example, and then request all video segments and images that include one but not the other or both in the same shot, greatly speeding the analysis process. Users can provide a handful of examples (as few as one), give that item a name, and piXserve will automatically keep an eye on that, and if it sees it in an image or video frame, automatically record its position and assign a searchable keyword to the image.
Enhanced Security and More Cost-Effective Analysis with Advanced Image Search
By simplifying and removing complexity from the process, any user can interact with the system intuitively. Moreover, piXserve, is an enterprise-class solution that is now available on the Amazon Web Services (AWS) Marketplace for the U.S. Intelligence Community. Users can simply log onto their AWS consoles, spin up piXlogic, input data, and receive results in minutes. Users pay by the hour – for as little as about $7 per hour. This pay-as-you-go licensing approach negates the need for agencies to invest in expensive software and hardware and allows users to efficiently find what they need and easily leverage large volumes of images and videos.
Images are crucial components to strengthening national security and are invaluable to our intelligence and defense communities in their efforts to expose and track potential threats. With new advances in AI-based software, these powerful analysis capabilities are now more broadly available.
For more information on piXlogic, piXserve, or the AWS marketplace, check out these additional resources: