SAFR® from RealNetworks, Inc., the pioneer in facial recognition and person-centric computer vision on live video, announces it has been awarded two Phase II Small Business Innovation Research (SBIR) contracts of approximately $950k each or $1.9M in total from AFWERX. These contracts provide funding to adapt the SAFR platform for use by the Air Force for perimeter security and secure access. Once developed for the USAF, the SBIR/STTR program allows for any other federal agency to award a sole-source contract for technology developed under the program. Enhancing situational awareness In partnership with Security Forces at a US Air Force base, SAFR will be enhanced to integrate real-time facial recognition across a range of fixed and mobile device embedded cameras to secure the perimeter and enhance situational awareness for those charged with securing some of the nation’s most sensitive assets. “Enabling Air Force Security Forces to detect persons of interest before they arrive at entry control points enhances force protection capabilities and the personal safety of our Defenders,” said 1st Lt Moore, USAF. In partnership with another USAF wing, SAFR will be further hardened against spoofing attacks to provide contactless secure access for authorised personnel using existing IP security cameras. This development will enable the elimination of touch-based keypads, a potential transmission surface of COVID-19 and contribute to force health and readiness. Biometric identity authentication SAFR is used by commercial customers around the world for tens of millions of recognitions per month" “Strong biometric identity authentication using face recognition has the potential to reduce the likelihood of contracting and spreading infectious elements including COVID-19 and seasonal flu into facilities, thus providing additional protection to our operational readiness,” said Mr. Donald Hudson, GG-15, Technical Director, USAF. “SAFR is used by commercial customers around the world for tens of millions of recognitions per month using on-premise and cloud deployments for secure access, perimeter security and a variety of other use-cases,” said Dan Grimm, General Manager of SAFR from RealNetworks. “As a US company, we are honoured to partner with AFWERX and these two Air Force wings to adapt our technology for mission-critical use by the US Air Force and other DoD customers.” Real-world accuracy and performance The SAFR platform is distinguished by its focus on real-world accuracy and performance: Optimised for live video - Face detection and recognition of a subject moving through a video frame in under 100ms with 99.87% accuracy Low bias - The lowest accuracy difference due to skin tone bias of any non-Chinese verification algorithm, as reported by NIST in their January 2020 report on the topic. This is a result of a diverse training data and focused, intentional efforts to eliminate bias. Deployment flexibility - In addition to fixed live video feeds, SDKs support edge deployments on resource-constrained autonomous devices like UGVs and UAVs that support ISR missions and require a small footprint and offline operation. Commercial readiness - Tens of millions of recognitions per month globally with both on-premise and hybrid cloud deployments. These contracts are the result of a partnership between AFRL and AFWERX to streamline the Small Business Innovation Research process and accelerate innovation by speeding up the experience, broadening the pool of potential applicants, and decreasing bureaucratic overhead.
RealNetworks Inc.’s SAFR, globally renowned company in the field of facial recognition technology and computer vision platform for live video, has announced the appointment of Eric Hess as Senior Director of Product Management. In this new position, Hess will lead the product strategy and will be responsible for expanding and accelerating the core SAFR application globally, with a particular emphasis on the public safety and gaming markets. Video analytics and facial recognition Eric Hess is a well-known expert in the use of video analytics and facial recognition technologies Eric Hess is a well-known expert in the use of video analytics and facial recognition technologies for expedient resolution of criminal investigations, surveillance, loss prevention, and identity solutions. Prior to joining SAFR, Hess served as the Senior Director of Video Analytics for IDEMIA, globally renowned company in biometric solutions. He also held senior sales and product management positions at MorphoTrak, and NEC’s Global Center of Excellence for Face Recognition. As a former Port of Seattle police officer, Hess has a unique appreciation for the mission and challenges of law enforcement and public safety customers. Commercial and public safety “We are very pleased to welcome Eric to the SAFR team,” said Dan Grimm, Vice President and General Manager of Computer Vision at RealNetworks. “He brings a unique mix of operational experience, technical background, and business acumen to ensure the successful adoption of facial recognition and video analytics across wide-ranging commercial and public safety projects.” “I am excited to join SAFR at a time when computer vision solutions are truly gaining momentum,” Hess said. “Advances in machine learning and cost reductions in computing power enable SAFR to bring solutions to public safety and commercial markets not previously served — improving school safety, enhancing security for public transportation and air travel, and reducing risk and liability for commercial venues where society gathers. Facial recognition can be a force for good and can be applied to help make life safer and more convenient.” Crime-prevention tactics expert As a recognised industry expert, Hess has been a speaker at numerous law enforcement and industry events, including INTERPOL, the Law Enforcement Video Association International (LEVA), the International Association for Identification (IAI), King County Prosecuting Attorney’s Office and, most recently, at the U.S. Secret Service’s Electronic Crimes Task Force in Oakland, California, USA.
RealNetworks has announced that SAFR, the foremost AI platform for live video, has joined NVIDIA’s Metropolis Software Partner Program to make it simpler for system integrators and enterprise customers to deploy the leading visual intelligence offering powered by NVIDIA technology. Computer vision solution SAFR instantly detects and matches millions of images of people with near-perfect accuracy in a fraction of a second Smart city professionals have historically struggled to find and deploy a U.S.-based computer vision solution that works in variable lighting conditions, angles of view, and high population density scenes. Now, those customers have easy access to SAFR’s industry-leading accuracy and performance in a highly optimised, scalable, and extensible format by becoming a part of NVIDIA’s Metropolis program. As the world’s highest-performance computer vision solution for live video, SAFR instantly detects and matches millions of images of people with near-perfect accuracy in a fraction of a second — even when they are blurred, obscured, tilted, or dimly lit. SAFR is also capable of assessing demographics, sentiment, or a person’s line-of-sight, without collecting any personally identifiable information. NVIDIA Metropolis IoT solution NVIDIA Metropolis is an IoT platform for intelligent video analytics that spans multiple NVIDIA products from edge to cloud. NVIDIA Metropolis paves the way to smarter and safer cities by applying deep learning to video streams for applications such as public safety and retail loss prevention. “This partnership makes it simpler than ever for our customers to access SAFR for smart cities, public safety, and retail use cases,” said Dan Grimm, Vice President and General Manager of Computer Vision at RealNetworks. Accelerated computer solutions firm Dan adds, “Our work with NVIDIA, globally renowned provider of accelerated computing solutions, will expand SAFR’s reach, enabling more cities — and their airports, transit systems, and retail stores — to benefit from an industry-proven platform and discover how visual intelligence can make the spaces we trust safer, smarter, and more convenient.”
As Vice President and General Manager of Computer Vision at RealNetworks, Dan Grimm leads the company’s facial recognition platform, SAFR. Prior to joining RealNetworks, Dan served as General Manager of Kindle Enterprise Publishing at Amazon. Dan also served as Associate Partner at Monitor Deloitte, where he led numerous strategy engagements advising C-suite and cabinet-level leaders in the United States, Europe, the Middle East, and Africa on driving top-line corporate growth, national prosperity, and economic development. How did you come to work in the security industry? We evaluated whose work we could best support with SAFR and identified the public servants and professionals keeping us safe in important spaces. They are asked to complete a near-impossible task: maintaining vigilance over hundreds of cameras in real-time — I’m delighted we’re able to help them do their jobs more effectively. What is the best professional advice you have received (and from whom)? Find the place where your gifts and passions intersect with the world’s need. And then dig in and make a difference. My pastor in college told me that, and it’s stuck with me ever since. Quick Facts Biggest hero Abraham Lincoln Favorite film The Last of the Mohicans Favorite meal Steamed Maryland Blue Crabs First job Warehouse Clerk Dogs or cats? Dogs What's something few people know about you? Many years ago, I appeared as an extra in the film, Mona Lisa Smile, with Julia Roberts, Julia Stiles, Maggie Gyllenhaal, and Ginnifer Goodwin. It was a brief scene, but great fun. Director Mike Newell said I did well — maybe I chose the wrong field! What's the most rewarding thing about what you do for a living? The opportunity to usher in the future with an extraordinary team. As a pioneer in the field of computer vision and facial recognition, I believe we have a responsibility to design, develop, and distribute this technology in ways that fundamentally enhance the human experience — that’s a challenge that I relish every day. Dan, along with his wife, brother, father-in-law, and some dear friends climbed Mt. Rainier to raise funds for Syrians in need What are your interests, hobbies and passions outside security? (And why?) When not immersed in the latest tech, I go the other direction and spend time in the wild. A few years ago, my wife, brother, father-in-law, and some dear friends climbed Mt. Rainier to raise funds for Syrians in need. It was a wonderful and humbling experience. Where was your last vacation? Would you recommend it to others and why? Camping in an airstream trailer in the mountains of the Pacific Northwest with my wife, our three children, and a 3-month-old pudelpointer puppy, Lewis. I recommend it highly as a family-bonding experience.
Facial recognition has seen huge breakthroughs since the U.S. National Institute of Standards and Technology (NIST) first began testing in 2010. Accuracy has seen massive gains, especially from 2013-2018. In the 2018 test, the most accurate algorithm was 20 times more accurate than the 2013 equivalent. Essentially, 95 percent of the matches that failed in 2013 now yield correct results. Compare that to 2010-2013, when the most accurate algorithm reduced its error rate by 30 percent. This reduction in error rates since 2013 is due to wholesale replacement of the old algorithms with new ones based on deep convolutional neural networks — completely revolutionising the technology. Optimal recognition results SAFR says it delivers optimal recognition results with 99.86 percent accuracy in under 100 milliseconds One entrant in the newly energised market is RealNetworks, whose SAFR for Security is an AI-based facial recognition solution for live video that integrates video management system (VMS) solutions. With 24/7 monitoring, SAFR detects and matches millions of faces accurately in real time, enabling teams to manage a watchlist across any number of video feeds. SAFR says it delivers optimal recognition results with 99.86 percent accuracy in under 100 milliseconds, even in real-world conditions where faces are in motion, at different angles, under poor lighting, or partially obscured. SAFR builds on RealNetworks’ 23-year history in video technologies. Launched in July 2018, SAFR — secure, accurate facial recognition — is enabling new applications for security, convenience, and analytics. Create security responses “We seek to be the world’s most trusted facial recognition platform and are delighted to partner with customers in the security industry and elsewhere to shape a more secure, convenient future worldwide,” says Dan Grimm, Vice President of Computer Vision and General Manager of SAFR at RealNetworks. “Security professionals are asked to keep us safe 24/7, monitoring a burgeoning number of cameras, and we help make them more effective.” SAFR targets facial recognition for live video, identifying camera-unaware faces moving in real-world conditions. In the April 2019 NIST results, SAFR tested as the fastest and most compact solution among algorithms with less than 0.022 False Non-Match Rate — 62 percent faster than the average speed, according to the company. SAFR now provides capabilities such as live video overlays alerting security professionals to events in real time, automatic bookmarks with rich metadata for investigative work, and alerts that can be customised to create security responses. SAFR uses one-sixth the compute power of competing facial recognition solutions Facial recognition algorithms Five years ago, facial recognition algorithms would struggle to match forward-facing people from still images, let alone camera-unaware moving faces from live video with variations in rotation and tilt. SAFR says they have achieved a balance of accuracy and performance for live video. A contributor to this accuracy is consistency across a range of skin tones. The algorithm was trained on a highly diverse global set of over 10 million non-simulated real-world faces. SAFR was optimised for speed and can sample a face multiple times during the same period of time as other algorithms, subsequently increasing its accuracy. SAFR achieves the performance through edge processing. Distributed architecture enables efficient bandwidth consumption, reducing the roundtrip latency of facial recognition speed to under 100 milliseconds. The savings lower total cost of ownership (TCO): SAFR uses one-sixth the compute power of competing facial recognition solutions, equating to $500,000 or so in savings on a 250-camera deployment. Integrated experience SAFR also uses off-the-shelf hardware and is optimised to leverage inexpensive GPUs SAFR also uses off-the-shelf hardware and is optimised to leverage inexpensive GPUs. SAFR can be deployed on premises or in the cloud, and supports Windows, Linux, macOS, iOS, and Android. When SAFR is paired with a VMS, such as Milestone XProtect or Genetec Security Center, the integrated experience includes 24/7 monitoring to detect and match faces in real-time. Features include live video overlays within the VMS to identify strangers, threats, concerns, unrecognised persons, VIPs, employees, or other tagged individuals in live video. Real-time alerts can be customised for when persons of interest appear on a video camera feed. Additionally, automatic bookmarks with rich metadata make for easier investigative review of security footage. Facial recognition technology is increasingly in demand to improve safety across various industry verticals. Better customer experience Large enterprises with high-visitor flows and heightened security — such as transportation hubs, stadiums, universities, and hospitals — need to know in real time when persons of interest or those on watchlists appear on camera. Sports stadiums could apply facial recognition to deny entry to banned patrons, locate lost children, or recognise VIPs to deliver a better customer experience. Hospitals need access control to restricted areas and pharmaceutical storage closets Hospitals need access control to restricted areas and pharmaceutical storage closets. Airports and transit centres value traffic flows, demographic composition, and dwell times to help improve scheduling. SAFR for Security is available worldwide, and the company partners with VMS providers such as Milestone, Genetec, Digifort, and IPConfigure by Paliton Networks. They are actively working to support additional VMS solutions and have sales teams located in major metropolitan cities around the world. Security professionals “The job of the security professional is critical in today’s world,” says Grimm. “SAFR for Security helps mitigate the challenges of the important work security professionals do to keep us all safe.” In designing and developing SAFR, RealNetworks considered diversity and the uniqueness of each person; Grimm says their massive global training data set is a competitive advantage. SAFR is designed with privacy in mind. All facial images and signatures are AES-256 encrypted in transit or at rest. “SAFR is powerful enterprise-grade software that is continuously improving through innovation and many years of expertise,” says Grimm.