Oosto’s Chief Technology Officer and Chief AI Scientist presented a bold new vision for video analytics leveraging contextual scene understanding and semantic segmentation at this week’s ISC East, the International Security Conference & Exposition, in New York.
In their presentation, Oosto laid out how the use of these new technologies can deliver real-time contextual analytics and more accurate alerts based on a more holistic understanding of a scene.
Providing limited insights
Historically, the AI in video analytics is usually single-threaded and purpose-built to perform a specific function like facial recognition, object detection, or license plate recognition. This limits an organization’s ability to have a more complete understanding of a scene from video surveillance. This also means that the metadata is limited to the single use case, disconnected from the other algorithms, and unable to holistically make sense of a scene.
Today’s video analytics provide limited insights which can translate to poor and missed alarms"
“Video analytics is still in its infancy. Today’s video analytics provide limited insights which can translate to poor and missed alarms,” said Dieter Joecker, Oosto's Chief Technology Officer, adding “Wandering through ISC East and talking to enterprise customers and the partners who serve them, it's clear that the world of physical security needs to move out of the dark ages and help organizations prevent incidents of violence and vandalism, or to minimize the damage immediately after.”
Live video surveillance
Dieter Joecker said, “Tomorrow, commercial enterprises will harness the power of contextual scene analysis – multithreaded AI – to deliver real-time contextual analytics and precision alerts based on a more holistic understanding of live video surveillance.”
He adds, “For example, when someone falls down in a store, this could mean any number of things: Were they actually bending over to tie their shoes? Were they pushed by another person? Was it a staged ‘slip & fall’ to generate a fraudulent claim? Is the person having a legitimate medical emergency? How an organization responds in real-time is based on the timeliness and quality of the alert.”
Semantic scene understanding
We can also start to capture more metadata to gain greater context about what’s occurring in real-time"
“Leading Vision AI companies are starting to exploit the power of semantic segmentation and edge computing to deliver real-time contextual analytics and alerts to achieve a more holistic understanding of video footage,” said Professor Marios Savvides, Director of Carnegie Mellon University’s CyLab Biometrics Center and Oosto Chief AI Scientist.
He adds, “We can also start to capture more metadata to gain greater context about what’s occurring in real-time and ensure that the right types of alerts are sent to the right personnel. Instead of relying on surveillance professionals to monitor video footage 24x7, security teams can use their skills to respond to very precise alerts. It’s not just about adding more algorithms. Leading companies are going to use the power of semantic scene understanding and edge computing to deliver real-time contextual analytics and alerts based on a more granular and complete understanding of a scene.”
First responder practitioners
The International Security Conference & Exposition, also known as ISC East, is the Northeast’s leading security & public safety event, hosted in collaboration with the premier sponsor Security Industry Association (SIA). The show brings together security dealers, installers, integrators, and consultants, along with corporate, government, and law enforcement/first responder practitioners, to share best practices and technologies designed to keep the communities safe and secure.
At the conference, Oosto presented its access control and watchlist alerting solutions based on facial recognition, which are used today by government organizations, airports, casinos, hospitals, and many other entities to improve security and safety in physical spaces. In addition, Oosto’s leadership was invited to speak at the conference and present the future concept of AI-based video analysis.
- Network / IP
- Remote surveillance
- Digital video surveillance
- Remote video surveillance
- IP video surveillance
- Electronic security systems
- Shop security systems
- Application security
- Remote security
- Mall security
- Perimeter security
- Shopping centre security
- Security devices
- Security cameras
- Covert cameras
- Security camera systems
- Security access systems
- Radio frequency Identification
- Voice recognition systems
- Facial recognition systems
- Video analytics
- Remote video monitoring
- Electronic access control
- Building security
- Facility security
- Store security
- Store surveillance
- Wireless security
- License plate recognition
- Door access control
- Security software
- IP Surveillance
- Security service
- Physical Security Information Management (PSIM)
- IP security solutions
- Covert Surveillance
- Integration software
- Event security
- Perimeter protection
- Internet of Things (IoT)
- Network Video Recorders
- Artificial intelligence (AI)
- Mobile access
- Video surveillance
- Machine Learning
- Touchless Security
