Contextual analytics helps achieve holistic understanding of video in real time — Oosto
Semantic segmentation can enable contextual analytics to gain a holistic understanding of video footage in real time, improving artificial intelligence (AI) performance in video analytics.
Oosto’s CTO, Dieter Joecker and chief AI scientist Marios Savvides discussed these claims last week at ISC East, the International Security Conference & Exposition, in New York.
Joecker explained how AI in video analytics is typically single-threaded and built to perform a specific function like facial recognition, object detection or license plate recognition.
At the same time, the executive said he believes this limits an organization’s ability to completely understand a scene from video surveillance, as it limits metadata to the single-use case.
“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,” Oosto’s CTO explained.
Savvides added that some vision AI companies are starting to explore the capabilities of semantic segmentation and edge computing to deliver real-time contextual analytics.
“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,” the AI expert explained.
“Instead of relying on surveillance professionals to monitor video footage 24×7, security teams can use their skills to respond to very precise alerts. It’s not just about adding more algorithms.”