Syntiant Corp., a leading end-to-end edge AI solution provider, announced it will be demonstrating a suite of deep learning solutions at CES 2023 to enable faster and easier deployments of security and surveillance technology in devices across consumer, commercial and industrial applications.
The company will display its edge AI audio, sensor and vision processing capabilities, including
audio event detection such as glass break, person or vehicle detection for smart cameras and doorbells, as well as inferences based on sensors, which include accelerometers for tamper detection.
CIO INFLUENCE: Anglicare Leverages Ribbon and Switch Connect for Voice Consolidation and Path for Microsoft Teams Deployment
Demos will take place from January 5-8, 2023 at Syntiant’s private suite at the Venetian Hotel (Room 108, 36th floor), as well as with industry partners. Technology demonstrations include:
- The Amazon Ring Alarm Glass Break Sensor (The Venetian Expo #52321 at the Amazon Experience Area), which uses artificial intelligence with the Syntiant NDP101 Neural Decision Processor™ (NDP) to accurately detect window glass breaking, while ignoring other typical household sounds to reduce false alarms. The device can detect the sound of window glass breaking from up to 25 feet and sends that notification to customers via the Ring app.
- Syntiant’s complete ultra-low-power deep learning models for security audio event detection, which includes simultaneously detecting glass breaking, smoke and carbon monoxide levels. Deployed using the NDP120 Neural Decision Processor with Syntiant’s Core 2 programmable deep learning architecture, the edge AI solution can run (multiple/concurrent) neural networks for five years on three AA batteries.
- Syntiant’s computer vision models for security and surveillance, such as person detection, vehicle and package detection, deployed on a variety of industry leading camera SoC solutions, including the Syntiant NDP200 Neural Decision Processor.
- A novel implementation of door tamper detection able to detect intrusive activities with a small, battery-operated device that is powered using the Syntiant Core 2™ inference engine and Syntiant’s deep learning models.
CIO INFLUENCE: Datometry Releases Driver Integration for BigQuery, Further Future-Proofing Its Customers’ Investments
“With the addition of our hardware-agnostic computer vision models alongside our edge-optimized NDP200 and NDP120 silicon, we have developed a complete solution for quickly and seamlessly deploying machine learning applications in security, access control and monitoring,” said Kurt Busch, CEO of Syntiant. “Whether it is off-the-shelf, ready to deploy on day one or a customized solution, we can deliver powerful edge AI to compute-constrained embedded devices in the home, automobile or enterprise.”
Packaged with the Syntiant Core 2, the company’s second-generation neural network, the Syntiant NDP200 and Syntiant NDP120 can run multiple applications simultaneously at under 1mW, including AI vision features such as person detection, object classification, motion tracking and occupancy monitoring, as well as multi-modal sensor fusion, multi-axis acceleration and other sensor capabilities. Syntiant also provides hardware agnostic, compute-efficient software solutions, with proprietary model architecture enabling world-leading inference speed and a minimized memory footprint across a broad range of processors.
CIO INFLUENCE: Ericsson presents a Green Financing Framework
[To share your insights with us, please write to sghosh@martechseries.com]
