EU and US could reach trade deal this weekend - Reuters
Investing.com -- NTT Corporation (NTT) has introduced a new large-scale integration (LSI) designed for real-time artificial intelligence (AI) inference processing of ultra-high-definition video. This technology, which is the first of its kind, enables real-time AI inference at 4K resolution and 30 frames per second, while maintaining low power consumption. The technology is designed for use in edge devices and terminals with strict power constraints.
The LSI uses an AI inference engine created by NTT, which enhances computing efficiency. This makes it suitable for use cases such as beyond visual line of sight drone operations for public infrastructure inspections. When installed on a drone, this technology allows the drone to detect individuals or objects from up to 150 meters above the ground, compared to a limit of 30 meters with conventional real-time AI video inferencing technology. This advancement could potentially reduce labor and costs in drone-based infrastructure inspection.
NTT's LSI is distinct as it enables AI inference at the edge and for power-constrained terminals, an achievement that Kazu Gomi, president and CEO of NTT Research, believes holds substantial potential for applications ranging from infrastructure inspection to public safety and live sporting events.
In edge and power-constrained terminals, AI devices typically have power consumption significantly lower than that of GPUs used in AI servers. The LSI overcomes these limitations by using the NTT-created AI inference engine, which reduces computational complexity while ensuring detection accuracy. This engine improves computing efficiency using interframe correlation and dynamic bit-precision control, allowing the execution of the object detection algorithm You Only Look Once (YOLOv3) with a power consumption of less than 20 watts.
NTT plans to commercialize this LSI within fiscal year 2025 through its operating company, NTT Innovative Devices Corporation. The technology was announced and demonstrated at Upgrade 2025, NTT's annual research and innovation summit, held in San Francisco on April 9-10, 2025.
Moving forward, researchers are studying the application of this LSI to the data-centric infrastructure (DCI) of the Innovative Optical and Wireless Network (IOWN) Initiative led by NTT and the IOWN Global Forum. DCI leverages the high-speed and low-latency capabilities of the IOWN All-Photonics Network to address challenges of modern networking infrastructure.
Moreover, NTT researchers are working with NTT DATA, Inc. to advance this LSI in relation to its proprietary Attribute-Based Encryption (ABE) technologies. ABE allows for fine-grained access control and flexible policy setting at the data layer, with shared-secret encryption technologies enabling secure data sharing that can be integrated into existing applications and data stores.
This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.