Edge AI (1) - Vision recognition, actively adopted by infrastructure and service providers… "Low-spec optimization is key."
Published2023.04.11 15:15As artificial intelligence technology embedded in intelligent CCTV systems becomes more advanced, it is expected to alleviate the labor burden on social safety infrastructure. With active technology transfer to the private sector in areas such as facial recognition and human recognition, and expansion of related technology infrastructure and services accelerating, edge AI—which distributes computing power and enables artificial intelligence implementation even on low-spec devices—is gaining attention.
Comments
Related news
Intelligent CCTV, “High Efficiency in Vehicle Number Recognition” VS “Actual Sites, Many Variables”
AI cameras at the edge are expected to expand their market presence primarily in the public sector and security market. While monitoring personnel have limitations in workforce and capabilities, AI can mechanically learn and infer predefined factors, and experts anticipate it will demonstrate effectiveness in real-world applications.
2023.03.30by 명세환 기자
Microchip Unveils Latest Embedded Insights for AI, Security, and Edge
Microchip will host 'Tech Insights Korea' online from April 25th to 27th, featuring topics on artificial intelligence/machine learning, safety and security, and connectivity and embedded solutions.
2023.04.05by 배종인 기자
KESSIA, "Edge AI Development, Embedded Technology is a Must"
Edge AI, which has recently garnered significant attention in the technology sector, has reached commercialization in the market as numerous companies have progressed beyond the product development phase in areas such as △video security △IoT devices △automotive solutions △wireless communications. Against this backdrop, there has been a sharp increase in models equipped with edge AI technology. In response to these developments, the embedded industry, which forms the foundation for digital transformation through edge AI, has convened to reinforce its commitment to expanding related industrial technology and strengthening the ecosystem.
2023.04.07by 명세환 기자
Korea Institute of Materials Science and Pukyong National University Launch 'Marine AI Materials Research Center'
The Korea Institute of Materials Science and Pukyong National University have launched the 'Marine AI Materials Research Center' to begin full-scale joint research combining AI-based materials development technology with the marine industry. Based on their research capabilities in energy and environmental materials, they will promote technology development for eco-friendly and smart marine new industries, and plan to cultivate it as a core research hub for marine materials in the southeastern region.
2026.09.15by 배종인 기자
[e4ds Tech Day 2026 ④] Sung-il Lim, Executive Director at TI, "Edge AI is no longer a high-cost SoC domain"
Sung-il Lim, Executive Director at Texas Instruments (TI), emphasized at the 'e4ds Tech Day 2026' held on the 8th that edge AI is no longer confined to the domain of high-cost SoCs, and an era has opened where it can be implemented even in one-dollar MCUs. The key is the company's own NPU 'TinyEngine,' which reduces AI inference latency by 90 times compared to MCUs and saves 120 times more power. By separating control and inference through a parallel structure of MCU and NPU, efficiency has been improved, and it can be applied across various industries including predictive maintenance, home appliances, wearables, and robots. The AM13E23019 MCU integrates Cortex-M33, TinyEngine, and analog functions to reduce BOM costs by 30%. TI is also strengthening the development environment with Edge AI Studio and AI-based CCStudio, emphasizing that "the essence of edge AI is not high performance but product commercialization."
2026.09.15by 배종인 기자
