Intellivix Launches Development of Next-Gen Defense AI Video Surveillance Platform
TECHWORLD ·
✦ AI Summary
Intellivix was selected as the lead organization for the Defense Acquisition Program Administration's "Defense Innovation Company R&D Project."
Intellivix has begun developing a next-generation defense AI video surveillance platform with UNIST and Sungkyunkwan University.
The core of the project is object detection in environments where visibility is poor and AI-based risk signal analysis, with total research funding of KRW 6.2 billion and a project period running from September 2026 to August 2029.
Intellivix announced on the 8th that it had been selected as the lead organization for the Defense Acquisition Program Administration's "Defense Innovation Company R&D Project." Intellivix has begun developing a next-generation defense AI video surveillance platform with the Ulsan National Institute of Science and Technology (UNIST) and Sungkyunkwan University.
The core of the project is object detection in environments where visibility is poor and AI-based analysis of risk signals. Total research funding is KRW 6.2 billion, and the project period runs from September 2026 to August 2029.
Intellivix plans to complete core technologies and prototype development by 2028. In 2029, it plans to conduct a field proof of concept (PoC) to verify detection performance and operational reliability. After that, it will pursue deployment to GOPs and coastal outposts following military performance evaluation and introduction procedures.
Intellivix is also pursuing the advancement of its low-visibility image sensing technology. The company plans to extend the surveillance range of its existing commercial low-visibility system, VIXallcam-M2, from the 200-meter class to the 500-meter class, and to upgrade image resolution from 800×480 to the 1600×960 class, expanding the image data available for long-range object analysis. Accordingly, it plans to double the horizontal resolution, double the vertical resolution, and quadruple the total pixel count.
Based on a strategy that integrates optical sensors, video analysis AI, and situation-interpretation VLM, the company combines optical imaging technology, vision AI, and a generative AI-based visual language model (VLM) while using near-infrared image sensing and optical processing. Through this, it expects to reduce image blurring caused by fog, snow, and rain, and to analyze distant objects and movement signals based on the captured video, while also improving detection performance in low-visibility environments and the reliability of situation analysis.
At the same time, the company is developing CEP technology to analyze individual signals in military surveillance environments in real time, and the result of that analysis will be the definition of meaningful threat situations. It also plans to develop a next-generation intelligent image sensing system that provides operators with automatically generated natural-language reports on major threat situations for field situation-based analysis and reporting.
Intellivix plans to verify the effectiveness of this system at GOPs and coastal outposts, and after verification, it aims to develop the "AI sentry" into a new export product for K-defense based on operational track record. Its initial target markets for expansion are U.S. border security and European border and coastal surveillance.
The company is also considering expanding the scope of application to tanks, armored vehicles, ships, drones, unmanned vehicles, and unmanned robots, and it is pursuing use as an environmental perception sensor for MUM-T systems. In addition, the technology is planned for application to defense surveillance and the safety of civilian mobility systems, and further expansion into safety AI cameras for autonomous vehicles and commercial vehicles, as well as sensors for ship safety, is expected as the technology advances.
Source: TECHWORLD · Kim Hye-jin
Original: https://www.epnc.co.kr/news/articleView.html?idxno=407969
References
This article was produced with the help of an automated content generation algorithm.
Source: TECHWORLD
View originalThis article was summarized and organized by BizCrush based on the original article from TECHWORLD. For exact quotations and full details, please refer to the original article.