i-PRO Announces Industry's First Network Camera Running Generative AI at the Edge
i-PRO has introduced its first network camera that executes Generative AI on-device, enabling real-time detection via free-text input without relying on cloud servers.
📋 Article Processing Timeline
- 📰 Published: April 2, 2026 at 00:00
- 🔍 Collected: April 1, 2026 at 16:47
- 🤖 AI Analyzed: April 15, 2026 at 22:45 (341h 57m after Collected)
i-PRO Co., Ltd. (Headquarters: Minato-ku, Tokyo; President and CEO: Masato Nakao) announced its first network camera capable of running Generative AI directly on the device (the edge) at ISC West 2026, an international security exhibition held in Las Vegas from March 23 to 27, 2026. This technology enables real-time detection based on free-text input without depending on the cloud or external servers.
The new product is an X-series multi-directional camera capable of 360-degree capture, equipped with a Generative AI engine powered by Ambarella's CV72 AI Vision SoC. All detection processing and feature extraction are performed inside the camera, enabling real-time detection of events based on natural language instructions, such as 'a person lying down.'
Furthermore, the camera adopts an open platform supporting Docker containers, allowing users to run their own or third-party AI applications directly on the hardware. On the security front, it features Secure Boot, signed firmware, and compliance with FIPS 140-3 Level 3, meeting the requirements of high-security applications. For video footage search, it integrates with multi-AI and monitoring software to support free-text searches using Generative AI. Video data is managed within on-premise environments.
In 2025, i-PRO introduced free-text video search for post-event analysis using Generative AI. This announcement marks the next step in the company's edge AI strategy, expanding Generative AI from post-analysis to real-time detection.
The X-series multi-directional camera is scheduled for sequential release worldwide starting June 2026, with sales in Japan expected to begin by the end of the year.
* Docker and the Docker logo are trademarks or registered trademarks of Docker, Inc. in the United States and other countries. All other brand, product, and company names mentioned are trademarks or registered trademarks of their respective companies.
The new product is an X-series multi-directional camera capable of 360-degree capture, equipped with a Generative AI engine powered by Ambarella's CV72 AI Vision SoC. All detection processing and feature extraction are performed inside the camera, enabling real-time detection of events based on natural language instructions, such as 'a person lying down.'
Furthermore, the camera adopts an open platform supporting Docker containers, allowing users to run their own or third-party AI applications directly on the hardware. On the security front, it features Secure Boot, signed firmware, and compliance with FIPS 140-3 Level 3, meeting the requirements of high-security applications. For video footage search, it integrates with multi-AI and monitoring software to support free-text searches using Generative AI. Video data is managed within on-premise environments.
In 2025, i-PRO introduced free-text video search for post-event analysis using Generative AI. This announcement marks the next step in the company's edge AI strategy, expanding Generative AI from post-analysis to real-time detection.
The X-series multi-directional camera is scheduled for sequential release worldwide starting June 2026, with sales in Japan expected to begin by the end of the year.
* Docker and the Docker logo are trademarks or registered trademarks of Docker, Inc. in the United States and other countries. All other brand, product, and company names mentioned are trademarks or registered trademarks of their respective companies.
FAQ
How is this different from conventional AI cameras?
Traditional cameras could only detect pre-trained specific objects. This new product uses Generative AI to detect objects based on free-text descriptions, such as 'a person lying down.'
Are there concerns about privacy or data leaks?
All processing happens on the camera itself (the edge), and video data is managed in an on-premise environment, minimizing the risks associated with cloud data transmission.
When will it be available globally?
Worldwide sales will start sequentially from June 2026. In Japan, sales are expected to begin by the end of 2026.