Grinn with its new project revolutionizes vehicle access systems for high-traffic areas such as office complexes. In environments where hundreds of vehicles enter and exit daily, traditional access control systems, like card-based gate openers, can become inefficient. While these systems are quicker than manual gate control, they still require drivers to locate and scan their cards—a process that wastes time and becomes inconvenient in adverse weather conditions like rain or snow. Grinn’s solution leverages Edge AI technology to streamline the process, enhancing both speed and user experience. By automating license plate recognition, the system allows for seamless vehicle entry and exit, particularly valuable during peak traffic hours.

The core of this system is powered by Grinn’s DanioSOM, a high-performance, compact system-on-module. The device includes two cameras, which enable simultaneous recognition of vehicles entering and exiting the facility. The system operates at a frame rate of 10 FPS (frames per second) and performs reliably even in low-light conditions. A gateway manages data processing and storage, eliminating the need for large, costly server rooms traditionally required for license plate recognition systems. Unlike traditional setups, where heavy computing tasks are sent to central servers, Grinn’s solution performs all computations at the Edge. The DanioSOM based system, which fits into a 10x10 cm box, replaces bulky server infrastructure, offering a significant reduction in energy consumption and operational costs. Moreover, because the data never leaves the local network, the system greatly enhances security by reducing the risk of hacking or unauthorized data access.

Grinn’s AI-powered license plate recognition system met all challenges head-on. Using convolutional neural networks (CNNs), the system quickly detects and reads vehicle license plates, cross-referencing them with a database of approved vehicles. The result? Gates open automatically within seconds, allowing vehicles to pass through seamlessly without the need for drivers to interact with any physical device. The solution not only improves traffic flow but also ensures a secure and cost-effective approach. By utilizing the power of Edge AI, all data is processed locally on the DanioSOM module, eliminating the need for external servers, reducing energy consumption, and enhancing security. Furthermore, Grinn’s system offers a smooth transition from old access control methods to new ones. Vehicle data can be input manually or automatically based on existing access cards. Once a vehicle is registered, the system will recognize it in the future without requiring the driver to scan a card. This hybrid approach ensures that the implementation is quick, non-intrusive, and can easily integrate with existing infrastructure.