{"id":8815,"date":"2024-06-05T10:32:00","date_gmt":"2024-06-05T08:32:00","guid":{"rendered":"https:\/\/v2.vision-tools.com\/?p=8815"},"modified":"2024-07-12T13:42:53","modified_gmt":"2024-07-12T11:42:53","slug":"voe-ai-box","status":"publish","type":"post","link":"https:\/\/www.vision-tools.com\/en\/products\/systems\/vision-over-ethernet\/voe-ai-box.html","title":{"rendered":"VoE – AI Box"},"content":{"rendered":"\n
\n
\"banner\"\/<\/figure>\n\n\n\n
\n
Start<\/a> > Products<\/a> > Systems<\/a> > Vision-over-Ethernet<\/a> > VoE – AI Box<\/h6>\n\n\n\n

VoE – AI Box<\/h1>\n\n\n\n

Edge devcie for AI image evaluation<\/h2>\n<\/div>\n\n\n\n
<\/div>\n\n\n\n
\n
\n
\n

AI Box – robust and powerful edge device for AI-based evaluations in industrial environments<\/h1>\n\n\n\n

The AI Box is a powerful GPU workstation with 512 CUDA and 64 Tensor Cores, designed for fast and efficient evaluation of images with Artificial Intelligence (AI).<\/p>\n\n\n\n

This edge device was developed for use in a rough industrial environment – fanless, energy-efficient and designed for a wide temperature range. Power can be supplied via PoE+ or via a separate 24V supply. As a field device, in an IP67 housing, it meets the high requirements for shock and vibration resistance. All connections are easily accessible and designed as robust M12 round plugs.<\/p>\n\n\n\n

The design as a separate module makes it possible to upgrade older systems with artificial intelligence. This allows you to remain flexible and to continue using your existing application.<\/p>\n\n\n\n

Via the integrated web server, previously trained AI models can be loaded onto the AI Box and configurations can be done.<\/p>\n\n\n\n

The image processing software communicates with the AI Box via the REST interface. Requests, including an image, are transmitted via http protocol. Only a few tenths of a second later, the evaluation results of the AI are available and can be converted and output via the machine interface.<\/p>\n\n\n\n

The necessary training of the AI algorithms can be done independently on a separate computer or with the VisionCockpit cloud application. Depending on the task, extensive pre-trained neural networks are available for selection.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Integration into the VoE product line<\/h2>\n\n\n\n
\"Integration<\/figure>\n\n\n\n
<\/div>\n\n\n