AI-Box - Smart Visual Inspection
AI-Box is our edge computer to solve visual inspection tasks right on your production line. Learning from real-world inspection cases that we implemented over the last years, we developed hardware and software to address the needs of an AI-driven inspection workflow.
The core of AI-Box runs a deep learning algorithm that has “learned” how to distinguish images from “OK” and “not OK” products. Using dedicated hardware, deep neural networks are executed to efficiently infer from any input image an output label. This output label represents the answer of the visual inspection and can be displayed or sent to another machine.
Unlike traditional rule-based inspection, our AI is trained on labeled images that you provide. This enables a new workflow where the bottleneck is no longer the vision engineer coding the inspection, but where the AI itself learns how to inspect.
GigE Vision and GeniCam
Supporting cameras through industry standards means you can choose from a wide range of options of grayscale, color, or even 3D cameras to suit your use case.
Power over Ethernet (PoE)
With PoE, cameras can directly connect data and power with a single cable, supporting up to 100m in length.
A dedicated FPGA enables real-time control of GPIOs for optimal setup of triggers for light and camera as well as other external peripherals.
Any visual inspection starts with taking images through cameras. With AI-Box, cameras and lights can be directly connected without the need for intermediate switches or controllers. AI-Box configures the cameras and triggers light and camera to take images that allow for a detailed surface inspection. Using High-Dynamic-Range (HDR) photography, even highly reflective surfaces can be acquired with sufficient local contrast.
Binary and multi-class classification
for each input image, the AI algorithm returns a single OK/NOK answer. Or you extend the training data by including different error classes, and our algorithm learns to distinguish multiple types of defects
for each input image, the AI algorithm can show exactly where the defect is in the image.
in cases where the defect covers a large part of the image, our algorithm recognizes when an image contains an anomaly not seen before. This algorithm can be trained utilizing only images of good parts and does not require the customer to provide images of defects.
AI-based solutions require a dedicated workflow, this is supported by AI-Box:
Create a new product, add classes or defect types you want to identify, and start acquiring and annotating images.
Review images, remove wrong labels or adapt annotations.
Let Deevio create a deep neural network-based model that is tailored to your new product and upload it to AI-Box
Change your inspection to the new model and start inspecting on the production line!
Manage Your Inspection Case
Create, review, adapt and export data sets that are ready to train an AI model.
Annotate images with use case-specific labels. Draw on top of images with our labeling tool to mark the exact location of a defect.
Data export: No lock-in, you can easily export images and annotation data from AI-Box
The AI-Box application is optimized to run on the AI-Box, a small and efficient machine vision PC that is built to our design.
In addition, the software stack runs on a wide range of NVIDIA-GPU-enabled PCs to serve any requirements for cycle time, image resolution, and complexity of the AI-models.
2xPoE/1x Gigabit Ethernet
System on a Chip (SoC)
Nvidia Tegra X2, 64 Bit
4-core ARM Cortex-A57, 2GHz
2-core Denver2, 2GHz
256 CUDA cores (Pascal), 1.12 GHz
8 GB DDR4
1 x M.2 SSD (256 GB)
1 x 32 GB eMMC
1 x SDXC slot
2 x GigE Vision with Trigger-and-Power-over-Ethernet
2 x Trigger-Over-Ethernet
8 x Input & 8 x Output, opto-isolated, 24 V
Encoder Interface RS-422
3 x input for one encoder
1 x 1000 MBit/s
1 x IEEE 802.11a/b/g/n/ac with external antenna socket
1 x internal socket for SIM, with external antenna socket
2 x USB 3.0 ports, 1 x micro USB maintenance port
1 x DisplayPort
Power & Dimensions
24 V (DC)
fan-less, via heat sink
Dimensions (W x D x H)
163 mm x 163 mm x 48 mm (without mounting plate)
163 mm x 210 mm x 48 mm (with mounting plate)