Integrating DepthAI into products

Difficulty of integrating DepthAI into products

When designing our platform from the grounds up, we always thought of user integration and made is as simple as possible to integrate it into other products.

What is SoM

OAK SoM (System on Module) is a small form-factor PCB that features a powerful Myriad X VPU (Vision Processing Unit). The VPU has 16 powerful SHAVE cores and also features the Neural Compute Engine — a dedicated hardware accelerator for deep neural network inference. In addition, OAK-SoM-IoT and OAK-SoM-Pro have NOR Flash, which can be used as an alternative to the USB boot. The idea of SoM is that customer can take and build their own device with it, since SoM is very complex, 12 layer PCB. That way our SoM devices serve as an abstraction layer. They can also be used in standalone mode - without a host computer, although not all devices support that use-case.

We have 3 types of SoM devices:

The main difference between them is in:

  • NOR flash capability, OAK-SoM does not have NOR flash by default, while the other two have 1Gbit NOR flash by default (in some iterations 125Mbit is used),

  • Boot modes they support, for example OAK-SoM-Pro also supports SD-card and Ethernet (EEPROM) boot.

OAK-SoM:

../../_images/BW10991.png

Baseboards

Just as our software and our library, our hardware is opensource too. That way it is not just a black box, you can see how our devices (PCB) are designed and you can change them however you like. Even high-school students designed their own baseboard by modifying existing opensource design. Most of complexity is on the SOM, so the baseboard can be a 2-layer PCB.

Here is an example of a baseboard without the SOM:

../../_images/baseboard.jpeg

And here is the OAK-D-IOT-40, which is a baseboard with on-board cameras and ESP32:

../../_images/DM1092_back.jpg

NOR Flash and Powering

The OAK-SoM-IoT and OAK-SoM-Pro have the QSPI NOR Flash, which is capable of quick random access location and is used to store and run code. This is the key factor to support the standalone use case.

Power consumption can vary depening on the application. A stereo vision application running Mobilenet-SSD V2 at 30 FPS typically consumes about 2.5 W, but more computationally heavy applications can consume up to 5 W. Most of this power is consumed by the Myriad X VPU.

For more information, see the respective datasheet on our GitHub hardawre repository (OAK-SoM Datasheet.

Got questions?

We’re always happy to help with code or other questions you might have.