# VisionEye SLAM Intro

VisionEye SLAM has Movidius™ Myriad™ X Vision Processing Unit, a dedicated hardware accelerator for deep neural network inference.

VisionEye contains following software modules

**HID SDK**: Human Interface Design (HID) provides communication between host (glasses) and device (VisionEye SLAM hardware component).

This SDK contains APIs related to device information software version, hardware version, attach USB, detach USB, register pose, IMU, and Event callbacks.

**UVC SDK**: USB Video Class(UVC) gets video stream from VisionEye SLAM hardware component

This SDK contains APIs related to stereo mode, registers stereo and RGB callback to SLAM, callbacks provide video streams either RGB or stereo

**VSC SDK**: Vendor Specific Device Class(VSC) gets custom video and stream from VisionEye SLAM hardware component

This SDK contains APIs related to ToF(time of flight) ,RGB , stereo depth, frame rate, map and camera controls.

**Edge SDK**: Edge computation gives real time pose and orientation of device.

Edge mode runs computation on VISION SLAM hardware component. This SDK contains APIs related to coordinate systems, enables disable 6DoF stream, sets post-filter coefficients rotation and translations and reads and writes i2c calls to hardware.

**EdgePlus SDK**: EdgePlus gives extra information based on camera position and orientation

This SDK contains APIs related to orientation, optimized map, register stereo plane, Tof plane callbacks.

**Slam SDK**: Host pose computation gives real time pose and orientation

Edge mode runs computation on Glasses CPU. This SDK contains APIs related pose, stereo plane, Tof plane register callbacks, load and save maps.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://thirdeyegen.gitbook.io/visioneye-slam-api-documentation/master.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.