Spectacular AI SDK documentation
壯觀的 AI SDK 文件

Spectacular AI SDK fuses data from cameras and IMU sensors (accelerometer and gyroscope) and outputs an accurate 6-degree-of-freedom pose of a device. This is called Visual-Inertial SLAM (VISLAM) and it can be used in, among other cases, tracking (autonomous) robots and vehicles, as well as Augmented, Mixed and Virtual Reality.
壯觀的 AI SDK 融合了來自攝像頭和 IMU 感測器（加速度計和陀螺儀）的數據，並輸出設備的精確 6 自由度姿態。這稱為視覺慣性 SLAM （VISLAM），除其他情況外，它可用於跟蹤（自主）機器人和車輛，以及增強現實、混合現實和虛擬實境。

The SDK also includes a Mapping API that can be used to access the full SLAM map for both real-time and offline 3D reconstruction use cases.
該 SDK 還包括一個 Mapping API，可用於訪問即時和離線 3D 重建用例的完整 SLAM 地圖。

SDK architecture
SDK 架構

The main parts of the SDK are documented on their own pages:
SDK 的主要部分記錄在各自的頁面上：

  • Core SDK: device-indepencent APIs shared between all devices supported by the SDK.
    核心 SDK：SDK 支援的所有設備之間共用的 device-independent API。

  • Wrappers: for devices supported out-of-the-box.
    包裝器：適用於開箱即用支持的設備。

The SDK also includes a set of tools implemented on top of the APIs, such as the sai-cli process command line tool for NeRFs and Gaussian Splatting.
SDK 還包括一組在 API 上實現的工具，例如用於 NeRF 和高斯展開的命令行工具。

System requirements
系統要求

Operating system. Windows or Linux. For Linux, Ubuntu 18+ is recommended, but other distribution (e.g., Yocto) can be supported as well. If the binaries do not work out-of-the-box, contact us for commercial support.
操作系統。Windows 或 Linux。對於 Linux，建議使用 Ubuntu 18+，但也可以支援其他發行版（例如 Yocto）。如果二進位檔無法開箱即用，請聯繫我們以獲取商業支援。

Architecture Binaries for x86-64 are available on the SDK releases. For Linux 64-bit ARM binaries are also available with a commercial license contact us for more info.
建築適用於 x86-64 的二進位檔在 SDK 版本中可用。對於 Linux，64 位 ARM 二進位檔也可通過商業許可證獲得，請聯繫我們以獲取更多資訊。

CPU. The SDK is designed to work in real-time on Cortex-A57 type or better embedded processors. This includes Jetson Nano and Raspberry Pi 4 (A72). Slower processors, such as Cortex-A53 work under certain conditions or with reduced accuracy and functionality. At least two A5x or better cores are required.
CPU 的 CPU 中。SDK 旨在在 Cortex-A57 類型或更高版本的嵌入式處理器上即時工作。這包括 Jetson Nano 和 Raspberry Pi 4 （A72）。速度較慢的處理器（如 Cortex-A53）在某些條件下工作，或者準確性和功能降低。至少需要兩個 A5x 或更好的內核。

RAM. 6-DoF pose tracking works with less than 50MB of RAM. However, certain optional features or configuration changes related to the Mapping API increase can the RAM consumption.
記憶體。6-DoF 姿勢跟蹤可在小於 50MB 的 RAM 下工作。但是，與 Mapping API 相關的某些可選功能或配置更改會增加 RAM 消耗。

Software dependencies. The Core SDK itself has zero non-trivial external software dependencies. However, Wrappers, SDK examples and tools built on the SDK have additional dependencies, which are not all designed to work on embedded platforms (especially the Python-based 3D visualizations). See the relevant documentation sub-pages for more info.
軟體依賴關係。Core SDK 本身具有零重要的外部軟體依賴項。但是，在 SDK 上構建的包裝器、SDK 示例和工具具有額外的依賴項，這些依賴項並非全部設計用於嵌入式平臺（尤其是基於 Python 的 3D 可視化）。有關更多資訊，請參閱相關的文檔子頁面。

Development dependencies
開發依賴項

For development purposes, we recommend a relatively recent Linux or Windows laptop computer.
出於開發目的，我們建議使用相對較新的 Linux 或 Windows 筆記型電腦。

Windows  Windows

The following setup is recommended to run the SDK examples
建議使用以下設置來運行 SDK 示例

For C++ development, you additionally need
對於 C++ 開發，您還需要

Linux  Linux的

You need at least Git, and Python and Pip
您至少需要 Git、Python 和 Pip

sudo apt update
sudo apt install python-is-python3 python3-pip git

For C++ development, you also need a relatively recent compiler (GCC or Clang) and CMake, e.g.,
對於 C++ 開發，您還需要一個相對較新的編譯器（GCC 或 Clang）和 CMake，例如，

sudo apt install cmake clang build-essential

FFmpeg

To use the recoding, replay API or tools depending on these APIs, you need to install FFmpeg. Linux
要使用 recoding、replay API 或依賴於這些 API 的工具，您需要安裝 FFmpeg。Linux的

apt install ffmpeg

On Windows, see here. FFmpeg must be in your PATH so that ffmpeg works on the command line.
在 Windows 上，請參閱此處。FFmpeg 必須位於您的應用程式中，以便ffmpeg在命令行上工作。