OmniInstrument/SLAM_project

Omni Instrument SLAM项目数据集是一个紧凑的机器人数据集，专为评估立体视觉、视觉惯性以及视觉惯性里程计（VIO）流程而设计。该数据集提供：
- [x] 立体图像对
- [x] 惯性测量（IMU）
- [x] 地面真实6自由度位姿（用于VIO）
- [x] 原始ROS 1和ROS 2记录

数据集分为三个部分：
- `stereo`：仅立体视觉（IMU静止）
- `stereoinertial`：立体视觉 + IMU
- `vio`：立体视觉 + IMU + 地面真实位姿

所有部分共享相同的架构，确保下游流程的一致性。数据收集协议包括立体视觉校准、立体惯性校准和VIO操作SLAM序列。数据格式包括图像、时间戳、陀螺仪、加速度计、同步时间偏移、位置和方向等信息。数据集还提供了ROS主题记录和Python使用示例。

The Omni Instrument SLAM Project Dataset is a compact robotics dataset designed for evaluating stereo, visual-inertial, and visual-inertial odometry (VIO) pipelines. It provides:
- [x] Stereo Image Pairs
- [x] Inertial measurements (IMU)
- [x] Ground-truth 6 DoF pose (for VIO)
- [x] Raw ROS 1 and ROS 2 recordings

The dataset is structured into three splits:
- `stereo`: Stereo-only (IMU stationary)
- `stereoinertial`: Stereo + IMU
- `vio`: Stereo + IMU + ground-truth pose

All splits share the same schema, enabling consistent downstream pipelines. The data collection protocol includes stereo calibration, stereo-inertial calibration, and VIO operational SLAM sequences. The data format includes images, timestamp, gyro, accel, sync_dt, position, and orientation. The dataset also provides ROS topic recordings and example usage in Python.