|
1 |
| -# VINS-Fusion |
2 |
| -## An optimization-based multi-sensor state estimator |
| 1 | +# Stereo-VPCCD |
| 2 | + |
| 3 | +## An Pointcloud Change Detection pipeline based on VINS-Fusion |
| 4 | + |
| 5 | +## 1.Prerequisites |
| 6 | + |
| 7 | +You can use any Linux distros as you like, most of the prerequisites are same with VINS-Fusion. |
| 8 | + |
| 9 | +### 1.1 **Linux** and **ROS** |
| 10 | + |
| 11 | +Ubuntu 20.04 recommended, cause this project switch the OpenCV major version from 3 to 4, and |
| 12 | +ROS Noetic is the first ROS 1 distro integrated with OpenCV 4. |
| 13 | + |
| 14 | +### 1.2 Ceres Solver |
| 15 | + |
| 16 | +If you use Ubuntu 20.04, simply do:`sudo apt install libceres* -y`. |
| 17 | +Manually installation please follow [Ceres Installation](http://ceres-solver.org/installation.html). |
| 18 | + |
| 19 | +### 1.3 PointCloud Library(PCL) |
| 20 | + |
| 21 | +I think pcl version 1.10 will be a good choice. If you are using Ubuntu 20.04, `sudo apt install libpcl-dev -y` |
| 22 | +will do that. Else follow [PCL](https://github.com/PointCloudLibrary/pcl). Version lower than 1.10 may works, but v1.12 |
| 23 | +never works. |
| 24 | + |
| 25 | +**MAKE SURE YOU INSTALL RIGHT VERSION BEFORE NEXT STEP.** |
| 26 | + |
| 27 | +Cause FAST-GICP will run into bug if you use a higher version of pcl. |
| 28 | + |
| 29 | +### 1.4 FAST-GICP |
| 30 | + |
| 31 | +Follow [fast_gicp](https://github.com/SMRT-AIST/fast_gicp), follow the installation with ros. |
| 32 | + |
| 33 | + |
| 34 | +____ |
3 | 35 |
|
4 | 36 | <img src="https://github.com/HKUST-Aerial-Robotics/VINS-Fusion/blob/master/support_files/image/vins_logo.png" width = 55% height = 55% div align=left />
|
5 | 37 | <img src="https://github.com/HKUST-Aerial-Robotics/VINS-Fusion/blob/master/support_files/image/kitti.png" width = 34% height = 34% div align=center />
|
6 | 38 |
|
7 |
| -VINS-Fusion is an optimization-based multi-sensor state estimator, which achieves accurate self-localization for autonomous applications (drones, cars, and AR/VR). VINS-Fusion is an extension of [VINS-Mono](https://github.com/HKUST-Aerial-Robotics/VINS-Mono), which supports multiple visual-inertial sensor types (mono camera + IMU, stereo cameras + IMU, even stereo cameras only). We also show a toy example of fusing VINS with GPS. |
| 39 | +VINS-Fusion is an optimization-based multi-sensor state estimator, which achieves accurate self-localization for |
| 40 | +autonomous applications (drones, cars, and AR/VR). VINS-Fusion is an extension |
| 41 | +of [VINS-Mono](https://github.com/HKUST-Aerial-Robotics/VINS-Mono), which supports multiple visual-inertial sensor |
| 42 | +types (mono camera + IMU, stereo cameras + IMU, even stereo cameras only). We also show a toy example of fusing VINS |
| 43 | +with GPS. |
8 | 44 | **Features:**
|
| 45 | + |
9 | 46 | - multiple sensors support (stereo cameras / mono camera+IMU / stereo cameras+IMU)
|
10 | 47 | - online spatial calibration (transformation between camera and IMU)
|
11 | 48 | - online temporal calibration (time offset between camera and IMU)
|
|
0 commit comments