在TUMVI数据集上测试VINS-Fusion算法

最新推荐文章于 2024-12-21 09:21:17 发布

GuoBen_

最新推荐文章于 2024-12-21 09:21:17 发布

阅读量2k

点赞数

分类专栏： VINS_Fusion 文章标签： slam yaml

本文链接：https://blog.youkuaiyun.com/GuoBen_/article/details/106912945

版权

本文介绍了如何在TUMVI数据集上测试VINS-Fusion算法，包括修改配置文件以适应数据集，并详细说明了测试过程，涉及在三个Terminal中分别打开RVIZ、VINS_Fusion以及播放数据集的步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

VINS_Fusion算法是一个非常优秀的视觉惯性里程计,但原版VINS_Fusion并没有提供与TUM数据集相应的配置文件,因此需要自己进行写yaml文件.

修改配置文件

tum_mono.yaml

%YAML:1.0

imu: 1         
num_of_cam: 1  

#common parameters
imu_topic: "/imu0"
image0_topic: "/cam0/image_raw"
output_path: "/home/guoben/output"

cam0_calib: "cam0.yaml"
image_width: 512
image_height: 512

# Extrinsic parameter between IMU and Camera.
estimate_extrinsic: 0   # 0  Have an accurate extrinsic parameters. We will trust the following imu^R_cam, imu^T_cam, don't change it.
                        # 1  Have an initial guess about extrinsic parameters. We will optimize around your initial guess.
                        # 2  Don't know anything about extrinsic parameters. You don't need to give R,T. We will try to calibrate it. Do some rotation movement at beginning.                        
#If you choose 0 or 1, you should write down the following matrix.
#Rotation from camera frame to imu frame, imu^R_cam
body_T_cam0: !!opencv-matrix
   rows: