Comments (9)
jianhengLiu
commented on August 12, 2024
可能是后端特征点估计飘了，可以分别尝试
- 不使用静止初始化
static_init: 0 - 调大深度置信区间
depth_max_dist: 6 - 增大特征点数量
max_cnt: 130
from dynamic-vins.
bzwwww
commented on August 12, 2024
我采用的是config中原始配置，并且尝试将 depth_max_dist: 6 更改 和将最大特征点改到 250 都没有成功
并且我的rviz中没有正常的轨迹显示，我认为程序可能没有正常运行？
from dynamic-vins.
jianhengLiu
commented on August 12, 2024
我这边用默认配置测试了一下好像都还正常
openloris: roslaunch vins_estimator openloris_vio_pytorch.launch
thusz: roslaunch vins_estimator realsense_vio_campus.launch
如果已经pull了最新版还是有问题的话，不清楚是不是这个commit(4e73b9e)可能版本有点差异？可以尝试改回来试试
from dynamic-vins.
jianhengLiu
commented on August 12, 2024
我这边用默认配置测试了一下好像都还正常
openloris: roslaunch vins_estimator openloris_vio_pytorch.launch
thusz: roslaunch vins_estimator realsense_vio_campus.launch
如果已经pull了最新版还是有问题的话，不清楚是不是这个commit(4e73b9e)可能版本有点差异？可以尝试改回来试试
from dynamic-vins.
bzwwww
commented on August 12, 2024
我之前运行的版本中是cv::SOLVEPNP_ITERATIVE，我重新clone了一下最新的版本，重新运行，还是会发现上述错误，但出现了不同的情况。
track_img中不再是深度图，同时我使用的不是ros-noetic中自带的OpenCV，我使用的版本是OpenCV4.5.5。您认为这两者中有关系吗？感谢您的帮助！
from dynamic-vins.
jianhengLiu
commented on August 12, 2024
有可能，我使用的是ros自带的opencv4.2.0
rviz显示不同可能是更改了topic，在display里重新选下应该就好
…---原始邮件---
发件人: ***@***.***>
发送时间: 2023年4月28日(周五) 下午3:24
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [HITSZ-NRSL/Dynamic-VINS] 运行过程出错：unstable features tracking, please slowly move you device! (Issue #25)
我之前运行的版本中是cv::SOLVEPNP_ITERATIVE，我重新clone了一下最新的版本，重新运行，还是会发现上述错误，但出现了不同的情况。
track_img中不再是深度图，同时我使用的不是ros-noetic中自带的OpenCV，我使用的版本是OpenCV4.5.5。您认为这两者中有关系吗？感谢您的帮助！
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
from dynamic-vins.
bzwwww
commented on August 12, 2024
我重新编译了OpenCV4.2.0的版本，已经可以成功运行，感谢您的帮助！
from dynamic-vins.
yg-0527
commented on August 12, 2024
你好，请问这个一直下载不了源码是怎么回事啊？我网络良好，也试过开vpn，都显示网页404。请问谁可以分享一下源码吗？万分感谢！！！！
from dynamic-vins.
bzwwww
commented on August 12, 2024
你好，还想问一下这份代码里还有闭环检测的功能吗，我拿这套代码跑kitti数据集时出现了比较大的偏差，想尝试开闭环之后试试。我在yaml文件中更改了下面的配置，但没有起作用。
loop_closure: 1 # start loop closure
fast_relocalization: 1 # useful in real-time and large project
from dynamic-vins.
Related Issues (20)
- evaluate vins + rgb image without depth
- Can you provide me with detailed materials about the added IMU-aided feature tracking? HOT 3
- About RPE
- ground truth of HITSZ & THUSZ Datasets HOT 3
- 运行cafe1-1.bag-imu.bag包时卡顿 HOT 1
- vins_result_no_loop.scv无内容
- roslaunch vins_estimator openloris_vio_pytorch.launch 刚运行报错[demo_server-1] process has died HOT 1
- Failed to load nodelet '/EstimatorNodelet of type vins_estimator/EstimatorNodelet HOT 1
- How to train my own detection model? HOT 1
- 指定yolo运行的gpu
- How to add RPE results into the figure of OpenLORIS results?
- NVIDIA Jeston Xavier NX 上部署的一些问题 HOT 6
- yolo_ros Problem HOT 1
- YOLO reshape array problem using ZED2 HOT 2
- yolo频率问题 HOT 3
- 你好 我运行的时候有点问题 HOT 8
- VO mode BUG🐛
- imu标定方法
- How to connect dynamic vins with px4? How to publish the data?
- yolo_ros和dynamic_vins的时间戳同步问题 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dynamic-vins.