Comments (6)
That happens when tracking is not initialized. Unless the scene is extremely dynamic in the beginning it should initialize within the first frame. (I assume you are using the RGB-D setup.)
Thanks for your reply ! yes , I used the RGB-D setup and running the code in TUM datasets( fr3_s _rpy and fr3_w_rpy). but it can't be initialized in any datasets,
so I increased the number of extracted features per frame in the corresponding settings file TUM3.yaml from 1000 to 1500 as you said before. the system can be initialized.Thank you!!
from dynaslam.
That happens when tracking is not initialized. Unless the scene is extremely dynamic in the beginning it should initialize within the first frame. (I assume you are using the RGB-D setup.)
from dynaslam.
I am experiencing that Light tracking is not working on fr3_w_xyz. Even with the update from 1000 to 1500. Any further experiences?
from dynaslam.
I am experiencing that Light tracking is not working on fr3_w_xyz. Even with the update from 1000 to 1500. Any further experiences?
I am also using fr3_w_xyz, setting the number of extracted features as 3000 makes no use for me. Did you solve the problem?
from dynaslam.
@BertaBescos
hello, when I used the RGB-D setup and running the code in TUM datasets(fr3_walking_halfsphere), default config. I saw the same problem: Light Tracking not working because Tracking is not initialized... Geometry not working.
and then I change the ORBextractor.nFeatures to 1500 2000 2500 3000. but the problem still exist. Can you tell me which config you used? I saw there a good result in the paper.
Please help me, Thanks a lot.
from dynaslam.
That happens when tracking is not initialized. Unless the scene is extremely dynamic in the beginning it should initialize within the first frame. (I assume you are using the RGB-D setup.)
Thanks for your reply ! yes , I used the RGB-D setup and running the code in TUM datasets( fr3_s _rpy and fr3_w_rpy). but it can't be initialized in any datasets, so I increased the number of extracted features per frame in the corresponding settings file TUM3.yaml from 1000 to 1500 as you said before. the system can be initialized.Thank you!!
good!
from dynaslam.
Related Issues (20)
- Help: virtual functions are pure within ‘DynaSLAM::NumpyAllocator’: HOT 1
- The problem of OpenCV3. HOT 2
- How to get the evaluation result for KITTI odometry 16-21 in DyanSLAM2?
- my version: numpy=1.16.6 tensorflow=1.12.3 python=2.7 how to slove the follow problem? HOT 1
- 运行数据集 HOT 2
- make error HOT 1
- why opencv3 can compile success ,but opencv 2.4.13 compile fail HOT 1
- problem on Check.py (ValueError: Exception encountered when calling layer "mrcnn_bbox" (type Reshape).)
- All masks pics output is pure black HOT 1
- Why doesn't working the KITTI odometry dataset in some data?
- Loading Mask R-CNN. This could take a while... Importing Mask R-CNN Settings... 段错误 (核心已转储)
- Light Tracking not working because Tracking is not initialized...
- DynaSLAM2
- Dynaslam2
- Arxiv review version said The project code will be released upon acceptance. [The RAL published version deleted this sentence] HOT 2
- How to reduce memory usage
- When can open source the code of dyanslam II?
- Python.h error
- Libffi Error - RGB-B build not generated
- python 版本
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 dynaslam.