Comments (2)
Hi,
GNSS (or GPS) data is used to generate the training set. For each query point cloud, we find positive/similar point clouds (that are not more than 10 meters away) and negative/dissimilar point clouds (that are at least 50 meters away).
For retrieval itself, we push the 3D point cloud through the trained network and compute its descriptor (a 256-dimensional real-valued vector). Then, we find the point cloud in the database with the most similar descriptor.
However, we need to have a position of the most similar point cloud in the database, to reason about the location of the query point cloud. This can come from GSNN/GPS, or we can possibly use a global map by merging all database point clouds using some point cloud-based SLAM method.
from minkloc3dv2.
Thank you for your prompt reply,It's very helpful to me.
from minkloc3dv2.
Related Issues (9)
- Sensor recommendation HOT 6
- MemoryError: std::bad_alloc HOT 4
- High RAM usage when training HOT 2
- Missing File "evaluate.py"
- how about the pointcloud generated by depth image? HOT 2
- How to train this network on customized dataset
- Are you serious about cuda 10.2 on ubuntu 20.04? HOT 3
- What threshold to keep positive place recognitions HOT 2
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 minkloc3dv2.