Comments (2)
Hi,
Indeed, in the open-world scenario, when a query point cloud represents a new, unvisited area, you need a threshold when comparing the query point descriptor cloud with descriptors of already visited point clouds.
I suggest using a validation set to select the threshold which maximizes a chosen metric (e.g. the accuracy of binary classification if a place was already visited).
I would use the following approach:
- Train a network (e.g. MinkLoc3Dv2) using a training set to produce a global descriptor for the input point cloud. (using the standard training approach).
- Use the validation set to choose the threshold to decide if the place was already visited. For each point cloud in the validation set, compute its descriptor using the trained network.
- For each query point cloud in the validation set, find the point cloud in the validation set with the closest descriptor. Assume the place was already visited ('positive place recognition') when an Euclidean distance between the descriptor of the query point cloud and this closest point cloud is below a threshold Theta. Otherwise, assume the place was not visited ('negative place recognition').
- In a loop, try different values of Theta, and find the value which maximizes the chosen metric using the validation set. The metric depends on your use case. It can be an accuracy or a balanced accuracy of the binary classification task "was the place already visited", where you classify a place as already visited when the Euclidean distance between descriptors is less than Theta.
from minkloc3dv2.
Thank you for the detailed response. We will try it out. Our initial thought was to compute the precision-recall curve and find the point with the max recall while keeping the precision at 100%. It is fairly similar to your approach :).
from minkloc3dv2.
Related Issues (9)
- Is gnss data necessary for retrieval? HOT 2
- 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
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.