Comments (2)
Hi, for your own dataset, I think you can do the following two steps: (1) for a given frame at current timestamp, use the calibration information to align the past frames with the current one. (2) preprocess the point clouds into BEV maps, and feed these BEV maps into the network.
I think even if your LiDAR data is not 360°, the network can still predict as expected. This is because the final output will be masked by the occupancy information. That said, if a given grid cell is not occupied by some LiDAR points, the prediction at this cell will be thresholded to zero (i.e., background).
Similarly, it does not matter if the angle is tilted, as long as such a tilted angle is not very large. All you need to do is provide the BEV maps into the network.
from motionnet.
Hi,
Thank you very much for your reply! I will definitely try this out in the upcoming days.
from motionnet.
Related Issues (17)
- How to create the fantastic picture? HOT 1
- split.npy file for the smaller nuscenes v1.0-mini dataset HOT 2
- some problem about the motionnet postprocess HOT 3
- Problems training train_single_seq HOT 2
- Training Set size not 17065 for NuScenes after preprocessing HOT 5
- Is the background loss filtering out dynamic objects? HOT 7
- Bug in nuscenes_dataloader.py [os.listdir does not guarantee the order of the returned list of files on other systems beyond Ubuntu] HOT 3
- Inactive bug in classify_speed_level HOT 1
- BrokenPipeError during training process HOT 8
- RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation HOT 3
- 对KITTI进行处理 HOT 1
- hello! When I run the gen_data.py, it has a problem in LidarPointCloud(from nuscenes.utils.data_classes import LidarPointCloud) HOT 3
- The datasets of gen_data.py HOT 2
- two optimizers in MGDA HOT 5
- if other datasets can be used by this model HOT 2
- Some questions about background_temporal_consistency loss 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 motionnet.