Comments (8)
- the transformation is largely following GenLaneNet. You can have a try on R_gv@E method and see if there's any improvement.
- sorry, that was a typo in OpenLane repo. We'll fix it. The correct coordinate system is vehicle coordinates.
from persformer_3dlane.
for this step
cam_extrinsics[:3, :3] = np.matmul(np.matmul(np.matmul(np.linalg.inv(R_vg),cam_extrinsic[:3, :3]),R_vg), R_gc)
could you help me figure out, what is this inv(R_vg) @ E @ R_vg @ R_gc
doing? To my mind, E_g2c is final target here, am I right? But I still can not understand each step transformation in above line. Could you give some interpretation that would be very appreciated :) thanks !
from persformer_3dlane.
same question as above
from persformer_3dlane.
@ChonghaoSima it seems quite strange that the annotations are in the vehicle_coordinate system. Specifically, the z
part of the annotations tends to be negative most of the times. it seems to in the camera coordinates after all.
For example, in lane3d_1000/training/segment-15832924468527961_1564_160_1584_160_with_camera_labels/150767882737686600.json
the first lane is (labels_dict is dictionary of the loaded json)
min(lanes_visualization_obj.labels_dict['lane_lines'][0]['xyz'][2])
Out[15]: -3.8558186921526554
max(lanes_visualization_obj.labels_dict['lane_lines'][0]['xyz'][2])
Out[16]: -2.2029994863655915
And the 2nd one is:
min(lanes_visualization_obj.labels_dict['lane_lines'][1]['xyz'][2])
Out[18]: -2.4630904216158926
max(lanes_visualization_obj.labels_dict['lane_lines'][0]['xyz'][2])
Out[19]: -2.2029994863655915
and the third one is:
min(lanes_visualization_obj.labels_dict['lane_lines'][2]['xyz'][2])
Out[20]: -3.8966073247935045
max(lanes_visualization_obj.labels_dict['lane_lines'][2]['xyz'][2])
Out[21]: -2.4456845933203346
from persformer_3dlane.
Please refer to https://github.com/OpenPerceptionX/OpenLane/issues/24. It should solve your questions. The annotations are under the Waymo camera coordinate (The typo has been updated in https://github.com/OpenPerceptionX/OpenLane/blob/main/anno_criterion/Lane/README.md).
from persformer_3dlane.
We will close this issue, if you still have the same questions, please reopen this.
from persformer_3dlane.
It should solve your questions. The annotations are under the Waymo camera coordinate (The typo has been updat
Seems the link is invalid, may you update the explanation of this issue?
from persformer_3dlane.
@usherbob Just change OpenPerceptionX to OpenDriveLab: https://github.com/OpenDriveLab/OpenLane/blob/main/anno_criterion/Lane/README.md
from persformer_3dlane.
Related Issues (20)
- Will apollo dataset pretrained model release?
- ZeroDivisionError: Weights sum to zero, can't be normalized HOT 2
- Some question about the results of x_far,x_close,z_far,z_close? HOT 1
- 加载EfficientNet模型报错“unexpected EOF”
- visualization HOT 2
- JSON file Error
- Single Inference HOT 1
- Unable to replicate the performance of GenLaneNet and 3DLaneNet on the openlane dataset based on your framework.
- sheared feature mapping
- TypeError: 'module' object is not callable HOT 2
- 分布训练
- 关于类别数问题 HOT 3
- 不使用分布式训练
- UnboundLocalError: local variable '_label_cam_height' referenced before assignment HOT 1
- apollo dataset pretrained model
- Some questions on code
- how to derive H_g2cam?
- 推理其他数据集发生错误
- Lane Detection Results
- nms installed error
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 persformer_3dlane.