Comments (11)
@memoiry for ground plane generation, we used a mixture of older methods that are probably considered obsolete now:
-
Ground segmentation and occupancy grid generation using probability fields:
https://www.researchgate.net/profile/Ali_Harakeh2/publication/282866885_Ground_Segmentation_and_Occupancy_Grid_Generation_Using_Probability_Fields/links/56baf64008ae0a6bc9557788/Ground-Segmentation-and-Occupancy-Grid-Generation-Using-Probability-Fields.pdf
from avod.
The second link is dead and planes in README is also dead.
from avod.
It looks like the ground plane algorithm is a little time-consuming, is that only the kitti testing, you are using this ground plane detection.
But when you are really deploying the model, it is a different story, for example, you are using a fixed ground plane ?
from avod.
Yes for deployment, we do constant ground plane to eliminate the time required for estimation. It works well in practice, but I doubt it to be a good approach for beating the KITTI benchmark.
from avod.
Thanks, my issue is solved
from avod.
@ @memoiry @yzhou-saic Have you solved the problem of ground plane about the test set?
from avod.
@hulaifeng @asharakeh So, how to generate the ground plane when testing?
from avod.
@jinfagang http://www.cs.toronto.edu/objprop3d/
from avod.
Thanks, my issue is solved
how to solve it?thank you
from avod.
@memoiry for ground plane generation, we used a mixture of older methods that are probably considered obsolete now:
- Ground segmentation and occupancy grid generation using probability fields:
https://www.researchgate.net/profile/Ali_Harakeh2/publication/282866885_Ground_Segmentation_and_Occupancy_Grid_Generation_Using_Probability_Fields/links/56baf64008ae0a6bc9557788/Ground-Segmentation-and-Occupancy-Grid-Generation-Using-Probability-Fields.pdf- http://www.cs.toronto.edu/objprop3d/
The second link is dead. Could you please update?
from avod.
I see the page in this link
from avod.
Related Issues (20)
- Checking the mAP for cars, cyclist, and pedestrian HOT 9
- Running AVOD on Jetson Xavier
- ImportError: No module named 'wavedata.tools' HOT 1
- Running in real time
- ImportError: cannot import name 'kitti_dataset_pb2' from 'avod.protos' HOT 1
- What is the meaing of each value of output file? HOT 1
- What is the difference between box_3d , 'box_8c', 'box_8co',box_4c,'box_4ca' encoding for a bounding box ?? HOT 4
- Convert checkpoints to frozen graph, "ValueError: graph_def is invalid at node u'global_step/Assign': Input tensor 'global_step:0' Cannot convert a tensor of type int32 to an input of type int32_ref."
- TypeError: build() got multiple values for argument 'layers_config' HOT 2
- Pretrained Model HOT 1
- Problems with Run Evaluator
- questions about usage of kitti(more specifically which files to download)? HOT 1
- Result of test set
- About the RPN loss (smooth_L1_LOSS)
- Model capability to work with a tilted camera frame HOT 1
- Excuse me, an error is reported when generating Mini-batch, for obj_label in obj_labels: TypeError: 'NoneType' object is not iterable. What is the reason for this?
- protoc: not found HOT 1
- could anyone send me a Pretrained model for SSD-AVOD / AVOD ? HOT 1
- request to give access for pretrained model
- Evaluate the mAP of only one image
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 avod.