jkk-research / urban_road_filter

Real-time LIDAR-based Urban Road and Sidewalk detection for Autonomous Vehicles 🚗
BSD 3-Clause "New" or "Revised" License
296 stars 80 forks source link

Add some usage examples #3

Closed chengwei0427 closed 2 years ago

chengwei0427 commented 2 years ago

Hi, Horvath

Great work! I'm very interested in your work. Can you add some usage demo about this work.

Thanks!

horverno commented 2 years ago

hi, sure, actually issue #2 will be about this

horverno commented 2 years ago

@chengwei0427 here is a usage example:

In a new terminal start roscore:

roscore

In a new terminal go to your bag folder (e.g. ~/Downloads):

cd ~/Downloads

Download a sample rosbag:

wget https://laesze-my.sharepoint.com/:u:/g/personal/herno_o365_sze_hu/EYl_ahy5pgBBhNHt5ZkiBikBoy_j_x95E96rDtTsxueB_A?download=1 -O leaf-2021-04-23-campus.bag

Play rosbag:

rosbag play -l ~/Downloads/leaf-2021-04-23-campus.bag

In a new terminal start the urban_road_filter node, rviz and rqt_reconfigure with roslaunch:

roslaunch urban_road_filter demo1.launch
chengwei0427 commented 2 years ago

good, I'll check and update. Thank you!

chengwei0427 commented 2 years ago

@chengwei0427 here is a usage example:

In a new terminal start roscore:

roscore

In a new terminal go to your bag folder (e.g. ~/Downloads):

cd ~/Downloads

Download a sample rosbag:

wget https://laesze-my.sharepoint.com/:u:/g/personal/herno_o365_sze_hu/EYl_ahy5pgBBhNHt5ZkiBikBoy_j_x95E96rDtTsxueB_A?download=1 -O leaf-2021-04-23-campus.bag

Play rosbag:

rosbag play -l ~/Downloads/leaf-2021-04-23-campus.bag

In a new terminal start the urban_road_filter node, rviz and rqt_reconfigure with roslaunch:

roslaunch urban_road_filter demo1.launch

It's amazing on my test data. But the code is hard to read,Can you add some English annotation?

2022-01-12 14-42-10屏幕截图

horverno commented 2 years ago

@chengwei0427 thanks for the feedback

1 will be about the refactor and english comments in the code @dobaybalazs is assigned to this task

In the meantime you can read the published paper as a pdf. It describes the algorithm in detail.

It's amazing on my test data. But the code is hard to read,Can you add some English annotation?

chengwei0427 commented 2 years ago

Another question, Does this method support 16-line or 32-line lasers? If yes, what parameters need to be adjusted? thanks again.

horverno commented 2 years ago

The original algorithm was developed for 16 channel LIDAR, so probably it will work (unless we have done something what breaks this compatibility). The star_shaped_method has the least limitations, so try to disable x_zero_method and z_zero_method in the rqt_reconfigure window. The star_shaped_method also works on special pointclouds (e.g. provided by a solid state LIDAR).

This issue is about the usage examples, so I will close this now, but feel free to open another issue about the compatibility if needed.

chengwei0427 commented 2 years ago

My questions are well solved. Thank you for your patient reply. Thanks again.

juliangaal commented 1 year ago

The original algorithm was developed for 16 channel LIDAR

Can you share some good parameters for, let's say, a VLP16?

horverno commented 1 year ago

Currently I don't have acees to VLP16, but as mentioned maybe you can try to adjust the interval param which adjusts the LIDAR's vertical resolution. Try it in a launch file, but as far as i remember rqt_reconfigure may also works.

Maybe @csaplaci also can suggest something.