kaist-avelab / k-radar_v1 Goto Github PK
View Code? Open in Web Editor NEW4D Radar Object Detection Dataset and Benchmark for Autonomous Driving in Various Weather Conditions
4D Radar Object Detection Dataset and Benchmark for Autonomous Driving in Various Weather Conditions
Thank you for the wonderful dataset and offering Google Drive to download the data!
The file meta_1.zip
(for sequence 1) does not have permissions for viewers to download it, unlike all other files. This needs to be manually changed :)
Thanks for the great research!
I have a few questions.
Can you tell us how 4d radar is calibrated with Lidar and camera?
Hi, Thank you for building and sharing this dataset. It is very useful. Great job!
Could you please provide a specification for how to use dataset, like data format, time synchronization and so on? I just downloaded part of zips (It is too big to be downloaded completely) but didn't found. Maybe it is in one of them?
And, the project mentioned that all development kits and labeling tools will be released too. Could you also show me how to get them please?
Thanks again!
Thanks for the great research!
I have a few questions.
Hi! Thanks again for sharing the great job!
I want to know is the complex number format stored in the 4DRT(4D Radar tensor) data? And when will the dataset be made public?
Thank you for the wonderful dataset and sharing Google Drive links to download it!
I have noticed there are no instructions on how to unzip/merge the three archives for radar data in each sequence. Take for example sequence 2, there are files radar_02.z01
, radar_02.z02
and radar_02.zip
. The final of those three contains reference to all 628 *.mat
files contained in the multi-part archive (seen using unzip -l radar_02.zip
). However, if extracted using unzip
, only 148 files are obtained (with some warnings about missing data). It seems like it skips radar_02.z01
and radar_02.z02
.
I have tried concatenating the three zip files and then opening a single file, but that also fails:
$ cat radar_02.z01 radar_02.z02 radar_02.zip > radar_combined_z01_z02_zip.zip
$ unzip radar_combined.zip
Archive: radar_combined_z01_z02_zip.zip
error: End-of-centdir-64 signature not where expected (prepended bytes?)
(attempting to process anyway)
warning [radar_combined_z01_z02_zip.zip]: zipfile claims to be last disk of a multi-part archive;
attempting to process anyway, assuming all parts have been concatenated
together in order. Expect "errors" and warnings...true multi-part support
doesn't exist yet (coming soon).
warning [radar_combined_z01_z02_zip.zip]: 27917287424 extra bytes at beginning or within zipfile
(attempting to process anyway)
file #1: bad zipfile offset (local header sig): 27917287428
(attempting to re-compensate)
error: invalid zip file with overlapped components (possible zip bomb)
Instructions found in the K-Lanes dataset unfortunately do not work in this case either:
To unzip the file in linux system(eg. Ubuntu 20.04)
// sudo apt-get install default-jdk
// jar xvf (file_you_downloaded).zip
This gives errors (for individual parts and the concatenated file from above) such as:
$ ▶ jar xfv radar_combined_z01_z02_zip.zip
java.util.zip.ZipException: invalid CEN header (bad signature)
at java.base/java.util.zip.ZipFile$Source.zerror(ZipFile.java:1607)
at java.base/java.util.zip.ZipFile$Source.initCEN(ZipFile.java:1557)
at java.base/java.util.zip.ZipFile$Source.<init>(ZipFile.java:1308)
at java.base/java.util.zip.ZipFile$Source.get(ZipFile.java:1271)
at java.base/java.util.zip.ZipFile$CleanableResource.<init>(ZipFile.java:733)
at java.base/java.util.zip.ZipFile$CleanableResource.get(ZipFile.java:850)
at java.base/java.util.zip.ZipFile.<init>(ZipFile.java:248)
at java.base/java.util.zip.ZipFile.<init>(ZipFile.java:177)
at java.base/java.util.zip.ZipFile.<init>(ZipFile.java:148)
at jdk.jartool/sun.tools.jar.Main.extract(Main.java:1388)
at jdk.jartool/sun.tools.jar.Main.run(Main.java:410)
at jdk.jartool/sun.tools.jar.Main.main(Main.java:1680)
Any help would be greatly appreciated :)
Hello,
I can now access the dataset link. It has 54 zip files with each having ~200 GB+ data.
Does that mean the total size of the dataset is approx. 50 x 200 = 10000 GB+ ???
Could you please clarify this?
Thanks,
Kevin
After retrying many times, I was able to connect to the NAS server and view the files.
There are ~50 zip archives, each ~200 GiB in size. I reached a steady download speed that meant > 3 weeks for a single zip file. The download can only take place via the browser itself, so successfully finishing a download over 3 weeks will be difficult (I haven't managed it).
Would it be possible to make links that can be downloaded in a terminal e.g. using wget
or curl
? Alternatively, making files available via something like AWS or GCS would make the data much more accessible; higher download speeds and terminal CLI tools for headless downloads.
Great work and dataset! I tried to download it through the NAS link but it seems your server is down. Very interested in when your dataset will be able to be downloaded again.
Thanks for publishing your interesting work!
I wonder if you plan to share your some pretrained model?, so we can try the model without training from scratch. As the dataset is huge to download.
Thanks.
Hello, how can I get the account and password of this website (https://kaistavelab.direct.quickconnect.to:54568/)? Can the public download it for free now? Thank you in advance for your reply.
Hi, I have read the Matlab code about the radar data processing. Here are my questions?
1、when transfer the DREA to XYZ, the code just mean the frist 10 doppler array? I think because the objects is dynamic, why not mean all the doppler dimension?
2、the speed is ranging from the -1.9 to 1.9m/s, and I think the radar form may be designed to detect much larger speed by using different chirps?
Hope to know more detail about the cfg of the radar.
Thanks for the great contribution! But just found that the link to the NAS server is down (https://kaistavelab.direct.quickconnect.to:54568/). Could you please help? Thanks!
Thanks for your great dataset.
For carrying out research on sensor fusion, we need the extrinsic parameters of the sensors (camera, lidar and radar) could you please offer that ?
Thanks for the contribution
I'd like to know if the raw IMU and GNSS data is available?
can this dataset be used to slam?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.