yuliangguo / 3d_lane_synthetic_dataset Goto Github PK
View Code? Open in Web Editor NEWThis is a synthetic dataset constructed to stimulate the development and evaluation of 3D lane detection methods.
This is a synthetic dataset constructed to stimulate the development and evaluation of 3D lane detection methods.
Hi @yuliangguo
I am trying to run this on video input but I am confused, how to get it done and where to visualize the the new video.
Does this script support videos? or do I need to write my own wrapper around the code?
I did see --video_root
argument in argsparser
but am confused how it works.
Thanks
Do you know where to find the object ground truth? The website give the wrong link.
https://apollo.auto/synthetic.html
命令执行顺序:
parse_apollo_sim_raw_data.py
prepare_data_split.py
prepare_data_subset
I read your paper and observed that there are 3D lane line visualizations in the appendix, how do I achieve this?
Hi @yuliangguo ,
Thanks for the amazing work!
Could you clarify the projective transformation of the second stage network in the paper is done by a spatial transformer network or just a homography? If it’s done by a spatial transformer module, could you explain a bit more about the reason? Since it’s a two-stage network, I guess a spatial transformer module is not necessary? Thanks in advance!
Hi,
I've downloaded the dataset from the Google Drive link.
But found only 7498 images in the folder.
I am sorry to bother you. could you tell me which simulation platform did you used to genetate this dataset?
Looking forward to your reply.
Could you please update the download link? The previous URL didn't open
Hi, I am curious about do you also label lane instance when driving in the intersection or near the intersection.
If yes, how will you label it?
Thank you
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.