Giter Club home page Giter Club logo

highd-dataset's People

Contributors

robertkrajewski avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

highd-dataset's Issues

How to extract maneuvers?

Hi, thank you for your great work.

I was wondering which code can be used to extract maneuvers as mentioned in the paper (Krajewski et al., 2018).
I looked through the available scripts but couldn't locate this one.

Thank you very much for your time

a problem about the visualization

image

I tried to run the main.py and the visualization result is shown above (a blank picture).

It sames dosen't capture the key part of the whole picture.

I tried to scroll down heavily and the gray lane appeared gradually but I still didn't see any vehicles by now.

So, it is there any good suggestions to handle this situation?

My matplotlib is 3.3.2

folder_name and video_name

According to the Quickstart guide, running the function args = create_args() in main.py should create dictionary entries (in the args dictionary) for 'folder_name' and 'video_name' , but it does not. Note that I pulled a few hours ago.

Help

After the program runs, the button on the screen clicks and does not respond

ExiD Dataset anomaly

I am writing this email with respect to an anomaly that I observed in the ExiD dataset. Sorry to raise this issue in the HighD repo.

Issue:
The width and length columns in files xx_tracksMeta.csv and xx_tracks.csv are not matching for the same recordingId and trackId.

Can you please clarify which values are correct?

I also tried to connect to the regarding this through email, but the email address is not working.

No module named data_management.read_csv

Hi all,

I just started using the tool. While executing main.py, I got the follolwing error:

$python '/home/thomas.huang/Desktop/highD Dataset/src/main.py'

Traceback (most recent call last):
File "/home/****/Desktop/highD Dataset/src/main.py", line 6, in
from data_management.read_csv import *
ImportError: No module named data_management.read_csv

It will be greatly appreciated if anyone can fix this. Thanks.

Error

Hi!

When i run the main.py i get the following error:

self.maximum_frames = self.static_info[(last_track[TRACK_ID])][FINAL_FRAME] - 1

TypeError: unhashable type: 'numpy.ndarray'

Any fix?

Thanks!

About the pickle file

After changing The paths of three files(01_recordingMeta.csv,01_tracks.csv,01_tracksMeta.csv), running mian.py keeps a message indicating that The static info file is either missing or contains incorrect characters.

TTC calculation

Hello,

I am wondering how do you calculate the TTC in the dataset? I was assuming that
TTC = dhw/(xVelocity - precedingXVelocity); where TTC is time-to-collision, dhw is the distance headway, xVelocity is the ego vehicle's velocity, and precedingXVelocity is the preceding vehicle's velocity.

However, when I check it with the data, it was not correct. Therefore, I am wondering how do you calculate TTC in the dataset?

Please see the examples below.

Example from dataset_01

Case 1: vehicle id 2 is following vehicle id 13, here are the parameters in "track_data" of the vehicle id 2:

dhw = 112.62
ttc = -17.38
thw = 3.51
precedingXVelocity= -38.53
xVelocity = -32.06

If we follow the equation above. TTC should be equal to 112.62/(32.06-38.53) = 112.62/-6.47 = -17.40
(I think minus sign here indicate driving direction so I will ignore it for now)

Case 2: vehicle id 8 is following vehicle id 2, here are the parameters in "track_data" of the vehicle id 8:

thw = 2.29
dhw = 72.05
ttc = -104.67
precedingXVelocity = -32.04
xVelocity = -31.36

If we follow the equation above. TTC should be equal to 72.05/(31.36-32.04) = 72.05/-0.68 = -105.95

Last track is not displayed in the python version

As said in the title, the last track is no displayed when using the python version.
In the default dataset (01_tracks.csv) the last truck (ID:1047) is never displayed.

Steps to reproduce

  • run 'python main.py'
  • jump to last frame using the interface
  • open 01_tracksMeta.csv and skip to the last line to get the ID missing

It seems that the visualization part compute a wrong index for the tracks to be displayed.
Adding to this, using a CSV with only one track raise a out of index error.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.