Coder Social home page Coder Social logo

tsenst / crowdflow Goto Github PK

View Code? Open in Web Editor NEW
104.0 7.0 22.0 1.99 MB

Optical Flow Dataset and Benchmark for Visual Crowd Analysis

License: GNU General Public License v3.0

Python 100.00%
computer-vision optical-flow dataset benchmark-suite crowd-analysis motion-estimation synthetic-images video-processing video-analytics video-surveillance

crowdflow's People

Contributors

bochinski avatar tsenst 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

crowdflow's Issues

Test on video

Hi,

How can i use your framework to test on my own video data.

more details ?

thanks for sharing your work, but could u pls. release more details...?
for example, i am repeating the work through the guidelines you gave in README, now i have the evaluation results of dual method of short-term, but i can't find your results to compare. I want to know if my results is wrong or not.

thanks a lot for that you have released the Common optical flow metrics (short-term), Tracking Accuracy (long-term), but only the digits, could u pls. release a little more estimate source code so i can check my evaluation results ?

forward to your reply, thanks!

Update the README.md file

In the section "Evaluation Framework"

The statement :
must be stored as /estimate/[mymethod]/images/IM01/frame_0000.flo

Should be updated as:
must be stored as /estimate/[mymethod]/IM01/frame_0000.flo

Gives file read error otherwise.

error when viewing the .TEX file

i view the file both in https://cn.overleaf.com and using TeXworks, but failed
the overleaf reported:

LaTeX Error: Environment table undefined.

You have created an environment (using \begin{…} and \end{…} commands) which is not recognized. Make sure you have included the required package for that environment in your preamble, and that the environment is spelled correctly.

 了解更多
See the LaTeX manual or LaTeX Companion for explanation.
Type  H <return>  for immediate help.
 ...                                              
                                                  
l.1 \begin{table}
                 
Your command was ignored.
Type  I <command> <return>  to replace it with another command,
or  <return>  to continue without it.

 main.tex, line 2
LaTeX Error: Missing \begin{document}.

attached is the tex file after evaluation.
short_term_results.zip

error with progressbar

error when using progressbar 2.5

run opticalflow_evaluate.py,

/usr/bin/python3.5 -u /home/xxx/CrowdFlow-master/opticalflow_evaluate.py /home/xxx/TUBCrowdFlow dual farneback plk

got error:

Traceback (most recent call last):
  File "/home/xxx/CrowdFlow-master/opticalflow_evaluate.py", line 92, in <module>
    main()
  File "/home/xxx/CrowdFlow-master/opticalflow_evaluate.py", line 74, in main
    bar.start(max_value=len(config_list) * len(parameter_list))
TypeError: start() got an unexpected keyword argument 'max_value'

Process finished with exit code 1

if edited the line 74#, replace max_value with maxval, still got error:


Traceback (most recent call last):
  File "/home/xxx/CrowdFlow-master/opticalflow_evaluate.py", line 92, in <module>
    main()
  File "/home/xxx/CrowdFlow-master/opticalflow_evaluate.py", line 74, in main
    bar.start(maxval=len(config_list) * len(parameter_list)) 
TypeError: start() got an unexpected keyword argument 'maxval'

this can be fixed by using progressbar 3.46.1 (tested)

module 'cv2.cv2' has no attribute 'DualTVL1OpticalFlow_create'

hello, what's the requirement of running this project, i followed the README in ubuntu16.04 with opencv 4.1.1 but got error:

python3 opticalflow_estimate.py /home/xxx/dataset/middlebury/test/ dual farneback plk

Traceback (most recent call last):
File "opticalflow_estimate.py", line 118, in
main()
File "opticalflow_estimate.py", line 116, in main
run_parameter(config_item)
File "opticalflow_estimate.py", line 39, in run_parameter
dual_proc = cv2.DualTVL1OpticalFlow_create(config_item["parameter"]["tau"],
AttributeError: module 'cv2.cv2' has no attribute 'DualTVL1OpticalFlow_create'

IM01 and IM01_hDyn

excuse me, what's the meaning and difference between IM01 and IM01_hDyn ?
What's the "_hDyn" stands for (was that stands for dynamic? then what does the "_h" mean ) ?
...and so on. Could u pls. share more description info. of the dataset ?

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.