search

shuaishiliu / SGCN

Code for "SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction" CVPR 2021
MIT License
90 stars 20 forks source link

Question about visualization in your paper #7

Closed Xiejc97 closed 2 years ago

Xiejc97 commented 3 years ago

Hi,

Thank you very much for your work and I'm very interested in trajectory prediction.

I have some problems about the visualization of predicted trajectory.

  1. How to visualize the predicted trajectories distribution in your paper Fig4?
  2. How to plot the trajectories in the scene picture just like the Fig5 in your paper? Will you provide the code if you like? I hope you can help me solve the problem. Thank you very muh!

Best, Jincan

shuaishiliu commented 3 years ago

Hi,

Thank you very much for your work and I'm very interested in trajectory prediction.

I have some problems about the visualization of predicted trajectory.

  1. How to visualize the predicted trajectories distribution in your paper Fig4?
  2. How to plot the trajectories in the scene picture just like the Fig5 in your paper? Will you provide the code if you like? I hope you can help me solve the problem. Thank you very muh!

Best, Jincan

Hi, The visualized trajectotry in Figure 4 is directly plotted used the world coordinates, and the Fig5 is plotted by converting the world coordinate to image coordinates. You can obtain the homography matrix in below line to covert them. ETH:https://icu.ee.ethz.ch/research/datsets.html UCY:https://graphics.cs.ucy.ac.cy/research/downloads/crowd-data

MZ82020 commented 2 years ago

@shuaishiliu Hello,

Thank you for your work. How can I convert the world coordinate to image coordinate please? Can you share with us the code for visualization of figures 4 and 5 please?

Thanks

MZ82020 commented 2 years ago

Hello @shuaishiliu, How can I convert the world coordinate to image coordinate please? Can you share with us the code for visualization of figures 4 and 5 please?