search

chengche6230 / ReST

[ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
MIT License
130 stars 15 forks source link

the images of CAMPUS and PETS datasets #22

Closed jingliang0910 closed 7 hours ago

jingliang0910 commented 1 week ago

image how can I prepare the images of CAMPUS and PETS datasets? In CAMPUS of your provided datasets, no existing image ，only some videos. How can I process these videos? I have used your "preprocess" function, but no image produced.

chengche6230 commented 3 days ago

Hi,

You can extract each frames of video by load_videos( ) function in preprocess.py, or by your own utility code. Just prepare the images with the same naming pattern.