mono_dataset_code icon indicating copy to clipboard operation
mono_dataset_code copied to clipboard

Published 20 hours ago • verified publisher icon tum-vision

create tum dataset for my video

Open yolingen23 opened this issue 5 years ago • 4 comments

I want to convert my own video data into a folder structure like TUM benchmarks. So you want to create times.txt, camera.txt, statistic.txt and times.txt. how do I do this automatically? or what do the columns in statistic.txt and times.txt mean?

fx fy cx cy k1 k2 p1 p2 inputWidth inputHeight "crop" / "full" / "none" / "e1 e2 e3 e4 0" outputWidth outputHeight 0.349153000000000 0.436593000000000 0.493140000000000 0.499021000000000 0.933271000000000 ???

yolingen23 avatar Jun 22 '19 21:06 yolingen23

Same problem. How can I calibrate from my image sequences

AI-ML-Enthusiast avatar May 29 '20 06:05 AI-ML-Enthusiast

Did you solve this?

zovelsanj avatar Dec 19 '22 10:12 zovelsanj

Same problems. Have anyone figured this out?

YangGangZhiQi avatar Jun 08 '23 09:06 YangGangZhiQi

Same problems. Have anyone figured this out?

Hi @YangGangZhiQi, can you please look at Readme at this fork? I have added descriptions for camera.txt and times.txt after testing in my custom dataset but couldn't automatically generate statistics.txt.

zovelsanj avatar Jun 12 '23 03:06 zovelsanj