veyepar: Detecting Road Conditions from Space Using PyTorch, Public Data, and Free Satellite Imagery

Author(s):	Cynthia Ukawu
Location	Ballroom B
Date	jul Sat 26	Days Raw Files
Start	10:15	First Raw Start	10:59
Duration	00:30:00	Offset	0:44:55
End	10:45	Last Raw End	11:59
Chapters	00:00 0:18:37 0:25:41
Total cuts_time	31 min.

https://www.pyohio.org/2025/program/talks/detecting-road-conditions-from-space-using-pytorch-public-data
raw-playlist raw-mp4-playlist encoded-files-playlist mp4 svg png

assets release.pdf Detecting_Road_Conditions_from_Space_Using_PyTorch_Public_Data_and_Free_Satellite_Imagery.json
logs
Admin: episode episode list cut list raw files day marks day marks day image_files

State:
Locked:	clear this to unlock
Locked by:	user/process that locked.
Start:	initially scheduled time from master, adjusted to match reality
Duration:	length in hh:mm:ss
Name:	Video Title (shows in video search results)
Emails:	email(s) of the presenter(s)
Released:	has someone authorised pubication
Normalise:
Channelcopy:	m=mono, 01=copy left to right, 10=right to left, 00=ignore.
Thumbnail:	filename.png
Description:	Monitoring the health of city streets and roadways is expensive, time-consuming, and often reactive. But what if we could automate part of that process using satellite imagery and Python? In this talk, we’ll walk through a real-world project that combines transfer learning, PyTorch, and publicly available datasets to classify road segment conditions (good, fair, poor) from aerial imagery. You'll learn how to work with messy real-world geospatial data, fine-tune a deep learning model using only a small training set (~2,000 examples), and overcome common challenges like blurry imagery, inconsistent labels, and overfitting. This session is practical and code-driven, aimed at data scientists and analysts working in mobility analytics, urban development, or infrastructure who want to apply machine perception techniques in their work. By the end, you’ll walk away with a reusable workflow for analyzing and predicting urban infrastructure quality — all using free tools and open data. markdown
Comment:	production notes

2025-07-26/10_59_55.ts Apply: 10:59:55 - 11:02:27 ( 00:02:32 ) S: 10:59:55 - E: 11:29:54 D: 00:29:59 (End: 152.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/10_59_55.ts :start-time=00.0 --audio-desync=0

	Raw File	Cut List
	10:59:55		seconds: 0.0 Wall: 10:59:55
Duration	00:29:59
	11:29:54		seconds: 152.0 Wall: 11:02:27
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/10_59_55.ts Apply: 11:02:27 - 11:10:35 ( 00:08:08 ) S: 10:59:55 - E: 11:29:54 D: 00:29:59 (Start: 152.0) (End: 640.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/10_59_55.ts :start-time=0152.0 --audio-desync=0

	Raw File	Cut List
	10:59:55		seconds: 152.0 Wall: 11:02:27
Duration	00:29:59
	11:29:54		seconds: 640.0 Wall: 11:10:35
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/10_59_55.ts Apply: 11:10:35 - 11:11:17 ( 00:00:42 ) S: 10:59:55 - E: 11:29:54 D: 00:29:59 (Start: 640.0) (End: 682.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/10_59_55.ts :start-time=0640.0 --audio-desync=0

	Raw File	Cut List
	10:59:55		seconds: 640.0 Wall: 11:10:35
Duration	00:29:59
	11:29:54		seconds: 682.0 Wall: 11:11:17
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/10_59_55.ts Apply: 11:11:17 - 11:29:54 ( 00:18:37 ) S: 10:59:55 - E: 11:29:54 D: 00:29:59 (Start: 682.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/10_59_55.ts :start-time=0682.0 --audio-desync=0

	Raw File	Cut List
	10:59:55		seconds: 682.0 Wall: 11:11:17
Duration	00:29:59
	11:29:54		seconds: 0.0 Wall: 10:59:55
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/11_29_55.ts Apply: 11:29:55 - 11:36:59 ( 00:07:04 ) S: 11:29:55 - E: 11:59:55 D: 00:30:00 (End: 424.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/11_29_55.ts :start-time=00.0 --audio-desync=0

	Raw File	Cut List
	11:29:55		seconds: 0.0 Wall: 11:29:55
Duration	00:30:00
	11:59:55		seconds: 424.0 Wall: 11:36:59
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/11_29_55.ts Apply: 11:36:59 - 11:42:21 ( 00:05:22 ) S: 11:29:55 - E: 11:59:55 D: 00:30:00 (Start: 424.0) (End: 746.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/11_29_55.ts :start-time=0424.0 --audio-desync=0

	Raw File	Cut List
	11:29:55		seconds: 424.0 Wall: 11:36:59
Duration	00:30:00
	11:59:55		seconds: 746.0 Wall: 11:42:21
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/11_29_55.ts Apply: 11:42:21 - 11:57:01 ( 00:14:40 ) S: 11:29:55 - E: 11:59:55 D: 00:30:00 (Start: 746.0) (End: 1626.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/11_29_55.ts :start-time=0746.0 --audio-desync=0

	Raw File	Cut List
	11:29:55		seconds: 746.0 Wall: 11:42:21
Duration	00:30:00
	11:59:55		seconds: 1626.0 Wall: 11:57:01
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

2025-07-26/11_29_55.ts Apply: 11:57:01 - 11:59:55 ( 00:02:54 ) S: 11:29:55 - E: 11:59:55 D: 00:30:00 (Start: 1626.0) show more...

vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/cattleya/2025-07-26/11_29_55.ts :start-time=01626.0 --audio-desync=0

	Raw File	Cut List
	11:29:55		seconds: 1626.0 Wall: 11:57:01
Duration	00:30:00
	11:59:55		seconds: 0.0 Wall: 11:29:55
Comments:
mp4 mp4.m3u	dv.m3u	Split: Sequence:: delete

Rf filename:	root is .../show/dv/location/, example: 2013-03-13/13:13:30.dv
Sequence:
get this:	check and save to add this