Maximum pixel size using deep learning

[Zaki]

Hi, how much is the maximum pixel-size on the images i use to do deep learning analysis in ArcGIS PRO?

I remember that i saw a video which said something about 30cm, does someone have the link to that video?

[DrVSSKiran]

It depends on your image resolution and the type of object which you wish
to detect.

For example.
If I want to detect a car or tree or road crosswalks I want 20 to 30 cm
pixel size. On another side, If I want to detect forest patches, land
parcels, or settlement clusters I can use 50 cm to 1-meter resolution.

Similarly, If you are working on Land Use and Land Cover you can work 30 cm
to 10-meter resolution. Even you can use deep learning on sentinel
datasets. Hope I answered your question.

Thanks

[DanPatterson · Accepted solution]

for what activity?

Building footprint extraction? 10-40 cm  Deep Learning with ArcGIS Pro Tips & Tricks: Part 2 (esri.com)

[Zaki]

Hi, it is building footprint extraction. Your reply answers the question perfectly 🙂