Hello,
I was wondering if anyone could share their experiences with estimating populations on photos they've taken with UAVs. Software or particular methods that you have found to work. I currently use a Y6 tri-copter from Event 38 with a GoPro Camera as well as a Canon SX 260 converted to near-infrared. I've used Agisoft Photoscan with great success in photo-stitching and dronemapper. I've dabbled with Fiji/image j, and Microsoft ICE but I've found they seem to have more of a learning curve for me.
Any ideas if population estimates work well in any of these programs or in others that I have not mentioned?
Thanks!
Replies
Hi Cala,
Thank you! This software is not commercially available yet, but I am working for it to be available soon.
I am happy to run a few images here or there for you or anyone who would like, this helps me to develop the software, but also if people find it useful I like to help out.
If you have a lot of imagery I could also do this as a fairly low cost service as well. Feel free to PM or email me (tcg at precisionsilver.com) and we can discuss.
best,
-Taylor
Hi Taylor.
Your software is great, I have mede some work withBanana crops, and I was wondering if There has been progress in the comercial version of your software?.
Best regards
(apologies for my english).
Pedro
Hi Pedro, send your sample files and more info to ruchit@harvesting.co
Hi
Thank you, the actual file is a very large Geotiff, I will clip it and send it via Dropbox.
Pedro
If you need some images I can send to you, I have sunflower, corn, soybean, wheat and potato if you need something in special
Hi Cala,
I was able to get some results on your sunflower image.
This one was very difficult. But it helped to improve my methods quite a bit, so thanks.
Like Morgan's corn image, there is a lot of perspective shift due to the wide angle lens. The performance really drops off in the corners of the image where the perspective is most oblique. I'd recommend in the future shooting with a narrower field of view from a higher altitude. The spatial resolution was great here, and in this case the counting would likely work with lower spatial resolution (larger GSD), so 2-3x higher altitude with half the field of view would likely work well.
Here is a low res version of the result with bounding boxes around the estimated plants.
The software identifies 91 plants in the image. Going through this by hand I calculated that it is accurate to within 5%, and is maybe a bit biased towards false positives over false negatives.
Thanks again for sending the images, I'll try to run through some more of them when I have some free time.
-Taylor
P.S. What do you all think?
@Eric, @Cala Thanks!
Yes, we can certainly crop the image down to the center section to reduce any errors, and in general you can set a region of interest to process on.
Guouu!!! it's impressive that your soft can count that photo, I share difficult photos so you can evaluate your soft limits if we have to use that type image, perhaps it's better to cut borders to minimize errors?, I send as it.
Great work, especially when dealing with so many overlapping plants.
That would be great! I'll take one of each. Feel free to send me a link on Dropbox or Google Drive. Or if you need it I can send an account to upload to.
I have gotten good results with corn and potato plants so far, but the soybeans I have seen I have not been able to separate the individual plants (I think it will have to be pretty early after emergence and very high-spatial-resolution/low-altitude images). Sunflowers and wheat sounds great too. Thanks