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?
You're welcome, and thanks again for providing the images. Keep in touch!
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.
P.S. What do you all think?
Great work, especially when dealing with so many overlapping plants.
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.
@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.
Fantastic software you have developed. Can this be applied to NIR images as well? I have some NIR images you can test it on if you are interested?
Thanks! Yes, it should work just fine with NIR images as well.
I would love to see your images and test against them. You can email me at tcg [at] precisionsilver.com,
or send me a PM through the DIYDrones site and we can arrange another method of transferring them.
Very good your work Taylor
Working in Brazil with sugar cane if you are interested in testing their software, I have some mosaics on different dates.
(sorry for my writing in English)
I just sent you a direct message through the forum. I'd be very interested to see the mosaics you have and see what kind of results we can get.
I have images of oil palm crops - both in RGB and NiR-GB. Can I share it with you so that you can count the stands as well.
I can't direct message you since we're not friends yet on the site. So I'm posting a reply here before I forget.
I'd be happy to take a look at your images. You can email them to me if they are small enough, or send me a link from dropbox, google drive, etc. if that is more convenient. Email: tcg [at] precisionsilver.com.
Do you have any news about the commercial license of your software?