Dear UAV fellows,
now that I have a drone with RGB and NGB cameras onboard, Pixhawk working well (except airspeed sensor), automatic triggering of both cameras at the same time (sync), Photoscan Pro to deliver orthomosaic/DEM pretty easy and fast, I can focus on the applications. I've selected vineyards and wine makers and surprisingly I could not find any straightforward way how I can sell my product. So let's find out if something interesting comes out of the discussion here. If you have your own experience in this area, please share it here.
I have access to a local wine grower here in Slovakia. I want to use this opportunity to do my own research and share the results and observations here. I intend to go out and map the vineyard (30ha) frequently according to the weather. The grower has several types of grapes and the main purpose would be to find out if NDVI or other VI can be used to monitor the plant stress and the reason why it occurs. I've included some figures from the book Remote Sensing of Vegetation 2010 that could be a good starting point. I realize this could be a long way to find out the simple facts that could help the growers and that the research is ongoing already elsewhere. First I have to find some source of funding to do this long-term research..
Replies
Hi Michal, i m a drone enthusiast (i ve 2 iris and various mini drones) and my father owns prestigious vineyards in St Emilion France (Regularly noted around 90 by Robert Parker). I would be interested to understand your approach and your objectives. There is a real mature market in France for Precision Viticulture. There are also a lot of people already offering services in this area (We have in France a clear UAV legal context and more than 300 registred drone companies.)
Well, nice to hear about the interest.. If you have so many companies already offering such services, try to ask them what is the real added value for the vine growers that they offer. So far I could not find anything real, just general description of products/services. My list of companies with Viticulture experience :
http://www.mavrx.co/product/vineyards/
http://www.delair-tech.com/en/references/precision-viticulture
This topic certainly needs a proper research. If someone says NDVI adds some value and they have the proof, then fine but show us the results. This is a thin line here.. A consumer grade camera converted to NIR camera is certainly not the best option here. The bands are broad and results unclear. I will have to study more literature now on this topic, especially the use of UAVs in viticulture. There has been some research done so let's see what has proven to be beneficial for the growers.
My concern is also the choice of the right sensor. There are indications that thermal or hyperspectral camera could do the job better. But those might cost too much. For testing this is not a good way because nobody will just borrow me such sensor without paying anything. And the producers of these sensors are too far from Slovakia anyway.. But let's see..
So all in all my objectives are simple: Find out what sensor can bring which added value that would be interesting enough for the wine growers to invest in such service.
Another problem that I cannot answer without testing: Is orthophoto enough or you need DEM ? Photoscan will deliver both but the question is how much of the actual plant is visible to my camera ? I presume not much, maybe just 50%.. Obviously this depends on many factors e.g. the width between the vine rows, vine height, weather conditions, shadow etc.. And I presume orthophoto will not be sufficient because you will see only the top layer. This needs testing too..
Michal, Just a precision, we have more than 300 drone companies and operators in France but not so much with experience in the precision agriculture field. There was meeting in April in Montpellier on precision viticulture http://www.agrotic.org/blog/seminaire_viti_precision/ (250 People were attending the event - the registrant list is publicly available it may be a good starting point for you.) I can introduce you to Henri Borreill the CEO of exametrics if you want. + You ll find enclosed a list of french drone operators
Well thanks. But I really need some funding now. This needs proper long-term research with multiple cameras involved. Some EU funds could help.. After that I can come to France and do my woodoo :)
I am the exact same situation in France and I have been trying to catch European funds from France. Forget it. Same philosophy as a bank : if you are already a big boy and have money, you will get European funds, if not, drop it.
You are better off using kickstarter.com from your own country (there is no kickstarter.com in France), survive the first year, then start chasing government money.
I would forget a few European countries for a decent start-up, including France. I am actually trying to move out to create my own one.
I have some options here, will see how it evolves.. First I need to know if there is market desire for this.. That means talking to farmers before I can focus on getting the funds..
Yes, I've read that article too. NDVI seems to be outrun by simple NIR-VIS index. However this has to be tested.. And there are other indexes too.. My fear is the size of the vineyard coverage.. From the above, one may see only top leaves, the side ones and the grapes are probably not visible to the camera.. So I'm not sure how much I can actually detect.. But again this is the early stage and we live in exciting times of experiment.. I would love to try some hyperspectral scanner for even better variety of indexes to be tested too.. But that is 100k stuff..
Hi Michal,
my comment is to find a plant pathology that shows up via NDVI and similar techniques and see if the pathology is apparent enough to actually make a quantitative difference at harvest in using NDVI as a monitoring technique,.
One very common example is water stress.. there are others both in insect pests and microbial/viruses threats still awaiting someone to experiment and see if NDVI works to isolate the signal from the noise(useful data from images).
In your case you should be using your NDVI cam on sick plants where the pathology has been identified and examining reflected IR in several bands it may take a bit more than a converted consumer cam if no one has done the research as to which band gives the clearest detection signal for that pathology if indeed NDVI in ANY band is applicable for early detection and interdiction.
Once you have a cheaper way to detect that pathology rather than the farmer simply taking a loss at harvest then you have something you can use in marketing and possibly have a market to engage with services and products.
good luck
hzl
ps examining several markets besides precision ag, but ag IS a big one in florida,california and the midwest in the US. YMMV of course.
Water stress due to no irrigation is a fact already known in this local vineyard.. So that is not something a grower is interested to see/know. Maybe wine growers in different parts of the world with different weather characteristics are using irrigation, but in Slovakia with mild weather, I doubt anyone is.
The opportunity I have is to predict the location of disease that will outbreak in a matter of hours or the next day. That is something valuable according to my talk with them. Because if a disease appears, it's already too late. They are immediately applying cure spray against specific disease to the whole vineyard to prevent further spread. So my question is: Are the top leaves of vine showing some symptoms of upcoming disease on a NDVI or VI map ? Hard to tell right now.. But this could be a way how to save money on pesticides that are frequently used during the season..
QUOTE
now that I have a drone with RGB and NGB cameras onboard, Pixhawk working well (except airspeed sensor), automatic triggering of both cameras at the same time (sync), Photoscan Pro to deliver orthomosaic/DEM pretty easy and fast, I can focus on the applications. I've selected vineyards and wine makers and surprisingly I could not find any straightforward way how I can sell my product
UNQUOTE
Love it ! LOL.
-
1
-
2
-
3
of 3 Next