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 Tim,
thanks for great input ! It's always best to talk to people like you who know about the vine everything.. The application of any technology in a specific field is always a dual know-how that needs to be set.
About the virus - So far I have experience with one agronomist who works for the local wine grower and producer here in Slovakia. First I thought this UAV spectral mapping application with exact quantification and localization of pests or diseases would be valuable for them but then I've got a surprising answer. The agronomist said that when a disease appears in some part of the vineyard and he finds out, he immediately applies a cure/pesticides to the whole vineyard as a matter of precaution. He says it's already too late ! So he does not want to save money on purpose using a variable rate application. Now I don't understand this logic but is it normal ? Maybe I have to approach different wine producer and see the reaction.. Maybe in the US people think different..
The UAV birds - nice thought, should be easy to make it happen. I can see some potential in experimenting with ultrasonic sound etc.. But this should be automated one day ! Charge, fly, re-charge, fly, all autonomous.. No need for people to take care of this.. But in current human environment, impossible to deliver.. People are just too afraid of fully autonomous flying things without an operator.. But in future I see potential..
I'm not selling vehicles.. I offer service product.. There are too many things that may go wrong with this technology and I don't want to make a customer pay for these faults. It's not a reliable business model anyway if you are selling a device that a usual non-pilot has to operate. Even training requires now a manual control before you can apply autopilot and that takes time, nerves, stress, crashes etc.. I really am looking forward to a day when all this is a fully autonomous vehicle without a stress of a crash etc.. I imagine I'm sitting on a beach, drinking cocktail and watching my UAVs how they fly simultaneously over may customers fields and autonomously recharge, upload the data. All processed data is available almost instantly on the cloud and I can focus on the real business and not the tools to deliver it. One day..
Daily jobs - stress, vigor, water maps - this is weather dependent and things like Trimble Greenseeker have advantage over UAVs. But who knows about the price of those devices and how many you need over the vineyard.. If UAV's are about to bring some added value then simple consumer grade NIR sensitive camera will not be enough I fear. Hyperspectral or thermal camera may be the way to go and add more value information for the management.. But those are expensive.. Maybe one day I will have a chance to get one..
You may send me your email if you wish to talk more in private.. But firstly I wanted to share info here, it could be beneficial for all of us. It's like Linux - the best things in life are for free :)
Briefly: With regard to detection of pathogenic organisms, especially fungal growth which is the largest issue vinyards manage, yes, it is true that by the time you detect it, it is already too late and you are then just trying to manage the problem as best you can.
The best control is indeed prophylactic in those cases.
That said, if you can detect conditions that increase risk - and then the farmer can apply more of the control measure in response to increased disease pressure - then THAT is valueable.
In the case of mildew control, farmers apply sulphur or other chemicals repeatedly throughout the season. If you can detect the residue of those applications - basically measure how much is still attatched to the vine - then you can perhaps guide people to re-apply only when necessary.
It should be easy to see if you can make that kind of detection - coordinate with a grower who will be spraing on a certain day, and make muiltiple passes before application, just after, and at intervals after that..
If the cameras cannot see the fungicides in their spectrum - maybe you can find an additive that people mix into the fungicide that serves as a marker for the application...
Regarding birds, the work has already been done regarding what noises to make. Loud bangs are effective, but kinda annoying to the neighbors. The less annoying method is to broadcast both the screeches of predatory birds, interspersed with the alarm cries of the pest bird. This lets other birds in the area think that there is A) a predator in the area and B) it is killing their friends...
I saw someone with an RC plane with raptor wings painted on it, using it to scare birds away from vineyards as much as 15 years ago. But I have never heared of it since - probably because of the necessary pilot skill and the time involved. Perfect application for an unmanned craft repeatedly flying a series of waypoints over a vineyard...
OK one more thing: If the disease is showing on grapes only and it does not show on leaves then most probably I will not be able to detect it by any camera.. The leaves of vine are shadowing the grapes which means a problem.. There is only a partial chance the grapes are visible from some angle but that depends on too many factors.. Could you perhaps list some diseases that are visible on the top layer leaves ? I mean the color can change or it may shrink or anything that is visible without a NIR camera needed first..
Yes, the fungal issues are interior to the vine canopy since that is where the warm humid conditions exist.
currently people are using humidity sensors inside the vine canopy - which is a very direct measurement, so it might be hard to compete with that kind of measurement, but those kind of measurements might be used to draw some kind of correlation with what the camera sees - and then develop a way to predict variances in disease pressure.
The other notion - of looking for the presence of the anti-fungal agent might also be the way to go for the same reason - even though they are needed mostly on the grapes, the whole vine gets sprayed. This application however wears away with wind, rain, new growth of the vine etc. So being able to look at how much functional protection you have with your last application would certainly be a valueable tool.
Now look what I found : http://smartvineyard.com/precision-viticulture-system/
Isn't that a UAV killer ?
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.
-
1
-
2
-
3
of 3 Next