We are excited to announce the official launch of AgroHelper’s platform for processing of aerial images and its new feature: The Health Map. Remote crop stress detection has never been faster.

The Health Map pinpoints areas with potential crop health issues in real time, seconds after the moment your drone captured farm field images are uploaded in the cloud based web app.


And…. it’s FREE! Try it now. No credit card required.


Before diving into the details, we would like to do something important.

First, we want to express our gratitude to all the people that helped us test and refine our software during our private beta last season. Specifically, big shout-out to our friend Andrei from MinuteDrone and to Radostin Kanazirov – a potato producer from Samokov, Bulgaria.

We listened hard to the feedback from the field and concluded that, at end of the day,

LESS IS MORE.


Here’s why.

Depending on the crop, agricultural producers survey their land several times per week. For example, a potato producer is going in the field at least 3 to 4 times per week during the growing stage of the crop. No surprise. That’s why drones and satellites used for remote aerial crop surveillance save considerable time and resources to farmers.

The reason why potato producers are going in the field at least 3 to 4 times per week, is that there are pests, like the Colorado potato beetle, that spread very fast and destroy hundreds of hectares per day. As a matter of fact, Colorado beetle adults are capable of consuming 10 cm2 of foliage per day. Now, imagine what hundreds of thousands or even millions of them can do (one adult female can deposit over 300 eggs on the surface of the host plant’s leaves during a period of four to five weeks).

Agrohelper Application

So, it’s important that such pests are detected and contained as soon as possible by the farmer.**

State-of-the-art software solutions for processing of drone captured farm field images first use a process called “stitching” to create an orthophoto map from hundreds of individual overlapping photos and only after that apply algorithms, such as NDVI, to detect crop health.

What’s stitching? Each individual photo captured by the drone camera contains different terrain features like crop rows, tractor trails or buildings. As the photos overlap, each individual feature is captured multiple times from different angles and perspectives. Stitching, as the name suggest, is a mathematical process that matches the photos to solve the puzzle and create one high-resolution map.

The problem is that stitching is both slow and unreliable. On average, it takes 5 to 10 hours to stitch a map from the images captured during one mission and a single cloud in the sky can sabotage its delivery. In practice, this means that you execute a survey mission in the morning and you can act based on the results the next day. As we already highlighted in our Colorado beetle example, a day late could equal hundred hectares destroyed and a big hole in the farmer’s annual revenues.

The solution we found: LESS IS MORE. We eliminated stitching from the process. Agrohelper’s proprietary software applies NDVI or similar algorithms and pinpoints areas with potential crop health issues without creating a high-resolution map first. So, our product needs less than 10 hours to get the job done. In fact, it can do it in real time.


AgroHelper’s Health Map feature indicates zones with potential issues like this:


Agrohelper Application

The output clearly indicates the zones with crop health issues that need to be ground-truthed today. Of course, we maintain our stitching feature and the platform can produce orthophoto maps on demand. However, we argue that there is a huge use case for our Health Map – you can spot the problem on time and apply targeted action the same day.


Would you like to test it? It’s free –try it now. No credit card required.


Mihail Marinov

Founding member & Head of Business Development at AgroHelper, Mihail Marinov is an agricultural finance specialist with 5+ years of experience in the field and advocate of precision agriculture technologies that help farmers to increase the output while decreasing the input per area unit.