Free Shipping on orders over US$39.99 How to make these links

AI in Agriculture: Computer Vision, Robots, and Scales for Pigs


Artificial intelligence is rapidly conquering agriculture and the food industry.

Computer vision in yield analysis

To feed billions of people, you need a lot of land. It is impossible to cultivate it manually these days. At the same time, plant diseases and insect invasion often cause crop failure. With the modern scale of agricultural business, such invasions are difficult to identify and neutralize in time.

This introduces yet another area where computer vision algorithms can help. Growers use computer vision to identify plant diseases, at the micro level, from close-up images of leaves and plants, and at the macro level, by identifying early signs of disease. of plants or pests from aerial photography. These projects are mostly based on a popular computer vision method: convolutional neural networks.

Note that I am talking here about computer vision in a broad sense. In many cases, images are not the best source of data. Many important aspects of plant life are best studied in other ways. Plant health can often be better understood, for example, by collecting hyperspectral images with special sensors or performing 3D laser scanning. Such methods are mainly used in agronomy. This type of data is usually high resolution and is closer to medical imaging than photographs. One of the systems for field monitoring is called AgMRI. To process this data, special models are needed, but their spatial structure allows the use of modern computer vision technologies, in particular, convolutional neural networks.

Millions have been invested in plant phenotyping and imaging research. The main task here is to collect large data sets of plants (usually in the form of photographs or three-dimensional images) and compare the phenotype data with the genotype of the plant. The results and data can be used to improve agricultural technologies worldwide.

Robotics in agriculture

Autonomous farming robots like Prospero are able to dig a hole in the ground and plant something in it, following predetermined general patterns and taking into account specific characteristics of the landscape. Robots can also take care of the growing process, working on each plant individually. When the time is right, the robots will harvest, again treating each plant exactly as it should. Prospero is based on the concept of swarm farming. Imagine an army of little Prospero crawling through the fields leaving in order, even the rows of plants behind them. Interestingly, Prospero actually appeared in 2011, before the heyday of the modern deep learning revolution. Today, robots are spreading quickly in agriculture, allowing you to automate more routine tasks:

  • Automated drones spray plants. Small, nimble drones can deliver hazardous chemicals more precisely than conventional aircraft. In addition, sprayer drones can be used for aerial photography to obtain data for the computer vision algorithms mentioned at the beginning of this article.
  • More and more specialized robots for harvesting are being developed and used. Combine harvesters have been around for a long time. However, only now, with the help of modern methods of computer vision and robotics, it is possible to create, for example, a robot that picks strawberries.
  • Robots like Hortibot can identify and kill individual weeds by mechanically removing them. This is another great achievement of modern robotics and computer vision as before it was impossible to distinguish weeds from useful plants and work on small plants using manipulators.

While many agricultural robots are still prototypes or being tested on a small scale, it’s clear that ML, AI, and robotics can do well in agriculture. It can be safely predicted that more and more agricultural tasks will be automated in the near future.

Care of farm animals

Many more ways to use AI in agriculture are actively being developed. For example, a pilot project at Neuromation is bringing computer vision to an industry that has yet to receive much attention from the deep learning community: animal husbandry.

There are, of course, attempts to apply machine learning to livestock tracking data. For example, Pakistani startup Cowlar introduced a collar that remotely monitors the activity and temperature of cows under the catchy slogan “FitBit for Cows.” French scientists have developed facial recognition in cows.

There are also attempts to use computer vision in a previously neglected industry worth hundreds of billions of dollars – pig farming. In modern farms, pigs are kept in relatively small groups, from which the most similar animals are selected. The main cost of pig production is feed, and optimizing the fattening process is the central task of modern pig production.

Farmers can solve this problem if they have detailed information about the weight gain of pigs. According to this site, animals are usually weighed only twice in their lifetime: at the beginning and at the end of fattening. If experts know how to fatten each piglet, it is possible to create an individual fattening program for each pig, and even an individual composition of food additives, which will significantly improve the yield. It is not very difficult to bring the animals to the scale, but it is a great stress for the animal, and the pigs lose weight from the stress. The new AI project plans to develop a new, non-invasive method of weighing animals. Neuromation will create a computer vision model that will estimate the weight of pigs from photo and video data. These estimates are then fed into classical, analytical machine learning models that improve the optimization process.

Agriculture on the frontier of artificial intelligence

Farming and animal husbandry are often considered primitive industries. Today, however, agriculture is increasingly appearing at the forefront of artificial intelligence.

The main reason here is that many agricultural tasks are carried out simultaneously:

  • Complex enough that they cannot be automated without the use of modern artificial intelligence and deep learning. Cultivated plants and pigs, although similar to each other, still do not leave the same assembly line, each tomato bush and each pig require an individual approach, and therefore, until recently, human intervention is absolutely necessary.
  • It is simple enough that with the current development of artificial intelligence, we can solve it, taking into account the individual differences between plants and animals while also automating the technologies to work with them. Driving a tractor in an open field is easier than driving a car in traffic, and weighing a pig is easier than learning how to pass the Turing test.

Agriculture is still one of the largest and most important industries on the planet, and even a small increase in efficiency will bring huge profits simply because of the size of this industry.



Source link

We will be happy to hear your thoughts

Leave a reply

Info Bbea
Logo
Enable registration in settings - general
Compare items
  • Total (0)
Compare
0
Shopping cart