New opportunities in food industry automation and science
Automotive, electronic manufacturing, mechanical engineering are always searching for a way to automate repeating tasks. In this post, I want to mention three segments where current progress in AI enabled new forms of automation.
Why is machine learning good for industries? Because not every part of the process is precise. Products are not always aligned in a grid and do not have same colour and shape. This is hard to cover by standard visual systems.
Here comes the power of machine learning. We do not need to add more rules to our process line. We only need to gather enough real-world images for deep learning. Let’s take a look at some interesting industrial use-cases for visual AI.
Machine learning in agriculture
We already see many new applications in this field. There is a buzz around drones that use a camera to monitor fields on regular basis. There are systems to reduce chemical usage by looking at each flower and spraying only important ones. By looking at flower one by one it can also provide customized fertilizers and pesticides based on the requirements of each plant. We could not imagine this to be possible in large areas 5 years ago.
Because of the huge areas of agriculture we often see moving units with cameras. These cameras can be used for different types of monitoring.
Farmers can adjust irrigation not only according to weather forecast but also live camera feed. We can place cameras around the field and detect persons or animals to enter different zones. Machine learning can be used to detect presence of different types of insect and automatically trigger actions. What if we point a camera to the plants and collect images of its growth every season? We can then predict future profits at early stage.
Ximilar (Vize.ai) supports these ideas with an important feature. With only few training images people can start monitoring what is important for them. All simple and easy to use. People do not have to wait for companies to understand the pain they have.
You can read more about applications of AI in agriculture here.
Machine learning in a food industry
“Food and Agriculture Organisation of the United Nations estimating that by 2050, feeding a global population of nine billion will require 70 per cent increase in food production”
In this case, we need to responsibly allocate food and minimize its wasting. In this article, we can read about how AI helps to sort food resources before we start to process them. Sorting raw material before processing leads to less waste during food processing.
Fast-foods can use machine learning and set of cameras to determine how much food to prepare at any time of the day. This again leads to less waste.
I can also see a significant opportunity in understanding human generated waste. Applications like smart trash bins can improve your shopping habits. By avoiding to buy food that always ends up in the trash you can savenature and money as well. This comes with trend we call IoT (internet of things). Your refrigerator can help you choose the right food for family members by recognizing faces as well as take care of expiration days and old vegetables.
Machine learning in Animal Science
This is something we really like to talk about with our customers in Ximilar (Vize.ai). There are almost never ending possibilities in the animal world. Cameras can help to count animals for scientific researches. Some scientists are interested in animal tracking. There are possibilities to analyze satellite images to find water resources or animal migration. When it comes to security one can avoid risks in human-animal conflicts by leveraging little camera and AI. I would like to write more about this in the another post.
Nowadays, it is hard to find a segment where machine learning and AI is not going to bring some value in future. I like to think about AI as an enabler for people who are working in the background on something valuable. We do not realize the exhausting work done every day by farmers and scientists around the world to bring us something as general as food and safety. What we can do for them is to bring tools and smart computers to make their lives easier.
This article was originally published by David Rajnoch.