Skip to content

metehan41/DeepWeedClassification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Weed Classification for Robotic Agriculture

Powtoon video: https://www.youtube.com/watch?v=kMjza42QGhQ

Fertilizers play a crucial role in enhancing crop production and ensuring bountiful harvests. However, overreliance on chemical fertilizers poses risks to both human health and the environment. These substances often contain harmful heavy metals like lead, mercury, cadmium, and uranium, which can inflict damage on vital organs such as the kidneys, liver, and lungs. Moreover, these heavy metals are linked to various other health hazards. These damages not only affect today but can also have irreversible consequences on nature in the future. One of the main solutions to all this harm is the usage of organic fertilizer but it could be hard for some of the farmers. We will not dive into details since we are not experts in terms of farming. The proposed research topic is “Weed Classification for Robotic Agriculture using Machine Learning”. The primary aim of this project is to develop a machine-learning model that can accurately identify and classify different types of weeds in agricultural fields. The output from this model will be used to guide agricultural robots to carry out targeted Figure 1. Enter Caption weed control, reducing the use of pesticides and promoting organic farming practices. This is particularly relevant in the context of sustainable agriculture, where minimizing the use of harmful chemicals is a key objective. The machine learning model developed in this project will be trained to recognize different types of weeds and classify them appropriately. This will enable the agricultural robots to identify the weeds in real-time and carry out targeted weed control. As a result, the amount of pesticide used can be significantly reduced, leading to more sustainable farming practices. Organic farming relies on ecologically sound pest control methods and primarily utilizes biological fertilizers derived from animal waste and nitrogen-fixing cover crops. This approach consciously avoids synthetic inputs like pesticides, fertilizers, and hormones, opting in- stead for techniques such as crop rotation, organic waste utilization, farm manure, rock additives, and crop residues to protect plants and optimize nutrient utilization. Organic farming stands as a sustainable and eco-friendly alternative to conventional agricultural practices, garnering increasing popularity on a global scale

Releases

No releases published

Packages

No packages published