Related Experiment Video
Updated: May 13, 2025
08:02
Robotic Sensing and Stimuli Provision for Guided Plant Growth
Published on: July 1, 2019
7.9K
Weed-crop dataset in precision agriculture: Resource for AI-based robotic weed control systems
Arjun Upadhyay1, Sunil G C1, Maria Villamil Mahecha1
1Department of Agricultural and Biosystems Engineering, North Dakota State University, Fargo, ND, USA.
Data in Brief
|April 14, 2025
Summary
Researchers developed a new dataset of weed images for training artificial intelligence. This resource aids in creating advanced deep learning models for robotic weed identification in precision agriculture.
Area of Science:
- Agricultural Engineering
- Computer Science
- Plant Science
Background:
- Effective weed management is essential for maximizing crop yield and growth.
- Advancements in robotics and deep learning (DL) are driving innovation in automated weed control.
- Developing accurate DL models for weed identification necessitates large, diverse datasets from natural field conditions.
Purpose of the Study:
- To present a comprehensive red, green, and blue (RGB) image dataset for training deep learning models for weed identification.
- To enhance the accuracy of real-time weed detection in precision agriculture through diverse, field-collected data.
- To provide a valuable resource for researchers, educators, and students in developing AI-driven agricultural solutions.
Main Methods:
- Collected a real-world dataset of 1120 labeled images using a Canon RGB camera mounted on a remote-controlled robotic platform.
- Captured images under diverse environmental conditions to simulate natural variability.
- The dataset includes five weed species and eight crop species relevant to various agricultural systems.
Main Results:
- The presented dataset offers a robust foundation for training and validating deep learning models for weed identification.
- The diverse nature of the dataset aims to improve the generalization and accuracy of object detection algorithms.
- This resource facilitates the development of more sophisticated AI for robotic weed management systems.
Conclusions:
- The RGB dataset is a significant contribution to the field of precision agriculture, enabling the development of more effective automated weed control.
- Further enrichment of this dataset by combining it with other weed-crop datasets will enhance DL algorithm capabilities.
- This work supports the integration of AI and robotics for efficient and sustainable weed management practices.
Related Concept Videos
02:16Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
02:35Key Elements for Plant Nutrition
18.5K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.5K
01:59Plant Breeding and Biotechnology
18.5K
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
18.5K