Search
Menu

Standard Digital Camera and AI Pair for Soil Monitoring

Facebook X LinkedIn Email
ADELAIDE, Australia, March 17, 2021 — Digital cameras and machine learning technology can provide a cost-effective method of monitoring soil moisture, according to new work from the University of South Australia and Middle Technical University (Iraq). The technology aims to address current difficulties with sensing soil moisture, such as buried sensors that are vulnerable to salts in the substrate and require specialized hardware or connections, and expensive thermal imaging cameras that can be susceptible to climatic conditions such as sunlight intensity, fog, and clouds.

The team’s approach uses a standard RGB digital camera to accurately monitor soil moisture under a wide range of conditions, with help from machine learning software.
Image showing the system function of UniSA and Middle Technical Uni's computer vision for smart irrigation. Courtesy of Ali Al-Naji.
Image showing the system function of University of South Australia and Middle Technical University’s computer vision for smart irrigation. Courtesy of Ali Al-Naji.

“The system we trialed is simple, robust, and affordable, making it promising technology to support precision agriculture,” said Ali Al-Naji, a professor at the University of South Australia. “It is based on a standard video camera that analyzes the differences in soil color to determine moisture content. We tested it at different distances, times, and illumination levels and the system was very accurate.”


The team connected the camera to an artificial neural network (ANN). The system was trained to recognize different soil moisture levels independent of any sky condition. The ANN allows the system to recognize the specific soil conditions of any location; it can be customized for each user and updated for changing climatic circumstances to ensure accuracy.

“Once the network has been trained it should be possible to achieve controlled irrigation by maintaining the appearance of the soil at the desired state,” said Javaan Chahl, a professor at the University of South Australia. “Now that we know the monitoring method is accurate, we are planning to design a cost-effective smart-irrigation system based on our algorithm using a microcontroller, USB camera, and water pump that can work with different types of soil.”


The system, Chahl added, has potential as a cost-effective, accurate, and, in terms of its components, readily available tool for improved irrigation technology under changing climate conditions.

The research was published in Heliyon (www.doi.org/10.1016/j.heliyon.2021.e06078).


Published: March 2021
Glossary
neural network
A computing paradigm that attempts to process information in a manner similar to that of the brain; it differs from artificial intelligence in that it relies not on pre-programming but on the acquisition and evolution of interconnections between nodes. These computational models have shown extensive usage in applications that involve pattern recognition as well as machine learning as the interconnections between nodes continue to compute updated values from previous inputs.
digital
Denoting the use of binary notation; i.e., the representation of data by bits (1 or 0).
video
Referring to the bandwidth and spectrum location of the signal produced by television or radar scanning.
machine vision
Machine vision, also known as computer vision or computer sight, refers to the technology that enables machines, typically computers, to interpret and understand visual information from the world, much like the human visual system. It involves the development and application of algorithms and systems that allow machines to acquire, process, analyze, and make decisions based on visual data. Key aspects of machine vision include: Image acquisition: Machine vision systems use various...
Research & TechnologyANNneural networkneural networksartificial neural networkscamerasdigitalVideosoilsoil analysismoisturemonitormonitoringUniversity of South Australiamachine visionImagingAustraliaagriculture

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.