Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence

• Published in: Computers and electronics in agriculture 2019-02, Vol.157, p.339-350
• Main Authors: Partel, Victor, Charan Kakarla, Sri, Ampatzidis, Yiannis
• Format: Article
• Language: English
• Subjects: Agrochemicals; Algorithms; Artificial intelligence; Computer simulation; Deep learning; Environmental impact; Graphics processing units; Image detection; Image processing; Impact damage; Machine learning; Machine vision; Mapping; Neural networks; Organic chemistry; Precision agriculture; Recall; Smart agriculture; Sprayers; Spraying; State of the art; Target detection; Target recognition; Vegetables; Weed detection; Weeds
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2018.12.048

•A smart sprayer for precision pest management was developed.•This low-cost technology can distinguish target weeds from non-target objects.•It sprays only on a selected target (weed).•Neural networks were utilizing for target detection and classification.•It can significantly reduce the quantity of agrochemicals applied. Most conventional sprayers apply agrochemicals uniformly, despite the fact that distribution of weeds is typically patchy, resulting in wastage of valuable compounds, increased costs, crop damage risk, pest resistance to chemicals, environmental pollution and contamination of products. To reduce these negative impacts, a smart sprayer was designed and developed utilizing machine vision and artificial intelligence to distinguish target weeds from non-target objects (e.g. vegetable crops) and precisely spray on the desired target/location. Two different experimental scenarios were designed to simulate a vegetable field and to evaluate the smart sprayer’s performance. The first scenario contained artificial weeds (targets) and artificial plants (non-targets). The second and most challenging scenario contained real plants; portulaca weeds as targets, and sedge weeds and pepper plants as non-targets. Two different embedded graphics processing unit (GPU) were evaluated as the smart sprayer processing unit (for image processing and target detection). The more powerful GPU (NVIDIA GTX 1070 Ti) achieved an overall precision of 71% and recall of 78% (for plant detection and target spraying accuracy) on the most challenging scenario with real plants, and 91% accuracy and recall for the first scenario with artificial plants. The less powerful GPU (NVIDIA Jetson TX2) achieved an overall precision and recall of 90% and 89% respectively on the first scenario with artificial plants, and 59% and 44% respectively on the second scenario with real plants. Finally, an RTK GPS was connected to the smart sprayer and an algorithm was developed to automatically generate weed maps and visualize the collected data (after every application). This smart technology integrates a state of the art (AI-based) weed detection system, a novel fast and precision spraying system, and a weed mapping system. It can significantly reduce the quantity of agrochemicals required, especially compared with traditional broadcast sprayers that usually treat the entire field, resulting in unnecessary application to areas that do not require treatment. It could also reduce costs, risk of c