Artificial Neural Networks and Computer Vision’s-Based Phytoindication Systems for Variable Rate Irrigation Improving

Abstract

The article proposes a methodology for optimizing the process of irrigation of crops using a phytoindication system based on computer vision methods. We have proposed an algorithm and developed a system for obtaining a map of irrigation for maize in low latency mode. The system can be installed on a center pivot irrigation and consists of 8 IP cameras connected to a DVR connected to a laptop. The algorithm consists of three stages. Image preprocessing stage - applying an integrated excess green and excess red difference (ExGR) index. The classification stage is the application of the method that we choose depending on the system’s operating conditions. At the final stage, a neural network trained using the Resilient Propagation method is used, which determines the rate of watering of plants in the current sector of the location of the sprinkler. The selected methods of pretreatment and classification made it possible to achieve an accuracy of plant identification up to 93%, growth stages - up to 92% (with unconsolidated maize sowing and good lighting). System performance up to 100 plants in one second, which exceeds the performance of similar systems. The neural network showed an accuracy of 92% on the training set and 87% on the test set. Dynamic analysis of spatial and temporal variability leads to an increase in productivity and efficiency of water use. In addition, given the ubiquitous distribution of agribusiness management systems, this approach is quite simple to implement in the farm’s conditions.

Keywords

• Artificial neural networks
• computer vision
• image classification
• irrigation
• machine learning