Publication

Abstract : Agriculture plays a crucial role in human life as millions of lives mainly dependent on agricultural products and it is also the basic foundation economy. In order to guarantee the best possible crop yield, plant health problems must be identified as soon as possible. The goal of this work is to build and implement an FPGA-based system to monitor plant health, using the image processing technique. The technology employs leaf color detection to determine whether a plant is healthy, diseased, or deficient. The system analyzes pixel values of picture of various plants that are stored in a memory, using RGB thresholding for categorization and Gaussian smoothing for noise reduction. To inform farmers when the proportion of diseased or deficient pixels exceeds a key threshold, an automated alarm system is also integrated. Verilog is used to implement the complete pipeline, which includes image acquisition, pre-processing, classification, and alarm production. ModelSim is used for simulation. This hardware-based method is more scalable and faster than typical software-based alternatives, making it appropriate for use in large-scale agricultural settings. The proposed system improved smart agricultural systems by addressing the issues of traditional methods and by providing a low-cost, reliable, and efficient system for the early detection of plant problems. the system designed promotes sustainable farming mechanisms thereby reducing the crop losses which will positively impact the food security and agricultural economy.