Enhanced Grasshopper Detection in Smart Crops Using Faster R-CNN Deep Learning Model

Grasshoppers inflict a consequential risk to agricultural outcome that require an effective identification technique for prompt management. Traditional methods of identifying pests often suffer from a lack of precision and efficiency, underscoring the need for sophisticated technology remedies. This research proposes an improved technique for identifying grasshoppers in smart crops by using the Faster Region-CNN deep learning model called FR-CNN. By using the deep learning's advantages and computer vision, our technique seeks to enhance the accuracy and speed of detection. The structure of the modified Faster R-CNN model, which includes dataset preparation, model training, and assessment, is explained in depth. systems, which points out its implicit impression on agricultural The experimental findings provide evidence of the effectiveness of our method in reliably detecting grasshoppers in complicated agricultural environments. Furthermore, the images of grasshopper evaluate the incorporation of the model into intelligent crop monitoring sustainability and production. The empirical findings have shown that the FR-CNN approach surpassed existing deep learning models, as evidenced by superior levels of accuracy, f1-score, and recall. Moreover, it achieved an unprecedented accuracy rate of 98.62%. The FR-CNN technique shows condescending execution when compared with concurrent state-of-the-art methods.