Identification and Area Calculation of the Egg Mass of Spodoptera Frugiperda Based on Faster-RCNN

Abstract

Spodoptera frugiperda is a migratory and destructive crop pest. The number of eggs is an important method to evaluate the pest situation, which can be estimated by the area of egg mass. The traditional manual method is inefficient, but the new method of egg mass image recognition improves the efficiency of eggs number estimation. In this paper, the optimized Faster-RCNN target detection algorithm was used to recognize the egg mass image of Spodoptera frugiperda. The Maximum Between-Class Variance method (Otsu) was used for threshold segmentation to obtain the position, shape and size of the egg mass and calculate the area of the egg mass. The mean value of the relative error of the egg mass area in the test samples was -0.02032, and the minimum value was -0.00047. The experimental results show that the egg area calculation method proposed in this paper is fast and accurate, which can meet the requirements of egg area measurement.