Quantity estimation modeling of the Rice Plant-hopper infestation area on rice stems based on a 2-Dimensional Wavelet Packet Transform and corner detection algorithm

• Visible-image-based method for quantity estimation of RPH infestation is proposed.
• Wavelet Packet combined with corner detection suit for quantity estimation of RPHs.
• The number of corners can be used to identify RPH infestation from non-infestation.
• Correlation coefficient between the number of RPHs and corners could reach 0.8277.

BackgroundOutbreaks of Rice Plant-hoppers (RPH) (Nilaparvata lugens, Sogatella furcifera, and Laodelphax striatellus) appear in Asia almost every year and have had significant impacts on rice yields. To implement timely, targeted pesticide applications, reduce input costs and benefit the environment, the accurate early detection and quantity estimation of RPH infestation is a critical part of integrated pest management (IPM) for rice production. To use visible images to detect and estimate RPH infestation areas on rice stems, related experiments and studies were performed to determine the feasibility of using a 2-Dimensional Wavelet Packet Transform (2DWPT) and a corner detection algorithm. Visible images of the rice stems were collected using a handheld camera. First, a series of pretreatments to these visible images were applied, including smoothing, denoising, image color space transformation and 2-Dimensional Wavelet Packet transformation. Second, the related image corner eigenvalues (i.e. the number of the corners) were extracted using a Smallest Univalue Segment Assimilating Nucleus (SUSAN) algorithm. Finally, a linear regression model was developed based on the corner eigenvalues.ResultsThe results show that the SUSAN corner detection algorithm used to extract the corner eigenvalues can also be used to distinguish the I (infestation) and N (non-infestation) areas with high accuracy. Most of the corner eigenvalues based on different image forms had a high correlation coefficient with the RPH quantity, and B-P10 (i.e., the corner eigenvalue of the RGB color space B component that was transformed via 2DWPT at node P10) had the highest correlation coefficient of 0.8277.ConclusionsIt is possible to detect and quantify the estimated RPH infestation area on rice stems by applying a 2DWPT and corner detection algorithm to visible images. Along with the micro-sensor mobile monitoring platform, the visible-image-based method is expected to be used as a redundant method in remote sensing to measure the stress induced by RPH.