*3.1. Optimal Window for Texture Features*

Based on the identification results obtained by using GLCM and GLDM textures with di fferent window scales, the variations in the Kappa coe fficient and OA are shown in Figure 3, where the overall accuracy and Kappa coe fficient clearly have the same trend using both GLCM and GLDM textures. The Kappa coe fficient and OA of the GLCM texture are higher than those of the GLDM texture at window scales from 3 to 51, but the Kappa coe fficient and OA of the GLCM texture become lower than those of GLDM at window scales from 51 to 71. The highest accuracies of the GLCM texture window sizes are 15, 17, 19, and 21 (the OA is 88% and the Kappa coe fficient is 0.76), and their DI values are 14.68, 12.69, 14.11, and 13.76, respectively. When using the GLDM texture, the most accurate window sizes are 7, 21, and 31 (the OA is 85% and the Kappa coe fficient is 0.70), and their DI values are 56.39, 11.18, and 12.64, respectively. Therefore, GLDM texture with a window size of 21 and GLCM texture with a window size of 17 are adopted for subsequent maize lodging recognition.

**Figure 3.** The changes in maize lodging recognition accuracy with gray-level cooccurrence matrix (GLCM) and gray-level difference matrix (GLDM) textures under different window sizes.

### *3.2. Performances of Di*ff*erent Feature Screening Methods*

In this paper, two feature sets are established to compare the performance of the AIC method and index method: the GLCM texture features extracted from the blue, green, and red bands (RGB\_GLCM) and the GLCM texture features extracted from blue, green, red, red-edge, and near-infrared bands (All\_band\_GLCM). When utilizing the AIC method to screen RGB\_GLCM and All\_band\_GLCM, we obtained fourteen and sixteen satisfactory features, respectively. The optimal texture characteristics obtained by employing the index method are shown in Table 4.


**Table 4.** The selected features using index method-based GLCM texture.

Note: GLCM\_G\_mean and GLCM\_B\_mean are GLCM mean textures derived from the green and blue bands, respectively. GLCM\_B\_Correlation and GLCM\_Nir\_Dissimilarity are the GLCM correlation texture of the blue band and GLCM correlation texture of the near-infrared band, respectively.

Tables 5 and 6 display the recognition accuracy of AIC and the index method under different classification algorithms. The Kappa coefficient and OA of the AIC method are generally higher than those of the index method. The AIC method combined with RGB\_GLCM enabled estimation of maize lodging with higher accuracy than that of the index method (average Kappa coefficient is 0.71, average OA is 85.67%). In contrast, when the All\_band\_GLCM is used, the average Kappa coefficient and average OA of the index method fall to 0.15 and 57.67%, respectively, considerably lower than those of the AIC method. Furthermore, comparing the AIC and index methods clarified that the index method seriously overestimated the lodging area (Figure 4).


**Table 5.** The Kappa coefficient of the Akaike information criterion (AIC) and index methods.


**Table 6.** The overall accuracy (OA) of AIC and index methods.

**Figure 4.** Maps of the distribution of lodging and nonlodging maize based on the AIC and index methods. (**a**) Part of the multispectral image of the study area; (**b**) Maize lodging area using AIC method and binary logistic regression classification (BLRC) under RGB\_GLCM; (**c**) Maize lodging area using index method and maximum likelihood classification (MLC) under RGB\_GLCM; (**d**) Maize lodging area using AIC method and MLC under All\_band\_GLCM; (**e**) Maize lodging area using index method and MLC under All\_band\_GLCM.

The analyzed data are displayed in Table 5, and Table 6 clearly shows that RGB\_GLCM achieves higher classification accuracy than All\_band\_GLCM for each screening method. During feature selection, we found that although RGB\_GLCM is included in All\_band\_GLCM, the features derived from one screening method are not the same. Consequently, under the condition of using the feature selection method, it is necessary to construct as many feature sets as possible to obtain the optimal lodging recognition features.

Table 7 illustrates the performance of the AIC and index method for discriminating lodging and nonlodging areas in different regions within the study location under the maximum likelihood classification method. The accuracy of the two methods differs only slightly in the green region. On the one hand, using RGB\_GLCM, the Kappa coefficient and OA of the index method were 0.034 and 1.00% higher than those of the AIC method, respectively. The same precision can be obtained

from these methods when employing RGB\_GLCM. On the other hand, the AIC method resulted in a smaller error than the index method in the yellow area. In particular, when using the All\_band\_GLCM, the Kappa coefficient and OA of the AIC method are 0.53 and 16.00% higher than those of the index method, respectively.


**Table 7.** The accuracy assessment of AIC and index methods within different regions.
