摘要：Rice disease detection is of great significance to rice disease management. It is difficult to identify the rice leaves with different colors in different disease periods by RGB image and without aided eyes. Traditional equipment and methods are relatively inefficient in meeting the needs of current disease detection. The accurate and efficient detection the infected areas from hyperspectral images has become a primary concern in current research. However, current spectral target detection research pays less attention to the time and computing resources consumed by detection. A disease detection method based on random forest (RF) and adaptive coherence estimator (ACE) is proposed here. Firstly, based on the spectral differences between diseased and healthy leaves, 18 characteristic spectral wavelengths with the highest importance were selected by an RF algorithm, and the spectral images of those characteristic wavelengths were synthesized. Then, the ACE model was established for the disease recognition of full wavelength spectral images, characteristic wavelength spectral images, and RGB images. At the same time, three other familiar target detection methods were selected as the control experiments. The detection results showed a similarity between the detection performance of the four detection methods for full wavelength spectral image and characteristic wavelength spectral image. This detection performance was higher than that of the RGB image, indicating that characteristic wavelength spectral image can replace full wavelength spectral image for disease detection. The detection performance of the ACE algorithm was better than other algorithms. The detection accuracy of 18 characteristic wavelengths was 97.41%. Compared with the hyperspectral full wavelength image detection results, the accuracy decreased by 1.12%, and the detection time decreased by 2/3, which greatly reduced the detection time. Based on these results, the target detection method combining the RF algorithm and the ACE algorithm can effectively and accurately detect rice bacterial blight disease, which provides a new method for automatic detection of plant disease in the field.
