Yang Yukun, Nie Jing, Kan Za, Yang Shuo, Zhao Hangxing, Li Jingbin
College of Mechanical and Electrical Engineering, Shihezi University, Shihezi, 832000, Xinjiang, China.
Industrial Technology Research Institute - XPCC, Xinjiang Production and Construction Corps (XPCC), Shihezi, 832000, Xinjiang, China.
Plant Methods. 2021 Nov 2;17(1):113. doi: 10.1186/s13007-021-00809-3.
At present, the residual film pollution in cotton fields is crucial. The commonly used recycling method is the manual-driven recycling machine, which is heavy and time-consuming. The development of a visual navigation system for the recovery of residual film is conducive, in order to improve the work efficiency. The key technology in the visual navigation system is the cotton stubble detection. A successful cotton stubble detection can ensure the stability and reliability of the visual navigation system.
Firstly, it extracts the three types of texture features of GLCM, GLRLM and LBP, from the three types of images of stubbles, residual films and broken leaves between rows. It then builds three classifiers: Random Forest, Back Propagation Neural Network and Support Vector Machine in order to classify the sample images. Finally, the possibility of improving the classification accuracy using the texture features extracted from the wavelet decomposition coefficients, is discussed.
The experiment proves that the GLCM texture feature of the original image has the best performance under the Back Propagation Neural Network classifier. As for the different wavelet bases, the vertical coefficient texture feature of coif3 wavelet decomposition, combined with the texture feature of the original image, is the feature having the best classification effect. Compared with the original image texture features, the classification accuracy is increased by 3.8%, the sensitivity is increased by 4.8%, and the specificity is increased by 1.2%.
The algorithm can complete the task of stubble detection in different locations, different periods and abnormal driving conditions, which shows that the wavelet coefficient texture feature combined with the original image texture feature is a useful fusion feature for detecting stubble and can provide a reference for different crop stubble detection.
目前，棉田残膜污染问题严峻。常用的回收方法是人工驱动回收机，该方法繁重且耗时。开发用于残膜回收的视觉导航系统有助于提高工作效率。视觉导航系统中的关键技术是棉茬检测。成功的棉茬检测可确保视觉导航系统的稳定性和可靠性。
首先，从棉茬、残膜和行间碎叶这三类图像中提取灰度共生矩阵（GLCM）、灰度游程长度矩阵（GLRLM）和局部二值模式（LBP）这三种纹理特征。然后构建随机森林、反向传播神经网络和支持向量机这三个分类器对样本图像进行分类。最后，探讨利用从小波分解系数中提取的纹理特征提高分类准确率的可能性。
实验证明，在反向传播神经网络分类器下，原始图像的GLCM纹理特征性能最佳。对于不同的小波基，coif3小波分解的垂直系数纹理特征与原始图像的纹理特征相结合，是分类效果最佳的特征。与原始图像纹理特征相比，分类准确率提高了3.8%，灵敏度提高了4.8%，特异性提高了1.2%。
该算法能够完成不同位置、不同时期以及异常驾驶条件下的棉茬检测任务，表明小波系数纹理特征与原始图像纹理特征相结合是用于棉茬检测的有效融合特征，可为不同作物的棉茬检测提供参考。
