Huang Yiqi, Li Jie, Yang Rui, Wang Fukuan, Li Yanzhou, Zhang Shuo, Wan Fanghao, Qiao Xi, Qian Wanqiang
College of Mechanical Engineering, Guangxi University, Nanning, China.
Lingnan Guangdong Laboratory of Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture and Rural Area, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China.
Front Plant Sci. 2021 Apr 30;12:626516. doi: 10.3389/fpls.2021.626516. eCollection 2021.
Mile-a-minute weed ( Kunth) is considered as one of top 100 most dangerous invasive species in the world. A fast and accurate detection technology will be needed to identify . It will help to mitigate the extensive ecologic and economic damage on our ecosystems caused by this alien plant. Hyperspectral technology fulfills the above requirement. However, when working with hyperspectral images, preprocessing, dimension reduction, and classifier are fundamental to achieving reliable recognition accuracy and efficiency. The spectral data of were collected using hyperspectral imaging in the spectral range of 450-998 nm. A different combination of preprocessing methods, principal component analysis (for dimension reduction), and three classifiers were used to analyze the collected hyperspectral images. The results showed that a combination of Savitzky-Golay (SG) smoothing, principal component analysis (PCA), and random forest (RF) achieved an accuracy (A) of 88.71%, an average accuracy (AA) of 88.68%, and a Kappa of 0.7740 with an execution time of 9.647 ms. In contrast, the combination of SG, PCA and a support vector machine (SVM) resulted in a weaker performance in terms of A (84.68%), AA(84.66%), and Kappa (0.6934), but with less execution time (1.318 ms). According to the requirements for specific identification accuracy and time cost, SG-PCA-RF and SG-PCA-SVM might represent two promising methods for recognizing in the wild.
律草（Kunth）被认为是世界上100种最危险的入侵物种之一。需要一种快速准确的检测技术来识别它。这将有助于减轻这种外来植物对我们生态系统造成的广泛生态和经济破坏。高光谱技术满足上述要求。然而，在处理高光谱图像时，预处理、降维和分类器是实现可靠识别精度和效率的基础。使用高光谱成像在450 - 998 nm光谱范围内收集了律草的光谱数据。采用不同的预处理方法组合、主成分分析（用于降维）和三种分类器对收集到的高光谱图像进行分析。结果表明，Savitzky - Golay（SG）平滑、主成分分析（PCA）和随机森林（RF）的组合实现了88.71%的准确率（A）、88.68%的平均准确率（AA）和0.7740的Kappa系数，执行时间为9.647毫秒。相比之下，SG、PCA和支持向量机（SVM）的组合在A（84.68%）、AA（84.66%）和Kappa（0.6934）方面表现较弱，但执行时间较短（1.318毫秒）。根据特定识别精度和时间成本的要求，SG - PCA - RF和SG - PCA - SVM可能是野外识别律草的两种有前景的方法。
