基于近红外超光谱成像的谷蠹活虫检测研究

Detection of Live Rhyzopertha dominica Based on Near-infrared Hyperspectral Imaging

快速准确地检测出仓储活虫是粮虫有效综合防治的关键。在谷蠹低温猝死后的0～7d，利用自行研制的近红外超光谱成像系统进行图像采集，谷蠹光谱反射率随死亡时间的增加而逐渐增大，到死后第3天时光谱曲线基本趋于稳定。应用主成分分析法提取出最优特征波长为1417．2nm，在特征波长下谷蠹图像平均灰度值与其体内的ATP合成酶活性和水分含量之间分别具有极显著的负指数相关关系和负线性相关关系。采用双区域连通阈值面积比的区域生长法自动判别谷蠹活虫，结果表明，在谷蠹死亡1．5d后，利用近红外超光谱成像技术能对活虫与死虫进行正确判别。

Detecting of live insects in granary rapidly and accurately is very critical for making the integrated management decisions. The low-temperature sudden death method was adopted to kill Rhyzopertha dominica. The near-infrared hyperspectral images were acquired by the self- developed imaging system over the period of O-7 d after the death of insects. The relative spec- tral reflectance of the insects increased gradually with the duration of the death time. Then the spectral curveof the insects became stable to the third day after the death. The optimal characteri- stic wavelength was 1 417.2 nm by the principle component analysis. The mean grey value of the insect images at 1 417.2 nm showed a significant negative exponential correlation with the activity of ATP-synthesizing enzyme and a strongly significant negative linear correlation with the mois- ture content in bodies. The region-growing method for identifying the live insects was used based on the area ratio of the two thresholds for connecting regions. Since the 1.5 th day after the death of the insects,the live and the dead had been identified completely based on near-infrared hyper- spectral imaging technology.