基于黄色诱捕板的黄曲条跳甲识别与计数方法

Identifying and counting phyllotreta striolata fabriciuson based on yellow sticky trap

为了及时掌握严重危害蔬菜生长的害虫—黄曲条跳甲的发生状况及其危害程度,提出了基于黄色诱捕板的黄曲条跳甲识别与计数方法.首先,采用最大类间方差法(OTSU)获得图像的黄色诱捕板区域.在黄色诱捕板上以连通区域面积阈值获得候选区域,并对候选区采用OTSU算法、颜色平滑算法和主动轮廓模型进行目标图像分割.在此基础上,对候选区域提取颜色特征、纹理特征和几何特征,并采用支持向量机的方法,对黄曲条跳甲进行识别和计数.所提出的基于黄色诱捕板的黄曲条跳甲识别与计数方法的准确率、精确率和召回率分别为88.16%,92.00%和81.56%,达到了及时获得黄曲条跳甲灾情的目标.

To grasp the occurrence of phyllotreta striolatas fabricius with serious damage to vegetable growth and the damage extent,a method for identifying and counting phyllotreta striolatas fabricius was proposed based on yellow sticky traps.The maximum inter-class variance algorithm(OTSU)algorithm was used to segment yellow sticky traps from the background images.OTSU algorithm,color smooth and active contour model were applied to segment phyllotreta striolatas fabricius from yellow sticky traps.Color feature,textural feature and shape feature of candidate areas were subsequently extracted,and support vector machine was built to identify and count the phyllotreta striolatas fabricius.The results show that the proposed method can achieve high accuracy of 88.16%,precision of 92.00%and recall of 81.56%,and the information of phyllotreta striolata fabricius can be obtained in real-time.