基于自生成标签的玉米苗期图像实例分割  

Instance segmentation model of maize seedling images based on automatic generated labels

作　　者：赵露露 邓寒冰[1,2] 周云成 苗腾[1,2] 赵凯 杨景[1] 张羽丰 ZHAO Lulu;DENG Hanbing;ZHOU Yuncheng;MIAO Teng;ZHAO Kai;YANG Jing;ZHANG Yufeng(College of Information and Electrical Engineering,Shenyang Agricultural University,Shenyang 110866,China;Liaoning Engineering Research Center for Information Technology in Agricultural,Shenyang 110866,China)

机构地区：[1]沈阳农业大学信息与电气工程学院,沈阳110866 [2]辽宁省农业信息化工程技术研究中心,沈阳110866

出　　处：《农业工程学报》2023年第11期201-211,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目(31901399);十四五国家重点研发计划项目子课题(2021YFD1500204);国家重点研发计划项目子课题(2022YFD2002303-01)。

摘　　要：在植物图像实例分割任务中,由于植物种类与形态的多样性,采用全监督学习时人们很难获得足量、有效且低成本的训练样本。为解决这一问题,该研究提出一种基于自生成标签的玉米苗期图像实例分割网络(automatic labelling based instance segmentation network,AutoLNet),在弱监督实例分割模型的基础上加入标签自生成模块,利用颜色空间转换、轮廓跟踪和最小外接矩形在玉米苗期图像(俯视图)中生成目标边界框(弱标签),利用弱标签代替人工标签参与网络训练,在无人工标签条件下实现玉米苗期图像实例分割。试验结果表明,自生成标签与人工标签的距离交并比和余弦相似度分别达到95.23%和94.10%,标签质量可以满足弱监督训练要求;AutoLNet输出预测框和掩膜的平均精度分别达到68.69%和35.07%,与人工标签质量相比,预测框与掩膜的平均精度分别提高了10.83和3.42个百分点,与弱监督模型(DiscoBox和Box2Mask)相比,预测框平均精度分别提高了11.28和8.79个百分点,掩膜平均精度分别提高了12.75和10.72个百分点;与全监督模型(CondInst和Mask R-CNN)相比,AutoLNet的预测框平均精度和掩膜平均精度可以达到CondInst模型的94.32%和83.14%,比Mask R-CNN模型的预测框和掩膜平均精度分别高7.54和3.28个百分点。AutoLNet可以利用标签自生成模块自动获得图像中玉米植株标签,在无人工标签的前提下实现玉米苗期图像的实例分割,可为大田环境下的玉米苗期图像实例分割任务提供解决方案和技术支持。Image segmentation has been widely used for the rapid and accurate detection of plants in the various robots of modern agriculture in recent years.However,fully supervised learning cannot obtain the sufficient,effective and low-cost mask labels(manual labeling) as training samples in the segmentation task of plant image instances,due to the diversity of plant species and forms.In this study,an automatic labelling-based instance segmentation network(AutoLNet) was proposed to improve the segmentation accuracy.The weak tags were also used to train the weak supervised deep learning model.Finally,the network model was used for the image segmentation of maize seedling stage.The top view of maize seedling stage was collected by unmanned aerial vehicle(UAV).Data enhancement was then used to improve the sample diversity.A weak label self-generation module was added in front of the backbone network using the weak supervised instance segmentation model.As such,the module was composed of color space conversion,contour tracking,and the minimum peripheral rectangle.The color threshold range of corn plants was firstly set to remove the background area of the image,in order to eliminate the influence of ground shadow and land on the foreground information.The foreground corn plant area was also expanded to remove the small noise points for the binary image with only foreground corn plants.Secondly,the edge detection was carried out on the binary image after threshold segmentation.The contour point set was then set for the foreground corn plants.Finally,the minimum peripheral rectangle of the foreground object was generated automatically in the original image using the coordinates of the contour point set.The final boundary frame was obtained to filter the threshold value.The weak label was generated automatically.The weak tags were used instead of manual tags to participate in network training.The image instance segmentation of maize seedling stage was realized without the manual tags,which was greatly reduced the labor cost tha

关 键 词：图像处理 深度学习 实例分割 弱监督学习 苗期玉米 植物表型 

分 类 号：S513[农业科学—作物学] TP391.41[自动化与计算机技术—计算机应用技术] S24[自动化与计算机技术—计算机科学与技术]