“精灵圈”是海岸带盐沼植被生态系统中的一种“空间自组织”结构,对盐沼湿地的生产力、稳定性和恢复力有重要影响。无人机影像是实现“精灵圈”空间位置高精度识别及解译其时空演化趋势与规律的重要数据源,但“精灵圈”像素与背景像素...“精灵圈”是海岸带盐沼植被生态系统中的一种“空间自组织”结构,对盐沼湿地的生产力、稳定性和恢复力有重要影响。无人机影像是实现“精灵圈”空间位置高精度识别及解译其时空演化趋势与规律的重要数据源,但“精灵圈”像素与背景像素在色彩信息和外形特征上差异较小,如何从二维影像中智能精准地识别“精灵圈”像素并对识别的单个像素形成个体“精灵圈”是目前的技术难点。本文提出了一种结合分割万物模型(Segment Anything Model,SAM)视觉分割模型与随机森林机器学习的无人机影像“精灵圈”分割及分类方法,实现了单个“精灵圈”的识别和提取。首先,通过构建索伦森-骰子系数(S?rensen-Dice coefficient,Dice)和交并比(Intersection over Union,IOU)评价指标,从SAM中筛选预训练模型并对其参数进行优化,实现全自动影像分割,得到无属性信息的分割掩码/分割类;然后,利用红、绿、蓝(RGB)三通道信息及空间二维坐标将分割掩码与原图像进行信息匹配,构造分割掩码的特征指标,并根据袋外数据(Out of Bag,OOB)误差减小及特征分布规律对特征进行分析和筛选;最后,利用筛选的特征对随机森林模型进行训练,实现“精灵圈”植被、普通植被和光滩的自动识别与分类。实验结果表明:本文方法“精灵圈”平均正确提取率96.1%,平均错误提取率为9.5%,为精准刻画“精灵圈”时空格局及海岸带无人机遥感图像处理提供了方法和技术支撑。展开更多
Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intellige...Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.展开更多
High yield,high quality,stable yield,adaptability to growth period,and modern mechanization are the basic requirements for crops in the 21st century.Soybean oleic acid is a natural unsaturated fatty acid with strong a...High yield,high quality,stable yield,adaptability to growth period,and modern mechanization are the basic requirements for crops in the 21st century.Soybean oleic acid is a natural unsaturated fatty acid with strong antioxidant properties and stability.Known as a safe fatty acid,it has the ability to successfully prevent cardiovascular and cerebrovascular disorders.Improving the fatty acid composition of soybean seeds,can not only speed up the breeding process of high-quality high-oil and high-oleic soybeans,but also have important significance in human health,and provide the possibility for the development of soybean oil as a new energy source.Hence,the aim of this study was to analyze the high oleic acid elated gene GmSAM22 in soybean.In this research the soybean oleic acid-related gene GmSAM22 was screened out by Genome-wide association analysis,a 662 bp fragment was acquired by specific PCR amplification,and the pMD18T cloning vector was linked by the use of a seamless cloning technique.Bioinformatics analysis of the signal peptide prediction,subcellular localization,protein hydrophobicity,transmembrane region analysis,a phosphorylation site,protein secondary and tertiary structure and protein interaction analysis of the protein encoded by the SAM22 gene was carried out.The plasmid of the gene editing vector is pBK041.The overexpression vector was transformed from pCAMBIA3301 as the base vector,and overexpression vector were designed.Positive plants were obtained by genetic transformation by the pollen tube channel method.Fluorescence quantitative PCR was performed on the T2 generation plants to detect the relative expression levels in different tissues.Southern Blot was used to detect the presence of hybridization signal.Screening genes BAR,35S,and NOS in plants were identified by conventional PCR.10 seeds with high and low oleic acid content were chosen for quantitative PCR identification,and finally,the concentration and morphology of soybean fatty acids were identified by nearfar infrared spectroscopy.On 10 seeds with an upper and lower oleic acid content,a quantitative fluorescence analysis was done.In Southern blot hybridization,the SAM22 gene was integrated into the recipient soybean plant in hands of a sole copy.Fluorescence quantitative PCR appeared that the average relative expression of the SAM22 gene in roots,stems,leaves,and seeds was 1.70,1.67,3.83,and 4.41,respectively.Positive expression seeds had a 4.77%increase in oleic acid content.The level of oleic acid in the altered seeds was reduced by 4.13%when compared to CK,and it was discovered that the GmSAM22 gene could be a regulatory and secondary gene that promotes the conversion of stearic acid to oleic acid in soybean.There has not been a discussion of gene cloning or functional verification.The cloning and genetic transformation of the soybean SAM22 gene can effectively increase the content of oleic acid,which lays a foundation for the study of soybean with high oleic acid.展开更多
文摘“精灵圈”是海岸带盐沼植被生态系统中的一种“空间自组织”结构,对盐沼湿地的生产力、稳定性和恢复力有重要影响。无人机影像是实现“精灵圈”空间位置高精度识别及解译其时空演化趋势与规律的重要数据源,但“精灵圈”像素与背景像素在色彩信息和外形特征上差异较小,如何从二维影像中智能精准地识别“精灵圈”像素并对识别的单个像素形成个体“精灵圈”是目前的技术难点。本文提出了一种结合分割万物模型(Segment Anything Model,SAM)视觉分割模型与随机森林机器学习的无人机影像“精灵圈”分割及分类方法,实现了单个“精灵圈”的识别和提取。首先,通过构建索伦森-骰子系数(S?rensen-Dice coefficient,Dice)和交并比(Intersection over Union,IOU)评价指标,从SAM中筛选预训练模型并对其参数进行优化,实现全自动影像分割,得到无属性信息的分割掩码/分割类;然后,利用红、绿、蓝(RGB)三通道信息及空间二维坐标将分割掩码与原图像进行信息匹配,构造分割掩码的特征指标,并根据袋外数据(Out of Bag,OOB)误差减小及特征分布规律对特征进行分析和筛选;最后,利用筛选的特征对随机森林模型进行训练,实现“精灵圈”植被、普通植被和光滩的自动识别与分类。实验结果表明:本文方法“精灵圈”平均正确提取率96.1%,平均错误提取率为9.5%,为精准刻画“精灵圈”时空格局及海岸带无人机遥感图像处理提供了方法和技术支撑。
文摘针对传统的滚动轴承故障诊断方法难以准确高效的实现故障分类,提出了一种融合对称点模式(Symmetrized Dot Pattern,SDP)和改进SAM⁃MobileNetv2的滚动轴承故障分类方法。首先,将轴承振动信号通过SDP算法转化为含有丰富特征信息的二维图像。然后,将二维图像输入到改进SAM⁃MobileNetv2网络模型中,对故障特征信息进行提取和分类。在改进SAM⁃MobileNetv2网络中,使用自适应激活函数ACON(Activate or not)对SAM⁃MobileNetv2中的ReLU6激活函数进行替换,提高模型分类性能。最后,将本模型与多种网络模型做对比。试验结果表明,本模型可以准确高效地实现对滚动轴承故障的分类,使用凯斯西储大学轴承故障数据的准确率为99.5%,使用渥太华大学轴承故障数据的准确率为97.2%。
基金supported by the National Natural Science Foundation of China(51805078)Project of National Key Laboratory of Advanced Casting Technologies(CAT2023-002)the 111 Project(B16009).
文摘Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.
基金funded by the National Major Special Project for Breeding New Varieties of Genetically Modified Organisms(2016ZX08004-004)National Natural Science Foundation of China(31771817).
文摘High yield,high quality,stable yield,adaptability to growth period,and modern mechanization are the basic requirements for crops in the 21st century.Soybean oleic acid is a natural unsaturated fatty acid with strong antioxidant properties and stability.Known as a safe fatty acid,it has the ability to successfully prevent cardiovascular and cerebrovascular disorders.Improving the fatty acid composition of soybean seeds,can not only speed up the breeding process of high-quality high-oil and high-oleic soybeans,but also have important significance in human health,and provide the possibility for the development of soybean oil as a new energy source.Hence,the aim of this study was to analyze the high oleic acid elated gene GmSAM22 in soybean.In this research the soybean oleic acid-related gene GmSAM22 was screened out by Genome-wide association analysis,a 662 bp fragment was acquired by specific PCR amplification,and the pMD18T cloning vector was linked by the use of a seamless cloning technique.Bioinformatics analysis of the signal peptide prediction,subcellular localization,protein hydrophobicity,transmembrane region analysis,a phosphorylation site,protein secondary and tertiary structure and protein interaction analysis of the protein encoded by the SAM22 gene was carried out.The plasmid of the gene editing vector is pBK041.The overexpression vector was transformed from pCAMBIA3301 as the base vector,and overexpression vector were designed.Positive plants were obtained by genetic transformation by the pollen tube channel method.Fluorescence quantitative PCR was performed on the T2 generation plants to detect the relative expression levels in different tissues.Southern Blot was used to detect the presence of hybridization signal.Screening genes BAR,35S,and NOS in plants were identified by conventional PCR.10 seeds with high and low oleic acid content were chosen for quantitative PCR identification,and finally,the concentration and morphology of soybean fatty acids were identified by nearfar infrared spectroscopy.On 10 seeds with an upper and lower oleic acid content,a quantitative fluorescence analysis was done.In Southern blot hybridization,the SAM22 gene was integrated into the recipient soybean plant in hands of a sole copy.Fluorescence quantitative PCR appeared that the average relative expression of the SAM22 gene in roots,stems,leaves,and seeds was 1.70,1.67,3.83,and 4.41,respectively.Positive expression seeds had a 4.77%increase in oleic acid content.The level of oleic acid in the altered seeds was reduced by 4.13%when compared to CK,and it was discovered that the GmSAM22 gene could be a regulatory and secondary gene that promotes the conversion of stearic acid to oleic acid in soybean.There has not been a discussion of gene cloning or functional verification.The cloning and genetic transformation of the soybean SAM22 gene can effectively increase the content of oleic acid,which lays a foundation for the study of soybean with high oleic acid.
