基于HSV与形状特征融合的花椒图像识别

光照条件变化会对花椒目标识别率产生影响,关系到机器视觉技术能否有效应用于生产现场的花椒采摘。通过对HSV特性图像识别技术的分析,提出HSV和形状特征融合的花椒识别算法。该算法采用同态滤波方法对光照进行补偿,解决因为光照不均匀而导致的花椒识别率低的问题,最后利用花椒圆度特征,排除树枝及树叶等的干扰,实现花椒的准确识别。利用同态滤波方法对光照进行补偿,对于光照不强或者发生遮挡的花椒图像有较大改善,通过试验得出其平均识别率达到94.0%,比单独采用HSV特性识别时,在顺光,背光和遮阴条件下,识别率分别提高4%,13%和21%,此外在遮阴条件下运行时间缩短14.6%。为遮阴条件下提高花椒识别率提供一种方法。     

利用MAS技术改良香稻‘R15’的直链淀粉含量

R15是适应性较广,产量较高的中熟晚籼香稻品系,但由于含有Wx^a基因,其直链淀粉含量高达23.5%,严重影响食用口感。因此,我们以含有Wx^b等位基因的不育系Y58S为供体,通过杂交、回交,利用RAD测序技术、分子标记辅助筛选等技术,经过8个世代的筛选,成功用Wx^b基因替换掉R15中的Wx^a基因,培育出1个新的纯合株系——‘深华R16’,其染色体上有10882234 bp长度的碱基,基因型和供体亲本‘Y58S’一致,占2.92%;有362363285 bp长度的DNA片段基因型和受体亲本‘R15’一致,占97.08%;其直链淀粉含量为14%。将‘Y58S’分别与‘深华R16’和‘R15’进行组配,结果表明,‘Y58S’/‘深华R16’组合的直链淀粉含量(13.9%)低于‘Y58S’/‘R15’组合的直链淀粉含量(19.9%),其它米质性状与农艺性状基本一致。本研究为分子标记辅助育种提供了新思路,培育出一新的水稻品系。     

基于随机森林的高寒湿地地区土地覆盖遥感分类方法

高寒湿地是青藏高原典型独特的生态系统,是全球气候变化的敏感地带和预警区。利用遥感技术快速、准确地分类提取高寒湿地的土地覆盖信息,对当地生态安全监测和保护具有重要意义。本文以若尔盖湿地国家级自然保护区为研究区,首先,以高分一号(GF-1)遥感影像为数据源,融合光谱特征、水体指数、地形特征、植被指数和纹理信息等26个变量进行随机森林(Random forest,RF)分类实验;然后,根据袋外数据(Out of bag,OOB)的特征变量重要性得分和精度评价结果,选出高寒湿地地区土地覆盖类型的最优分类方案和特征;最后,对特征变量进行降维,并基于相同的变量,采用极大似然法(Maximum likelihood classification,MLC)、支持向量机(Support vector machine,SVM)、人工神经网络(Artificial neural network,ANN)和RF等方法进行分类,比较不同方法的优适性。结果表明:结合GF-1影像光谱、水体、植被、纹理特征和地形信息,使用26个变量的RF模型的分类精度最高,总体精度(Overall accuracy,OA)为90.07%,Kappa系数为0.86;通过RF模型的变量重要性分析可以有效选出重要的特征信息,在降低特征变量维度的同时,还能保证较高的分类精度; 4种分类方法中,RF算法是高寒湿地地区较合适的分类方法,OA比MLC基准方法高17.63个百分点,比SVM和ANN等机器学习算法分别高6.98、6.56个百分点。     

枣实蝇对枣果挥发物的选择行为

[目的]探究对枣实蝇有引诱作用的挥发性物质,研发基于行为调节的防治技术。[方法]采用Y型嗅觉仪测定了枣实蝇成虫对6种枣果挥发物的选择行为反应,并在室内试验的基础上进行田间引诱试验。[结果]室内试验结果显示,枣实蝇成虫对6种枣果挥发物具有显著正趋性。枣实蝇雌虫对棕榈酸乙酯、月桂酸乙酯、肉豆蔻酸的选择率较强,选择率均为30%以上;雄虫对亚油酸乙酯、油酸乙酯的选择率较强,选择率均为25%以上,从不同浓度梯度(原液、10%溶液、1%溶液)的选择率和选择系数来看,随浓度的递减,其选择率和选择系数也在递减,原液的选择率分别为10%溶液及1%溶液的2.5倍及5倍以上。田间试验发现:肉豆蔻酸对枣实蝇雌虫的诱集效果较强,2 d最多诱捕数量为15头·只^-1,平均诱捕数量为11.4头·只^-1,十四酸乙酯次之。在6种不同挥发物中油酸乙酯和亚油酸乙酯对枣实蝇雄虫的引诱效果较强。经单因素方差分析发现,在6种挥发性物质及混合物中,月桂酸乙酯及十四酸乙酯对枣实蝇雌雄虫的引诱效果之间存在显著性差异。其他挥发物之间无显著差异。[结论]枣果挥发物中棕榈酸乙酯、月桂酸乙酯、肉豆蔻酸与枣实蝇偏爱选择密切相关。在田间试验中:枣实蝇成虫对肉豆蔻酸的选择率较强,为研发枣实蝇引诱剂提供了理论依据。     

Wide hybridization and introgression breeding in safflower: Effectiveness of different selection methods

Possibility of using interspecific hybridization to increase genetic diversity of drought tolerance in safflower (Carthamus tinctorius L.) and effectiveness of different selection methods is poorly understood. The main objectives of this study were to evaluate the effectiveness of (a) interspecific hybridization to expand genetic diversity in safflower for agronomic traits and drought tolerance in advance generations and (b) different selection methods (direct vs. indirect) for improving seed yield. Interspecific hybridizations were performed between species of C. tinctorius × C. palaestinus (TP), C. palaestinus × C. oxyacantha (PO) and C. tinctorius × C. oxyacantha (TO). Based on the field screening of genotypes in F3 generation, four groups of selected genotypes (derived from combination of direct and indirect selection under both drought and normal environments along with selection based on drought tolerance index (STI)) were evaluated in F4 and F5 generations. Indirect selection for seed yield was significantly more efficient than direct selection. Selection in stress environment resulted to more efficiency than selection in normal environment. No significant difference was observed between direct selection and selection based on STI. The result showed that TP was the best population to combine high seed yield and drought tolerance in safflower.     

翅形态特征在重阳木斑蛾成虫性别鉴定中的应用

为了明确重阳木斑蛾的翅形态特征在其性别鉴定中的作用,探索雌雄难于区分的成虫的数值鉴定方法。采用图像处理与分析技术,通过爱普生扫描仪获取重阳木斑蛾前翅图,利用BugShape v1.0软件提取雌雄成虫翅的轮廓特征,利用tpsDig2软件获取翅脉交叉点位置特征,并利用独立样本t检验和标志点空间普氏叠加和扭曲分析,以明确此类特征在该成虫雌雄鉴定中的作用。结果表明,重阳木斑蛾成虫左右前翅轮廓特征在同一性别中差异不显著。仅利用左前翅数据进行分析时,翅面积、短轴长度、等效圆半径、偏心率、球状性和圆形度在两个性别中存在极显著差异,周长和长轴长度的差异达到显著水平,而紧凑度和叶状性差异不显著。使用左右前翅作为数据集进行分析时,除紧凑度和叶状性差异仍不显著外,其余参数均达到极显著水平。雌雄前翅轮廓特征作为指标来判别性别时正确率为100%,但存在左右翅相互错判现象。翅膀内部翅脉交叉点的空间位置在个体间存在较大差异,主要表现在相对于翅的横向方向变异大。雌雄间的差异主要存在于外缘附近的翅脉交叉点。结论:通过前翅的轮廓特征可以区分重阳木斑蛾雌雄成虫的差异。翅脉交叉点空间位置在雌雄间和个体间存在一定的变异。     

Identification of an H1N1 subtype of swine influenza virus and serological analysis

To investigate the epizootic of swine influenza virus(SIV), 60 nasal swabs were collected from a clinical cases of pig farm in Tai'an City, Shandong Province of China in April 2017. SIV was isolated by inoculating into 10-day-old Special Pathogen Free embryonated eggs and the whole genome was sequenced. An H1N1 subtype SIV was isolated and designated as A/swine/Shandong/TA04/2017(H1N1). Phylogenetic analysis showed that apart from the polymerase A(PA) fragment belonging to the 2009 pandemic H1N1 branch, seven genome segments belonged to avian-like H1N1 influenza virus lineage. The cleavage site sequence of the hemagglutinin(HA) protein was PSIQSR↓G, which is a typical molecular biological characteristic. Five potential N-glycosylation sites(N14, N26, N277, N484 and N543) were found in the HA gene. To further investigate the epidemiology of SIV in this farm, the 995 serum samples were assessed with EAH1N1 2009 pandemic H1N1 and H3 N2 antigens. The results showed that the total positive rate was 65.43%. The positive rates of single virus infection detected by EAH1N1, 2009 pdmH1N1 and H3 N2 for serum HI(Hemagglutination inhibition) were 48.35, 30.85 and 7.47%, respectively. The results showed that SIV in Shandong Province has been reassorted in some segments and the SIV-positive rate was high on the SIV outbreak farm. These data provide evidence of an epizootic of SIV.     

基于注意力机制及多尺度特征融合的番茄叶片缺素图像分类方法

针对番茄早期缺素性状不明显及各生长期特征差异较大所导致的特征区域尺寸不一致、难提取、难辩别等问题，提出了一种基于注意力机制及多尺度特征融合卷积神经网络的番茄叶片缺素图像分类方法（Multi-Scale Feature Fusion Convolutional Neural Networks Based On Atte ntion Mechanism，MSFF-AM-CNNs）。首先根据番茄叶片缺素特点提出了多尺度特征融合结构（Multi-Scale Feature Fusion Module，MSFF Module）；其次在DenseNet基础上，结合浅层网络主要提取纹理、细节特征，深层网络主要提取轮廓、形状特征的特点分别提出具有针对性的特征提取方法，通过不同形式引入注意力机制及多尺度特征融合结构，使全局多尺度信息融合多个特征通道、选择性地强调信息特征并达到对特征精准定位的功能；同时引入Focal Loss函数以减少易分类样本的权重。试验结果表明，MSFF-AM-CNNs的平均召回率、平均F1得分、平均准确率较原模型DenseNet-121均大幅提升，其中缺氮和缺钾叶片的准确率分别提高了8.06和6.14个百分点，召回率分别提高了6.31和5.00个百分点，F1得分分别提高了7.25和5.55个百分点，平均识别准确率可达95.92%，具有较高的识别准确率及广泛的适用性，能够满足番茄叶片缺素图像的高精度分类需求，可为植物叶片缺素识别提供参考。     

Phenotypic indicators for cultured pearl size improvement in the black‐lipped pearl oyster (Pinctada margaritifera): towards selection for the recipient growth performance

The black‐lipped pearl oyster, Pinctada margaritifera, is the most important farmed species in French Polynesia and the basis of the most valuable export industry. Mass production of black pearls relies on a surgical operation requiring tissue from a donor pearl oyster to be grafted, together with a nucleus made of shell, into the gonad of a recipient oyster. Improving pearl size through family selection remains one of the main challenges for future aquaculture development. This study analyses the relative contribution of donor and recipient oysters to pearl size. To this end, hatchery‐produced donor oysters of two batches, large and small (based on shell height), were used to supply grafts for recipients, which were then monitored individually for their growth performance by recording shell height, width, and thickness, and total live weight (flesh + shells) every 6 months (four biometric measurement times) over 20 months of culture. Pearls issued from the two batches of donors showed no significant differences in nacre weight or thickness. In contrast, recipient oyster shell height and total weight were increasingly positively correlated with these pearl size parameters over the culture period, becoming significant at 8 months post‐grafting. Potential therefore exists to use shell height and oyster weight as phenotypic indicators for selective breeding of recipient oysters with high growth performance to increase pearl size in P. margaritifera.     

8个格木天然林种源苗期生长差异与早期选择

为研究格木不同天然种源家系苗的生长差异,选出相对速生的优良种源,本研究对8个格木天然林种源、110个家系1年生的苗高和地径等生长量指标进行测量,结合各家系的种子表型性状进行方差分析、多重比较、相关性分析和聚类分析。结果表明:不同种源的格木苗期生长量差异显著,具备种源选择的基础;不同种源的苗期生长量差异主要来源于种源内,具备从优良种源内选择优良家系的基础;苗期生长量与种子大小、种子厚和千粒重等性状呈极显著正相关关系,大粒、饱满种子可作为优良种源和家系选择的初选参考指标。初步选出浦北、北流种源作为格木优良种源。本研究为格木速生种源及家系的早期选择提供依据。