红外相机技术在河北雾灵山国家级自然保护区中的应用

为了充实河北雾灵山自然保护区的野生动物资源本底资料,提高监测能力和监测水平,雾灵山保护区自2015年开始将红外相机技术应用到野生动植物的资源调查和管护中。目前应用红外相机技术发现兽类5目10科14种,鸟类4目6科10种,掌握了区内主要物种猪獾(Arctonyx collaris)、狍(Capreolus)和勺鸡(Pucrasia macrolopha)的日活动节律,补充了保护区的本底调查资料,为保护区进一步开展金钱豹(Panthera pardus)、斑羚(Naemorhedus goral)和鸟类多样性等科学研究奠定了基础,为保护区制定关于野生动物资源的相关管护政策提供了科学依据。     

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。     

移动互联网环境下农机企业危机沟通的思考*

从危机沟通的渠道、危机沟通的具体策略、危机沟通的后续行动三个方面,为中国农机企业的危机沟通提供可行建议。以形象修护理论为基础,结合移动互联网环境传播特点以及中国农业机械化发展的实际情况,分析新浪新闻手机客户端、今日头条手机客户端上的两条农机质量纠纷视频。推荐农机企业使用的8条具体策略包括:否认事件不实部分;表明事件的意外属性;阐明自身出发点;阐明自己的贡献及所做出的努力;提出物质补偿;提出改进措施;承担有错部分;主动向用户征询意见。提出危机沟通应在线上、线下两种渠道进行,危机沟通应与具体行动相结合。     

A novel approach to estimating the competitive ability of Cirsium arvense in cereals using unmanned aerial vehicle imagery

Eight experiments were carried out in Denmark to determine the yield loss of spring barley due to Cirsium arvense in farmers' fields and to suggest and evaluate a novel approach for quantifying C. arvense infestation in large plots. Literature about the competitive ability of C. arvense is old, scattered and inconclusive, and existing models for estimating crop yield loss are based on data from North America. This study showed that C. arvense coverage could be quantified from unmanned aerial vehicle imagery using a manual image analysis procedure. This gave similar results as scoring the coverage. Yield loss of spring barley due to C. arvense infestation assessed at harvest was given by Y = 100·(1−exp(−0.00170·X)) where Y is the percentage of crop yield loss and X is the percentage of C. arvense coverage. The yield loss was much lower than estimates from models that have been developed in North America. It is speculated that the main reason for this is the later emergence of C. arvense than the crop due to lower soil temperatures in spring. Grain moisture increased linearly with C. arvense coverage: M = 0.0310·X where M is the proportional (%) increase in grain moisture and X is the proportion (%) of C. arvense coverage. Automated image analysis procedures are needed to estimate C. arvense coverage on field scales, and further experiments are needed to reveal whether the low competitive ability of C. arvense found in this study is representative for Northern Europe.     

食用菌品牌形象的视觉艺术价值

从视觉艺术的角度研究食用菌品牌形象的设计。通过讨论品牌名称、标志物和文字等食用菌品牌视觉要素,提出了食用菌品牌形象的视觉艺术价值设计原则。食用菌品牌形象的视觉艺术价值体现在品牌设计的多个方面,创新的视觉艺术能让食用菌品牌形象真正体现艺术的价值。     

基于CNN的小麦籽粒完整性图像检测系统

为了快速、准确识别小麦籽粒的完整粒和破损粒,设计了基于卷积神经网络(CNN)的小麦籽粒完整性图像检测系统,并成功应用于实际检测中。采集完整粒和破损粒两类小麦籽粒图像,对图像进行分割、滤波等处理后,建立单粒小麦的图像数据库和形态特征数据库。采用LeNet-5、AlexNet、VGG-16和ResNet-34等4种典型卷积神经网络建立小麦籽粒完整性识别模型,并与SVM和BP神经网络所建模型进行对比。结果表明,SVM和BP神经网络所建模型的验证集识别准确率最高为92. 25%; 4种卷积神经网络模型明显优于两种传统模型,其中,识别性能最佳的AlexNet的测试集识别准确率为98. 02%,识别速率为0. 827 ms/粒。基于AlexNet模型设计了小麦籽粒完整性图像检测系统,检测结果显示,100粒小麦的检测时间为26. 3 s,其中,图像采集过程平均用时21. 2 s,图像处理与识别过程平均用时为5. 1 s,平均识别准确率为96. 67%。     

A data transfer method for improving seed identification of maize (Zea mays) haploid breeding based on genetic similarity

Maize haploid breeding technology is able to identify haploid seeds non‐destructively, rapidly and at low cost with the help of Near‐infrared (NIR) spectral analysis. However, due to the hybridization of numerous parents and the low production rate of haploid, the haploid data collection becomes a burden for engineering this technology. Biologically, there are considerable similarities between the progeny of the same female parent and different male parents. Based on this advantage, similar spectral data can be transferred when the NIR technology is employed. A revised method of Transfer adaptive boost (TrAdaBoost) is proposed to improve identifying for the backpropagation neural network (BPNN) classifier. To avoid the negative transfer, a screening thresh is used to select out similar data, and the amount of these data are limited to join current training. The results show that the identification performances are improved significantly when the data amount is small. This method shows a high ability to make the seed identification more convenient for engineering maize haploid breeding.     

基于双目立体视觉的重叠柑橘空间定位

果实的精准识别和定位是智能采摘面临的难题之一。基于双目立体视觉，提出了一种针对户外重叠柑橘的三维空间定位方法。首先，从双目左右图像中提取重叠柑橘果实轮廓并进行高斯平滑，通过曲率分析，找出异常的轮廓像素点；其次，依次连接相邻两个异常像素点，分析该线段上的像素点到柑橘轮廓的距离，在相邻两正常线段的交点处完成重叠柑橘轮廓分割，并通过寻找异常线段剔除对应的非柑橘轮廓像素点；再者，采用最小二乘椭圆拟合方法重建柑橘目标轮廓，并获取柑橘的中心；最后，根据双目极线约束和图像相似度，对重叠柑橘中心点进行匹配，并基于视差原理计算柑橘中心的深度值及三维空间坐标，确定重叠柑橘的遮挡关系。户外实验结果表明,所提出的方法定位误差为6.38 mm，满足柑橘采摘机器人户外采摘作业的定位精度要求。     

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。     

Cotton Image Segmentation Algorithm Based on Fusion Method of Markov Random Field and Quantum Particle Swarm Cluster

[Objective] The aim of this study was to improve the cotton image segmentation accuracy in a picking robot image processing system. [Method] An image segmentation algorithm based on a fusion method of Markov random field and quantum particle swarm optimization clustering was proposed. The process of the proposed algorithm is as follows: first, transform the RGB (red, green, blue) images into grayscale; second, use it to segment these images; finally, the threshold of the connected area is set on the basis of the segmented image to obtain the target area. Then, the cotton front image and the cotton side image are selected from the images collected from different angles. The segmentation experiment was carried out by using this algorithm, and compared with the Otsu algorithm, the fuzzy C-means algorithm, the quantum particle swarm image segmentation algorithm and the Markov random field image segmentation algorithm. [Result] The results showed that the segmentation accuracy and peak signal to noise ratio of the proposed algorithm were 98.94% and 77.48 dB. When compared with the Otsu algorithm, fuzzy C-means algorithm, quantum particle swarm optimization algorithm and Markov random field algorithm, the average segmentation accuracy and peak signal to noise ratio of the proposed algorithm increased by 2.47%–4.56%, and 9.81–13.11 dB, respectively. [Conclusion] The proposed algorithm had higher segmentation accuracy and higher peak signal to noise ratio than the other algorithms tested.