基于红外热成像的夜间农田实时语义分割

农田环境实时语义分割是构成智能农机的视觉环境感知的重要环节，夜间农田语义分割可以使智能农机在夜间通过视觉感知农田环境进行全天候作业，而夜间无光环境下，可见光摄像头成像效果较差，将造成语义分割精度的下降。为保证夜间农田环境下红外图像语义分割的精度与实时性，该研究提出了一种适用于红外图像的红外实时双边语义分割网络（Infrared Real-time Bilateral Semantic Segmentation Network，IR-BiSeNet），根据红外图像分辨率低，细节模糊的特点该网络在实时双边语义分割网络（Bilateral Semantic Segmentation Net，BiSeNet）结构基础上进行改进，在其空间路径上，进一步融合红外图像低层特征，在该网络构架中的注意力提升模块、特征融合模块上使用全局最大池化层替换全局平均池化层以保留红外图像纹理细节信息。为验证提出方法的有效性，通过在夜间使用红外热成像采集的农田数据集上进行试验，数据集分割目标包括田地、行人、植物、障碍物、背景。经试验验证，提出方法在夜间农田红外数据集上达到了85.1%的平均交并比（Mean Intersection over Union，MIoU），同时达到40帧/s的处理速度，满足对夜间农田的实时语义分割。     

医学图像精细化分割方法研究

指出了深度学习方法在医学图像分割中取得较大的进展,但医学图像处理的复杂性使得全自动分割方法难以取得较好的分割效果。在卷积网络分割的基础上,结合应用场景使用适当的后处理手段来提升图像的分割效果是一种比较有临床意义的研究方法。主要研究了基于概率图的全连接条件随机场模型和基于用户交互的深度编辑网络,并分析总结了这两种方法的实现原理和各自优势,并对未来的研究工作进行了一些展望。     

棉花单核苷酸多态性标记研究进展

单核苷酸多态性标记已在农作物研究中得到广泛应用并取得重大进展。为了便利棉花SNP(Single nucleotide polymorphism)标记的研究和应用,介绍了利用基因芯片、简化基因组测序、重测序等在棉花中开发SNP标记的方法 ,综述了SNP标记在棉花遗传图谱构建、数量位点的定位和分子标记辅助育种、基因组测序以及系统进化等研究中的应用。并对异源四倍体棉花中SNP标记开发时,同源序列位点和部分同源序列位点上的SNP标记辨别问题进行了系统探讨,对其快捷的开发、检测方式和在数量基因定位中的应用前景进行了展望。     

SSR标记技术在马铃薯遗传育种研究中的应用

基于PCR基础上发展起来的SSR分子标记技术具有共显性遗传、多态性高、重复性好、稳定性好、操作简单等优点，本文简述了SSR分子标记技术的基本原理与特点，重点对马铃薯SSR引物的开发及其在马铃薯品种鉴定、遗传图谱构建与数量性状基因定位、分子标记辅助选择育种的研究现状进行了分析，并对其应用前景进行了展望。     

Object‐Based Mapping of Karst Rocky Desertification using a Support Vector Machine

Accurate and cost‐effective mapping of karst rocky desertification (KRD) is still a challenge at the regional and national scale. Visual interpretation has been utilised in the majority of studies, while an automated method based on pixel data has been investigated repeatedly. An object‐based method coupling with support vector machine (SVM) was developed and tested using Enhanced Thematic Mapper Plus (ETM+) images from three selected counties (Liujiang, Changshun and Zhenyuan) with different karst landscapes in SW China. The method supports a strategy of defining a mapping unit. It combined ETM+ images and ancillary data including elevation, slope and Normalized Difference Vegetation Index images. A sequence of scale parameters estimation, image segmentation, training data sampling, SVM parameters tuning and object classification was performed to achieve the mapping. A quantitative and semi‐automated approach was used to estimate scale parameters for segmenting an object at an optimal scale. We calculated the sum of area‐weighted standard deviation (WS), rate of change for WS, local variance (LV) and rate of change for LV at each scale level, and the threshold of the aforementioned index that indicated the optimal segment level and merge level. The KRD classification results had overall accuracies of 85·50, 84·00 and 84·86 per cent for Liujiang, Changshun and Zhenyuan, respectively, and kappa coefficients are up to 0·8062, 0·7917 and 0·8083, respectively. This approach mapped six classes of KRD and offered a visually appealing presentation. Moreover, it proposed a conceptual and size‐variable object from the classification standard of KRD. The results demonstrate that the application of our method provides an efficient approach for the mapping of KRD. Copyright © 2012 John Wiley & Sons, Ltd.     

实例教学法在建筑电气施工图识图教学中的运用--以人为本，学以致用

文章针对识图教学过程中运用实例教学的重要性进行阐述,并针对实例教学法在建筑电气施工识图教学中的应用加以探讨,以提供理论参考。     

基于高斯自适应拟合的苹果目标分割方法研究

苹果目标的准确识别是苹果机械化采摘需要解决的关键问题之一。为此,基于YUV颜色空间模型,提出了一种结合色差分量与高斯自适应拟合算法的苹果目标分割方法。该方法采用首先将苹果目标由RGB颜色空间转换至YUV颜色空间,并利用色差分量V建立果实与背景分割的高斯分布拟合模型,根据拟合结果自动获取分割阈值,以实现自然场景下苹果目标的准确分割。为了验证文中算法的有效性,利用多幅图像进行了试验并与Otsu自适应阈值分割算法进行了比较。试验结果表明,采用文中算法得到的苹果果实的平均检出率达87.08%,识别率领先Otsu算法9.91%。因此,对于着色度较为均匀的苹果目标,采用高斯自适应拟合方法可以有效提高其识别率。     

基于MatLab和DSP的哈密瓜纹理分割与分类

以新疆特色水果哈密瓜为研究对象,提出一种利用Matlab辅助DSP提取哈密瓜纹理的方法。该方法首先利用Matlab把待处理的图像转换为数据文件(dat文件),然后利用DSP强大的运算能力分割哈密瓜表面纹理特征,并将分割结果同样以dat文件传递给Mat Lab,最后利用Mat Lab强大的数据分析与图像显示能力建立哈密瓜分类模型。实验结果表明,该方法能够有效地对哈密瓜表面纹理进行分割与分类,分类准确率为88.10%。该方法不但能够缩短DSP系统的开发周期,且能够为今后开发基于DSP的哈密瓜品质实时检测系统奠定基础。     

Basic characterization of avian β‐defensin genes in the Japanese quail,Coturnix japonica

In this study, we identified a cluster of 14 avian β‐defensins (AvBD; approximately 66 kbp) in the Japanese quail, Coturnix japonica. Except for AvBD12 (CjAvBD12) and ‐13, the CjAvBDs coding sequences exhibited greater than 78.0% similarity to the respective orthologous chicken AvBD genes (GgAvBD). The putative amino acid sequence encoded by each CjAvBD contained six cysteine residues and the GXC (X1‐2) motif considered essential for the β‐defensin family. Each CjAvBDs also formed a sub‐group with the respective orthologous genes of various bird species in a phylogenetic tree analysis. Synteny between the CjAvBD cluster and GgAvBD cluster was confirmed. The CjAvBD cluster was mapped on the long‐arm end of chromosome 3 by linkage analysis based on single nucleotide polymorphisms (SNPs) of CjAvBD1 and CjAvBD12 (approximately 46kbp), as well as GgAvBD cluster. We also confirmed that CjAvBD1, ‐4, ‐5, ‐9, and ‐10 are transcribed in 20 tissues, including immune and digestive tissues. However, our experimental data indicated that the CjAvBD cluster lacks the AvBD3 and ‐7 loci, whereas the CjAvBD101α, ‐101β, and ‐101θ loci arose from gene duplication of the AvBD6 orthologous locus in the CjAvBD cluster after differentiation between Coturnix ‐ Gallus.     

ICAI Realizaltion for the K-map Simplification of Logical Function

Based on the theory of the K map simplification of logical function(KSLF),this article releases a ICAI Realization for KSLF.Providing three kinds of teaching style:commonness, teaching, practice.This product,wich supports for the K map simplification with random item,is not only helpful to the construction of the curriculum of digital circuit ,but also to the design for digital application system.Under the practice method, This product's guides,checks,and corrects the student's whole process forthe proceeding of KSLF automaticly under the teaching method.