基于视觉注意力模型的红外人体图像兴趣区域提取*

由于红外人体图像所处背景的复杂性,使用阈值分割定位红外人体图像往往把大量的非人体图像一起分离出来,这给后续工作带来了巨大的计算量.研究了红外人体图像的典型特点和人眼视觉判断人体轮廓图像的敏感特征,使用该特征建立了简单的人眼视觉对人体的注意力模型,并构建特征判别概率函数,对待定目标进行概率的估算,最终使用该模型快速地剔除非人体红外图像的干扰,并准确地定位人体兴趣区域.     

螺旋CT的三维空间面皮参数平面化方法*

将三维空间面皮转换为二维平面可以使获取面皮特征、颅骨与面皮的关联信息更方便。通过改进的轮廓线提取方法剔除原始切片冗余数据,对重构得到的面皮数据进行空间坐标系的规范,并以最近邻区域(NNR)划分方法将空间面皮的点云数据点集化,最后结合新划分的平面点数据集的特点提出了线性插补的参数平面化方法和基于链表的参数平面化方法。实验证明两种方法的效果良好,验证了其正确性和可行性。     

甘肃中部地区农村劳动力转移的问题及对策

摘 要 甘肃中部地区在农村劳动力转移过程中出现了从未有过的“五化”（整体人口低能化、劳动者队 伍的老龄化、村庄凋敝化、公共管理弱化、男性鳏夫化）现象。通过对该现象进行深入分析,有针对性地 提出了大力提高农村人口素质,创新农地产权制度,大力发展民营企业,着力推进农村就业公共服务体系 建设,有序、较快推进农村城镇化等对策建议。     

超冗余移动机械臂的逆运动学快速求解

为了快速并精确地求解一类冗余移动机械臂(MM)运动学的优化逆解,提出了一种基于遗传信
赖域算法和解析解法相结合的运动学求逆方法. 首先使用解析解法求出机械臂逆解关于移动
车运动参数的表达式,据此表达式引入关节最佳柔顺性准则确定信赖域算法的目标函数;然
后用遗传信赖域算法快速求解此只包含移动车运动参数为自变量的目标函数的最优化问题,
据此求出运动学逆解. 仿真算例表明,该方法能快速求出精确和优化的运动学逆解.     

Local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics

Medical image segmentation is of pivotal importance in computer-aided clinical diagnosis. Many factors, including noises, bias field effect, local volume effect, as well as tissue movement may affect the med- ical image, thus causing blurring or uneven characteristics when forming a picture. Such quality defects will inevitably impair the gray-scale difference between adjacent tissues and lead to insufficient segmentation or even leakage during tissue or organ segmentation. In the present investigation, a local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics （LARFS） was proposed. By combining segmentation algorithm principles for traditional region growing （RG） and robust feature statistics （RFS）, the location and neighborhood image information of input seed point can be comprehensively analyzed by LARFS. Results show that, for different segmentation objects, under controlling the input parameter of growing factor within certain range, LARFS segmentation algorithm can adapt well to the regional geometric shape. And be- cause the robust feature statistics is applied in the contour evolution process, LARFS algorithm is not sensitive to noises and not easily influenced by image contrast and object topology. Hence, the leakage and excessive segmentation effects are ameliorated with a smooth edge, and the accuracy can be controlled within the effective error range.     

A Thermo-Mechanical Study of Some Epoxy Adhesives Subjected to Combined Dynamic and Static Stresses

The object of the present study was to investigate the effect of superimposed dynamic and static stresses on mechanical and thermal properties of some epoxy adhesives. It was found that combinations of shear creep and torsional oscillations, applied simultaneously to adhesive joints at temperatures within the glassy range of the adhesive, led to strengthening of the joints in shear and to an increase in the glass transition temperature of the adhesive. Similar loading stresses applied at temperatures close to the T_g of the adhesive, led to opposite effects on the above mentioned properties of the joints. The width of the glassy-rubbery transition of the adhesives increased, in the whole range of temperatures used in this study and for all epoxy compositions, as a result of subjecting the joints to superimposed dynamic and static stresses. The broadening of the glass transition was interpreted as a result of the stiffening of polymer network during the combined stressing experiments. A linear relationship was found between the area of endothermal peaks in the first DSC scan of specimens subjected prior to test to superimposed dynamic and static stresses at temperatures below T_g, and the shear strength of the joints. In agreement with this observation and with literature data, a linear relationship was revealed also between the glass transition temperature of the resins (measured in the first DSC scan) and the shear strength of the joints. Based on experimental observations and on some literature information, it was suggested that the strengthening of the joint, as well as the changes in thermal properties of the adhesives, are mainly due to physical processes, such as short-range orientation of network chains and an increase in intermolecular interaction between highly polar sites of the network. The possibility that superimposed stressing led to changes in chemical crosslinking was discussed but it seems that no such reactions occurred.     

2008~2016年MODIS多角度大气校正气溶胶产品在中国的时空分布及变化趋势

探究全国大气气溶胶分布及变化特征,准确了解中国地区气溶胶光学特性对研究大气环境污染、应对全球气候变化是非常重要的。对2008~2016年的MODIS MAIAC气溶胶光学厚度数据在中国的适用性进行验证,并采用Mann-Kendall方法,从不同的时空尺度和气溶胶类型上分析中国地区AOD值的时空变化特征。结果表明：①验证表明C6的MAIAC反演结果在中国AERONET匹配点上表现良好,C6的MAIAC反演AOD结果适用于中国区域;②从年际尺度上看,2008~2016年AOD年均值整体呈波动下降;从季节尺度上看,AOD季节变化呈春季整体高、夏季中心高、秋冬季水平低的特点,各省AOD平均值及各省份划区AOD平均值随季节变化趋势相似。③在空间上,AOD呈东南高、西北低、高值中心聚集的特征。④中国AOD变化整体呈现出东部减少且集聚,西部增加且分散的变化特征。可进一步探究不同种类气溶胶分布和气溶胶与典型大气污染物分布关系,以期为中国环境污染治理提供更好的决策指导。     

认知任务驱动的fMRI脑功能网络构建方法

针对脑功能网络的构建受到特定大脑图谱对兴趣点描述准确度及覆盖度的限制,提出了基于认知任务信息和神经影像数据的脑功能网络构建方法。首先计算fMRI体素对于认知任务的敏感度,然后在此基础上选取兼顾分布均衡和去中心化的大脑兴趣点,从而构建任务驱动的脑功能网络。实验通过在人脸情绪识别认知任务相关的梭状回构造任务驱动的脑功能网络,其度中心性、聚类系数、全局效率、局部效率这四个复杂网络指标均优于典型大脑图谱梭状回中兴趣点构成的网络。结果表明,计算得到的大脑兴趣点具有更强的整合性,更适合用于表征特定认知任务下的脑功能网络。     

基于X线的成人OSA计算机辅助诊断综述

阻塞性睡眠呼吸暂停（Obstructive Sleep Apnea,OSA）是成年人较为常见的呼吸类疾病之一,该疾病的特点是睡眠过程中频繁出现上气道完全或部分塌陷,严重影响人们的睡眠质量以及身体健康。阻塞性睡眠呼吸暂停综合征的诊断主要依靠多导睡眠监测,但这种方法无法满足目前大量的诊断需求。随着人工智能的出现及发展,假设深度学习可以有效地协助医生进行诊断该综合征。主要从阻塞性睡眠呼吸暂停的临床诊断方式出发,介绍了颅面侧位片作为诊断数据集的优势,以及人工智能诊断OSA的现状,提出了人工智能辅助医师诊断OSA的技术路线,分析了目前该诊断系统仍然存在的问题和挑战。     

无人机群目标搜索的主动感知方法

为提升蚁群搜索算法在规模大的栅格环境中对未知目标的搜索效率,提出基于蚁群算法的主动感知搜索框架。该框架通过应用历史环境信息来选择无人机的运动方式,并由无人机运动方式和感知域信息得到新的环境信息,从而实现无人机群的智能自动化搜索功能。新方法计算出一种具有探索偏好的未搜索概率,可使无人机搜索时偏向未搜索程度高的栅格,以此来提高算法的搜索能力。同时,以未搜索概率和信息素作为运动方式决策的依据来建立一种新的运动方式选择机制。该机制不仅考虑了目标可能出现的区域,又可兼顾未知区域,从而可实现无目标先验信息条件下的搜索过程。仿真结果表明,此算法在规模大的栅格环境中,与现有算法相比具有更高的搜索效率,并且得到的目标分布信息将更加全面。