反锐化掩模法在简牍文字增强中的应用

简牍图像分割是简牍文字识别的关键步骤,增强图像中的文字区域,可以有效降低简牍图像分割的难度,并且为文字识别打下基础.本文以长沙简牍博物馆所收藏的简牍文物为研究模型,首先对简牍图像进行预处理,利用对比拉伸变换增强对比度,然后在此基础上利用反锐化掩模法对简牍图像进行增强,试验表明,该方法对简牍图像文字信息具有良好的增强效果.     

多尺度Retinex算法在简牍图像增强中的应用

简牍图像增强是简牍文字修复和文字信息提取最为关键的一个步骤.以长沙简牍博物馆收藏的简牍文物为实物模型,以该馆提供的简牍数字图像为研究对象,提出了基于多尺度Retinex(MSR)算法的简牍图像增强方法,论述了本算法的原理及实现方法.采用MSR算法来消除光照对简牍图像的退化影响,以达到增强图像暗区细节信息的目的;同时针对MSR输出图像偏暗,提出了直方图拉伸算法.试验结果表明:本算法能够提高简牍图像对比度的同时,能显著地增强图像暗区的细节信息并且使简牍图像具有较好、较高的色彩保真度.本方法克服了目前常规的图像增强方法的不足,能够满足简牍考古人员的要求.     

Canny边缘算子在简牍文字修复中的应用

本文以长沙简牍博物馆所收藏的简牍文物为研究模型,对简牍文字的提取和修复进行了研究.提出了使用Canny边缘检测算子来提取文字的轮廓信息.然后再通过设置灰度阀值和人机交互相结合的方式对文字轮廓进行修复,最后再对文字轮廓进行填充,从而实现了简牍文字的提取与修复.试验表明,该方法对简牍图像的文字信息具有良好的修复效果.     

HSV色彩空间的Retinex结构光图像增强算法

在结构光几何重建中,由于拍摄方式和场景照明情况的复杂多变,使得产生的图像可能会因为光线的亮暗不均造成图像细节的缺失.为此,提出一种基于HSV色彩空间变换的带颜色恢复Retinex算法和色彩饱和度校正策略.针对颜色保持的需要,首先将传统RGB空间上的多尺度Retinex算法转换到HSV颜色空间;然后通过分析HSV颜色空间模型来增强模型中的V分量,同时利用相关系数使S分量随着V分量的增强进行自适应调整;最后将HSV模型转换到RGB空间,使增强后的图像颜色得到保持.实验结果表明,该算法应用于结构光条纹图像的增强中将使结构光图像在颜色得到保持的同时细节信息也得到了增强,更利于后续条纹信息的提取及自动编码.     

基于改进的空间直方图变换的图像信息挖掘算法研究

直方图均衡是常用的图像对比度增强技术.然而直方图并不包含任何空间颜色的分布信息,因此其在图像编辑方面的应用还很局限.为了解决这个问题,可以采用空间直方图技术以实现跟踪的目的.空间直方图是将直方图与每一种颜色的位置的均值和方差联合起来的图像描述方法.提出了一种新的空间直方图变换方法以实现图像的局部还原,更确切地说是采用一个参考空间直方图来修正所处理的图像中感兴趣区域的颜色值.基于图像的阴影去除和修复的仿真结果表明了该方法的有效性.     

红外与可见光图像快速融合算法

为了增强融合效果,提高融合速度,提出一种快速有效的红外与可见光图像融合算法.首先采用局部直方图均衡和中值滤波对红外与可见光图像进行对比度增强和去噪处理;然后对增强后图像进行线性融合,生成伪彩色融合图像;最后简化Lab颜色空间与RGB颜色空间之间的转换模型,并在简化的Lab空间实现全局颜色迁移,将可见光参考图像的一阶统计信息融合进伪彩色图像,获得自然感的真彩色图像.对比实验结果表明,采用文中算法生成的融合图像更加清晰、自然,速度更快、更简单.     

基于NLEMD的Retinex图像增强算法

为了将已有的受光照影响严重的图片恢复出细节信息更加丰富且光照平衡的图片,提出了基于NLEMD的Retinex图像增强算法.该算法采用多幅图像(其中包括一副待增强的图像和将待增强图像分别提高nl,n2,…,nm倍照射系数的多幅图像)协同NLEMD和Retinex算法来实现图像的增强.采用将待增强图像提高,l倍照射系数来获得多幅图像的目的是为了获得更丰富的图像暗处或明处的细节信息,然后利用NLEMD充分提取这些已知图像的各个频率信息;选取其中一幅图像经过NLEMD分解后所得的剩余分量,用Retinex增强算法增强;最后叠加所有图像的高频信息和Retinex算法增强后的剩余分量,得到增强后的图像.实验结果表明,算法增强后的图像克服了传统Retinex算法增强后图像对比度低和引入了噪声的缺陷,且暗处细节信息更加丰富,获得了更舒适的视觉效果.     

拉普拉斯与双边滤波的图像去运动模糊算法

运动模糊图像盲复原是图像复原中的关键问题之一,由于模糊信息的复杂性以及图像噪声的影响,导致复原的结果有振铃效应.为解决这些问题,提出基于拉普拉斯先验的改进算法.在原有的模糊核估计过程中,引入拉普拉斯锐化增强,增强图像的边缘信息,达到改善模糊核估计结果的目的.在复原时,针对图像振铃噪声,引入了双边滤波,抑制该噪声对复原结果的影响,进一步改善复原图像的质量.与三种现有图像去模糊算法相比,该方法能更准确地估计模糊信息,对图像复原具有更好的鲁棒性.     

融合深度神经网络和空洞卷积的语义图像分割研究

语义分割是计算机视觉中的基本任务,是对图像中的不同目标进行像素级的分割与分类.针对多尺度的目标分割难题,本文提出了一种基于Res Net网络的方法,通过定义并联支路,将浅层特征图像信息融合到深层特征图像中,提出新的空洞空间金字塔模块,该模块采用并行的不同采样率的空洞卷积进行特征提取与融合,从而更有效的提取不同层的特征以及上下文信息,并且在新模块中加入批规范化计算,增强参数调优的稳定性.本文还采用了Adam自适应优化函数,在训练的过程中,使得每个参数的更新都具有独立性,提升了模型训练的稳定性.本文结果在PASCAL VOC 2012语义分割测试集中取得了77.31%mIOU的成果,优于Deeplab V3的效果.     

基于自适应邻域对比度增强的直方图均衡算法

图像增强技术可分为局部增强和整体增强两种.在分析文字图像褪化因素及特点的基础上,提出一种基于自适应邻域对比度增强的直方图均衡法,它不仅能在增大整幅文字图像动态范围的同时增强局部对比度,去除扩散,而且能抑制一定的背景噪声.在此基础上,用灰度拉伸技术进一步加大文字图像的对比度,去除背景噪声,改善了褪化文字的视觉效果.     

Effects of mental fatigue on biomechanics of slips

The objective of this study was to investigate the effects of mental fatigue on biomechanics of slips. A total of 44 healthy young participants were evenly categorised into two groups: no fatigue and mental fatigue. Mental fatigue was induced by performing an AX-continuous performance test. The participants in both groups were instructed to walk on a linear walkway, and slips were induced unexpectedly during walking. We found that mental fatigue has adverse effects in all the three phases of slips. In particular, it leads to increased likelihood of slip initiation, poorer slip detection and a more insufficient reactive recovery response to slips. Based on the findings from the present study, we can conclude that mental fatigue is a risk factor for slips and falls. In order to prevent slip-induced falls, interventions, such as providing frequent rest breaks, could be applied in the workplace to avoid prolonged exposures to cognitively demanding activities.     

Slipping of the foot on the floor when pulling a pallet truck

Workers pulling pallet trucks are likely to slip when pulling and stepping on a low-friction floor. This study investigated the slipping of male participants when pulling a pallet truck, walking backward, and stepping on either a dry, wet, or glycerol-contaminated vinyl surface. The weight of the load on the truck was either low (0 kg), medium (295 kg), or high (568 kg). A motion-tracking system was used to collect the three-dimensional coordinates of the markers on the shoes. It was found that subjects might slip either upon landing of the leading foot on the toe (slip I) or before taking off of the lagging foot on the heel (slip II). The results indicated that the slip distances for both types of slip were significantly affected by the load and surface conditions and their interactions. Micro-slips (slips between 0.1 and 3 cm) and midi-slips (slips between 3 and 10 cm) were more common in slip I than in slip II. On glycerol-contaminated surfaces, the probabilities of a slide, or a slip more than 10 cm, for both slips I and II were over 40%. The implications of the results were discussed.     

MRSVD敏感分量在单频周跳探测修复中的应用

准确探测微小周跳历元是周跳修复的关键,精准修复周跳是高质量北斗卫星导航系统（BeiDou Navigation Satellite System,BDS）定位的难点,为此提出一种基于多分辨奇异值分解（Multi-Resolution Singular Value decomposition,MRSVD）的敏感分量预测模型,用于周跳探测与修复。该方法对探测信号构造Hankle矩阵,并对其进行MRSVD分析,得到一组具有不同分辨率的分量信号。然后对分量信号进行敏感因子评估分析,选取包含周跳特征的分量,构成敏感特征向量,凸显信号的周跳信息,进而通过模极大值谱精准检测出信号中奇异点的位置,实现对微小周跳的准确探测。以筛选出的MRSVD敏感特征向量为基础,构建最小二乘支持向量机（Least Square Support Vector Machine,LS-SVM）预测模型,进行周跳修复。实验结果表明,该方法能够对载波相位中出现的微小周跳进行准确探测与修复,证明了该方法的可行性和有效性。     

Designing a genetic neural fuzzy antilock-brake-system controller

A typical antilock brake system (ABS) senses when the wheel lockup is to occur, releases the brakes momentarily, and then reapplies the brakes when the wheel spins up again. In this paper, a genetic neural fuzzy ABS controller is proposed that consists of a nonderivative neural optimizer and fuzzy-logic components (FLCs). The nonderivative optimizer finds the optimal wheel slips that maximize the road adhesion coefficient. The optimal wheel slips are for the front and rear wheels. The inputs to the FLC are the optimal wheel slips obtained by the nonderivative optimizer. The fuzzy components then compute brake torques that force the actual wheel slips to track the optimal wheel slips; these torques minimize the vehicle stopping distance. The FLCs are tuned using a genetic algorithm. The performance of the proposed controller is compared with the case when maximal brake torques are applied causing a wheel lockup, and with the case when wheel slips are kept constant while the road surface changes     

检测GPS载波相位中周跳的R+1法

提出一种检测全球定位系统（GPS）载波相位信号中周跳的新方法，该方法是在同步观测序列中选出R个连续历元的观测作为正常观测，也叫拟准观测，使用拟准检定法检测相邻历元的观测值中的周跳。如果发现周跳，随即对该周跳进行修复，然后移动一个历元继续探测和修复。还提出了两种初始化的方案：多项式拟合法和最小二乘平差法。模拟试验表明R＋1法可以用来检测和修复发生在一个观测序列中单个的或连续的周跳，也可以检测和修复同时发生在多个观测序列中的周跳，还可以检测发生在基准星上的周跳，对于双差载波相位，可以检测到小至1周的周跳。     

GPS姿态系统中周跳的检测及修复方法

讨论了利用GPS载波相位信号测量载体姿态中出现的周跳问题及解决方法。首先根据静态情况下GPS载波相位信号的特点提出了一种基于外推法的周跳检测和修复方法。在此基础上又用故障检测的原理提出了一种利用冗余双差载波相位观测量的周跳检测和修复方法，该方法可以应用于动态情况，其适用条件是要求相邻历元至少有4颗卫星锁定，并且整周模糊度已经固定。文中利用实测数据对提出的方法进行了验证，结果表明两种周跳检测及修复方法是有效的，在GPS姿态系统中，综合运用这两种方法可大大减少系统的初始化次数。     

Gait parameters as predictors of slip severity in younger and older adults

This study investigated the association between slip severity and pre-slip gait characteristics of younger and older subjects. Sixteen younger and eleven older healthy adults walked onto an unexpectedly slippery surface. Slip severity was categorized as either hazardous or non-hazardous using a 1.0 ms peak slip velocity threshold. The results showed that hazardous slips were associated with greater step lengths (normalized by leg length) (SLR), larger and more rapidly changing foot - floor angles (FFA) at heel strike, and increased cadence across the two subject groups. Older subjects were found to walk with shorter SLR and with smaller and more slowly changing FFA at heel strike compared to younger subjects. However, both younger and older subjects experienced hazardous slips at the same rate. A logistic regression model relating SLR and cadence to slip severity predicted that increased SLR and decreased cadence would result in increased probability of hazardous slip (R2 = 0.45, chi2 = 15.30, p<0.01). A second logistic regression model relating FFA with slip severity predicted that increased FFA would result in increased probability of hazardous slip (R2 = 0.53, chi2 = 16.55, p<0.01). These results suggest that gait characteristics prior to foot contact play an important role in the severity of an ensuing slip. The finding that older adults experienced hazardous slips at the same rate as young adults even though their SLR and FFA are smaller suggests that age is also playing a role in other aspects of postural control that impact slip severity.     

Influence of self-efficacy on execution discrepancy and decision performance

Researchers of decision-making and human–computer interactions have been concerned with the issue of action slips and the development of supportive functionalities to reduce the occurrence of the slips. However, it remains unclear how to measure slips in a decision-making context and how motivational factors can help to reduce action slips. In this study, we formulate the construct of execution discrepancy to represent an individual’s deviation from his/her planned actions and propose a self-regulatory model to explain the antecedents and consequences of this construct. The model specifies that self-efficacy exerts a positive influence on the reduction of execution discrepancy that, in turn, leads to enhanced decision performance. An experiment was conducted based on the multi-attribute decision paradigm, and decision-makers’ eye movements were tracked to measure their execution discrepancy. The results support our hypothesis that self-efficacy serves as an important motivational factor to modulate cognitive efforts needed to reduce execution discrepancy during strategy execution. In addition to its theoretical and methodological contribution to the construct of execution discrepancy, this study may have essential implications for the design of technological artifacts that can predict and prevent possible action slips.     

一种有效的GPS周跳探测与修复方法研究

利用GPS载波相位进行姿态测量时,要达到很高的精度必须保证观测数据中没有载波相位周跳的发生,因此,正确探测与修复周跳是GPS姿态测量中的一个关键问题.通过分析比较常用周跳探测方法,采用电离层残差法对周跳进行探测,同时提出一种基于拟合方法的周跳修复方法.该方法能解决电离层残差检测周跳时的多值性问题,能够检测较小周跳和10周以上大的周跳,并且能很好地区分和修复周跳发生历元的载波相位值.利用实测数据验证了该方法的有效性与可行性.     

竹资源专题信息提取纹理特征量构建研究

在"同物异谱""异物同谱"问题较为严重的区域,单纯利用光谱信息难以有效地提取出竹资源专题信息。研究以ALOS影像为数据源,以南方多山县顺昌为试验区域,在考虑海拔、坡向、坡度等地形因子的前提下,通过分析竹、马尾松、杉木和其他树种等典型植被的纹理特征差异,构建了最佳纹理量,在此基础上,分别利用基于像元与面向对象的监督分类方法进行竹资源专题信息提取。经精度验证,提取的总体精度分别为71.5%、74.0%,说明:单纯利用纹理特征量亦能使竹资源专题信息的提取精度达到与单纯利用光谱信息相当的水平;通过最佳纹理量的构建,可以较有效地利用地物的纹理信息,从而更有效地利用遥感影像丰富的信息;实践证明了纹理特征量用于竹资源专题信息提取的可行性,为综合利用光谱与纹理信息进行专题信息提取的研究提供了实例支撑和技术参考,可以预见,基于光谱、纹理特征和地形因子的竹资源专题信息提取精度将得到进一步提高;在纹理特征量构建基础上进行竹资源专题信息提取,面向对象的监督分类较之于传统基于像元的监督分类的精度稍高,连续性更好。