增强半虚拟现实座舱技术

为提高半虚拟现实座舱中用户视觉真实感与人-座舱交互性能,提出了一种增强半虚拟现实座舱技术,将手图像实时融合到虚拟座舱环境中,使用户能实时看到自己的真实手。通过肤色检测算法实时分割摄像机采集图像,应用改进的自适应加权立体匹配算法与视图变形算法对图像进行视点校正,通过虚实匹配与虚实融合将手图像无缝融合到虚拟环境中,为用户提供增强虚拟环境中的可视化图像。测试结果表明:增强半虚拟现实座舱技术方案中触觉与视觉反馈真实,在头盔式虚拟环境中用户交互能点击到的最小方块边长为8mm。采用增强半虚拟现实技术方案完成座舱内典型交互动作的时间比传统数据手套方案与半虚拟交互方案平均分别降低约50%与18%,极大提高了人-座舱交互性能,可有效增强虚拟现实座舱系统实用性,并降低开发成本。     

城市道路交叉口自动事件监测系统

提出一种基于事件特征来检测交通事件的监测系统.系统选取3个特征值,交通流、车辆角度和车辆加速度.从CCD摄像头获取图像序列之后做车辆检测,提取车辆移动方向、交通流和车辆加速度来获得检测结果.该方法通过计算得到正确率97.8%,误报率1.02%,检测时间只要30 s.结果表明,该方法比检测效果更好.     

基于多特征的纹理特征提取方法研究与应用

纹理是图像的1种重要视觉特征,常用于识别和区分图像。纹理特征的提取则是其应用需首先解决的问题。通过总结分析目前较为常用的纹理特征提取方法,基于灰度共生矩阵(GLCM )算法、局部二值模式(LBP)算法和小波变换(DWT )算法的特点,提出基于多特征的纹理特征提取算法,即将各算法提取的特征进行融合。融合中使用权重对参数进行配置。论文设计了1种图像检索实验,通过图像检索实验比较了各算法提取的特征对纹理的描述能力。结果表明,对于Co rel图像库,笔者提出的多特征的纹理特征提取算法检索的平均查准率相对于GLCM 算法提高了20%,相对于LBP算法提高了9%,相对于DWT算法提高了10%,相对于徐少平等人提出的特征融合方法提高了15%。证实了文中所提出的算法能够兼顾各算法的优点,并具有较好的旋转不变性和尺度不变性。其不足之处是需要同时提取GLCM 算法,LBP算法,DWT 算法下的纹理特征,计算所需时间是后3种算法时间之和,使算法的实用性受到了一定的限制。      

公路沿线环境的遥感监测方法

随着城市建设的飞速发展,公路成为带动区域经济发展的重要基础设施之一。道路网络不断加密,不仅占用了大量土地,还产生了许多生态效应。因而,开展道路沿线环境状况的动态监测及其安全分析,对于自然资源开发、区域生态环境保护以及可持续发展都非常重要,并为项目环评提供依据。     

Review of pixel-level image fusion

Image fusion can be performed at different levels:signal,pixel,feature and symbol levels.Almost all image fusion algorithms developed to date fall into pixel level.This paper provides an overview of the most widely used pixel-level image fusion algorithms and some comments about their relative strengths and weaknesses.Particular emphasis is placed on multiscale-based methods.Some performance measures practicable for pixel-level image fusion are also discussed.At last,prospects of pixel-level image fusion ar...     

基于三维各向异性扩散的图像平滑及三维重构效果分析

为了实现理想的三维重构效果,在重构前需要对切片集进行预处理。主要研究各向异性扩散的平滑方法,并将二维各向异性扩散平滑技术向三维空间进行推广,并就二维和三维各向异性扩散平滑技术对三维重构效果进行了分析,结果表明三维各向异性扩散具有更好的各向协同的平滑效果。     

Eye and Iris Detection Using Projection and Radial Symmetry Transform

This paper presents an eye and iris detection algorithm for human facial images. The authors combine three features of the eye to develop the algorithm: 1) the pixels surrounding the eyes are more variable than other parts of the face; 2) eye pixels are darker than their neighbors; 3) eyes often exhibit radial symmetric properties. Through the first feature, two rough regions of both eyes are detected on the face. Eye masks are then formed based on the second feature, and a fast radial symmetry transform is applied to the two rough regions of both eyes. Finally, accurate iris centers are located by searching the maximum value of the radial symmetry transform results. Using 450 human facial images from the Caltech face database, experiments show that the success rate of the proposed method is 91.7%. The effectiveness of the method was also verified through detection of video frames.     

Study on chromatographic fingerprint of sarcandra glabra （Thunb.） by microwave-assisted extraction coupled to HPLC/DAD

Microwave-assisted extraction (MAE) was used for extraction of effective components of sarcandra glabra (Thunb.), and then chromatographic fingerprint of sarcandra glabra (Thunb.) was studied by high performance liquid chromatography/diode array detector (HPLC/DAD). The conditions of MAE were optimized by an orthogonal experiment, and then the authentication and validation of the chromatographic fingerprint were conducted. Nine peaks were identified as common peaks in the fingerprint chromatograms, and isofraxidin was considered as a reference compound and quantified. Relative standard deviations of retention time and peak area of each component were less than 3% and 8%, respectively. Similarity and difference analysis were conducted by use of PCA and relation coefficient. Twenty batches of sarcandra glabra (Thunb.) samples from two different producing areas could be classified into two different groups in the PCA model. The results showed that MAE-HPLC/DAD method was simple, efficient and stable for the study of complex chromatographic fingerprint of sarcandra glabra (Thunb.), which could provide more reliable and precise information for quality evaluation.     

基于小波变换的医学图像特征点互信息配准

医学图像配准是医学图像分析诊断的基础,也是图像融合等图像处理需要先行解决的问题.目前医学图像配准方法基本上分为基于形状特征和基于像素相似性两种方法.文中用小波变换提取图像特征点,将特征点互信息作为图像配准的相似性测度,并使用粒子群算法来求解配准所需的空间变换参数.实验结果表明,此方法减少了计算量,具有较快的配准速度,能准确地实现多模态医学图像的配准。     

巫奉高速公路工程地质遥感勘察

针对巫奉高速公路地形地貌、地质条件复杂,滑坡、崩塌、岩溶等不良地质现象发育的特点,运用多级地质遥感勘察手段,基于地学遥感分析技术,采用Landsat ETM+、SPOT-5、1∶8 000航空立体像,对等多源、多尺度、多时相遥感影像数据,从宏观到微观研究路线沿线的地质灾害现象及其区域分布规律,并从工程地质勘察的角度提出公路建设应注意的问题.