【摘 要】
：
提出了一种新的基于柯西分布的光照模型(shading model,SM)变化检测方法。在一种快速动态背景图像初始化的基础上,建立了Gaussian统计背景模型;基于使用统计假设检验方法检测变化区域的结果,利用YCbCr颜色空间的亮度、颜色信息,识别和消除视频序列图像中的阴影和反光等。试验表明,该文所提出的方法可以承受整体或局部的、缓慢或突然的背景光线变化,以及由场景背景中小的背景扰动、阴影或反光导
论文部分内容阅读
提出了一种新的基于柯西分布的光照模型(shading model,SM)变化检测方法。在一种快速动态背景图像初始化的基础上,建立了Gaussian统计背景模型;基于使用统计假设检验方法检测变化区域的结果,利用YCbCr颜色空间的亮度、颜色信息,识别和消除视频序列图像中的阴影和反光等。试验表明,该文所提出的方法可以承受整体或局部的、缓慢或突然的背景光线变化,以及由场景背景中小的背景扰动、阴影或反光导致的噪声,可以较精确地检测背景目标,改善了SM方法在较暗区域的目标检测效果。
其他文献
根据合肥站4 a的观测资料,对比分析了整层大气可降水量(precipitable water vapor,PWV)与地面水汽压(surface vapor pressure,SVP)之间的几种经验关系。统计结果表明,PWV与SVP的对数关系、线性关系和二次曲线关系回归方程的年决定系数普遍大于0.820;二次曲线关系的经验系数随年度变化较明显;线性关系的经验系数则相对具有年度稳定性;二次曲线关系更符
基于复杂自适应系统理论,采用自下而上的基于智能体的建模分析方法,模拟了自然环境与钉螺生长相互作用导致的钉螺生长的主要行为特征、生命状态和数量变化,开发实现了模拟模型,同时输入实测数据进行实例模拟,结果表明该模型能够作为血吸虫病防控工作中钉螺数量估测的一种辅助实验方法和工具。
The influence derived from atmosphere transmitting of radar wave, in the application of high-resolution airborne Synthetic Aperture Radar (SAR) stereo positioning, may produce some phase errors, and e
This paper applied an integrated method combining grey relation analysis, wavelet analysis and statistical analysis to study climate change and its effects on runoff of the Kaidu River at multi-time s
In order to improve the effectiveness of Fuzzy Synthetic Evaluation (FSE) models, a Parameter Correlation Analysis (PCA) was introduced into the FSE and a case study was carried out in the Naoli River
Many kinds of uncertainties are involved, such as random, fuzzy, grey, unascertained property and so on, in soil erosion process. To exactly predict the non-point source pollution loads, some uncertai
Agricultural village is an important rural type in China. The evolution process and mechanism of its cultural landscape are different from those of the industrialized village. The paper focuses this t
Taking Nanjing as a case, the paper explains the spatial behavior differences existing in the information technology use among different groups of residents and households, by virtue of analyzing the
A non-dimensional relative sensitivity coefficient was employed to predict the responses of reference crop evapotranspiration (ET0) to perturbation of four climate variables in Taoer River Basin of th
由于交叉皮层模型(intersecting cortical model,ICM)图标信号具有平移、旋转以及尺度不变性,因此,基于ICM的图像匹配算法能够提高实时目标图与基准目标图的匹配率,但根据ICM图标信号获取的不变特征对噪声信号较敏感。针对这一问题,提出了基于ICM和小波变换的图像匹配识别算法。仿真结果表明,本文算法在平移、尺度、旋转变化以及噪声环境下仍具有较高的匹配率。