【摘 要】
：
针对月球卫星的景象匹配定位问题,为"嫦娥二号"卫星设计了相应的匹配模式,并构造约束模型进行了匹配矩阵的修正,实现了"嫦娥二号"线阵CCD观测图和美国LRO卫星局部基准图的子图像块大规模匹配。实验中,首先通过构建匹配矩阵和测试库验证了单对图像归一化互信息匹配的可行性和局限性,然后通过约束模型修正,显著性水平取0.1时,使匹配成功率从60.7%提高到89.0%,并且测试库中89.0%的正确匹配对被匹配
论文部分内容阅读
针对月球卫星的景象匹配定位问题,为"嫦娥二号"卫星设计了相应的匹配模式,并构造约束模型进行了匹配矩阵的修正,实现了"嫦娥二号"线阵CCD观测图和美国LRO卫星局部基准图的子图像块大规模匹配。实验中,首先通过构建匹配矩阵和测试库验证了单对图像归一化互信息匹配的可行性和局限性,然后通过约束模型修正,显著性水平取0.1时,使匹配成功率从60.7%提高到89.0%,并且测试库中89.0%的正确匹配对被匹配矩阵所保留。实验结果表明,所提方法对"嫦娥二号"观测图的高效、高成功率匹配可行,能够为进一步的月球卫星位
其他文献
Crowded scene analysis is currently a hot and challenging topic in computer vision field. The ability to analyze motion patterns from videos is a difficult, but critical part of this problem. In this
目前模式识别领域中缺乏有效的多类概率建模方法,对此提出利用纠错输出编码作为多类概率建模框架,将二元纠错输出编码研究的概率输出问题转化为线性超定方程的求解问题,通过线性最小二乘法来求解并获取多类后验概率的结果;而对于三元纠错输出编码的等价非线性超定方程组,提出一种迭代法则来求解多类概率输出.实验中通过与3种经典方法相比较可以发现,新方法求取的概率输出具有更好的分布形态,并且该方法具有较好的分类性能.
In signal and image processing,we want to recover a faithful representation of an original scene from blurred,noisy image data.This process can be transformed mathematically into solving a linear syst
The estimation of the signal variance is a critical challenge in wavelet-domain minimum mean square error(MMSE) based image denoising.In contrast to the conventional approaches that treat the neighbor
An intelligent verification platform based on a structured analysis model is presented.Using an abstract model mechanism with specific signal interfaces for user callback,the unified structured analys
The orientation and correction of mural images by registering them with laser scanning data is critical for the digital protection of ancient murals.This paper proposes a method for the non-rigid regi
Shadow maps sample scene visibility in the light source space and offer an efficient solution to generate hard shadows.However,they suffer from aliasing artifacts because of discretization errors,inad
An algorithm is proposed,which combines global and local information of fingerprint images to detect singular points.Its mathematically proven that normal lines of gradient of double orientation field
This study proposes a robust video hashing for video copy detection.The proposed method,which is based on representative-dispersive frames(R-D frames),can reveal the global and local information of a
道岔大量存在于车站、编组站等地。正确的识别道岔的开口方向是行车安全的关键。文章提出一种基于铁轨交点的道岔自动检测方法,该方法可自动检测铁轨的交点,结合先验知识,自动定位道岔所在区域并放大,从而起到警示机车司机安全行车的作用。