TP2

检测视频中的运动目标以及阴影，并消除阴影，基于opencv，将RGB颜色空间根据一定的转换关系转换到HSV空间，最后消除阴影， 可以在vc6.0和vs2008上正常运行(Shadow detection algorithm based on HSV color space)

说明：  根据Itti视觉注意模型得到图像的显著区域。本算法简单并且对一般简单的图像能够提取出比较好的显著区域。(According to Itti visual attention model are significant regions in the image. The algorithm is simple and easy on the general good image to extract a significant area.)

Image watermark using 3 level DWT

说明：  ：基于主动轮廓识别和被动轮廓识别方法各自的优缺点，提出结合主动和被动的方法，先对图像进行被动轮廓的预处理，然 后再应用主动轮廓的方法，通过比较选出Canny算子进行预处理，再通过基于概率的方法分割图像，最后再应用Snake模型进行 轮廓提取。并取得较好的应用。(: Identification Based on Active Contour and passive contour recognition advantages and disadvantages of each method, proposed method of combining active and passive, passive first outline of the image pre-processing before applying the active contour method, by comparing the pre-selected Canny operator treatment, and then through the image segmentation method based on probability, and finally application of Snake model for contour extraction. And get better application.)

从回波中估计多普勒参数是合成孔径雷达运动补偿的关键。文中研究了多目标回波对参数估计的影响，从理论上推导了估计多普勒中心和调频率对回波的不同要求，并用两个指标举例分析了一段实测机载SAR数据，给出了实际应用中参数估计时选择回波的原则。(Doppler parameters estimation from radar echoes is a key step in SAR(Synthetic Aperture Radar}motion cornpensation． This paper researched the efect of multiple targets echoes to estimate parameters and deducted theoretically the different requirement for echoes in estimating doppler centroid and doppler frequency modulation rate．Th en giving a real airborne SAR echo as example，we analyzed it with two measurements and concluded the principle about choosing echoes in practice．)

说明：  基于边缘特征的SAR图像与光学图像匹配，测度为Hausdorff距离(SAR images based on edge features and optical image matching, for the Hausdorff distance measure )

完成了对车道线进行了识别，主要流程为灰度化，边缘检测，hough变换。(We completed the lane line identification, the main process of graying, edge detection, hough transform.)

matlab数字图象处理工具箱 包括imstack2vectors 霍夫变换等许多工具(imstack2vectors Hough transform matlab digital image processing toolbox includes many tools)

灰度或彩色多模态医学图像的融合，利用加权平均融合算法，程序具体很好的通用性，并且提供几种图像融合客观评价指标，还给出3组宝贵的已配准医学图像(Color gray or fusion multimodal medical images, using a weighted average fusion algorithm, program specific good versatility and provide an objective uation of several image fusion, the three groups are also given valuable medical image registration has been)

使用snake方法进行图像处理的原代码，简单准确(use snake image processing methods for the original code simpler and more accurate)