Hyperspectralterrain-classfic

针对粒子概率假设密度(PH D)滤波算法在虚警、漏检情况下，b标状态估计不稳定和b标可观测性车弱的问题，提出了一种基于序贯融合的粒子PH D滤波方法，利用雷达和红外传感器多目标进行融合跟踪杏基本思想是先对红外传感器进行粒子PH D滤波，丙将红外传感器滤波结果作为雷达的预测值，然后利用P达观测的数据进行更新，这样通过雷达和红外传感器交替上作保证目标状态的可观测性，从滤波器输出结身即可得到目标的状态信息仿真结果表明，在虚警、漏检和密集目标环境下，该方法是有效的和稳健的(The problem of target state estimation instability and observability weakerin the presence offalse alarms and missed detection was deal with. On the basis of sequential fusion, a particleprobabil- ity hypothesis density(PHD) filter for multrsensor multrtarget tracking was proposed. Observed da to collected from the infrared sensor was estimated with the particle PHD filter. Then the results from the filter were set as the radar predicted value by the radar observations. The multrtarget state can be updated to guarantee observing the target state. In this way, the global state is updated at the fusion center. Simulation results show that the proposed algorithm is effective and robust under the false warning, omission and concentrated target environment. )

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)

图像处理中的数字识别代码，包括数字训练集合和训练分类算法，可以实际应用。(digital recognition)

SURF算法较SIFT算法速度快，SURF算法源代码。(SURF code)

c 实现 canny算子(c realize canny )

本程序包括图像的几何变换、图像的灰度变换、图像的空域增强、图像的频域增强、图像的形态学处理、图像的分割和区域增长、还有图像的数字识别等一系列有关图像的基本操作和处理。(This procedure including the image geometric transform, the image gradation transformation, the image air zone strengthens, the image frequency range to strengthen, image morphology processing, the image division and the region grows, also has the image digital recognition and so on a series of related image elementary operation eo and processing. )

对CANNY算子进行改进，其中详细的分析了CANNY算子的原理，已经应用改进的canny算子进行边缘检测，效果较好(CANNY operator improvements, including a detailed analysis of the principle of CANNY operator has been applied to improve the canny operator edge detection, better )

重要的纹理分割分类基础程序，可以进行更深入的探讨和优化，应用于遥感影像中。(Important basis for classification of texture segmentation procedure can be carried out more in-depth exploration and optimization, application of remote sensing images.)

这是一个简单的图象处理的小软件的原代码，试试吧，不错的(This is a simple image of the original small software code, try it, good)

说明：  实现机器视觉双目标定，三维重建等算法，具有很好地擦考价值( Robot with two cameras to switch recognition system. (Note that not binocular vision) and the reference used opencv1.0 cmv. )