空间域滤波

人耳识别，包含图像预处理，图像特征点的提取，比较实用(Ear recognition)

该代码实现了sift特征提取，特征点自动匹配，效率较高(The code realizes sift registration)

大恒相机二次开发，单次采集

图像匹配最新的源码 matlab 适合初学者和进阶者作者hongshengli (The latest source of image matching matlab for beginners and advanced by Author hongshengli)

程序包括三种经典的边缘检测方法，均可独立运行，参数可调(Program includes three classical edge detection methods can be run independently, adjustable parameters)

这篇文章是一种特征降维的方法，不过跟一般的计较离散度的方法不同，这个特征变换的准则是：尽可能地保留原始样本的熵(Kernel Entropy Component Analysis Jenssen, R Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume: PP , Issue: 99 )

CVPR2013中出现的一种显著性特征检测算法，该算法用于模拟人眼视觉识别过程，提取图像中的显著性特征借后期目标对象的检测跟踪等使用，该算法(Context-Aware Saliency Detection。matlab implementation of an classical saliency detection alrogithm,which imitate our recognition process of eyes)

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. )

利用正交匹配跟踪原子库对信号进行稀疏分解程序(Using orthogonal matching pursuit atom libraries for signal sparse decomposition process)

本系统中VIS欠缺的SIFT_VC.lib文件。。。 http://www.pudn.com/downloads224/sourcecode/math/detail1055031.html(This is lib file, which is used in Video Intelligent System (VIS) based on the Microsoft Visual Studio 2008 compiler environment and OpenCV 2.0 library. It includes foreground detection, motion object detection, motion object tracking, trajectories generation and analysis modules. It realizes a friendly interface based on dialog, which provides a convenient example for new learners. keywords: opencv, mixture of gaussian model, sift feature and ransac method, mean shift, particle filter, kalman filter, object detection and tracking, video intelligent system.)