hw

优化了的DLT算法，能够很好地跟踪目标。请下载woman等视频序列(Optimized DLT algorithm can track the target very well. Download woman and other video sequences)

采用基于LSB的随机图像隐藏技术实现将一幅图像（目标图像）隐藏到另一幅图像（载体图像）中。包含目标图像yctx.bmp，载体图像Miss.bmp，图像隐藏代码randlsbimghide.m文件，图像读取代码randlsbimgget.m文件，随机位选择代码randinterval.m文件。(LSB-based technique of random images to achieve a hidden image (object image) to another piece of hidden images (vector image) in the. Includes target image yctx.bmp, vector image Miss.bmp, image hidden code randlsbimghide.m file, image file reading code randlsbimgget.m, random bits select the code randinterval.m file.)

随机中点位移法matlab程序代码，生成三维山地模型(Random Midpoint Displacement Method for Mountains Generation)

说明：  将ply格式的3D物体文件导入Matlab中，并且可以把Matlab中的Patch object导出成ply格式。(Ply format to 3D objects in the file into Matlab, and Matlab can be derived in the Patch object into a format ply.)

用点扩散函数psf对波前编码系统产生的模糊图像进行复原得到清晰图像(use the PSF of wavefront coding system to restore its blurred image )

核自适应滤波算法krls的matlab程序。已将klms算法弄成函数，加载即可使用。(Nuclear adaptive filtering algorithm krls matlab program. Klms algorithm has inflicted function, load can be used.)

很棒的盲源分离的源代码 值得大家做盲信号处理的好的源代码(Great blind source separation of the source code is worth doing good blind signal processing source code)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

针对多聚焦图像融合，采用基于小波分解和点扩展函数模型PSF相结合的融合方法。(For multi-focus image fusion, based on wavelet decomposition and the point spread function PSF model combining fusion.)

说明：  对火焰图像的特征进行提取，如火焰闪烁频率、火焰区域面积，火焰燃烧区域裁剪等( the Feature Extraction of flame )