piotr_toolbox

针对杂波环境下的多个机动目标跟踪问题, 本文将多模型概率假设密度 (Multiple-model probability hypothesis density, MM-PHD) 滤波器和平滑算法相结合, 提出了 MM-PHD 前向 – 后向平滑器. 为了避免引入复杂的随机有限集 (Random finite set, RFS) 理论, 本文根据 PHD 的物理空间 (Physical space) 描述法推导得到了 MM-PHD 平滑器的后向更 新公式. 由于 MM-PHD 前向–后向平滑器的递推公式中包含有多个积分(By integrating the multiple-model probability hypothesis density (MM-PHD) filter with the smoothing al- gorithms, an MM-PHD forward-backward smoother is proposed in this paper for tracking multiple maneuvering targets in clutter. To avoid use of complex random finite set (RFS) theory, the backward updated equation of the MM-PHD smoother can be derived according to the physical-space explanation of the PHD)

对采样得到的180幅断层图像进行重建，并针对其中的一幅图像进行处理，并且统计图像中颗粒的大小和数目！(Tomographic images of 180 samples obtained were rebuilt, and for which an image processing and image size and number of particles statistics!)

联合特征选择和子空间相关性学习的跨模态检索，map优于典型相关性分析的跨模态检索(Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval)

计算机与机器视觉：理论，算法与实践，第四版；E. R. DAVIES 著；高清文字版(Computer and Machine Vision:Theory, Algorithms,Practicalities Fourth Edition E. R. DAVIES)

DCT数字水印基于CVI平台。用c编写的。(DCT digital watermarking)

Image watermark using 3 level DWT

说明：  这是一个关于基于方向谷形检测的静脉纹路分割的MATLAB程序代码，(Vein vein segmentation based on directional valley detection)

通过GAN和WGAN在python的tensorflow平台上实现图片生成，与真实图片基本一致。(Through GAN and WGAN, the image generation is realized on the tensorflow platform of python, which is basically the same as the real picture.)

说明：  《数字图像处理与机器视觉:Visual C++与Matlab实现》5 图像分割,霍夫变换,Hough变换直线检测的Matlab实现(&quot Digital image processing and machine vision: Visual C++ and Matlab to achieve&quot 5 image segmentation, Hough transform, Hough transform line detection of the Matlab implementation)

说明：  将基于小波变换的嵌入水印后的宿主图像进行压缩处理再提取灰度水印。(will be based on the wavelet transform the embedded watermark image of the host compressed again from Gray watermark.)