matlab-hough

利用卷积神经网络进行特征提取，并将卷积特征可视化(Feature extraction using convolutional neural networks and visualization of convolution features)

粒子滤波器源代码，有助于学习。附有图像序列。(Particle Filter source code, contribute to learning. With image sequences.)

说明：  用MATLAB进行图形样板匹配的源程序，（开发平台MATLAB7.0）(Using MATLAB graphics to match the source model, (development platform MATLAB7.0))

Matlab遥感道路提取之Hough检测(Matlab to extract the Hough detect remote road)

VC++处理图像模糊或柔化的效果示例源程序，类似Photoshop中的图像高斯模糊效果，每点击一次鼠标右键，程序为模糊一次，直到你满意为止。注意程序仅实现了模糊的功能，其它功能比如程序优化和效率方面的考虑还比较少，因此程序运行速度方面可能会欠缺一些(VC++ deal with image blur or soften the effect of sample source code, similar to Photoshop' s image Gaussian Blur effect, each click the right mouse button, the procedures for fuzzy time until you are satisfied. Note that the program is only vague functions, other functions such as process optimization and efficiency considerations is still relatively small, the speed of the program is running may lack some of the)

此代码为显著性检测代码，显著性检测效果不错(This code is a significant detection code to detect significant good results)

SAR图像目标检测是SAR ATR(自动目标识别)的关键步骤,也是近年来SAR图像解译应用的一大研究热点.在广泛文献调研的基础上,本文从SAR图像目标检测的历史沿革、研究现状开始,综述了SAR图像目标检测的研究进展及存在问题(SAR image target detection is the SAR ATR (automatic target recognition) a critical step in SAR image interpretation is also applied in recent years, a major research focus. In the extensive literature on the basis of research, this article from the SAR image target detection to the history and study of the status quo began an overview of SAR image target detection Progress and Problems)

本代码是基于MATLAB环境下的一种基于DWT的数字水印的嵌入与提取，本算法对各种噪声具有一定的抗鲁棒性。(The code is based on the MATLAB environment based DWT digital watermark embedding and extraction, the algorithm has certain anti robustness of various noise.)

说明：  模拟飞机爬升的仿真程序，可输出各种飞行姿态，很不错(Simulating an aircraft climb of the simulation program can output a variety of flight attitude, very good)

说明：  SSD: Single Shot MultiBox Object Detector, in PyTorch A PyTorch implementation of Single Shot MultiBox Detector from the 2016 paper by Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang, and Alexander C. Berg. The official and original Caffe code can be found here. Table of Contents Installation Datasets Train Evaluate Performance Demos Future Work Reference