-
chapter-5
Wily book Digital Image processing fundamental dip
- 2013-08-18 13:50:17下载
- 积分：1
-
edge-detectinterpolation
new edge-directed interpolation这篇文章所提算法的matlab实现(new edge-directed interpolation algorithm in this article referred to realize matlab)
- 2008-03-13 16:07:17下载
- 积分：1
-
adaptivethreshold
与坐标相关的阈值也叫动态阈值、局部阈值、自适应阈值，局部阈值法：自适应图像分割。(Threshold associated with coordinates, also called dynamic threshold, local threshold, adaptive threshold, local threshold method: adaptive image segmentation.)
- 2013-05-27 09:49:07下载
- 积分：1
-
CO_SUT
计算机图形学 c语言实现的直线段裁剪算法(Computer graphics c language to achieve a straight line segment clipping algorithm)
- 2007-11-13 16:36:11下载
- 积分：1
-
代码
用于仿真OAM光束在真空中进行夫琅禾费衍射，附件是其相关书籍(Used to simulate Fraunhofer diffraction of OAM beam in vacuum)
- 2018-06-09 18:16:13下载
- 积分：1
-
SAR_banmatu_ultimate_success
该m文件是用来仿真合成孔径雷达SAR的斑马图，即菱形图的，是本人自己设计的，可用。(M file is used to simulate the synthetic aperture radar SAR zebra figure, namely diamond chart, is my own design, is available.)
- 2021-01-06 23:28:54下载
- 积分：1
-
SFCT
一种新的目标跟踪算法。将压缩感知引入到序列图像目标跟踪中，可以实现目标的稳定快速跟踪。(A new target tracking algorithm. The compressed sensing is introduced into the sequence of image target tracking, stabilization target can be achieved fast track.)
- 2014-04-23 22:45:42下载
- 积分：1
-
py-faster-rcnn-master
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.)
- 2020-12-11 15:39:18下载
- 积分：1
-
testcurvaturecalculate1
采用曲率的方法，等间隔三点的大小计算夹角的大小，根据阈值标记指尖指根区域。(Curvature of the methods used, such as the size of three intervals calculated the size of the angle, according to the threshold refers to the root area marked fingertips.)
- 2010-05-23 15:51:20下载
- 积分：1
-
SARSimulation
合成孔径雷达（SAR）回波模拟半实物仿真平台的构建(Synthetic aperture radar (SAR) analog echo-loop Simulation Platform)
- 2009-07-07 22:23:20下载
- 积分：1
