-
yolov3-master-protorch
说明： 目前一种快速稳健的卷积神经网络yolov3的代码，在protorch平台上运行(At present, the code of yolov3, a fast and robust convolutional neural network, runs on the platform of protorch)
- 2020-02-11 10:55:14下载
- 积分：1
-
DLTs-L-approximation-code
近景摄影DLT的L近似值的求解代码 此程序主要应用于桥梁挠度的测量中(The L approximation close range photogrammetry DLT solving code This program is mainly used in the bridge deflection measurement)
- 2013-03-27 00:34:23下载
- 积分：1
-
fcm
模糊C均值分类，用于图像处理中 很好用的，极力推荐 (Fuzzy C-means classification, used for image processing in a very good use, and strongly recommend)
- 2009-03-13 17:44:03下载
- 积分：1
-
DCT
实现对一幅灰度和彩色图像作的离散余弦变换,选择适当的DCT系数阈值对其进行DCT反变换.(The realization of a piece of gray and color images for the discrete cosine transform, select the appropriate thresholds for DCT coefficients of its inverse transform DCT.)
- 2008-12-13 21:51:01下载
- 积分：1
-
final1AHE0310
通过PCA+Retinex对图像进行图像增强处理(Image enhancement processing by PCA+Retinex)
- 2018-03-08 11:29:53下载
- 积分：1
-
MediaFocusManager_10803
浏览图片的缩略图时，点击某张缩略图，被点击的缩略图会在当前视图放大并且全屏显示，背景用黑色透明视图遮挡。再次点击图片，将回到缩略图浏览状态(Media Focus Manager)
- 2013-08-23 09:27:34下载
- 积分：1
-
Project1
EM算法。问题背景是，有N条长为L的DNA序列，每条序列里面有一条长尾K的目标序列，但不知道他的位置，目标序列内的核苷酸服从foreground product multinomial distribution，非目标序列服从background
multinomial distribution，改程序意在求解两种分布的参数。(EM algorithm. Background to the issue is that there are N pieces of length L of DNA sequences, each sequence which has a target sequence Nagao K, but do not know his position, the target nucleotide sequence within obedience foreground product multinomial distribution, non-target sequence obey background multinomial distribution, the program is intended to change the parameters in solving the two distributions.)
- 2016-04-05 09:35:05下载
- 积分：1
-
harris_code
harris角点检测算法，代码可以通过修改sigma, thresh, radius, disp的值控制角点数量。(harris corner detection algorithm, the code can be by modifying the sigma, thresh, radius, disp corner of the value of quantity control.)
- 2009-03-31 13:51:32下载
- 积分：1
-
DensePose-master
DensePose用深度学习把2D图像坐标映射到3D人体表面上，再加上以每秒多帧的速度处理密集坐标，最后实现动态人物的精确定位和姿态估计。该技术集目标检测、姿态估计、目标部分/实例分割等多种计算机视觉任务于一身的一个综合问题。(DensePost maps 2D image coordinates to 3D human body surface by in-depth learning, and processes dense coordinates at the speed of multiple frames per second. Finally, it realizes precise positioning and attitude estimation of dynamic characters. This technology integrates many kinds of computer vision tasks, such as target detection, attitude estimation, target part/instance segmentation, etc.)
- 2019-06-17 21:25:31下载
- 积分：1
-
DCT
说明： 图像的DCT变换 提取高频分量 和低频分量 (DCT change)
- 2011-04-12 20:10:04下载
- 积分：1
