hanshuning的专栏

#include <iostream>#include <opencv2/opencv.hpp>using namespace std;using namespace cv;void main(){ VideoCapture cap; cap.open("C:/Users/Win10/Downloads/live2.avi"); //打开视频,以上两句等价于VideoCapture cap("E ://2.avi"); //cap.open("http://ww.

#include <opencv2/opencv.hpp>#include<iostream>using namespace cv;using namespace std;int main(){ //initialize and allocate memory to load the video stream from camera VideoCapture camera1(1 + cv::CAP_DSHOW); /*camera1.set(CAP_PROP_.

1. 将图片地址写入到xml创建工程，运行一下文件：C:\Program Files\opencv\sources\samples\cpp\imagelist_creator.cppcmd运行：cd至\工程目录\x64\Debug>，命令：.\工程名.exe imagelist.yaml .rgb1.png rgb2.png rgb3.png rgb4.png rgb5.png rgb6.png rgb7.png rgb8.png rgb9.png rgb10.png rgb11.p.

realsense鼠标点击彩色深度图获取对应位置深度// License: Apache 2.0. See LICENSE file in root directory.// Copyright(c) 2017 Intel Corporation. All Rights Reserved.#include <librealsense2/rs.hpp> // Include RealSense Cross Platform API#include <opencv2/openc.

realsense鼠标截取彩色深度图区域保存深度信息至csv// License: Apache 2.0. See LICENSE file in root directory.// Copyright(c) 2017 Intel Corporation. All Rights Reserved.#include <librealsense2/rs.hpp> // Include RealSense Cross Platform API#include <opencv2/op

realsense鼠标选择区域保存深度信息到csv文件// License: Apache 2.0. See LICENSE file in root directory.// Copyright(c) 2017 Intel Corporation. All Rights Reserved.#include <librealsense2/rs.hpp> // Include RealSense Cross Platform API#include <opencv2/openc

realsense鼠标点击深度图获取对应位置深度// License: Apache 2.0. See LICENSE file in root directory.// Copyright(c) 2017 Intel Corporation. All Rights Reserved.#include <librealsense2/rs.hpp> // Include RealSense Cross Platform API#include <opencv2/opencv..

实现功能：1. 获取realsense设备的 rgb、depth和两个IR红外视频流；2.摁下p键,保存rgb、depth和两个IR红外各一张图至工程所在文件夹；// License: Apache 2.0. See LICENSE file in root directory.// Copyright(c) 2017 Intel Corporation. All Rights Reserved.#include <librealsense2/rs.hpp> // Inclu

#include <iostream>#include <opencv2/opencv.hpp>using namespace std;using namespace cv;void main(){ Mat img = imread("C:\\Users\\Win10\\Downloads\\rasterImg.pgm", 0); if (empty(img)) { cout<<"NULL"; return; } normaliz..

参考：https://github.com/IntelRealSense/librealsense/blob/development/doc/depth-from-stereo.mdStereoscopic VisionDepth from Stereo is a classic computer vision algorithm inspired by human binocula...

http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/core/basic_linear_transform/basic_linear_transform.html#basic-linear-transform 两种常用的点过程（即点算子），是用常数对点进行 乘法 和 加法 运算： 两个参数 和 一般称作 ...

环境：vs2019，python3.7，opencv4.1.1代码来源：https://www.learnopencv.com/multi-person-pose-estimation-in-opencv-using-openpose/下载：https://github.com/spmallick/learnopencv/blob/master/OpenPose-Multi-Person/...

#include <iostream>#include <opencv2/opencv.hpp>using namespace std;using namespace cv;void main() { VideoCapture cap; cap.open("C:\\Users\\87035\\Desktop\\安全帽视频\\V90726-094954...

opencv-python的安装创建一个python项目，视图-其他窗口-python环境，右面概述选改为包（PyPI）。在搜索框里输入opencv-python，在下拉框选择 运行命令：pip install tensorflow-gpu。开始安装。C++版本的安装https://blog.youkuaiyun.com/m0_37360684/article/details/89716881...

sudo -s再roslaunch openni2_launch openni2.launch

修改GlobalDefaults.ini配置文件$ sudo gedit /etc/openni/GlobalDefaults.ini 将第60行前面的分号去掉（即取消注释）;UsbInterface=2再次尝试运行openni2.launch ，如果不行还需要重启一下电脑

1.创建ROS程序包cd catkin_wscatkin_create_pkg ImgPcl std_msgs rospy roscpp sensor_msgs cv_bridge image_transport pcl_conversions pcl_ros pcl_msgscd ImgPclmkdir src//在此创建.cpp文件3。添加P

http://wiki.ros.org/face_recognition$ cd ~/catkin_ws/src$ git clone https://github.com/procrob/procrob_functional.git --branch catkin //下载程序包，完成后可见在 cd ~/catkin_ws/src下有procrob_functional文件夹$ cd

给一张图片，在视野中找到。获取物体的二维坐标。语音相关的话题注释掉了。//给一个物体，在视野中查找#include #include #include #include #include #include #include #include #include

//Includes all the headers necessary to use the most common public pieces of the ROS system. #include //Use image_transport for publishing and subscribing to images in ROS #include

//Includes all the headers necessary to use the most common public pieces of the ROS system. #include //Use image_transport for publishing and subscribing to images in ROS #include

//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include //Use cv_brid

ImgCapMouse.cpp文件#include #include #include #include #include #include #include "opencv2/video/tracking.hpp" #include #include #include using namespace cv; u

安装openni2-camera和openni2-launchsudo apt-get install ros-hydro-openni2-camerasudo apt-get install ros-hydro-openni2-launch安装一些依赖$ sudo apt-get install git g++ make python libusb-1.0-0-dev l

//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include //Use cv_brid

//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include //Use cv_bridge t

//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include //Use cv_bridge t

imageCapture.cpp//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include

//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#include //Use cv_bridge t

ros下的camshiftdemo.cpp//Includes all the headers necessary to use the most common public pieces of the ROS system.#include //Use image_transport for publishing and subscribing to images in ROS#inc

colorhistogram.h#if !defined COLHISTOGRAM#define COLHISTOGRAM#include #include class ColorHistogram {  private:    int histSize[3];float hranges[2];    const float* r

http://wg-perception.github.io/object_recognition_core/http://wg-perception.github.io/object_recognition_core/install.html#install到下面一命令出错：cd .. && rosdep install --from-paths src -i -yE

1.下载$ cd ~/catkin_ws/src$ git clone https://github.com/procrob/procrob_functional.git --branch catkin$ cd ~/catkin_ws$ catkin_make$ source ~/catkin_ws/devel/setup.bash1.1文件说明：data文

1.创建好的工作空间catkin_ws2.创建程序包beginner_opencv,注意其依赖项 cd ~/catkin_ws/srcatkin_create_pkg beginner_opencv sensor_msgs cv_bridge roscpp std_msgs image_transport3.编写节点image_converter.cpp及相关配置

#include #include #include #include #include #include #include using namespace cv; using namespace std; MatND getHistogram(Mat &img)//得到直方图 { int chann

还是先上我的程序吧，实现了对视频流的匹配，在视频中标出目标物体的位置并计算出物体所在的中心坐标：#include #include #include #include #include #include #include using namespace cv; using namespace std; int m

#include #include #include #include #include #include using namespace cv; using namespace std; MatND getHistogram(Mat &img)//得到直方图 { int channels[]={0};//考察0通道 in

原理是：背景差分+肤色检测。背景差分：取前30帧图像取平均值，计算前30帧之差的和，再求均值。在背景平均值上下浮动的阈值之外的被检测出来。肤色检测：利用YCrCb空间。两个结果相与操作。这种方式的优点：1.有效解决了肤色检测结果中总是检测到人脸的情况；                                2.解决背景差分检测结果杂乱的情况；

#include#include"math.h"#include #include #include #include using namespace cv;using namespace std;#define P 7#define N 120int W[N][N]={0};int u[P][N]={ { -1,-1,-1,1,1,1,1,-1,-1,-1,

main.cpp#include#include #include #include #include #include #include #include "linefinder.h"#include#include using namespace cv;using namespace std;int main(){ stringstream ss;