// 简单实现
cv::namedWindow("Example 2-3", cv::WINDOW_AUTOSIZE); cv::VideoCapture cap; cap.open(0);
cout << "Opened file: " << argv[1] << endl; cv::Mat frame, frame_threshold;
int low_r = 30, low_g = 30, low_b = 30;
int high_r = 100, high_g = 100, high_b = 100; for (;;) { cap >> frame; if (frame.empty()) break; // Ran out of film inRange(frame, cv::Scalar(low_b, low_g, low_r), cv::Scalar(high_b, high_g, high_r), frame_threshold);
//-- Show the frames
imshow("Video Capture", frame);
imshow("Object Detection", frame_threshold); if ((char)cv::waitKey(33) >= 0) break; } return 0;

  

// 完整实现
#include "opencv2/imgproc.hpp"
#include "opencv2/highgui.hpp"
#include <iostream>
#include <stdlib.h>
using namespace std;
using namespace cv;
void on_low_r_thresh_trackbar(int, void*);
void on_high_r_thresh_trackbar(int, void*);
void on_low_g_thresh_trackbar(int, void*);
void on_high_g_thresh_trackbar(int, void*);
void on_low_b_thresh_trackbar(int, void*);
void on_high_b_thresh_trackbar(int, void*);
int low_r = 30, low_g = 30, low_b = 30;
int high_r = 100, high_g = 100, high_b = 100;
int main()
{
Mat frame, frame_threshold;
VideoCapture cap(0);
namedWindow("Video Capture", WINDOW_NORMAL);
namedWindow("Object Detection", WINDOW_NORMAL);
//-- Trackbars to set thresholds for RGB values
createTrackbar("Low R", "Object Detection", &low_r, 255, on_low_r_thresh_trackbar);
createTrackbar("High R", "Object Detection", &high_r, 255, on_high_r_thresh_trackbar);
createTrackbar("Low G", "Object Detection", &low_g, 255, on_low_g_thresh_trackbar);
createTrackbar("High G", "Object Detection", &high_g, 255, on_high_g_thresh_trackbar);
createTrackbar("Low B", "Object Detection", &low_b, 255, on_low_b_thresh_trackbar);
createTrackbar("High B", "Object Detection", &high_b, 255, on_high_b_thresh_trackbar);
while ((char)waitKey(1) != 'q') {
cap >> frame;
if (frame.empty())
break;
//-- Detect the object based on RGB Range Values
inRange(frame, Scalar(low_b, low_g, low_r), Scalar(high_b, high_g, high_r), frame_threshold);
//-- Show the frames
imshow("Video Capture", frame);
imshow("Object Detection", frame_threshold);
}
return 0;
}
void on_low_r_thresh_trackbar(int, void*)
{
low_r = min(high_r - 1, low_r);
setTrackbarPos("Low R", "Object Detection", low_r);
}
void on_high_r_thresh_trackbar(int, void*)
{
high_r = max(high_r, low_r + 1);
setTrackbarPos("High R", "Object Detection", high_r);
}
void on_low_g_thresh_trackbar(int, void*)
{
low_g = min(high_g - 1, low_g);
setTrackbarPos("Low G", "Object Detection", low_g);
}
void on_high_g_thresh_trackbar(int, void*)
{
high_g = max(high_g, low_g + 1);
setTrackbarPos("High G", "Object Detection", high_g);
}
void on_low_b_thresh_trackbar(int, void*)
{
low_b = min(high_b - 1, low_b);
setTrackbarPos("Low B", "Object Detection", low_b);
}
void on_high_b_thresh_trackbar(int, void*)
{
high_b = max(high_b, low_b + 1);
setTrackbarPos("High B", "Object Detection", high_b);
}

  参考:https://www.w3cschool.cn/opencv/opencv-k1vh2cod.html

cv::inRange的更多相关文章

  1. opencv函数之cv.InRange函数

    2018-03-0421:22:46 (1)cv.InRange函数 void cvInRange(//提取图像中在阈值中间的部分 const CvArr* src,//目标图像const CvArr ...

  2. 『OpenCV3』基于色彩分割图片

    一.遍历图像实现色彩掩码 本节我们实现这样一个算法,我们指定某种颜色和一个阈值,根据输入图片生成一张掩码,标记符合的像素(和指定颜色的差异在阈值容忍内). 源代码如下,我们使用一个class完成这个目 ...

  3. openCV 色彩空间

    ---恢复内容开始--- 1.使用cv2.inrange()获取某个范围内的图像取值,指定某个通道的最小值和最大值 import numpy as np def color_space(image): ...

  4. Python+OpenCV图像处理(四)—— 色彩空间

    一.色彩空间的转换 代码如下: #色彩空间转换 import cv2 as cv def color_space_demo(img): gray = cv.cvtColor(img, cv.COLOR ...

  5. 车道线识别/Opencv/传统方法

    车道检测(Advanced Lane Finding Project) 实现步骤: 使用提供的一组棋盘格图片计算相机校正矩阵(camera calibration matrix)和失真系数(disto ...

  6. OpenCV---像素运算

    像素运算 分为算术运算和逻辑运算 算术运算: 加减乘除 调节亮度 调整对比度 逻辑运算: 与或非 遮罩层控制 一:算术运算 import cv2 as cv import numpy as np de ...

  7. OpenCV---色彩空间(二)HSV追踪颜色对象和通道分离与合并

    一:HSV追踪有颜色对象 def inRange(src, lowerb, upperb, dst=None) #lowerb是上面每个颜色分段的最小值,upperb是上面每个颜色分段的最大值,都是列 ...

  8. 3、OpenCV Python 色彩空间

    __author__ = "WSX" import cv2 as cv import numpy as np def color_space( img ): gray_img = ...

  9. [视觉识别]OpenCV + CNN 大神符识别

    数据集 Mnist数据集:http://yann.lecun.com/exdb/mnist/ 训练 import numpy as np from keras.datasets import mnis ...

  10. 用Camshift算法对指定目标进行跟踪

    原理 Camshift算法是Continuously Adaptive Mean Shift algorithm的简称. 它是一个基于MeanSift的改进算法.它首次由Gary R.Bradski等 ...

随机推荐

  1. Word15 财务部年度报告office真题

    1.课程的讲解之前,先来对题目进行分析,首先需要在考生文件夹下,将Wrod素材.docx文件另存为Word.docx,后续操作均基于此文件,否则不得分.   2.这一步非常的简单,打开下载素材文件,在 ...

  2. pip安装psycopg2报错Could not find a version that satisfies the requirement psycopg2

    pip安装psycopg2报错 在使用命令(pip install psycopg2)安装psycopg2时,会报错: ERROR: Could not find a version that sat ...

  3. VMvare虚拟机的安装及新建虚拟机(一)

    a:hover { color: rgba(255, 102, 0, 1) } 一.VMvare虚拟机的安装 1.首先双击--你下载的安装包,这里我分享百度云盘,供大家下载:http://pan.ba ...

  4. div里元素横向排列 居中对齐

      <div>             <img src="//s.weituibao.com/1582958061265/mlogo.png" alt=&quo ...

  5. C. Tea Tasting

    https://codeforces.com/contest/1795/problem/C 用二分+前缀和+差分卡过 #include <iostream> #include <cs ...

  6. 集合(Collection)

    前几天做数据结构题碰到了集合,当时并没有学,只是通过做题对此稍微有了了解.今天正好学到了,来做一下学习记录. 一.集合总体框架 由上图可知,集合的实现方式有两大类: (1)线性接口:该集合的顶层接口是 ...

  7. 利用Opencv+Python 实现二维码识别

    pip3 install pyzbar   准备工作: 二维码图片,我这里直接打印在了一张A4纸上,或者直接在草料网站上生成 草料二维码生成器,存放在手机上进行显示.在安装条码扫描库的时候大家注意:z ...

  8. Pytorch之数据处理

    使用TensorDataset和DataLoader来简化   from torch.utils.data import TensorDataset from torch.utils.data imp ...

  9. Kubernetes--管理资源标签(标签)

    随着同类型资源对象的数量越来越多,分类管理也变得越来越有必要:基于简单且直接的标准将资源对象划分为多个较小的分组,无论是对开发人员还是对系统工程师来说,都能提升管理效率,这也正是 Kubernetes ...

  10. nginx 可视化配置平台

    nginx是一个高性能的HTTP和反向代理服务器.在部署项目中,经常会用到,但是配置是比较麻烦的,很容易出错,今天大叔给大家推荐一个非常好用的可视化平台 -- nginx-gui. 项目功能 配置管理 ...