#include <fstream>
#include <sstream>
#include <iostream>
#include <string.h> #include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp> using namespace cv;
using namespace dnn;
using namespace std; // Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float maskThreshold = 0.3; // Mask threshold vector<string> classes;
vector<Scalar> colors; // Draw the predicted bounding box
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask); // Postprocess the neural network's output for each frame
void postprocess(Mat& frame, const vector<Mat>& outs); int main()
{
// Load names of classes
string classesFile = "./mask_rcnn_inception_v2_coco_2018_01_28/mscoco_labels.names";
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line); // Load the colors
string colorsFile = "./mask_rcnn_inception_v2_coco_2018_01_28/colors.txt";
ifstream colorFptr(colorsFile.c_str());
while (getline(colorFptr, line))
{
char* pEnd;
double r, g, b;
r = strtod(line.c_str(), &pEnd);
g = strtod(pEnd, NULL);
b = strtod(pEnd, NULL);
Scalar color = Scalar(r, g, b, 255.0);
colors.push_back(Scalar(r, g, b, 255.0));
} // Give the configuration and weight files for the model
String textGraph = "./mask_rcnn_inception_v2_coco_2018_01_28/mask_rcnn_inception_v2_coco_2018_01_28.pbtxt";
String modelWeights = "./mask_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb"; // Load the network
Net net = readNetFromTensorflow(modelWeights, textGraph);
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setPreferableTarget(DNN_TARGET_CPU); // Open a video file or an image file or a camera stream.
string str, outputFile;
VideoCapture cap();//根据摄像头端口id不同,修改下即可
//VideoWriter video;
Mat frame, blob; // Create a window
static const string kWinName = "Deep learning object detection in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL); // Process frames.
while (waitKey() < )
{
// get frame from the video
cap >> frame; // Stop the program if reached end of video
if (frame.empty())
{
cout << "Done processing !!!" << endl;
cout << "Output file is stored as " << outputFile << endl;
waitKey();
break;
}
// Create a 4D blob from a frame.
blobFromImage(frame, blob, 1.0, Size(frame.cols, frame.rows), Scalar(), true, false);
//blobFromImage(frame, blob); //Sets the input to the network
net.setInput(blob); // Runs the forward pass to get output from the output layers
std::vector<String> outNames();
outNames[] = "detection_out_final";
outNames[] = "detection_masks";
vector<Mat> outs;
net.forward(outs, outNames); // Extract the bounding box and mask for each of the detected objects
postprocess(frame, outs); // Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
vector<double> layersTimes;
double freq = getTickFrequency() / ;
double t = net.getPerfProfile(layersTimes) / freq;
string label = format("Mask-RCNN on 2.5 GHz Intel Core i7 CPU, Inference time for a frame : %0.0f ms", t);
putText(frame, label, Point(, ), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(, , )); // Write the frame with the detection boxes
Mat detectedFrame;
frame.convertTo(detectedFrame, CV_8U); imshow(kWinName, frame); }
cap.release();
return ;
} // For each frame, extract the bounding box and mask for each detected object
void postprocess(Mat& frame, const vector<Mat>& outs)
{
Mat outDetections = outs[];
Mat outMasks = outs[]; // Output size of masks is NxCxHxW where
// N - number of detected boxes
// C - number of classes (excluding background)
// HxW - segmentation shape
const int numDetections = outDetections.size[];
const int numClasses = outMasks.size[]; outDetections = outDetections.reshape(, outDetections.total() / );
for (int i = ; i < numDetections; ++i)
{
float score = outDetections.at<float>(i, );
if (score > confThreshold)
{
// Extract the bounding box
int classId = static_cast<int>(outDetections.at<float>(i, ));
int left = static_cast<int>(frame.cols * outDetections.at<float>(i, ));
int top = static_cast<int>(frame.rows * outDetections.at<float>(i, ));
int right = static_cast<int>(frame.cols * outDetections.at<float>(i, ));
int bottom = static_cast<int>(frame.rows * outDetections.at<float>(i, )); left = max(, min(left, frame.cols - ));
top = max(, min(top, frame.rows - ));
right = max(, min(right, frame.cols - ));
bottom = max(, min(bottom, frame.rows - ));
Rect box = Rect(left, top, right - left + , bottom - top + ); // Extract the mask for the object
Mat objectMask(outMasks.size[], outMasks.size[], CV_32F, outMasks.ptr<float>(i, classId)); // Draw bounding box, colorize and show the mask on the image
drawBox(frame, classId, score, box, objectMask); }
}
} // Draw the predicted bounding box, colorize and show the mask on the image
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask)
{
//Draw a rectangle displaying the bounding box
rectangle(frame, Point(box.x, box.y), Point(box.x + box.width, box.y + box.height), Scalar(, , ), ); //Get the label for the class name and its confidence
string label = format("%.2f", conf);
if (!classes.empty())
{
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ":" + label;
} //Display the label at the top of the bounding box
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, , &baseLine);
box.y = max(box.y, labelSize.height);
rectangle(frame, Point(box.x, box.y - round(1.5*labelSize.height)), Point(box.x + round(1.5*labelSize.width), box.y + baseLine), Scalar(, , ), FILLED);
putText(frame, label, Point(box.x, box.y), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(, , ), ); Scalar color = colors[classId%colors.size()]; // Resize the mask, threshold, color and apply it on the image
resize(objectMask, objectMask, Size(box.width, box.height));
Mat mask = (objectMask > maskThreshold);
Mat coloredRoi = (0.3 * color + 0.7 * frame(box));
coloredRoi.convertTo(coloredRoi, CV_8UC3); // Draw the contours on the image
vector<Mat> contours;
Mat hierarchy;
mask.convertTo(mask, CV_8U);
findContours(mask, contours, hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);
drawContours(coloredRoi, contours, -, color, , LINE_8, hierarchy, );
coloredRoi.copyTo(frame(box), mask); }

https://github.com/spmallick/learnopencv/tree/master/Mask-RCNN

https://www.learnopencv.com/deep-learning-based-object-detection-and-instance-segmentation-using-mask-r-cnn-in-opencv-python-c/

line: (303,392) (313,104) (0.0532837,-0.178375,0.288),(0,0,0)

0.0930815

----------------------------------------------------

line: (304,393) (465,390) (0.0540282,-0.178375,0.288),(0,0,0)

0.0931887

----------------------------------------------------

line: (302,391) (314,34) (0.0525392,-0.178375,0.288),(-1.27422,-1.06591,1.721)

0.798125

----------------------------------------------------

line: (307,189) (312,34) (-0.096823,-0.176517,0.285),(-1.27422,-1.06591,1.721)

0.737782

----------------------------------------------------

line: (304,392) (512,385) (0.0532837,-0.178375,0.288),(0,0,0)

0.0930815

----------------------------------------------------

line: (307,395) (410,393) (0,0,0),(0.0540282,-0.178375,0.288)

0.0931887

----------------------------------------------------

line: (305,278) (313,34) (0,0,0),(-1.27422,-1.06591,1.721)

0.830633

----------------------------------------------------

line: (271,377) (279,130) (0.0421168,-0.178375,0.288),(0,0,0)

0.0916397

----------------------------------------------------

line: (272,378) (278,192) (0.0428612,-0.178375,0.288),(0,0,0)

0.0917259

----------------------------------------------------

line: (63,361) (275,354) (0.0301005,-0.177755,0.287),(0.0249073,-0.177755,0.287)

0.00259657

----------------------------------------------------

line: (308,38) (477,62) (-1.263,-1.07149,1.73),(0,0,0)

0.828137

----------------------------------------------------

line: (305,391) (311,198) (0.0525392,-0.178375,0.288),(-0.0901926,-0.176517,0.285)

0.071372

----------------------------------------------------

line: (307,394) (445,391) (0,0,0),(0.0525392,-0.178375,0.288)

0.0929756

----------------------------------------------------

line: (273,379) (276,292) (0.0436057,-0.178375,0.288),(-0.0210156,-0.177136,0.286)

0.0323166

----------------------------------------------------

line: (401,385) (512,389) (0.0480725,-0.178375,0.288),(0,0,0)

0.0923694

----------------------------------------------------

line: (315,35) (402,49) (-1.27346,-1.06901,1.726),(0,0,0)

0.831336

----------------------------------------------------

line: (418,384) (514,382) (0.047328,-0.178375,0.288),(0,0,0)

0.0922733

----------------------------------------------------

line: (176,359) (271,356) (0.0286167,-0.177755,0.287),(0,0,0)

0.090022

----------------------------------------------------

line: (385,386) (511,390) (0.0488169,-0.178375,0.288),(0,0,0)

0.092467

----------------------------------------------------

line: (67,359) (181,355) (0.0286167,-0.177755,0.287),(0,0,0)

0.090022

----------------------------------------------------

line: (311,37) (425,53) (-1.26747,-1.07149,1.73),(0,0,0)

0.829843

----------------------------------------------------

line: (275,131) (278,69) (-0.138573,-0.175278,0.283),(0,0,0)

0.111719

----------------------------------------------------

line: (66,360) (241,354) (0.0293586,-0.177755,0.287),(0.0249073,-0.177755,0.287)

0.00222563

----------------------------------------------------

line: (118,360) (275,355) (0.0293586,-0.177755,0.287),(0,0,0)

0.0900817

----------------------------------------------------

line: (441,383) (510,382) (0.0465835,-0.178375,0.288),(0,0,0)

0.0921785

----------------------------------------------------

line: (309,92) (310,37) (0,0,0),(-1.26747,-1.07149,1.73)

0.829843

----------------------------------------------------

line: (306,391) (308,321) (0.0525392,-0.178375,0.288),(0.000425389,-0.177755,0.287)

0.0260588

----------------------------------------------------

line: (274,248) (278,154) (0,0,0),(-0.121747,-0.175278,0.283)

0.106706

----------------------------------------------------

line: (454,384) (511,386) (0.047328,-0.178375,0.288),(0,0,0)

0.0922733

----------------------------------------------------

line: (362,387) (440,389) (0.0495614,-0.178375,0.288),(0,0,0)

0.092566

----------------------------------------------------

line: (221,359) (271,357) (0.0286167,-0.177755,0.287),(0,0,0)

0.090022

----------------------------------------------------

line: (344,390) (396,393) (0,0,0),(0.0540282,-0.178375,0.288)

0.0931887

----------------------------------------------------

line: (314,393) (376,395) (0.0540282,-0.178375,0.288),(0,0,0)

0.0931887

----------------------------------------------------

line: (115,355) (180,354) (0,0,0),(0.0249073,-0.177755,0.287)

0.0897459

----------------------------------------------------

line: (296,388) (358,391) (0,0,0),(0.0525392,-0.178375,0.288)

0.0929756

----------------------------------------------------

line: (449,329) (514,378) (0.00638257,-0.178375,0.288),(0,0,0)

0.0892444

常用模型下载地址:https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md

opencv C++ mask_rcnn的更多相关文章

  1. opencv4 mask_rcnn模型调(c++)

    昨天有人问我关于调用mask_rcnn模型的问题,忽然想到最近三个月都没用opencv调用训练好的mask_rcnn模型了,今晚做个尝试,所以重新编译了 opencv4,跑个案例试试 #include ...

  2. opencv在图像显示中文

    在图像定位和模式识别时,经常需要把结果标注到图片上,标注内容可以是数字字母.矩形框等(opencv支持的)或者是中文汉字(借助freetype). 1.显示数字/矩形框 #include <op ...

  3. opencv中Mat与IplImage,CVMat类型之间转换

    opencv中对图像的处理是最基本的操作,一般的图像类型为IplImage类型,但是当我们对图像进行处理的时候,多数都是对像素矩阵进行处理,所以这三个类型之间的转换会对我们的工作带来便利. Mat类型 ...

  4. opencv源码:cascadedetect

    级联分类器检测类CascadeClassifier,提供了两个重要的方法: CascadeClassifier cascade_classifier; cascade_classifier.load( ...

  5. 基于OpenCV的车辆检测与追踪的实现

    最近老师布置了一个作业,是做一个基于视频的车辆检测与追踪,用了大概两周的时间做了一个简单的,效果不是很理想,但抑制不住想把自己的一些认识写下来,这里就把一些网络上的博客整理一下分享给大家,希望帮助到大 ...

  6. OpenCV人脸识别Eigen算法源码分析

    1 理论基础 学习Eigen人脸识别算法需要了解一下它用到的几个理论基础,现总结如下: 1.1 协方差矩阵 首先需要了解一下公式: 共公式可以看出:均值描述的是样本集合的平均值,而标准差描述的则是样本 ...

  7. OpenCV人脸识别LBPH算法源码分析

    1 背景及理论基础 人脸识别是指将一个需要识别的人脸和人脸库中的某个人脸对应起来(类似于指纹识别),目的是完成识别功能,该术语需要和人脸检测进行区分,人脸检测是在一张图片中把人脸定位出来,完成的是搜寻 ...

  8. OpenCV模板匹配算法详解

    1 理论介绍 模板匹配是在一幅图像中寻找一个特定目标的方法之一,这种方法的原理非常简单,遍历图像中的每一个可能的位置,比较各处与模板是否“相似”,当相似度足够高时,就认为找到了我们的目标.OpenCV ...

  9. android studio 使用 jni 编译 opencv 完整实例 之 图像边缘检测!从此在andrid中自由使用 图像匹配、识别、检测

    目录: 1,过程感慨: 2,运行环境: 3,准备工作: 4,编译 .so 5,遇到的关键问题及其解决方法 6,实现效果截图. (原创:转载声明出处:http://www.cnblogs.com/lin ...

随机推荐

  1. 虚拟机ipv6环境搭建操作指南

      一.vmware的相关配置 (1)点击编辑,选择虚拟网络编辑器 (2)选择带NAT模式的VMnet8网络,点击NAT设置 (3)在NAT设置中启用IPV6 (4)设置好后,点击应用 (5)再选择镜 ...

  2. 队列(queue)和堆栈(stack)的学习

    队列 1 . 先进先出  .队列尾进行插入,队列头进行删除,获取,修改.      -----first come  ,first served .   --first in  .first  out ...

  3. 0006SpringBoot中@Configuration与@Bean联合使用

    需求:将某个普通类做为组件注册到容器中,可通过如下办法 1.定义HelloService类 package springboot_test.springboot_test.service; publi ...

  4. TreadPool

    ThreadPool概述 提供一个线程池,该线程池可用于执行任务.发送工作项.处理异步 I/O.代表其他线程等待以及处理计时器. 创建线程需要时间.如果有不同的小任务要完成,就可以事先创建许多线程/在 ...

  5. python----四种内置数据结构(dict、list、tuple、set)

    1.dict 无序,可更改 2.tuple 有序,不可更改 3.list 有序,可更改(增加,删除) 4.set 无序,可能改 {元素1,元素2,元素3.....}和字典一样都是用大括号定义,不过不同 ...

  6. python ini文件内容的读取

    (1)新建一个项目,再次新建一个文件 test_cfg.ini (2)再次新建 get_test_cfg.py,用来读取/写入/更改 ini的文件内容 #!/usr/bin/env python # ...

  7. 关键字local、global和内置函数【locals、globals】

    每个函数都有着自已的命名空间,叫做局部名字空间,它记录了函数的变量,包括函数的参数和局部定义的变量.每个模块拥有它自已的命名空间,叫做全局命名空间,它记录了模块的变量,包括函数.类.其它导入的模块.模 ...

  8. redis与spring整合实例

    1)首先是redis的配置. 使用的是maven工程,引入redis与spring整合的相关jar包 <!-- redis服务 start--> <dependency> &l ...

  9. mapbox展示动态图标

    mapbox-gl通过为marker设置css动画,实现动态闪烁效果,先放个效果图 . 1.主要就是为元素设置一个动画, myfirst动画让元素随时间放大 .marker { /* backgrou ...

  10. 04_Returners组件:返回jobid的结果到mysql

    1.前期调研 0.环境 salt 2019 python3.6  很重要 [root@IP ~]# salt-call --versions-report Salt Version: Salt: 20 ...