本文为OpenCV DNN模块官方教程的扩展，介绍如何使用OpenCV加载TensorFlow Object Detection API训练的模型做实例分割，以Mask-RCNN为例来检测缺陷。TensorFlow Object Detection API的github链接地址如下：https://github.com/tensorflow/models/tree/master/research/object_detection
本文以TensorFlow 1.x为例(TF2.x等后续稳定支持OpenCV后介绍)，介绍OpenCV DNN模块调用Mask-RCNN模型做实例分割的步骤如下：
(1) 下载或自己训练生成 .pb 格式的模型文件。本文以自己训练好的缺陷检测模型frozen_inference_graph.pb为例：
(2) 使用指令用.pb文件生成.pbtxt文件, Mask-RCNN使用tf_text_graph_mask_rcnn.py，指令如下：
主要参数三个：
--input 输入.pb模型文件完整路径；
--output 输出.pbtxt文件完整路径；
--config 输入config文件完整路径
完整指令：
代码语言：javascript复制python tf_text_graph_mask_rcnn.py --input E:PracticeTensorFlowDataSetmask_defects2modelexportfrozen_inference_graph.pb --output E:PracticeTensorFlowDataSetmask_defects2modelexportfrozen_inference_graph.pbtxt --config E:PracticeTensorFlowDataSetmask_defects2modeltrainmask_rcnn_inception_v2_coco.config运行结果：
(3) 配置OpenCV4.4，加载图片测试 ，代码如下：
代码语言：javascript复制#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 = 0.4; // Confidence threshold
float maskThreshold = 0.5; // Mask threshold
vector<string> classes;
vector<Scalar> colors;
// 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(255, 178, 50), 5);
//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, 1, &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(255, 255, 255), FILLED);
putText(frame, label, Point(box.x, box.y), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 255, 0), 2);
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 = (0.5 * 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, -1, color, 5, LINE_8, hierarchy, 100);
coloredRoi.copyTo(frame(box), mask);
}
// For each frame, extract the bounding box and mask for each detected object
void postprocess(Mat& frame, const vector<Mat>& outs)
{
Mat outDetections = outs[0];
Mat outMasks = outs[1];
// 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[2];
const int numClasses = outMasks.size[1];
outDetections = outDetections.reshape(1, outDetections.total() / 7);
for (int i = 0; i < numDetections; i)
{
float score = outDetections.at<float>(i, 2);
if (score > confThreshold)
{
// Extract the bounding box
int classId = static_cast<int>(outDetections.at<float>(i, 1));
int left = static_cast<int>(frame.cols * outDetections.at<float>(i, 3));
int top = static_cast<int>(frame.rows * outDetections.at<float>(i, 4));
int right = static_cast<int>(frame.cols * outDetections.at<float>(i, 5));
int bottom = static_cast<int>(frame.rows * outDetections.at<float>(i, 6));
left = max(0, min(left, frame.cols - 1));
top = max(0, min(top, frame.rows - 1));
right = max(0, min(right, frame.cols - 1));
bottom = max(0, min(bottom, frame.rows - 1));
Rect box = Rect(left, top, right - left 1, bottom - top 1);
// Extract the mask for the object
Mat objectMask(outMasks.size[2], outMasks.size[3], CV_32F, outMasks.ptr<float>(i, classId));
// Draw bounding box, colorize and show the mask on the image
drawBox(frame, classId, score, box, objectMask);
}
}
}
/***************Image Test****************/
int main()
{
// Load names of classes
string classesFile = "./model2/label.names";
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);
// Load the colors
string colorsFile = "./model2/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 = "./model2/defect_label.pbtxt";
String modelWeights = "./model2/frozen_inference_graph.pb";
// Load the network
Net net = readNetFromTensorflow(modelWeights, textGraph);
// Open a video file or an image file or a camera stream.
string str, outputFile;
Mat frame, blob;
// Create a window
static const string kWinName = "OpenCV DNN Mask-RCNN Demo";
// Process frames.
frame = imread("./imgs/4.jpg");
// Create a 4D blob from a frame.
//blobFromImage(frame, blob, 1.0, Size(frame.cols, frame.rows), Scalar(), true, false);
//blobFromImage(frame, blob, 1.0, Size(1012, 800), Scalar(), true, false);
blobFromImage(frame, blob, 1.0, Size(800, 800), 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(2);
cout << outNames[0] << endl;
cout << outNames[1] << endl;
outNames[0] = "detection_out_final";
outNames[1] = "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() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
string label = format("test use time: %0.0f ms", t);
putText(frame, label, Point(10, 20), FONT_HERSHEY_SIMPLEX, 0.8, Scalar(0, 0, 255), 2);
// Write the frame with the detection boxes
Mat detectedFrame;
frame.convertTo(detectedFrame, CV_8U);
imwrite("result.jpg", frame);
//resize(frame, frame, Size(frame.cols / 3, frame.rows / 3));
imshow(kWinName, frame);
waitKey(0);
return 0;
}测试图像：
运行结果：
