qt +opencv dnn+tensorflow实现敏感区域预警
作者:互联网
qt +opencv dnn+tensorflow实现值班预警
在安保过程中大家有没有过这样的经历,有人进入敏感区域时没有及时发现。今天就用qt +opencv dnn+tensorflow实现实现敏感区域预警
如下图:
打开预警后,有人进入摄像头区域就会发出声音报警。
实现主要原理代码如下:(将图片Mat改成摄像头即可)
以下代码,有部分来源于网上(一并感谢原作者)
#include “stdafx.h”
#include
#include
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace dnn;
float confThreshold, nmsThreshold;
std::vectorstd::string classes;
void postprocess(Mat& frame, const std::vector& out, Net& net);
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
int main(int argc, char** argv)
{
confThreshold = 0.5;
nmsThreshold = 0.4;
float scale = 1.0;
Scalar mean = { 0, 0, 0 };
bool swapRB = true;
int inpWidth = 300;
int inpHeight = 300;
String modelPath = "frozen_inference_graph.pb";
String configPath = "ssd_mobilenet_v1_coco_2017_11_17.pbtxt";
String framework = "";
int backendId = cv::dnn::DNN_BACKEND_OPENCV;
int targetId = cv::dnn::DNN_TARGET_CPU;
String classesFile = R"(object_detection_classes_coco.txt)";
// Open file with classes names.
if (!classesFile.empty()) {
const std::string& file = classesFile;
std::ifstream ifs(file.c_str());
if (!ifs.is_open())
CV_Error(Error::StsError, "File " + file + " not found");
std::string line;
while (std::getline(ifs, line)) {
classes.push_back(line);
}
}
// Load a model.
Net net = readNet(modelPath, configPath, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
std::vector<String> outNames = net.getUnconnectedOutLayersNames();
static const std::string kWinName = "opencv dnntest";
// Process frames.
Mat frame, blob;
frame = imread("test.jpg");
// Create a 4D blob from a frame.
Size inpSize(inpWidth > 0 ? inpWidth : frame.cols,
inpHeight > 0 ? inpHeight : frame.rows);
blobFromImage(frame, blob, scale, inpSize, mean, swapRB, false);
// Run a model.
net.setInput(blob);
if (net.getLayer(0)->outputNameToIndex("im_info") != -1)
{
resize(frame, frame, inpSize);
Mat imInfo = (Mat_<float>(1, 3) << inpSize.height, inpSize.width, 1.6f);
net.setInput(imInfo, "im_info");
}
std::vector<Mat> outs;
net.forward(outs, outNames);
postprocess(frame, outs, net);
// Put efficiency information.
std::vector<double> layersTimes;
double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("Inference time: %.2f ms", t);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));
imshow(kWinName, frame);
waitKey(0);
return 0;
}
void postprocess(Mat& frame, const std::vector& outs, Net& net)
{
static std::vector outLayers = net.getUnconnectedOutLayers();
static std::string outLayerType = net.getLayer(outLayers[0])->type;
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
if (net.getLayer(0)->outputNameToIndex("im_info") != -1)
{
CV_Assert(outs.size() == 1);
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7) {
float confidence = data[i + 2];
if (confidence > confThreshold) {
int left = (int)data[i + 3];
int top = (int)data[i + 4];
int right = (int)data[i + 5];
int bottom = (int)data[i + 6];
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1);
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "DetectionOutput") {
CV_Assert(outs.size() == 1);
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7) {
float confidence = data[i + 2];
if (confidence > confThreshold) {
int left = (int)(data[i + 3] * frame.cols);
int top = (int)(data[i + 4] * frame.rows);
int right = (int)(data[i + 5] * frame.cols);
int bottom = (int)(data[i + 6] * frame.rows);
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1); // Skip 0th background class id.
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "Region") {
for (size_t i = 0; i < outs.size(); ++i) {
float* data = (float*)outs[i].data;
for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols) {
Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
Point classIdPoint;
double confidence;
minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
if (confidence > confThreshold) {
int centerX = (int)(data[0] * frame.cols);
int centerY = (int)(data[1] * frame.rows);
int width = (int)(data[2] * frame.cols);
int height = (int)(data[3] * frame.rows);
int left = centerX - width / 2;
int top = centerY - height / 2;
classIds.push_back(classIdPoint.x);
confidences.push_back((float)confidence);
boxes.push_back(Rect(left, top, width, height));
}
}
}
}
else
CV_Error(Error::StsNotImplemented, "Unknown output layer type: " + outLayerType);
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i) {
int idx = indices[i];
Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
}
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 255, 0));
std::string label = format("%.2f", conf);
if (!classes.empty()) {
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ": " + label;
}
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = max(top, labelSize.height);
rectangle(frame, Point(left, top - labelSize.height),
Point(left + labelSize.width, top + baseLine), Scalar::all(255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar());
}
搞明白原理后。用qt作界面。加下声音处理模块,就可以自已实现一个安保报警系统了。(本系统初步完善后会提供免费下载)
扩展:可以实现对多种动物的动态检测预警。
使用opencv打开IP摄像机。多路报警等。
因为机器较老实现速度在300ms左右达不到实时要求。 i7的机器可达到30-50ms基本与摄像机同步。使用tensorflow的原因之一是因为经测试比同级别的yolo3模块要快10-20倍。
标签:std,outs,qt,int,frame,dnn,data,top,敏感区域 来源: https://blog.csdn.net/slmrj/article/details/103775119