Skip to content

E
evsuits
提交 00b9954e authored 作者: blu's avatar blu
浏览文件
操作

yolo

上级 eb73e47d
隐藏空白字符变更
内嵌 并排
正在显示 包含 502 行增加 和 217 行删除
opencv-yolo/Makefile
浏览文件 @ 00b9954e
CC = g++ CC = g++
CFLAGS = -g -Wall -std=c++11 CFLAGS = -g -Wall -std=c++2a
SRCS = main.cpp SRCS = main.origin.cpp
PROG = main PROG = main
SRCS2 = main.cpp
PROG2 = yolo
OPENCV = `pkg-config opencv4 --cflags --libs` OPENCV = `pkg-config opencv4 --cflags --libs`
LIBS = $(OPENCV) LIBS = $(OPENCV)
all: $(PROG) $(PROG2)
$(PROG):$(SRCS) $(PROG):$(SRCS)
$(CC) $(CFLAGS) -o $(PROG) $(SRCS) $(LIBS) $(CC) $(CFLAGS) -o $(PROG) $(SRCS) $(LIBS)
\ No newline at end of file
$(PROG2):$(SRCS2)
$(CC) $(CFLAGS) -o $(PROG2) $(SRCS2) $(LIBS) -I../opencv-motion-detect/inc -I../opencv-motion-detect/vendor/include
\ No newline at end of file
opencv-yolo/main.cpp
浏览文件 @ 00b9954e
// This code is written at BigVision LLC. It is based on the OpenCV project. It is subject to the license terms in the LICENSE file found in this distribution and at http://opencv.org/license.html
// Usage example: ./object_detection_yolo.out --video=run.mp4
// ./object_detection_yolo.out --image=bird.jpg
#include <fstream> #include <fstream>
#include <sstream> #include <sstream>
#include <iostream> #include <iostream>
#include <tuple>
#include "fs.h"
#include "spdlog/spdlog.h"
#ifdef _MY_HEADERS_ #ifdef _MY_HEADERS_
#include <opencv2/core/types_c.h> #include <opencv2/core/types_c.h>
...@@ -16,22 +15,10 @@ ...@@ -16,22 +15,10 @@
#include <opencv2/opencv.hpp> #include <opencv2/opencv.hpp>
#endif #endif
const char* keys =
"{help h usage ? | | Usage examples: \n\t\t./PROG --image=dog.jpg \n\t\t./object_detection_yolo.out --video=run_sm.mp4}"
"{image i |<none>| input image }"
"{video v |<none>| input video }"
;
using namespace cv; using namespace cv;
using namespace dnn; using namespace dnn;
using namespace std; using namespace std;
// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float nmsThreshold = 0.4; // Non-maximum suppression threshold
int inpWidth = 416; // Width of network's input image
int inpHeight = 416; // Height of network's input image
vector<string> classes;
// Remove the bounding boxes with low confidence using non-maxima suppression // Remove the bounding boxes with low confidence using non-maxima suppression
int postprocess(Mat& frame, const vector<Mat>& out); int postprocess(Mat& frame, const vector<Mat>& out);
...@@ -41,234 +28,251 @@ void drawPred(int classId, float conf, int left, int top, int right, int bottom, ...@@ -41,234 +28,251 @@ void drawPred(int classId, float conf, int left, int top, int right, int bottom,
// Get the names of the output layers // Get the names of the output layers
vector<String> getOutputsNames(const Net& net); vector<String> getOutputsNames(const Net& net);
int main(int argc, char** argv)
{ class YoloDectect {
CommandLineParser parser(argc, argv, keys); private:
parser.about("Use this script to run object detection using YOLO3 in OpenCV."); // Initialize the parameters
if (parser.has("help")) const string selfId = "YoloDetector";
{ float confThreshold = 0.5; // Confidence threshold
parser.printMessage(); float nmsThreshold = 0.4; // Non-maximum suppression threshold
return 0; int inpWidth = 416; // Width of network's input image
} int inpHeight = 416; // Height of network's input image
// Load names of classes vector<string> classes;
string classesFile = "coco.names"; Net net;
ifstream ifs(classesFile.c_str()); Mat blob;
string line;
while (getline(ifs, line)) classes.push_back(line);
// Give the configuration and weight files for the model
String modelConfiguration = "yolov3-tiny.cfg";
String modelWeights = "yolov3-tiny.weights";
// Load the network
Net net = readNetFromDarknet(modelConfiguration, modelWeights);
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; VideoCapture cap;
VideoWriter video; VideoWriter video;
Mat frame, blob; bool bOutputIsImg = false;
string outFileBase;
try { bool cmdStop = false;
outputFile = "yolo_out_cpp.avi";
if (parser.has("image")) // Get the names of the output layers
{ vector<String> getOutputsNames(const Net& net)
// Open the image file {
str = parser.get<String>("image"); static vector<String> names;
ifstream ifile(str); if (names.empty()) {
if (!ifile) throw("error"); //Get the indices of the output layers, i.e. the layers with unconnected outputs
cap.open(str); vector<int> outLayers = net.getUnconnectedOutLayers();
str.replace(str.end()-4, str.end(), "_yolo_out_cpp"); //.jpg
outputFile = str; //get the names of all the layers in the network
vector<String> layersNames = net.getLayerNames();
// Get the names of the output layers in names
names.resize(outLayers.size());
for (size_t i = 0; i < outLayers.size(); ++i)
names[i] = layersNames[outLayers[i] - 1];
} }
else if (parser.has("video")) return names;
{ }
// Open the video file
str = parser.get<String>("video"); // draw the predicted bounding box
//ifstream ifile(str); void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
//if (!ifile) throw("error"); {
cout << "open video stream: " << str << endl; // draw a rectangle displaying the bounding box
if(!cap.open(str)){ rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
cout << "failed to open video stream: " << str << endl;
} //get the label for the class name and its confidence
str.replace(str.end()-4, str.end(), "_yolo_out_cpp.avi"); string label = format("%.2f", conf);
}else{ if (!classes.empty()) {
// Open the webcaom CV_Assert(classId < (int)classes.size());
cap.open(parser.get<int>("device")); label = classes[classId] + ":" + label;
} }
cout << "output file: " << outputFile << endl; // display the label at the top of the bounding box
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = max(top, labelSize.height);
rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1);
} }
catch(...) {
cout << "Could not open the input image/video stream" << endl; // post process
return 0; vector<tuple<string, double, Rect>> postprocess(Mat& frame, const vector<Mat>& outs)
} {
vector<int> classIds;
// Get the video writer initialized to save the output video vector<float> confidences;
if (!parser.has("image")) { vector<Rect> boxes;
video.open(outputFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH), cap.get(CAP_PROP_FRAME_HEIGHT)));
for (size_t i = 0; i < outs.size(); ++i) {
// Scan through all the bounding boxes output from the network and keep only the
// ones with high confidence scores. Assign the box's class label as the class
// with the highest score for the box.
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;
// Get the value and location of the maximum score
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));
}
}
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with lower confidences
vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
vector<tuple<string, double, Rect>> ret;
for (size_t i = 0; i < indices.size(); ++i) {
int idx = indices[i];
Rect box = boxes[idx];
ret.push_back(tuple<string, double, Rect>(classes[classIds[idx]], confidences[idx], box));
drawPred(classIds[idx], confidences[idx], box.x, box.y, box.x + box.width, box.y + box.height, frame);
}
return ret;
} }
// Create a window //
//static const string kWinName = "Deep learning object detection in OpenCV"; protected:
//namedWindow(kWinName, WINDOW_NORMAL);
//
// Process frames. public:
long frameCnt = 0; typedef int (*callback)(vector<tuple<string, double, Rect>>, Mat);
long detCnt = 0; YoloDectect(string path = "")
while (waitKey(1) < 0)
{ {
// get frame from the video if(path.empty()) {
if(!cap.read(frame)) { path = ".";
cout << "failed to open video stream" << endl;
break;
} }
cout << "frameCnt: " << frameCnt << endl; // Load names of classes
frameCnt++; string classesFile = path + "/coco.names";
// Give the configuration and weight files for the model
String modCfg = path + "/yolov3-tiny.cfg";
String modWeights = path + "/yolov3-tiny.weights";
// Stop the program if reached end of video if(!fs::exists(classesFile) || !fs::exists(modCfg) || !fs::exists(modWeights)) {
if (frame.empty()) { spdlog::error("{} failed to load configration files", selfId);
cout << "Done processing !!!" << endl; exit(1);
cout << "Output file is stored as " << outputFile << endl;
waitKey(3000);
break;
} }
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) {
classes.push_back(line);
}
// Load the network
net = readNetFromDarknet(modCfg, modWeights);
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setPreferableTarget(DNN_TARGET_CPU);
}
vector<tuple<string, double, Rect>> process(Mat &inFrame, Mat &outFrame)
{
if(inFrame.empty()) {
return vector<tuple<string, double, Rect>>();
}
// Create a 4D blob from a frame. // Create a 4D blob from a frame.
blobFromImage(frame, blob, 1/255.0, cvSize(inpWidth, inpHeight), Scalar(0,0,0), true, false); blobFromImage(inFrame, blob, 1/255.0, cvSize(inpWidth, inpHeight), Scalar(0,0,0), true, false);
//Sets the input to the network //Sets the input to the network
net.setInput(blob); net.setInput(blob);
// Runs the forward pass to get output of the output layers // Runs the forward pass to get output of the output layers
vector<Mat> outs; vector<Mat> outs;
net.forward(outs, getOutputsNames(net)); net.forward(outs, getOutputsNames(net));
// Remove the bounding boxes with low confidence // Remove the bounding boxes with low confidence
int numDet = postprocess(frame, outs); auto ret = postprocess(inFrame, outs);
if(numDet == 0 && parser.has("image")) {
continue; // The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
}
// 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; vector<double> layersTimes;
double freq = getTickFrequency() / 1000; double freq = getTickFrequency() / 1000;
double t = net.getPerfProfile(layersTimes) / freq; double t = net.getPerfProfile(layersTimes) / freq;
string label = format("Inference time for a frame : %.2f ms", t); spdlog::info("{} infer time: {} ms", selfId, t);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(255, 255, 0));
inFrame.convertTo(outFrame, CV_8U);
// Write the frame with the detection boxes return ret;
Mat detectedFrame;
frame.convertTo(detectedFrame, CV_8U);
if (parser.has("image")) {
string ofname = outputFile + to_string(detCnt) + ".jpg";
imwrite(ofname, detectedFrame);
detCnt++;
}
else {
video.write(detectedFrame);
}
//imshow(kWinName, frame);
} }
cap.release();
if (!parser.has("image")) video.release();
return 0;
}
// Remove the bounding boxes with low confidence using non-maxima suppression int process(string inVideoUri, callback cb = nullptr, string outFile = "processed.jpg")
int postprocess(Mat& frame, const vector<Mat>& outs)
{
vector<int> classIds;
vector<float> confidences;
vector<Rect> boxes;
for (size_t i = 0; i < outs.size(); ++i)
{ {
// Scan through all the bounding boxes output from the network and keep only the if(inVideoUri.empty()) {
// ones with high confidence scores. Assign the box's class label as the class inVideoUri = "0";
// with the highest score for the box. }
float* data = (float*)outs[i].data;
for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols) ghc::filesystem::path p(outFile);
{ auto dir = p.parent_path();
Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
Point classIdPoint; if((inVideoUri.substr(inVideoUri.find_last_of(".") + 1) == "jpg")) {
double confidence; bOutputIsImg = true;
// Get the value and location of the maximum score outFileBase = string(dir / p.stem());
minMaxLoc(scores, 0, &confidence, 0, &classIdPoint); }
if (confidence > confThreshold) else {
{ bOutputIsImg = false;
int centerX = (int)(data[0] * frame.cols); if(!cap.open(inVideoUri)) {
int centerY = (int)(data[1] * frame.rows); spdlog::error("{} failed to open input video {}", selfId, inVideoUri);
int width = (int)(data[2] * frame.cols); return -1;
int height = (int)(data[3] * frame.rows); }
int left = centerX - width / 2; if(!video.open(outFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH), cap.get(CAP_PROP_FRAME_HEIGHT)))) {
int top = centerY - height / 2; spdlog::error("{} failed to open output video {}", selfId, inVideoUri);
return -1;
classIds.push_back(classIdPoint.x);
confidences.push_back((float)confidence);
boxes.push_back(Rect(left, top, width, height));
} }
} }
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with
// lower confidences
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);
}
return indices.size(); long frameCnt = 0;
} long detCnt = 0;
Mat frame, outFrame;
while (waitKey(1) < 0) {
// get frame from the video
if(cmdStop) {
break;
}
// Draw the predicted bounding box if(!cap.read(frame)) {
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame) spdlog::error("{} failed to read frame from {}", selfId, inVideoUri);
{ break;
//Draw a rectangle displaying the bounding box }
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
frameCnt++;
//Get the label for the class name and its confidence
string label = format("%.2f", conf); // Stop the program if reached end of video
if (!classes.empty()) if (frame.empty()) {
{ continue;
CV_Assert(classId < (int)classes.size()); }
label = classes[classId] + ":" + label; vector<tuple<string, double, Rect>> ret = process(frame, outFrame);
if(ret.size() == 0 && bOutputIsImg) {
// no detection
continue;
}
if (bOutputIsImg) {
string ofname = outFileBase + to_string(detCnt) + ".jpg";
imwrite(ofname, outFrame);
detCnt++;
}
else {
video.write(outFrame);
}
}
cap.release();
if(!bOutputIsImg) video.release();
return 0;
} }
};
//Display the label at the top of the bounding box
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = max(top, labelSize.height);
rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1);
}
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net) int main(int argc, char** argv)
{ {
static vector<String> names; YoloDectect det;
if (names.empty()) det.process("rtsp://admin:ZQEAAI@192.168.0.101:554/h264/ch1/main/av_stream");
{
//Get the indices of the output layers, i.e. the layers with unconnected outputs return 0;
vector<int> outLayers = net.getUnconnectedOutLayers();
//get the names of all the layers in the network
vector<String> layersNames = net.getLayerNames();
// Get the names of the output layers in names
names.resize(outLayers.size());
for (size_t i = 0; i < outLayers.size(); ++i)
names[i] = layersNames[outLayers[i] - 1];
}
return names;
} }
opencv-yolo/main.origin.cpp 0 → 100644
浏览文件 @ 00b9954e
// This code is written at BigVision LLC. It is based on the OpenCV project. It is subject to the license terms in the LICENSE file found in this distribution and at http://opencv.org/license.html
// Usage example: ./object_detection_yolo.out --video=run.mp4
// ./object_detection_yolo.out --image=bird.jpg
#include <fstream>
#include <sstream>
#include <iostream>
#ifdef _MY_HEADERS_
#include <opencv2/core/types_c.h>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#else
#include <opencv2/core/types_c.h>
#include <opencv2/opencv.hpp>
#endif
const char* keys =
"{help h usage ? | | Usage examples: \n\t\t./PROG --image=dog.jpg \n\t\t./object_detection_yolo.out --video=run_sm.mp4}"
"{image i |<none>| input image }"
"{video v |<none>| input video }"
;
using namespace cv;
using namespace dnn;
using namespace std;
// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float nmsThreshold = 0.4; // Non-maximum suppression threshold
int inpWidth = 416; // Width of network's input image
int inpHeight = 416; // Height of network's input image
vector<string> classes;
// Remove the bounding boxes with low confidence using non-maxima suppression
int postprocess(Mat& frame, const vector<Mat>& out);
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net);
int main(int argc, char** argv)
{
CommandLineParser parser(argc, argv, keys);
parser.about("Use this script to run object detection using YOLO3 in OpenCV.");
if (parser.has("help"))
{
parser.printMessage();
return 0;
}
// Load names of classes
string classesFile = "coco.names";
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);
// Give the configuration and weight files for the model
String modelConfiguration = "yolov3-tiny.cfg";
String modelWeights = "yolov3-tiny.weights";
// Load the network
Net net = readNetFromDarknet(modelConfiguration, modelWeights);
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;
VideoWriter video;
Mat frame, blob;
try {
outputFile = "yolo_out_cpp.avi";
if (parser.has("image"))
{
// Open the image file
str = parser.get<String>("image");
ifstream ifile(str);
if (!ifile) throw("error");
cap.open(str);
str.replace(str.end()-4, str.end(), "_yolo_out_cpp"); //.jpg
outputFile = str;
}
else if (parser.has("video"))
{
// Open the video file
str = parser.get<String>("video");
//ifstream ifile(str);
//if (!ifile) throw("error");
cout << "open video stream: " << str << endl;
if(!cap.open(str)){
cout << "failed to open video stream: " << str << endl;
}
str.replace(str.end()-4, str.end(), "_yolo_out_cpp.avi");
}else{
// Open the webcaom
cap.open(parser.get<int>("device"));
}
cout << "output file: " << outputFile << endl;
}
catch(...) {
cout << "Could not open the input image/video stream" << endl;
return 0;
}
// Get the video writer initialized to save the output video
if (!parser.has("image")) {
video.open(outputFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH), cap.get(CAP_PROP_FRAME_HEIGHT)));
}
// Create a window
//static const string kWinName = "Deep learning object detection in OpenCV";
//namedWindow(kWinName, WINDOW_NORMAL);
// Process frames.
long frameCnt = 0;
long detCnt = 0;
while (waitKey(1) < 0)
{
// get frame from the video
if(!cap.read(frame)) {
cout << "failed to open video stream" << endl;
break;
}
cout << "frameCnt: " << frameCnt << endl;
frameCnt++;
// Stop the program if reached end of video
if (frame.empty()) {
cout << "Done processing !!!" << endl;
cout << "Output file is stored as " << outputFile << endl;
waitKey(3000);
break;
}
// Create a 4D blob from a frame.
blobFromImage(frame, blob, 1/255.0, cvSize(inpWidth, inpHeight), Scalar(0,0,0), true, false);
//Sets the input to the network
net.setInput(blob);
// Runs the forward pass to get output of the output layers
vector<Mat> outs;
net.forward(outs, getOutputsNames(net));
// Remove the bounding boxes with low confidence
int numDet = postprocess(frame, outs);
if(numDet == 0 && parser.has("image")) {
continue;
}
// 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("Inference time for a frame : %.2f ms", t);
putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(255, 255, 0));
// Write the frame with the detection boxes
Mat detectedFrame;
frame.convertTo(detectedFrame, CV_8U);
if (parser.has("image")) {
string ofname = outputFile + to_string(detCnt) + ".jpg";
imwrite(ofname, detectedFrame);
detCnt++;
}
else {
video.write(detectedFrame);
}
//imshow(kWinName, frame);
}
cap.release();
if (!parser.has("image")) video.release();
return 0;
}
// Remove the bounding boxes with low confidence using non-maxima suppression
int postprocess(Mat& frame, const vector<Mat>& outs)
{
vector<int> classIds;
vector<float> confidences;
vector<Rect> boxes;
for (size_t i = 0; i < outs.size(); ++i)
{
// Scan through all the bounding boxes output from the network and keep only the
// ones with high confidence scores. Assign the box's class label as the class
// with the highest score for the box.
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;
// Get the value and location of the maximum score
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));
}
}
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with
// lower confidences
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);
}
return indices.size();
}
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
//Draw a rectangle displaying the bounding box
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
//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);
top = max(top, labelSize.height);
rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1);
}
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net)
{
static vector<String> names;
if (names.empty())
{
//Get the indices of the output layers, i.e. the layers with unconnected outputs
vector<int> outLayers = net.getUnconnectedOutLayers();
//get the names of all the layers in the network
vector<String> layersNames = net.getLayerNames();
// Get the names of the output layers in names
names.resize(outLayers.size());
for (size_t i = 0; i < outLayers.size(); ++i)
names[i] = layersNames[outLayers[i] - 1];
}
return names;
}
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论