一、opencv的示例模型文件
opencv的dnn模块读取models.yml文件中包含的目标检测模型有以下5种：
1、OpenCV’s face detection network
opencv_fd:
model: “opencv_face_detector.caffemodel”
config: “opencv_face_detector.prototxt”
mean: [104, 177, 123]
scale: 1.0
width: 300
height: 300
rgb: false
sample: “object_detection”
2、 YOLO object detection family from Darknet
(https://pjreddie.com/darknet/yolo/)
Might be used for all YOLOv2, TinyYolov2 and YOLOv3
- yolo:
model: “yolov3.weights”
config: “yolov3.cfg”
mean: [0, 0, 0]
scale: 0.00392
width: 416
height: 416
rgb: true
classes: “object_detection_classes_yolov3.txt”
sample: “object_detection” - tiny-yolo-voc:
model: “tiny-yolo-voc.weights”
config: “tiny-yolo-voc.cfg”
mean: [0, 0, 0]
scale: 0.00392
width: 416
height: 416
rgb: true
classes: “object_detection_classes_pascal_voc.txt”
sample: “object_detection”
3、Caffe implementation of SSD model
from https://github.com/chuanqi305/MobileNet-SSD
ssd_caffe:
model: “MobileNetSSD_deploy.caffemodel”
config: “MobileNetSSD_deploy.prototxt”
mean: [127.5, 127.5, 127.5]
scale: 0.007843
width: 300
height: 300
rgb: false
classes: “object_detection_classes_pascal_voc.txt”
sample: “object_detection”
4、TensorFlow implementation of SSD model
from https://github.com/tensorflow/models/tree/master/research/object_detection
ssd_tf:
model: “ssd_mobilenet_v1_coco_2017_11_17.pb”
config: “ssd_mobilenet_v1_coco_2017_11_17.pbtxt”
mean: [0, 0, 0]
scale: 1.0
width: 300
height: 300
rgb: true
classes: “object_detection_classes_coco.txt”
sample: “object_detection”
5、TensorFlow implementation of Faster-RCNN model
from https://github.com/tensorflow/models/tree/master/research/object_detection
faster_rcnn_tf:
model: “faster_rcnn_inception_v2_coco_2018_01_28.pb”
config: “faster_rcnn_inception_v2_coco_2018_01_28.pbtxt”
mean: [0, 0, 0]
scale: 1.0
width: 800
height: 600
rgb: true
sample: “object_detection”
二、示例代码
OpenCV’s face detection network
#include <fstream>
#include <sstream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include "common.hpp"
using namespace cv;
using namespace dnn;
float confThreshold, nmsThreshold;
std::vector<std::string> classes;
void postprocess(Mat& frame, const std::vector<Mat>& out, Net& net);
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
void callback(int pos, void* userdata);
int main(int argc, char** argv)
{
// 根据选择的检测模型文件进行配置
confThreshold = 0.5;
nmsThreshold = 0.4;
float scale = 1.0;
Scalar mean{104,177,123};
bool swapRB = false;
int inpWidth = 300;
int inpHeight = 300;
String modelPath = "../../data/testdata/dnn/opencv_face_detector.prototxt";
String configPath = "../../data/testdata/dnn/opencv_face_detector.caffemodel";
String framework = "";
int backendId = cv::dnn::DNN_BACKEND_OPENCV;
int targetId = cv::dnn::DNN_TARGET_CPU;
String classesFile = "";
// 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);
}
}
classes.push_back("face");
// Load a model.
Net net = readNet(modelPath, configPath, framework);
net.setPreferableBackend(backendId);
net.setPreferableTarget(targetId);
std::vector<String> outNames = net.getUnconnectedOutLayersNames();
// Create a window
static const std::string kWinName = "Deep learning object detection in OpenCV";
// Open a video file or an image file or a camera stream.
VideoCapture cap;
cap.open(0);
// Process frames.
Mat frame, blob;
while (waitKey(1) < 0) {
cap >> frame;
if (frame.empty()) {
waitKey();
break;
}
// 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); // blob的 N = 1
std::vector<Mat> outs;
net.forward(outs, outNames);
// 获取检测结果
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
CV_Assert(outs.size() == 1); // N = 1, 一幅图，一个输出结果blob
// Network produces output blob with a shape 1x1xNx7 where N is a number of
// detections and an every detection is a vector of values
// [batchId, classId, confidence, left, top, right, bottom]
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);
}
}
// NMS处理检测结果，绘制
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);
}
// 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);
}
return 0;
}
// 绘制检测矩形框
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());
}