前言

人脸检测跟踪技术在监控安防，消费领域用途广泛，比如手机上的人脸解锁， 美颜App。人脸检测技术最经典的算法之一——Haar Cascade Classifier级联分类器在opencv中早已经被集成，Haar特征比较简单，巧妙利于图像积分图进行快速计算，但是缺点就是精度不高。基于深度学习的目标检测算法层出不穷，犹如雨后春笋，人脸检测由于其特殊性发展出了一系列专用的检测算法，比如深度级联人脸检测， MTCNN等。

MTCNN是基于深度学习的人脸检测算法，MTCNN算法不仅包含人脸检测，还可以进行人脸对齐(Face Alignment)，细节不展开叙述。

本文采用开源的人脸检测跟踪工程，利用pybind11将其封装为python接口，在python中实现人脸检测跟踪。

开发测试环境

windows 10, 64bit
Anaconda3, with pyhon 3.7
Visual Studio 2017
pycharm
opencv3.4.0
ncnn(tencent开源深度学习库)

NCNN环境配置

步骤：

下载ncnn库：
https://github.com/Tencent/ncnn

使用cmake进行编译

使用visual studio编译生成ncnn.lib

image.png

python API封装

继承faceTrack类，将其封装为python的类

PYBIND11_MODULE(face_tracking_demo, m) {
    
    NDArrayConverter::init_numpy();
    
    py::class_<FaceTracker>(m, "FaceTracker")
        .def(py::init<>())
        .def("trackerInit", &FaceTracker::trackerInit, py::arg("model_path"), py::arg("min_face"))
        .def("trackerUpdate", &FaceTracker::trackerUpdate, py::arg("img"));
}

demo.cpp



#include <opencv2/opencv.hpp>
#include"include/ncnn_mtcnn_tld_so.hpp"
#include <stdio.h>
#include<pybind11/pybind11.h>
#include<pybind11/stl.h>
#include<pybind11/numpy.h>

#include"ndarray_converter.h"

using namespace cv;
using namespace std;

namespace py = pybind11;

class FaceTracker :private faceTrack
{
public:
   FaceTracker() { faceTrack(); };
   ~FaceTracker() {};

public:
   void trackerInit(const std::string& model_path, const int min_face) {
       this->Init(model_path, min_face);
   }
   std::vector<int> trackerUpdate(cv::Mat& image) {
       cv::Rect rect;
       this->DetectFace(rect, image);
       return vector<int>{rect.x, rect.y, rect.x + rect.width, rect.y + rect.height};
   };

public:
   std::string version = "v1.0.0";

};



#if 0

int main() {
   cv::VideoCapture capture;
   capture.open("./test.avi");

   cv::Mat frame;
   faceTrack tracker;
   std::string modelPath = "./models";
   int minFace = 40;
   tracker.Init(modelPath, minFace);

   while (capture.read(frame)) {
       int q = cv::waitKey(1);
       if (q == 27) break;
       cv::Rect result;
       double t1 = (double)getTickCount();
       tracker.DetectFace(result, frame);
       printf("total %gms\n", ((double)getTickCount() - t1) * 1000 / getTickFrequency());
       printf("------------------\n");
       rectangle(frame, result, Scalar(0, 0, 255), 2);
       imshow("frame", frame);
       //      outputVideo << frame;
   }
   //  outputVideo.release();
   capture.release();
   cv::destroyAllWindows();
   return 0;
}


#endif // 0


#if 1
PYBIND11_MODULE(face_tracking_demo, m) {
   
   NDArrayConverter::init_numpy();
   
   py::class_<FaceTracker>(m, "FaceTracker")
       .def(py::init<>())
       .def("trackerInit", &FaceTracker::trackerInit, py::arg("model_path"), py::arg("min_face"))
       .def("trackerUpdate", &FaceTracker::trackerUpdate, py::arg("img"));
}

#endif

python测试代码

import demo16.face_tracking_demo as demo
import cv2

capture = cv2.VideoCapture()
capture.open('./demo16/test.avi')

tracker = demo.FaceTracker()
tracker.trackerInit(model_path='./demo16/models/', min_face=40)

while True:
    ret, frame = capture.read()
    if not ret:
        print('Finish!')
        break

    rect = tracker.trackerUpdate(frame)

    cv2.rectangle(frame, (rect[0], rect[1]), (rect[2], rect[3]), (0, 255, 255), 2)
    cv2.imshow('tracking', frame)
    cv2.waitKey(33)