NtKinect: Kinect V2 C++ Programming with OpenCV on Windows10

How to recognize human face with Kinect V2 in ColorSpace coordinate system

Prerequisite knowledge

• NtKinect: How to recognize human skeleton with Kinect V2

Recognizing Human Face

In Kinect for Windows SDK 2.0, face recognition is defined as follows.

enum _FacePointType {
    FacePointType_None= -1,
    FacePointType_EyeLeft= 0,
    FacePointType_EyeRight= 1,
    FacePointType_Nose= 2,
    FacePointType_MouthCornerLeft= 3,
    FacePointType_MouthCornerRight= 4,
    FacePointType_Count= ( FacePointType_MouthCornerRight + 1 ) 
};

enum _FaceProperty {
    FaceProperty_Happy= 0,
    FaceProperty_Engaged= 1,
    FaceProperty_WearingGlasses= 2,
    FaceProperty_LeftEyeClosed= 3,
    FaceProperty_RightEyeClosed= 4,
    FaceProperty_MouthOpen= 5,
    FaceProperty_MouthMoved= 6,
    FaceProperty_LookingAway= 7,
    FaceProperty_Count= ( FaceProperty_LookingAway + 1 ) 
};

enum _DetectionResult {
    DetectionResult_Unknown= 0,
    DetectionResult_No= 1,
    DetectionResult_Maybe= 2,
    DetectionResult_Yes= 3
};

typedef struct _PointF {
    float X;
    float Y;
} PointF;

If you define USE_FACE constant before including NtKinect.h, the functions and variables of NtKinect for face recognition become effective.

After calling setSkeleton() function to recognize skeleton, you can call setFace() function to recognize human face.

NtKinect's Functions for Face Recognition

NtKinect's member variable for Face Recognition

All the human faces recognized by skeleton may not be recognized. If you want to know a skeleton's face state such as "Is the skeleton smiling?", you can judge it by skeletonTrackingId[i] == faceTrackingId[j] and faceProperty[j][FaceProperty_Happy] == DetectionResult_Yes. (version 1.4 or later)
When using NtKinect version 1.3 or earlier, judge it by comparing the face position kinect.skeleton[i][JointType_Head] and the kinect.faceRect[j].

How to write program

1. Start using the Visual Studio's project KinectV2.zip of "NtKinect: How to get RGB camera image with Kinect V2 (Fundamental Settings)"
2. Change the project so that the Kinect20.Face.lib library is also linked.

Right-click on the project name in Solution Explorer and select Properties from the menu.






Select "Additional dependency file" in "Input" of "Linker" in "Configuration Properties" and select "Edit".






Add Kinect20.Face.lib.





3. Since some files need to be copied before the execution, change the project for the following command to be added. "configuration property" -> "build event" -> "after build event" -> "command line".

  xcopy "$(KINECTSDK20_DIR)Redist\Face\x64" "$(OutDir)" /e /y /i /r





4. Change the contents of "main.cpp" as follows.

Define the USE_FACE constant before including NtKinect.h.

Call the kinect.setSkeleton() function. However each joint of kinect.skeleton is displayed on RGB image in this example, you can omit the process. It is important to recognize skeleton by calling kinect.setSkeleton() function before face recognition.

Then, call kinect.setFace() function. Since the values of kinect.faceRect, kinect.facePoint, kinect.faceProperty, and kinect.faceDirection are set, you can use them as necessary.

main.cpp

#include <iostream> #include <sstream> #define USE_FACE #include "NtKinect.h" using namespace std; void doJob() { NtKinect kinect; while (1) { kinect.setRGB(); kinect.setSkeleton(); for (auto person : kinect.skeleton) { for (auto joint : person) { if (joint.TrackingState == TrackingState_NotTracked) continue; ColorSpacePoint cp; kinect.coordinateMapper->MapCameraPointToColorSpace(joint.Position,&cp); cv::rectangle(kinect.rgbImage, cv::Rect((int)cp.X-5, (int)cp.Y-5,10,10), cv::Scalar(0,0,255),2); } } kinect.setFace(); for (cv::Rect r : kinect.faceRect) { cv::rectangle(kinect.rgbImage, r, cv::Scalar(255, 255, 0), 2); } for (vector<PointF> vf : kinect.facePoint) { for (PointF p : vf) { cv::rectangle(kinect.rgbImage, cv::Rect((int)p.X-3, (int)p.Y-3, 6, 6), cv::Scalar(0, 255, 255), 2); } } cv::imshow("rgb", kinect.rgbImage); auto key = cv::waitKey(1); if (key == 'q') break; } cv::destroyAllWindows(); } int main(int argc, char** argv) { try { doJob(); } catch (exception &ex) { cout << ex.what() << endl; string s; cin >> s; } return 0; }

5. When you run the program, RGB images are displayed. Exit with 'q' key.

Recognized face information is displayed on the RGB image.

In this example, the rectangular area of the face is displayed with a cyan square, and a yellow rectangle is written at the position of face parts (left eye, right eye, nose, left end of mouse, right end of mouse).





6. Please click here for this sample project KinectV2_face.zip。

Since the above zip file may not include the latest "NtKinect.h", Download the latest version from here and replace old one with it.