1 概述 完成 Android 相機預覽功能以後,在此基礎上我使用 dlib 與 opencv 庫做了一個關於人臉檢測的 demo。該 demo 在相機預覽過程中對人臉進行實時檢測,並將檢測到的人臉用矩形框描繪出來。具體實現原理如下: 採用雙層 View,底層的 TextureView 用於預覽,程 ...
1 概述
完成 Android 相機預覽功能以後,在此基礎上我使用 dlib 與 opencv 庫做了一個關於人臉檢測的 demo。該 demo 在相機預覽過程中對人臉進行實時檢測,並將檢測到的人臉用矩形框描繪出來。具體實現原理如下:
採用雙層 View,底層的 TextureView 用於預覽,程式從 TextureView 中獲取預覽幀數據,然後調用 dlib 庫對幀數據進行處理,最後將檢測結果繪製在頂層的 SurfaceView 中。
2 項目配置
由於項目中用到了 dlib 與 opencv 庫,因此需要對其進行配置。主要涉及到以下幾個方面:
2.1 C++支持
在項目創建過程中依次選擇 Include C++ Support、C++11、Exceptions Support ( -fexceptions )以及 Runtime Type Information Support ( -frtti ) 。最後生成的 build.gradle 文件如下:
defaultConfig {
applicationId "com.example.lightweh.facedetection"
minSdkVersion 23
targetSdkVersion 28
versionCode 1
versionName "1.0"
testInstrumentationRunner "android.support.test.runner.AndroidJUnitRunner"
externalNativeBuild {
cmake {
arguments "-DCMAKE_BUILD_TYPE=Release"
cppFlags "-std=c++11 -frtti -fexceptions"
}
}
}
其中,arguments 參數是後添加上去的,主要用於指定 CMake 的編譯模式為 Release,因為在 Debug 模式下 dlib 庫中相關演算法的運行速度非常慢。前期如果需要調試 C++ 代碼,可先將 arguments 參數註釋。
2.2 dlib 與 opencv 下載
到dlib官網下載最新版本的源碼,解壓後將文件夾中的dlib目錄複製到 Android Studio 工程的 cpp 目錄下。
到 sourceforge 下載最新的 opencv-android 庫,解壓後將文件夾中的 native 目錄同樣複製到 Android Studio 工程的 cpp 目錄下,並改名為 opencv。
2.3 CMakeLists 配置
在 CMakeLists 文件中,我們首先包含 dlib 的 cmake 文件,接下來添加 opencv 的 include 文件夾並引入 opencv 的 so 庫,同時將 jni_common 目錄中的文件及人臉檢測相關文件添加至 native-lib 庫中,最後進行鏈接。
# 設置native目錄
set(NATIVE_DIR ${CMAKE_SOURCE_DIR}/src/main/cpp)
# 設置dlib
include(${NATIVE_DIR}/dlib/cmake)
# 設置opencv include文件夾
include_directories(${NATIVE_DIR}/opencv/jni/include)
# 設置opencv的so庫
add_library(
libopencv_java3
SHARED
IMPORTED)
set_target_properties(
libopencv_java3
PROPERTIES
IMPORTED_LOCATION
${NATIVE_DIR}/opencv/libs/${ANDROID_ABI}/libopencv_java3.so)
# 將jni_common目錄中所有文件名,存至SRC_LIST中
AUX_SOURCE_DIRECTORY(${NATIVE_DIR}/jni_common SRC_LIST)
add_library( # Sets the name of the library.
native-lib
# Sets the library as a shared library.
SHARED
# Provides a relative path to your source file(s).
${SRC_LIST}
src/main/cpp/face_detector.h
src/main/cpp/face_detector.cpp
src/main/cpp/native-lib.cpp)
find_library( # Sets the name of the path variable.
log-lib
# Specifies the name of the NDK library that
# you want CMake to locate.
log)
target_link_libraries( # Specifies the target library.
native-lib
dlib
libopencv_java3
jnigraphics
# Links the target library to the log library
# included in the NDK.
${log-lib})
# 指定release編譯選項
set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_RELEASE} -s -O3 -Wall")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -s -O3 -Wall")
由於 C++ 代碼中用到了頭文件 "android/bitmap.h",所以鏈接時需要添加 jnigraphics 庫。
3 JNI相關 Java 類定義
3.1 VisionDetRet 類
VisionDetRet 類的相關對象主要負責 C++ 與 Java 之間的數據傳遞。
public final class VisionDetRet {
private int mLeft;
private int mTop;
private int mRight;
private int mBottom;
VisionDetRet() {}
public VisionDetRet(int l, int t, int r, int b) {
mLeft = l;
mTop = t;
mRight = r;
mBottom = b;
}
public int getLeft() {
return mLeft;
}
public int getTop() {
return mTop;
}
public int getRight() {
return mRight;
}
public int getBottom() {
return mBottom;
}
}
3.2 FaceDet 類
FaceDet 類為 JNI 函數調用類,主要定義了一些需要 C++ 實現的 native 方法。
public class FaceDet {
private static final String TAG = "FaceDet";
// accessed by native methods
@SuppressWarnings("unused")
private long mNativeFaceDetContext;
static {
try {
// 預載入native方法庫
System.loadLibrary("native-lib");
jniNativeClassInit();
Log.d(TAG, "jniNativeClassInit success");
} catch (UnsatisfiedLinkError e) {
Log.e(TAG, "library not found");
}
}
public FaceDet() {
jniInit();
}
@Nullable
@WorkerThread
public List<VisionDetRet> detect(@NonNull Bitmap bitmap) {
VisionDetRet[] detRets = jniBitmapDet(bitmap);
return Arrays.asList(detRets);
}
@Override
protected void finalize() throws Throwable {
super.finalize();
release();
}
public void release() {
jniDeInit();
}
@Keep
private native static void jniNativeClassInit();
@Keep
private synchronized native int jniInit();
@Keep
private synchronized native int jniDeInit();
@Keep
private synchronized native VisionDetRet[] jniBitmapDet(Bitmap bitmap);
}
4 Native 方法實現
4.1 定義 VisionDetRet 類對應的 C++ 類
#include <jni.h>
#define CLASSNAME_VISION_DET_RET "com/lightweh/dlib/VisionDetRet"
#define CONSTSIG_VISION_DET_RET "()V"
#define CLASSNAME_FACE_DET "com/lightweh/dlib/FaceDet"
class JNI_VisionDetRet {
public:
JNI_VisionDetRet(JNIEnv *env) {
// 查找VisionDetRet類信息
jclass detRetClass = env->FindClass(CLASSNAME_VISION_DET_RET);
// 獲取VisionDetRet類成員變數
jID_left = env->GetFieldID(detRetClass, "mLeft", "I");
jID_top = env->GetFieldID(detRetClass, "mTop", "I");
jID_right = env->GetFieldID(detRetClass, "mRight", "I");
jID_bottom = env->GetFieldID(detRetClass, "mBottom", "I");
}
void setRect(JNIEnv *env, jobject &jDetRet, const int &left, const int &top,
const int &right, const int &bottom) {
// 設置VisionDetRet類對象jDetRet的成員變數值
env->SetIntField(jDetRet, jID_left, left);
env->SetIntField(jDetRet, jID_top, top);
env->SetIntField(jDetRet, jID_right, right);
env->SetIntField(jDetRet, jID_bottom, bottom);
}
// 創建VisionDetRet類實例
static jobject createJObject(JNIEnv *env) {
jclass detRetClass = env->FindClass(CLASSNAME_VISION_DET_RET);
jmethodID mid =
env->GetMethodID(detRetClass, "<init>", CONSTSIG_VISION_DET_RET);
return env->NewObject(detRetClass, mid);
}
// 創建VisionDetRet類對象數組
static jobjectArray createJObjectArray(JNIEnv *env, const int &size) {
jclass detRetClass = env->FindClass(CLASSNAME_VISION_DET_RET);
return (jobjectArray) env->NewObjectArray(size, detRetClass, NULL);
}
private:
jfieldID jID_left;
jfieldID jID_top;
jfieldID jID_right;
jfieldID jID_bottom;
};
4.2 定義人臉檢測類
人臉檢測演算法需要用大小位置不同的視窗在圖像中進行滑動,然後判斷視窗中是否存在人臉。本文采用的是 dlib 中的是HOG(histogram of oriented gradient)方法對人臉進行檢測,其檢測效果要好於 opencv。dlib 中同樣提供了 CNN 方法來進行人臉檢測,效果好於 HOG,不過需要使用 GPU 加速,不然程式運行會非常慢。
class FaceDetector {
private:
dlib::frontal_face_detector face_detector;
std::vector<dlib::rectangle> det_rects;
public:
FaceDetector();
// 實現人臉檢測演算法
int Detect(const cv::Mat &image);
// 返回檢測結果
std::vector<dlib::rectangle> getDetResultRects();
};
FaceDetector::FaceDetector() {
// 定義人臉檢測器
face_detector = dlib::get_frontal_face_detector();
}
int FaceDetector::Detect(const cv::Mat &image) {
if (image.empty())
return 0;
if (image.channels() == 1) {
cv::cvtColor(image, image, CV_GRAY2BGR);
}
dlib::cv_image<dlib::bgr_pixel> dlib_image(image);
det_rects.clear();
// 返回檢測到的人臉矩形特征框
det_rects = face_detector(dlib_image);
return det_rects.size();
}
std::vector<dlib::rectangle> FaceDetector::getDetResultRects() {
return det_rects;
}
4.3 native 方法實現
JNI_VisionDetRet *g_pJNI_VisionDetRet;
JavaVM *g_javaVM = NULL;
// 該函數在載入本地庫時被調用
JNIEXPORT jint JNI_OnLoad(JavaVM *vm, void *reserved) {
g_javaVM = vm;
JNIEnv *env;
vm->GetEnv((void **) &env, JNI_VERSION_1_6);
// 初始化 g_pJNI_VisionDetRet
g_pJNI_VisionDetRet = new JNI_VisionDetRet(env);
return JNI_VERSION_1_6;
}
// 該函數用於執行清理操作
void JNI_OnUnload(JavaVM *vm, void *reserved) {
g_javaVM = NULL;
delete g_pJNI_VisionDetRet;
}
namespace {
#define JAVA_NULL 0
using DetPtr = FaceDetector *;
// 用於存放人臉檢測類對象的指針,關聯Jave層對象與C++底層對象(相互對應)
class JNI_FaceDet {
public:
JNI_FaceDet(JNIEnv *env) {
jclass clazz = env->FindClass(CLASSNAME_FACE_DET);
mNativeContext = env->GetFieldID(clazz, "mNativeFaceDetContext", "J");
env->DeleteLocalRef(clazz);
}
DetPtr getDetectorPtrFromJava(JNIEnv *env, jobject thiz) {
DetPtr const p = (DetPtr) env->GetLongField(thiz, mNativeContext);
return p;
}
void setDetectorPtrToJava(JNIEnv *env, jobject thiz, jlong ptr) {
env->SetLongField(thiz, mNativeContext, ptr);
}
jfieldID mNativeContext;
};
// Protect getting/setting and creating/deleting pointer between java/native
std::mutex gLock;
std::shared_ptr<JNI_FaceDet> getJNI_FaceDet(JNIEnv *env) {
static std::once_flag sOnceInitflag;
static std::shared_ptr<JNI_FaceDet> sJNI_FaceDet;
std::call_once(sOnceInitflag, [env]() {
sJNI_FaceDet = std::make_shared<JNI_FaceDet>(env);
});
return sJNI_FaceDet;
}
// 從java對象獲取它持有的c++對象指針
DetPtr const getDetPtr(JNIEnv *env, jobject thiz) {
std::lock_guard<std::mutex> lock(gLock);
return getJNI_FaceDet(env)->getDetectorPtrFromJava(env, thiz);
}
// The function to set a pointer to java and delete it if newPtr is empty
// C++對象new以後,將指針轉成long型返回給java對象持有
void setDetPtr(JNIEnv *env, jobject thiz, DetPtr newPtr) {
std::lock_guard<std::mutex> lock(gLock);
DetPtr oldPtr = getJNI_FaceDet(env)->getDetectorPtrFromJava(env, thiz);
if (oldPtr != JAVA_NULL) {
delete oldPtr;
}
getJNI_FaceDet(env)->setDetectorPtrToJava(env, thiz, (jlong) newPtr);
}
} // end unnamespace
#ifdef __cplusplus
extern "C" {
#endif
#define DLIB_FACE_JNI_METHOD(METHOD_NAME) Java_com_lightweh_dlib_FaceDet_##METHOD_NAME
void JNIEXPORT
DLIB_FACE_JNI_METHOD(jniNativeClassInit)(JNIEnv *env, jclass _this) {}
// 生成需要返回的結果數組
jobjectArray getRecResult(JNIEnv *env, DetPtr faceDetector, const int &size) {
// 根據檢測到的人臉數創建相應大小的jobjectArray
jobjectArray jDetRetArray = JNI_VisionDetRet::createJObjectArray(env, size);
for (int i = 0; i < size; i++) {
// 對檢測到的每一個人臉創建對應的實例對象,然後插入數組
jobject jDetRet = JNI_VisionDetRet::createJObject(env);
env->SetObjectArrayElement(jDetRetArray, i, jDetRet);
dlib::rectangle rect = faceDetector->getDetResultRects()[i];
// 將人臉矩形框的值賦給對應的jobject實例對象
g_pJNI_VisionDetRet->setRect(env, jDetRet, rect.left(), rect.top(),
rect.right(), rect.bottom());
}
return jDetRetArray;
}
JNIEXPORT jobjectArray JNICALL
DLIB_FACE_JNI_METHOD(jniBitmapDet)(JNIEnv *env, jobject thiz, jobject bitmap) {
cv::Mat rgbaMat;
cv::Mat bgrMat;
jniutils::ConvertBitmapToRGBAMat(env, bitmap, rgbaMat, true);
cv::cvtColor(rgbaMat, bgrMat, cv::COLOR_RGBA2BGR);
// 獲取人臉檢測類指針
DetPtr mDetPtr = getDetPtr(env, thiz);
// 調用人臉檢測演算法,返回檢測到的人臉數
jint size = mDetPtr->Detect(bgrMat);
// 返回檢測結果
return getRecResult(env, mDetPtr, size);
}
jint JNIEXPORT JNICALL
DLIB_FACE_JNI_METHOD(jniInit)(JNIEnv *env, jobject thiz) {
DetPtr mDetPtr = new FaceDetector();
// 設置人臉檢測類指針
setDetPtr(env, thiz, mDetPtr);
return JNI_OK;
}
jint JNIEXPORT JNICALL
DLIB_FACE_JNI_METHOD(jniDeInit)(JNIEnv *env, jobject thiz) {
// 指針置0
setDetPtr(env, thiz, JAVA_NULL);
return JNI_OK;
}
#ifdef __cplusplus
}
#endif
5 Java端調用人臉檢測演算法
在開啟人臉檢測之前,需要在相機 AutoFitTextureView 上覆蓋一層自定義 BoundingBoxView 用於繪製檢測到的人臉矩形框,該 View 的具體實現如下:
public class BoundingBoxView extends SurfaceView implements SurfaceHolder.Callback {
protected SurfaceHolder mSurfaceHolder;
private Paint mPaint;
private boolean mIsCreated;
public BoundingBoxView(Context context, AttributeSet attrs) {
super(context, attrs);
mSurfaceHolder = getHolder();
mSurfaceHolder.addCallback(this);
mSurfaceHolder.setFormat(PixelFormat.TRANSPARENT);
setZOrderOnTop(true);
mPaint = new Paint();
mPaint.setAntiAlias(true);
mPaint.setColor(Color.RED);
mPaint.setStrokeWidth(5f);
mPaint.setStyle(Paint.Style.STROKE);
}
@Override
public void surfaceChanged(SurfaceHolder surfaceHolder, int format, int width, int height) {
}
@Override
public void surfaceCreated(SurfaceHolder surfaceHolder) {
mIsCreated = true;
}
@Override
public void surfaceDestroyed(SurfaceHolder surfaceHolder) {
mIsCreated = false;
}
public void setResults(List<VisionDetRet> detRets)
{
if (!mIsCreated) {
return;
}
Canvas canvas = mSurfaceHolder.lockCanvas();
//清除掉上一次的畫框。
canvas.drawColor(Color.TRANSPARENT, PorterDuff.Mode.CLEAR);
canvas.drawColor(Color.TRANSPARENT);
for (VisionDetRet detRet : detRets) {
Rect rect = new Rect(detRet.getLeft(), detRet.getTop(), detRet.getRight(), detRet.getBottom());
canvas.drawRect(rect, mPaint);
}
mSurfaceHolder.unlockCanvasAndPost(canvas);
}
}
同時,需要在佈局文件中添加對應的 BoundingBoxView 層,保證與 AutoFitTextureView 完全重合:
<?xml version="1.0" encoding="utf-8"?>
<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:tools="http://schemas.android.com/tools"
android:layout_width="match_parent"
android:layout_height="match_parent"
tools:context=".CameraFragment">
<com.lightweh.facedetection.AutoFitTextureView
android:id="@+id/textureView"
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:layout_centerVertical="true"
android:layout_centerHorizontal="true" />
<com.lightweh.facedetection.BoundingBoxView
android:id="@+id/boundingBoxView"
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:layout_alignLeft="@+id/textureView"
android:layout_alignTop="@+id/textureView"
android:layout_alignRight="@+id/textureView"
android:layout_alignBottom="@+id/textureView" />
</RelativeLayout>
BoundingBoxView 添加完成以後,即可在 CameraFragment 中添加對應的人臉檢測代碼:
private class detectAsync extends AsyncTask<Bitmap, Void, List<VisionDetRet>> {
@Override
protected void onPreExecute() {
mIsDetecting = true;
super.onPreExecute();
}
protected List<VisionDetRet> doInBackground(Bitmap... bp) {
List<VisionDetRet> results;
// 返回檢測結果
results = mFaceDet.detect(bp[0]);
return results;
}
protected void onPostExecute(List<VisionDetRet> results) {
// 繪製檢測到的人臉矩形框
mBoundingBoxView.setResults(results);
mIsDetecting = false;
}
}
然後,分別在 onResume 與 onPause 函數中完成人臉檢測類對象的初始化和釋放:
@Override
public void onResume() {
super.onResume();
startBackgroundThread();
mFaceDet = new FaceDet();
if (mTextureView.isAvailable()) {
openCamera(mTextureView.getWidth(), mTextureView.getHeight());
} else {
mTextureView.setSurfaceTextureListener(mSurfaceTextureListener);
}
}
@Override
public void onPause() {
closeCamera();
stopBackgroundThread();
if (mFaceDet != null) {
mFaceDet.release();
}
super.onPause();
}
最後,在 TextureView 的回調函數 onSurfaceTextureUpdated 完成調用:
@Override
public void onSurfaceTextureUpdated(SurfaceTexture texture) {
if (!mIsDetecting) {
Bitmap bp = mTextureView.getBitmap();
// 保證圖片方向與預覽方向一致
bp = Bitmap.createBitmap(bp, 0, 0, bp.getWidth(), bp.getHeight(), mTextureView.getTransform(null), true );
new detectAsync().execute(bp);
}
}
6 測試結果
經測試,960x720的 bitmap 圖片在華為手機(Android 6.0,8核1.2GHz,2G記憶體)上執行一次檢測約耗時800~850ms。Demo 運行效果如下:
7 Demo 源碼
Github:FaceDetection
8. 參考
- https://github.com/tzutalin/dlib-android
- https://github.com/gv22ga/dlib-face-recognition-android
- https://blog.csdn.net/yanzi1225627/article/details/7934710
- https://blog.csdn.net/hjimce/article/details/64127654