基于Dlib模型的疲劳驾驶

晚安，chris
已于 2022-07-25 10:30:03 修改
阅读量877
点赞数 2
文章标签： python 深度学习人工智能
于 2022-07-22 16:08:17 首次发布
原文链接：https://blog.csdn.net/cungudafa/article/details/103499230?utm_source=app
版权
参考于：https://blog.csdn.net/cungudafa/article/details/103499230?utm_source=app
代码基本与上面链接一样，但对于判定规则及判定阈值做了修改，且没有包含前端界面，代码较为简单，对于判定规则有不同意见的，欢迎大家提，我也是自己做了简单的测试定的，此代码不需要深度学习所以对运行设备要求不高。
# -*- coding: utf-8 -*-
# import the necessary packages
from scipy.spatial import distance as dist
from imutils.video import FileVideoStream
from imutils.video import VideoStream
from imutils import face_utils
import numpy as np # 数据处理的库 numpy
import argparse
import imutils
import math
import dlib
import cv2

# 计算眼睛长宽比
def eye_aspect_ratio(eye):
    # 垂直眼标志（X，Y）坐标
    A = dist.euclidean(eye[1], eye[5])# 计算两个集合之间的欧式距离
    B = dist.euclidean(eye[2], eye[4])
    # 计算水平之间的欧几里得距离
    # 水平眼标志（X，Y）坐标
    C = dist.euclidean(eye[0], eye[3])
    # 眼睛长宽比的计算
    ear = (A + B) / (2.0 * C)
    # 返回眼睛的长宽比
    return ear

# 计算嘴巴长宽比
def mouth_aspect_ratio(mouth):
    A = np.linalg.norm(mouth[2] - mouth[10])  # 51, 59
    B = np.linalg.norm(mouth[4] - mouth[8])  # 53, 57
    C = np.linalg.norm(mouth[0] - mouth[6])  # 49, 55
    mar = (A + B) / (2.0 * C)
    return mar

# 世界坐标系(UVW)：填写3D参考点，该模型参考http://aifi.isr.uc.pt/Downloads/OpenGL/glAnthropometric3DModel.cpp
object_pts = np.float32([[6.825897, 6.760612, 4.402142],  #33左眉左上角
                         [1.330353, 7.122144, 6.903745],  #29左眉右角
                         [-1.330353, 7.122144, 6.903745], #34右眉左角
                         [-6.825897, 6.760612, 4.402142], #38右眉右上角
                         [5.311432, 5.485328, 3.987654],  #13左眼左上角
                         [1.789930, 5.393625, 4.413414],  #17左眼右上角
                         [-1.789930, 5.393625, 4.413414], #25右眼左上角
                         [-5.311432, 5.485328, 3.987654], #21右眼右上角
                         [2.005628, 1.409845, 6.165652],  #55鼻子左上角
                         [-2.005628, 1.409845, 6.165652], #49鼻子右上角
                         [2.774015, -2.080775, 5.048531], #43嘴左上角
                         [-2.774015, -2.080775, 5.048531],#39嘴右上角
                         [0.000000, -3.116408, 6.097667], #45嘴中央下角
                         [0.000000, -7.415691, 4.070434]])#6下巴角

# 相机坐标系(XYZ)：添加相机内参
K = [6.5308391993466671e+002, 0.0, 3.1950000000000000e+002,
     0.0, 6.5308391993466671e+002, 2.3950000000000000e+002,
     0.0, 0.0, 1.0]# 等价于矩阵[fx, 0, cx; 0, fy, cy; 0, 0, 1]
# 图像中心坐标系(uv)：相机畸变参数[k1, k2, p1, p2, k3]
D = [7.0834633684407095e-002, 6.9140193737175351e-002, 0.0, 0.0, -1.3073460323689292e+000]

# 像素坐标系(xy)：填写凸轮的本征和畸变系数
cam_matrix = np.array(K).reshape(3, 3).astype(np.float32)
dist_coeffs = np.array(D).reshape(5, 1).astype(np.float32)

# 绘制正方体12轴
line_pairs = [[0, 1], [1, 2], [2, 3], [3, 0],
            [4, 5], [5, 6], [6, 7], [7, 4],
            [0, 4], [1, 5], [2, 6], [3, 7]]

# 重新投影3D点的世界坐标轴以验证结果姿势
reprojectsrc = np.float32([[10.0, 10.0, 10.0],
                           [10.0, 10.0, -10.0],
                           [10.0, -10.0, -10.0],
                           [10.0, -10.0, 10.0],
                           [-10.0, 10.0, 10.0],
                           [-10.0, 10.0, -10.0],
                           [-10.0, -10.0, -10.0],
                           [-10.0, -10.0, 10.0]])


def get_head_pose(shape):# 头部姿态估计
    
    # （像素坐标集合）填写2D参考点，注释遵循https://ibug.doc.ic.ac.uk/resources/300-W/
    # 17左眉左上角/21左眉右角/22右眉左上角/26右眉右上角/36左眼左上角/39左眼右上角/42右眼左上角/
    # 45右眼右上角/31鼻子左上角/35鼻子右上角/48左上角/54嘴右上角/57嘴中央下角/8下巴角
    image_pts = np.float32([shape[17], shape[21], shape[22], shape[26], shape[36],
                            shape[39], shape[42], shape[45], shape[31], shape[35],
                            shape[48], shape[54], shape[57], shape[8]])
    # solvePnP计算姿势——求解旋转和平移矩阵：
    # rotation_vec表示旋转矩阵，translation_vec表示平移矩阵，cam_matrix与K矩阵对应，dist_coeffs与D矩阵对应。
    _, rotation_vec, translation_vec = cv2.solvePnP(object_pts, image_pts, cam_matrix, dist_coeffs)
    # projectPoints重新投影误差：原2d点和重投影2d点的距离（输入3d点、相机内参、相机畸变、r、t，输出重投影2d点）
    reprojectdst, _ = cv2.projectPoints(reprojectsrc, rotation_vec, translation_vec, cam_matrix,dist_coeffs)
    reprojectdst = tuple(map(tuple, reprojectdst.reshape(8, 2)))# 以8行2列显示

    # 计算欧拉角calc euler angle
    # 参考https://docs.opencv.org/2.4/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html#decomposeprojectionmatrix
    rotation_mat, _ = cv2.Rodrigues(rotation_vec)#罗德里格斯公式（将旋转矩阵转换为旋转向量）
    pose_mat = cv2.hconcat((rotation_mat, translation_vec))# 水平拼接，vconcat垂直拼接
    # decomposeProjectionMatrix将投影矩阵分解为旋转矩阵和相机矩阵
    _, _, _, _, _, _, euler_angle = cv2.decomposeProjectionMatrix(pose_mat)
    
    pitch, yaw, roll = [math.radians(_) for _ in euler_angle]
 
 
    pitch = math.degrees(math.asin(math.sin(pitch)))
    roll = -math.degrees(math.asin(math.sin(roll)))
    yaw = math.degrees(math.asin(math.sin(yaw)))
    print('pitch:{}, yaw:{}, roll:{}'.format(pitch, yaw, roll))

    return reprojectdst, euler_angle# 投影误差，欧拉角


def main():

    # 定义两个常数
    # 眼睛长宽比
    # 闪烁阈值
    EYE_AR_THRESH = 0.2
    EYE_AR_CONSEC_FRAMES = 2
    # 初始化帧计数器和眨眼总数
    COUNTER = 0
    TOTAL = 0
    EYECOUNTER = 0 #眨眼总帧数
    MOUTHCOUNTER = 0 #哈欠总帧数
    HEADCOUNTER = 0 #瞌睡总帧数
    EYECLOSE = 0
    CLOSE = False
    # 打哈欠长宽比
    # 闪烁阈值
    MAR_THRESH = 0.79
    MOUTH_AR_CONSEC_FRAMES = 2
    # 瞌睡点头
    HAR_THRESH = 0.3
    NOD_AR_CONSEC_FRAMES = 2
    # 初始化帧计数器和打哈欠总数
    mCOUNTER = 0
    mTOTAL = 0
    # 初始化帧计数器和点头总数
    hCOUNTER = 0
    hTOTAL = 0

    

    # 第四步：打开cv2 本地摄像头
    cap = cv2.VideoCapture(0)
    if not cap.isOpened():
        print("Unable to connect to camera.")
        return

    # 初始化DLIB的人脸检测器（HOG），然后创建面部标志物预测
    print("[INFO] loading facial landmark predictor...")
    # 第一步：使用dlib.get_frontal_face_detector() 获得脸部位置检测器
    detector = dlib.get_frontal_face_detector()
    # 第二步：使用dlib.shape_predictor获得脸部特征位置检测器
    predictor = dlib.shape_predictor('/home/rst/Desktop/fatigue_detecting-master/model/shape_predictor_68_face_landmarks.dat')
    
    # 第三步：分别获取左右眼面部标志的索引
    (lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]
    (rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]
    (mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["mouth"]
    # 从视频流循环帧
    while True:
        # 第五步：进行循环，读取图片，并对图片做维度扩大，并进灰度化
        ret, frame = cap.read()
        if len(frame) > 0:
            frame = imutils.resize(frame, width=720)
            gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
            # 第六步：使用detector(gray, 0) 进行脸部位置检测
            rects = detector(gray, 0)
            
            # 第七步：循环脸部位置信息，使用predictor(gray, rect)获得脸部特征位置的信息
            for rect in rects:
                shape = predictor(gray, rect)
                
                # 第八步：将脸部特征信息转换为数组array的格式
                shape = face_utils.shape_to_np(shape)
                
                # 第九步：提取左眼和右眼坐标
                leftEye = shape[lStart:lEnd]
                rightEye = shape[rStart:rEnd]
                # 嘴巴坐标
                mouth = shape[mStart:mEnd]
                
                # 第十步：构造函数计算左右眼的EAR值，使用平均值作为最终的EAR
                leftEAR = eye_aspect_ratio(leftEye)
                rightEAR = eye_aspect_ratio(rightEye)
                ear = (leftEAR + rightEAR) / 2.0
                # 打哈欠
                mar = mouth_aspect_ratio(mouth)
        
                # 第十一步：使用cv2.convexHull获得凸包位置，使用drawContours画出轮廓位置进行画图操作
                leftEyeHull = cv2.convexHull(leftEye)
                rightEyeHull = cv2.convexHull(rightEye)
                # cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
                # cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)
        
                # 第十二步：进行画图操作，用矩形框标注人脸
                # left = rect.left()
                # top = rect.top()
                # right = rect.right()
                # bottom = rect.bottom()
                # cv2.rectangle(frame, (left, top), (right, bottom), (0, 255, 0), 3)    
        
                '''
                    分别计算左眼和右眼的评分求平均作为最终的评分，如果小于阈值，则加1，如果连续3次都小于阈值，则表示进行了一次眨眼活动
                '''
                # 第十三步：循环，满足条件的，眨眼次数+1
                if ear < EYE_AR_THRESH:# 眼睛长宽比：0.2
                    COUNTER += 1
                    if COUNTER == 30:
                        CLOSE = True  # 报警器报警关闭后重制为false
                        continue
                else:
                    # 如果连续2次都小于阈值，则表示进行了一次眨眼活动
                    if COUNTER >= EYE_AR_CONSEC_FRAMES:# 阈值：2
                        TOTAL += 1
                    # 重置眼帧计数器
                    COUNTER = 0
                # 每100帧重制眨眼次数及哈欠次数
                EYECOUNTER += 1
                if EYECOUNTER == 300:
                    TOTAL = 0
                    EYECOUNTER = 0
                

                # 同理，判断是否打哈欠    
                if mar > MAR_THRESH:# 张嘴阈值0.79
                    mCOUNTER += 1
                    cv2.putText(frame, "Yawning!", (10, 60),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
                else:
                    # 如果连续2次都小于阈值，则表示打了一次哈欠
                    if mCOUNTER >= MOUTH_AR_CONSEC_FRAMES:# 阈值：2
                        mTOTAL += 1 
                    # 重置嘴帧计数器
                    mCOUNTER = 0
                MOUTHCOUNTER += 1
                if MOUTHCOUNTER == 300:
                    mTOTAL = 0
                    MOUTHCOUNTER = 0

                cv2.putText(frame, "Yawning: {}".format(mTOTAL), (150, 60),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
                cv2.putText(frame, "mCOUNTER: {}".format(mCOUNTER), (300, 60),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2) 
                cv2.putText(frame, "MAR: {:.2f}".format(mar), (480, 60),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)

                # 第十四步：进行画图操作，68个特征点标识
                for (x, y) in shape:
                    cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
                # 画左眼
                # for (x, y) in leftEye:
                #     cv2.circle(frame, (x, y), 1, (0, 0, 255), -1)
                # # 画右眼
                # for (x, y) in rightEye:
                    # cv2.circle(frame, (x, y), 1, (0, 0, 255), -1)   
                    
                # 第十五步：进行画图操作，同时使用cv2.putText将眨眼次数进行显示
                cv2.putText(frame, "Faces: {}".format(len(rects)), (10, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
                cv2.putText(frame, "Blinks: {}".format(TOTAL), (150, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
                cv2.putText(frame, "COUNTER: {}".format(COUNTER), (300, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2) 
                cv2.putText(frame, "EAR: {:.2f}".format(ear), (450, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)

                # 第十五步：获取头部姿态
                reprojectdst, euler_angle = get_head_pose(shape)
                har = euler_angle[0, 0]# 取pitch旋转角度
                if har > HAR_THRESH:# 点头阈值0.3
                    hCOUNTER += 1
                else:
                    # 如果连续2次都小于阈值，则表示瞌睡点头一次
                    if hCOUNTER >= NOD_AR_CONSEC_FRAMES:# 阈值：2
                        hTOTAL += 1
                    # 重置点头帧计数器
                    hCOUNTER = 0
                # 重置打瞌睡次数
                HEADCOUNTER += 1
                if HEADCOUNTER == 300:
                    hTOTAL = 0
                    HEADCOUNTER = 0
                
                # 绘制正方体12轴
                for start, end in line_pairs:
                    cv2.line(frame, reprojectdst[start], reprojectdst[end], (0, 0, 255))
                # 显示角度结果
                cv2.putText(frame, "X: " + "{:7.2f}".format(euler_angle[0, 0]), (10, 90), cv2.FONT_HERSHEY_SIMPLEX,0.75, (0, 255, 0), thickness=2)# GREEN
                cv2.putText(frame, "Y: " + "{:7.2f}".format(euler_angle[1, 0]), (150, 90), cv2.FONT_HERSHEY_SIMPLEX,0.75, (255, 0, 0), thickness=2)# BLUE
                cv2.putText(frame, "Z: " + "{:7.2f}".format(euler_angle[2, 0]), (300, 90), cv2.FONT_HERSHEY_SIMPLEX,0.75, (0, 0, 255), thickness=2)# RED    
                cv2.putText(frame, "Nod: {}".format(hTOTAL), (450, 90),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,0), 2)

    
                print('眼睛实时长宽比:{:.2f} '.format(ear))
            # 300帧以内眨眼12次或者打哈欠5次或者闭眼超过一秒或者打瞌睡超过5次就报警
            if TOTAL >= 12 or CLOSE == True or mTOTAL >= 5 or hTOTAL >= 10:
                cv2.putText(frame, "SLEEP!!!", (200, 200),cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)
            cv2.putText(frame, "Press 'q': Quit", (20, 500),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (84, 255, 159), 2)
            # 窗口显示 show with opencv
            cv2.imshow("Frame", frame)
            
            # if the `q` key was pressed, break from the loop
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
            
    # 释放摄像头 release camera
    cap.release()
    # do a bit of cleanup
    cv2.destroyAllWindows()


if __name__ == '__main__':
    main()