opencv dlib 总 – 小飞侠

test.py

import cv2 as cv
import dlib
import imutils
import numpy as np
from imutils import face_utils as fu


# 计算眼睛的纵横比
def eye_aspect_ratio(eye):
    # 计算上下的欧式距离
    a = np.linalg.norm(eye[1] - eye[5])
    b = np.linalg.norm(eye[2] - eye[4])
    # 计算左右的欧式距离
    c = np.linalg.norm(eye[0] - eye[3])
    # 计算纵横比并返回
    d = (a + b) / (2.0 * c)
    return d


# 计算嘴巴的纵横比
def mouth_aspect_ratio(mouth):
    # 计算上下的欧式距离
    a = np.linalg.norm(mouth[3] - mouth[9])  # 52, 59
    b = np.linalg.norm(mouth[14] - mouth[18])  # 63, 67
    # 计算左右的欧式距离
    c = np.linalg.norm(mouth[0] - mouth[6])  # 49, 55
    d = np.linalg.norm(mouth[12] - mouth[16])  # 61, 65
    # 计算纵横比并返回
    e = (a + b) / (c + d)
    return e


# 连续3帧眨眼次数
EYE_COUNTER = 0
# 总共眨眼次数
EYE_TOTAL = 0

# 连续3帧张嘴次数
MOUTH_COUNTER = 0
# 总共张嘴次数
MOUTH_TOTAL = 0

# 打开摄像头
cap = cv.VideoCapture(0, cv.CAP_DSHOW)
# 建立人脸检测器
detector = dlib.get_frontal_face_detector()
# 建立68关键点检测器
predictor = dlib.shape_predictor('./1.dat')

# 返回人脸的左眼和右眼在68关键点中的起始和结束
(lStart, lEnd) = fu.FACIAL_LANDMARKS_IDXS["left_eye"]
(rStart, rEnd) = fu.FACIAL_LANDMARKS_IDXS["right_eye"]

# 返回人脸的嘴巴在68关键点中的起始和结束
(mStart, mEnd) = fu.FACIAL_LANDMARKS_IDXS["mouth"]

# 只要能正确打开摄像头
while cap.isOpened():
    # 获取每一帧
    _, frame = cap.read()
    # 设置输出宽度
    frame = imutils.resize(frame, width=750)
    # 转变为灰度图加快识别
    gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
    # 返回这一帧的所有人脸框
    faces = detector(gray, 0)
    # 遍历所有框框
    for face in faces:
        # 返回该框的68个坐标
        shape = predictor(gray, face)
        # 转变为坐标矩阵
        shape = fu.shape_to_np(shape)
        # 返回左眼和右眼的坐标
        leftEye = shape[lStart:lEnd]
        rightEye = shape[rStart:rEnd]
        # 计算左眼和右眼的纵横比
        leftEAR = eye_aspect_ratio(leftEye)
        rightEAR = eye_aspect_ratio(rightEye)
        # 取平均值
        earAVG = (leftEAR + rightEAR) / 2.0
        # 计算左眼和右眼的凸包
        leftEyeHull = cv.convexHull(leftEye)
        rightEyeHull = cv.convexHull(rightEye)
        # 圈出凸包，即眼睛的范围
        cv.drawContours(frame, [leftEyeHull], -1, (255, 255, 255), 1)
        cv.drawContours(frame, [rightEyeHull], -1, (255, 255, 255), 1)

        # 返回嘴巴的坐标
        Mouth = shape[mStart:mEnd]
        # 计算嘴巴的纵横比
        mar = mouth_aspect_ratio(Mouth)
        # 计算嘴巴的凸包
        MouthHull = cv.convexHull(Mouth)
        # 圈出凸包，即嘴巴的范围
        cv.drawContours(frame, [MouthHull], -1, (255, 255, 255), 1)

        '''
        若眼睛纵横比小于0.3 且 连续3帧
        则认为闭眼
        '''
        if earAVG < 0.3:
            EYE_COUNTER += 1
        else:
            if EYE_COUNTER >= 3:
                EYE_TOTAL += 1
            EYE_COUNTER = 0

        '''
            若嘴巴纵横比大于0.5 且 连续3帧
            则认为打哈欠
        '''
        if mar > 0.5:
            MOUTH_COUNTER += 1
        else:
            if MOUTH_COUNTER >= 3:
                MOUTH_TOTAL += 1
            MOUTH_COUNTER = 0

        # 接下来是对输出的处理
        # 左上角输出眨眼次数
        cv.putText(
            frame,
            "Blinks:{0}".format(EYE_TOTAL),
            (10, 20),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 255, 255),
            2,
            cv.LINE_AA
        )
        # 紧接实时earAVG
        cv.putText(
            frame,
            "earAVG:{0}".format(earAVG),
            (200, 20),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 255, 255),
            2,
            cv.LINE_AA
        )

        # 左上角输出打哈欠次数
        cv.putText(
            frame,
            "Yawning:{0}".format(MOUTH_TOTAL),
            (10, 50),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 255, 255),
            2,
            cv.LINE_AA
        )
        # 紧接实时mar
        cv.putText(
            frame,
            "mar:{0}".format(mar),
            (200, 50),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 255, 255),
            2,
            cv.LINE_AA
        )

        # 右下角提示退出信息
        cv.putText(
            frame,
            "Press 'Esc' to Quit",
            (515, 550),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 255, 255),
            2,
            cv.LINE_AA
        )
    # 输出每一帧
    cv.imshow('camera', frame)
    # 按Esc退出
    if cv.waitKey(1) & 0xff == 27:
        break

# 关闭所有窗口
cv.destroyAllWindows()
# 释放摄像头
cap.release()

main.py

import cv2 as cv
import dlib
import imutils
from imutils import face_utils as fu

import eye
import head
import mouth

# 连续3帧眨眼次数
EYE_COUNTER = 0
# 总共眨眼次数
EYE_TOTAL = 0
# 持续闭眼计数(单位为帧)
ALWAYS_CLOSE_EYES_COUNTER = 0
# 持续闭眼警告标志
AL_eye_flag = False

# 初始化帧计数器和点头总数
hCOUNTER = 0
hTOTAL = 0
# 持续低头计数(单位为帧)
ALWAYS_CLOSE_HEAD_COUNTER = 0
# 持续低头警告标志
AL_head_flag = False

# 连续3帧张嘴次数
MOUTH_COUNTER = 0
# 总共张嘴次数
MOUTH_TOTAL = 0

# 打开摄像头
cap = cv.VideoCapture(0, cv.CAP_DSHOW)
# 建立人脸检测器
detector = dlib.get_frontal_face_detector()
# 建立68关键点检测器
predictor = dlib.shape_predictor('./1.dat')

while cap.isOpened():
    # 获取每一帧
    _, frame = cap.read()
    # 设置输出宽度
    frame = imutils.resize(frame, width=750)
    # 转变为灰度图加快识别
    gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
    # 返回这一帧的所有人脸框
    faces = detector(gray, 0)
    # 遍历所有框框
    for face in faces:
        # 返回该框的68个坐标
        shape = predictor(gray, face)
        # 转变为坐标矩阵
        shape = fu.shape_to_np(shape)
        # 计算左右眼纵横比的平均值
        earAVG = eye.eye_detecting(frame, shape)
        # 计算嘴巴的纵横比
        mar = mouth.mouth_detecting(frame, shape)
        # 获取头部姿态
        reprojectdst, euler_angle = head.get_head_pose(shape)
        '''
            若眼睛纵横比小于0.3 且 连续3帧
            则认为闭眼
        '''
        if earAVG < 0.3:
            EYE_COUNTER += 1
            ALWAYS_CLOSE_EYES_COUNTER += 1
        else:
            if EYE_COUNTER >= 3:
                EYE_TOTAL += 1
            EYE_COUNTER = 0
            ALWAYS_CLOSE_EYES_COUNTER = 0
        # 持续闭眼判断
        if ALWAYS_CLOSE_EYES_COUNTER >= 18:
            AL_eye_flag = True
        else:
            AL_eye_flag = False
        '''
            若嘴巴纵横比大于0.5 且 连续3帧
            则认为打哈欠
        '''
        if mar > 0.5:
            MOUTH_COUNTER += 1
        else:
            if MOUTH_COUNTER >= 3:
                MOUTH_TOTAL += 1
            MOUTH_COUNTER = 0
        '''
            头部pitch大于0.3 且 连续3帧
            则认为点头一次
        '''
        har = euler_angle[0, 0]  # 取pitch旋转角度
        if har > 15:  # 点头阈值15
            hCOUNTER += 1
            ALWAYS_CLOSE_HEAD_COUNTER += 1
        else:
            # 如果连续3次都小于阈值，则表示瞌睡点头一次
            if hCOUNTER >= 3:  # 阈值：3
                hTOTAL += 1
            # 重置点头帧计数器
            hCOUNTER = 0
            ALWAYS_CLOSE_HEAD_COUNTER = 0
        if ALWAYS_CLOSE_HEAD_COUNTER >= 18:
            AL_head_flag = True
        else:
            AL_head_flag = False

        # 接下来是对输出的处理
        # 左上角输出眨眼次数
        cv.putText(
            frame,
            "Blinks:{0}".format(EYE_TOTAL),
            (10, 20),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (0, 0, 255),
            2,
            cv.LINE_AA
        )
        # 紧接实时earAVG
        cv.putText(
            frame,
            "earAVG:{0}".format(earAVG),
            (200, 20),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (0, 0, 255),
            2,
            cv.LINE_AA
        )
        # 如果检测到超过2秒的持续闭眼则告警
        if AL_eye_flag:
            cv.putText(
                frame,
                "WARNING EYE",
                (200, 150),
                cv.FONT_HERSHEY_COMPLEX_SMALL,
                2,
                (100, 100, 255),
                2,
                cv.LINE_AA
            )

        # 左上角输出打哈欠次数
        cv.putText(
            frame,
            "Yawning:{0}".format(MOUTH_TOTAL),
            (10, 50),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (0, 0, 255),
            2,
            cv.LINE_AA
        )
        # 紧接实时mar
        cv.putText(
            frame,
            "mar:{0}".format(mar),
            (200, 50),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (0, 0, 255),
            2,
            cv.LINE_AA
        )

        for start, end in head.line_pairs:
            a = reprojectdst[start]
            b = reprojectdst[end]
            x1 = int(a[0])
            y1 = int(a[1])
            x2 = int(b[0])
            y2 = int(b[1])
            cv.line(frame, (x1, y1), (x2, y2), (0, 0, 255), 1)
        # 显示角度结果
        cv.putText(
            frame,
            "X: " + "{:7.2f}".format(euler_angle[0, 0]),
            (10, 90),
            cv.FONT_HERSHEY_SIMPLEX,
            0.75,
            (0, 255, 0),
            2
        )
        cv.putText(
            frame,
            "Y: " + "{:7.2f}".format(euler_angle[1, 0]),
            (150, 90),
            cv.FONT_HERSHEY_SIMPLEX,
            0.75,
            (255, 0, 0),
            2
        )
        cv.putText(
            frame,
            "Z: " + "{:7.2f}".format(euler_angle[2, 0]),
            (300, 90),
            cv.FONT_HERSHEY_SIMPLEX,
            0.75,
            (0, 0, 255),
            2
        )
        cv.putText(
            frame,
            "Nod: {}".format(hTOTAL),
            (450, 90),
            cv.FONT_HERSHEY_SIMPLEX,
            0.7,
            (255, 255, 0),
            2
        )
        cv.putText(
            frame,
            "har: {}".format(har),
            (10, 120),
            cv.FONT_HERSHEY_SIMPLEX,
            0.7,
            (255, 255, 0),
            2
        )
        # 如果检测到超过2秒的持续低头则告警
        if AL_head_flag:
            cv.putText(
                frame,
                "WARNING HEAD",
                (200, 250),
                cv.FONT_HERSHEY_COMPLEX_SMALL,
                2,
                (100, 100, 255),
                2,
                cv.LINE_AA
            )

        # 右下角提示退出信息
        cv.putText(
            frame,
            "Press 'Esc' to Quit",
            (515, 550),
            cv.FONT_HERSHEY_COMPLEX_SMALL,
            1,
            (255, 0, 0),
            2,
            cv.LINE_AA
        )
    # 输出每一帧
    cv.imshow('camera', frame)
    # 按Esc退出
    if cv.waitKey(1) & 0xff == 27:
        break

# 关闭所有窗口
cv.destroyAllWindows()
# 释放摄像头
cap.release()

head.py

import math

import cv2 as cv
import numpy as np

# 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)

# 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]])
# 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]]


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 = cv.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, _ = cv.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
    # print(type(reprojectdst))
    # print("repro = {0}".format(reprojectdst))
    # 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, _ = cv.Rodrigues(rotation_vec)  # 罗德里格斯公式（将旋转矩阵转换为旋转向量）
    pose_mat = cv.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 = cv.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

eye.py

import cv2 as cv
import numpy as np
from imutils import face_utils as fu


# # 连续3帧眨眼次数
# EYE_COUNTER = 0
# # 总共眨眼次数
# EYE_TOTAL = 0

# 计算眼睛的纵横比
def eye_aspect_ratio(eye):
    # 计算上下的欧式距离
    a = np.linalg.norm(eye[1] - eye[5])
    b = np.linalg.norm(eye[2] - eye[4])
    # 计算左右的欧式距离
    c = np.linalg.norm(eye[0] - eye[3])
    # 计算纵横比并返回
    d = (a + b) / (2.0 * c)
    return d


# 返回左右眼纵横比的平均值
def eye_detecting(frame, shape):
    # 返回人脸的左眼和右眼在68关键点中的起始和结束
    (lStart, lEnd) = fu.FACIAL_LANDMARKS_IDXS["left_eye"]
    (rStart, rEnd) = fu.FACIAL_LANDMARKS_IDXS["right_eye"]
    # 返回左眼和右眼的坐标
    leftEye = shape[lStart:lEnd]
    rightEye = shape[rStart:rEnd]
    # 计算左眼和右眼的纵横比
    leftEAR = eye_aspect_ratio(leftEye)
    rightEAR = eye_aspect_ratio(rightEye)
    # 取平均值
    earAVG = (leftEAR + rightEAR) / 2.0
    # 计算左眼和右眼的凸包
    leftEyeHull = cv.convexHull(leftEye)
    rightEyeHull = cv.convexHull(rightEye)
    # 圈出凸包，即眼睛的范围
    cv.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
    cv.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)
    return earAVG

mouth.py

import cv2 as cv
import numpy as np
from imutils import face_utils as fu


# # 连续3帧张嘴次数
# MOUTH_COUNTER = 0
# # 总共张嘴次数
# MOUTH_TOTAL = 0

# 计算嘴巴的纵横比
def mouth_aspect_ratio(mouth):
    # 计算上下的欧式距离
    a = np.linalg.norm(mouth[3] - mouth[9])  # 52, 59
    b = np.linalg.norm(mouth[14] - mouth[18])  # 63, 67
    # 计算左右的欧式距离
    c = np.linalg.norm(mouth[0] - mouth[6])  # 49, 55
    d = np.linalg.norm(mouth[12] - mouth[16])  # 61, 65
    # 计算纵横比并返回
    e = (a + b) / (c + d)
    return e

# 返回嘴巴的纵横比
def mouth_detecting(frame, shape):
    # 返回人脸的嘴巴在68关键点中的起始和结束
    (mStart, mEnd) = fu.FACIAL_LANDMARKS_IDXS["mouth"]
    # 返回嘴巴的坐标
    Mouth = shape[mStart:mEnd]
    # 计算嘴巴的纵横比
    mar = mouth_aspect_ratio(Mouth)
    # 计算嘴巴的凸包
    MouthHull = cv.convexHull(Mouth)
    # 圈出凸包，即嘴巴的范围
    cv.drawContours(frame, [MouthHull], -1, (0, 255, 0), 1)
    return mar

原文链接：https://blog.csdn.net/m0_50859743/article/details/123022161

你可能也喜欢