代码都是开源的代码，用的是opencv的DNN人脸检测算法。

测试过程中的所用到的模块的版本：

python (3.5.1)

opencv-python (4.1.2.30)

opencv-contrib-python (4.1.2.30)

1、先贴出第一版本的代码：

from __future__ import division
import cv2
import time
import sys

def detectFaceOpenCVDnn(net, frame):
    frameOpencvDnn = frame.copy()
    frameHeight = frameOpencvDnn.shape[0]
    frameWidth = frameOpencvDnn.shape[1]
    blob = cv2.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], False, False)
    net.setInput(blob)
    detections = net.forward()
    bboxes = []
    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > conf_threshold:
            x1 = int(detections[0, 0, i, 3] * frameWidth)
            y1 = int(detections[0, 0, i, 4] * frameHeight)
            x2 = int(detections[0, 0, i, 5] * frameWidth)
            y2 = int(detections[0, 0, i, 6] * frameHeight)
            bboxes.append([x1, y1, x2, y2])
            cv2.rectangle(frameOpencvDnn, (x1, y1), (x2, y2), (0, 255, 0), int(round(frameHeight/150)), 8)
    return frameOpencvDnn, bboxes

if __name__ == "__main__" :
    DNN = "TF"
    if DNN == "CAFFE":
        modelFile = "res10_300x300_ssd_iter_140000_fp16.caffemodel"
        configFile = "deploy.prototxt"
        net = cv2.dnn.readNetFromCaffe(configFile, modelFile)
    else:
        modelFile = "opencv_face_detector_uint8.pb"
        configFile = "opencv_face_detector.pbtxt"
        net = cv2.dnn.readNetFromTensorflow(modelFile, configFile)

    conf_threshold = 0.7
    source = "rtsp://***:***@192.168.**.**:554/h264/ch1/main/av_stream"
    if len(sys.argv) > 1:
        source = sys.argv[1]
    cap = cv2.VideoCapture(source)
    hasFrame, frame = cap.read()
    vid_writer = cv2.VideoWriter('output-dnn-{}.avi'.format(str(source).split(".")[0]),cv2.VideoWriter_fourcc('M','J','P','G'), 15, (frame.shape[1],frame.shape[0]))
    frame_count = 0
    tt_opencvDnn = 0
    while(1):
        hasFrame, frame = cap.read()
        if not hasFrame:
            break
        frame_count += 1
        t = time.time()
        outOpencvDnn, bboxes = detectFaceOpenCVDnn(net,frame)
        tt_opencvDnn += time.time() - t
        fpsOpencvDnn = frame_count / tt_opencvDnn
        label = "OpenCV DNN ; FPS : {:.2f}".format(fpsOpencvDnn)
        cv2.putText(outOpencvDnn, label, (10,50), cv2.FONT_HERSHEY_SIMPLEX, 1.4, (0, 0, 255), 3, cv2.LINE_AA)
        cv2.imshow("Face Detection Comparison", outOpencvDnn)
        vid_writer.write(outOpencvDnn)
        if frame_count == 1:
            tt_opencvDnn = 0
        
        k = cv2.waitKey(10)
        if k == 27:
            break
    cv2.destroyAllWindows()
    vid_writer.release()

注：上面关于rtsp流的地址，请改为自己摄像机的地址！

2、在上面的这个例子执行过程中，会发现当检测到人脸时，程序会断开并提示报错信息：

error while decoding MB 78 12, bytestream -5

这个报错信息中的数字可能会与你的不太一样，但是大致的意思是跟python线程有关：

于是接着搜索 “python多线程使用”，然后经过修改和调试后的最新版本：

from __future__ import division
import cv2
import time
import sys
import queue
import threading
q = queue.Queue()

def detectFaceOpenCVDnn(net, frame):
    frameOpencvDnn = frame.copy()
    frameHeight = frameOpencvDnn.shape[0]
    frameWidth = frameOpencvDnn.shape[1]
    blob = cv2.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], False, False)

    net.setInput(blob)
    detections = net.forward()
    bboxes = []
    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > conf_threshold:
            x1 = int(detections[0, 0, i, 3] * frameWidth)
            y1 = int(detections[0, 0, i, 4] * frameHeight)
            x2 = int(detections[0, 0, i, 5] * frameWidth)
            y2 = int(detections[0, 0, i, 6] * frameHeight)
            bboxes.append([x1, y1, x2, y2])
            cv2.rectangle(frameOpencvDnn, (x1, y1), (x2, y2), (0, 255, 0), int(round(frameHeight/150)), 8)
    return frameOpencvDnn, bboxes


def receive():
    print("start Receive")
    source = "rtsp://***:***@192.168.**.**:554/h264/ch1/sub/av_stream"
    if len(sys.argv) > 1:
        source = sys.argv[1]
    cap = cv2.VideoCapture(source)
    hasFrame, frame = cap.read()
    q.put(frame)
    while(hasFrame):
        hasFrame, frame = cap.read()
        q.put(frame)


def display():
    print("start Display")
    frame_count = 0
    tt_opencvDnn = 0
    while(1):
        if q.empty() != True:
            frame = q.get()
            frame_count += 1
            t = time.time()
            outOpencvDnn, bboxes = detectFaceOpenCVDnn(net,frame)
            tt_opencvDnn += time.time() - t
            fpsOpencvDnn = frame_count / tt_opencvDnn
            label = "OpenCV DNN ; FPS : {:.2f}".format(fpsOpencvDnn)
            cv2.putText(outOpencvDnn, label, (10,50), cv2.FONT_HERSHEY_SIMPLEX, 1.4, (0, 0, 255), 3, cv2.LINE_AA)
            cv2.imshow("Face Detection Comparison", outOpencvDnn)
            vid_writer.write(outOpencvDnn)
            if frame_count == 1:
                tt_opencvDnn = 0
            k = cv2.waitKey(10)
            if k == 27:
                break


if __name__ == "__main__" :

    # OpenCV DNN supports 2 networks.
    # 1. FP16 version of the original caffe implementation ( 5.4 MB )
    # 2. 8 bit Quantized version using Tensorflow ( 2.7 MB )
    DNN = "TF"
    if DNN == "CAFFE":
        modelFile = "res10_300x300_ssd_iter_140000_fp16.caffemodel"
        configFile = "deploy.prototxt"
        net = cv2.dnn.readNetFromCaffe(configFile, modelFile)
    else:
        modelFile = "opencv_face_detector_uint8.pb"
        configFile = "opencv_face_detector.pbtxt"
        net = cv2.dnn.readNetFromTensorflow(modelFile, configFile)

    conf_threshold = 0.7

    source = "rtsp://***:***@192.168.**.**:554/h264/ch1/sub/av_stream"
    if len(sys.argv) > 1:
        source = sys.argv[1]

    cap = cv2.VideoCapture(source)
    hasFrame, frame = cap.read()

    vid_writer = cv2.VideoWriter('output-dnn-{}.avi'.format(str(source).split(".")[0]),cv2.VideoWriter_fourcc('M','J','P','G'), 15, (frame.shape[1],frame.shape[0]))
      
    p1 = threading.Thread(target = receive)
    p2 = threading.Thread(target = display)
    p1.start()
    p2.start()

    cv2.destroyAllWindows()
    vid_writer.release()

其实细心的朋友可能已经发现，我调用的rtsp的视频流地址source已经由第一个版本的main主码流改为了sub辅码流，这是因为主码流的视频分辨率是1080P的，对于我这太笔记本来说，处理起来相当吃力；所以我为了降低视频分辨率，改成了获取实时辅码流sub！

以上代码都是亲测的，如果有朋友使用代码测试过程中遇到问题，请对照相关模块的版本！再有问题请留言提问！