这个网络摄像头面部检测有什么问题？

Question

Dlib 有一个非常方便、快速和高效的对象检测例程，我想制作一个类似于示例 here.

的很酷的面部跟踪示例

得到广泛支持的 OpenCV 具有速度相当快的 VideoCapture 模块（与调用唤醒网络摄像头和获取图片的程序需要 1 秒或更多时间相比，抓拍时间为 1/5 秒）。我将其添加到 Dlib 中的人脸检测器 Python 示例中。

如果您直接显示和处理 OpenCV VideoCapture 输出，它看起来很奇怪，因为显然 OpenCV 存储 BGR 而不是 RGB 顺序。调整后，它起作用了，但是很慢：

from __future__ import division
import sys

import dlib
from skimage import io


detector = dlib.get_frontal_face_detector()
win = dlib.image_window()

if len( sys.argv[1:] ) == 0:
    from cv2 import VideoCapture
    from time import time

    cam = VideoCapture(0)  #set the port of the camera as before

    while True:
        start = time()
        retval, image = cam.read() #return a True bolean and and the image if all go right

        for row in image:
            for px in row:
                #rgb expected... but the array is bgr?
                r = px[2]
                px[2] = px[0]
                px[0] = r
        #import matplotlib.pyplot as plt
        #plt.imshow(image)
        #plt.show()

        print( "readimage: " + str( time() - start ) )

        start = time()
        dets = detector(image, 1)
        print "your faces: %f" % len(dets)
        for i, d in enumerate( dets ):
            print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
                i, d.left(), d.top(), d.right(), d.bottom()))
            print("from left: {}".format( ( (d.left() + d.right()) / 2 ) / len(image[0]) ))
            print("from top: {}".format( ( (d.top() + d.bottom()) / 2 ) /len(image)) )
        print( "process: " + str( time() - start ) )

        start = time()
        win.clear_overlay()
        win.set_image(image)
        win.add_overlay(dets)

        print( "show: " + str( time() - start ) )
        #dlib.hit_enter_to_continue()



for f in sys.argv[1:]:
    print("Processing file: {}".format(f))
    img = io.imread(f)
    # The 1 in the second argument indicates that we should upsample the image
    # 1 time.  This will make everything bigger and allow us to detect more
    # faces.
    dets = detector(img, 1)
    print("Number of faces detected: {}".format(len(dets)))
    for i, d in enumerate(dets):
        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
            i, d.left(), d.top(), d.right(), d.bottom()))

    win.clear_overlay()
    win.set_image(img)
    win.add_overlay(dets)
    dlib.hit_enter_to_continue()


# Finally, if you really want to you can ask the detector to tell you the score
# for each detection.  The score is bigger for more confident detections.
# Also, the idx tells you which of the face sub-detectors matched.  This can be
# used to broadly identify faces in different orientations.
if (len(sys.argv[1:]) > 0):
    img = io.imread(sys.argv[1])
    dets, scores, idx = detector.run(img, 1)
    for i, d in enumerate(dets):
        print("Detection {}, score: {}, face_type:{}".format(
            d, scores[i], idx[i]))

从这个程序的计时输出来看，似乎处理和抓取图片都需要五分之一秒，所以你会认为它应该每秒显示一到两次更新 - 但是，如果你提高大约 5 秒后，您的手就会显示在网络摄像头视图中！

是否有某种内部缓存阻止它获取最新的网络摄像头图像？我可以调整或多线程网络摄像头输入过程来修复延迟吗？这是在具有 16gb RAM 的 Intel i5 上。

更新

根据此处，它建议读取抓取视频逐帧。这可以解释它会抓取下一帧和下一帧，直到它最终赶上它正在处理时抓取的所有帧。我想知道是否有一个选项可以设置帧速率或将其设置为丢帧，然后只需单击网络摄像头中的面部图片 now 即可阅读？ http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_gui/py_video_display/py_video_display.html#capture-video-from-camera

Answer 1

如果你想显示在 OpenCV 中读取的帧，你可以借助 cv2.imshow() 函数来完成，而不需要改变颜色顺序。另一方面，如果你仍然想在matplotlib中显示图片，那么你不能避免使用这样的方法：

b,g,r = cv2.split(img)
img = cv2.merge((b,g,r))

这是我目前唯一能帮到你的事=)

Answer 2

我尝试了多线程，它同样慢，然后我只在线程中使用 .read() 进行多线程，没有处理，没有线程锁定，而且它工作得非常快 - 可能是 1 秒左右延迟，不是 3 或 5。参见 http://www.pyimagesearch.com/2015/12/21/increasing-webcam-fps-with-python-and-opencv/

from __future__ import division
import sys
from time import time, sleep
import threading

import dlib
from skimage import io


detector = dlib.get_frontal_face_detector()
win = dlib.image_window()

class webCamGrabber( threading.Thread ):
    def __init__( self ):
        threading.Thread.__init__( self )
        #Lock for when you can read/write self.image:
        #self.imageLock = threading.Lock()
        self.image = False

        from cv2 import VideoCapture, cv
        from time import time

        self.cam = VideoCapture(0)  #set the port of the camera as before
        #self.cam.set(cv.CV_CAP_PROP_FPS, 1)


    def run( self ):
        while True:
            start = time()
            #self.imageLock.acquire()
            retval, self.image = self.cam.read() #return a True bolean and and the image if all go right

            print( type( self.image) )
            #import matplotlib.pyplot as plt
            #plt.imshow(image)
            #plt.show()

            #print( "readimage: " + str( time() - start ) )
            #sleep(0.1)

if len( sys.argv[1:] ) == 0:

    #Start webcam reader thread:
    camThread = webCamGrabber()
    camThread.start()

    #Setup window for results
    detector = dlib.get_frontal_face_detector()
    win = dlib.image_window()

    while True:
        #camThread.imageLock.acquire()
        if camThread.image is not False:
            print( "enter")
            start = time()

            myimage = camThread.image
            for row in myimage:
                for px in row:
                    #rgb expected... but the array is bgr?
                    r = px[2]
                    px[2] = px[0]
                    px[0] = r


            dets = detector( myimage, 0)
            #camThread.imageLock.release()
            print "your faces: %f" % len(dets)
            for i, d in enumerate( dets ):
                print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
                    i, d.left(), d.top(), d.right(), d.bottom()))
                print("from left: {}".format( ( (d.left() + d.right()) / 2 ) / len(camThread.image[0]) ))
                print("from top: {}".format( ( (d.top() + d.bottom()) / 2 ) /len(camThread.image)) )
            print( "process: " + str( time() - start ) )

            start = time()
            win.clear_overlay()
            win.set_image(myimage)
            win.add_overlay(dets)

            print( "show: " + str( time() - start ) )
            #dlib.hit_enter_to_continue()



for f in sys.argv[1:]:
    print("Processing file: {}".format(f))
    img = io.imread(f)
    # The 1 in the second argument indicates that we should upsample the image
    # 1 time.  This will make everything bigger and allow us to detect more
    # faces.
    dets = detector(img, 1)
    print("Number of faces detected: {}".format(len(dets)))
    for i, d in enumerate(dets):
        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
            i, d.left(), d.top(), d.right(), d.bottom()))

    win.clear_overlay()
    win.set_image(img)
    win.add_overlay(dets)
    dlib.hit_enter_to_continue()


# Finally, if you really want to you can ask the detector to tell you the score
# for each detection.  The score is bigger for more confident detections.
# Also, the idx tells you which of the face sub-detectors matched.  This can be
# used to broadly identify faces in different orientations.
if (len(sys.argv[1:]) > 0):
    img = io.imread(sys.argv[1])
    dets, scores, idx = detector.run(img, 1)
    for i, d in enumerate(dets):
        print("Detection {}, score: {}, face_type:{}".format(
            d, scores[i], idx[i]))

Answer 3

我感受到你的痛苦。事实上，我最近使用了那个网络摄像头脚本（多次迭代；大量编辑）。我觉得我让它工作得很好，我想。为了让您看到我做了什么，我创建了一个包含详细信息的 GitHub Gist（代码；HTML 自述文件；示例输出）：

https://gist.github.com/victoriastuart/8092a3dd7e97ab57ede7614251bf5cbd

Answer 4

可能问题是设置了阈值。如上所述here

dots = detector(frame, 1)

应改为

dots = detector(frame)

避免门槛。这对我有用，但同时存在帧处理速度过快的问题。

这个网络摄像头面部检测有什么问题？

What's wrong with this webcam face detection?

python

opencv

webcam

dlib