如何使用OpenCV提高我的口罩检测项目的FPS？

Question

我正在我的树莓派上建立一个面罩探测器，但问题是视频超级滞后。有没有什么方法可以让视频输出超过1帧/秒？我是Python的新手，我正在使用我在网上找到的代码来测试它是否工作。当我正常使用Pi相机时，我得到了很好的FPS，但当我使用掩模检测器时，它给我的FPS几乎为0。任何帮助都将不胜感激！

Here is my code

from gpiozero import Buzzer, LED
from time import sleep
import sys
import RPi.GPIO as GPIO
import time
trig = 18
red = LED(14)
green = LED(15)
GPIO.setwarnings(False)
GPIO.setmode(GPIO.BCM)
GPIO.setup(trig,GPIO.OUT)
buzzer = GPIO.PWM(trig, 1000)
# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import argparse
import imutils
import time
import cv2
import os
 
def detect_and_predict_mask(frame, faceNet, maskNet):
    # grab the dimensions of the frame and then construct a blob
    # from it
    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300),
        (104.0, 177.0, 123.0))
 
    # pass the blob through the network and obtain the face detections
    faceNet.setInput(blob)
    detections = faceNet.forward()
 
    # initialize our list of faces, their corresponding locations,
    # and the list of predictions from our face mask network
    faces = []
    locs = []
    preds = []
 
    # loop over the detections
    for i in range(0, detections.shape[3]):
        # extract the confidence (i.e., probability) associated with
        # the detection
        confidence = detections[0, 0, i, 2]
 
        # filter out weak detections by ensuring the confidence is
        # greater than the minimum confidence
        if confidence > args["confidence"]:
            # compute the (x, y)-coordinates of the bounding box for
            # the object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")
 
            # ensure the bounding boxes fall within the dimensions of
            # the frame
            (startX, startY) = (max(0, startX), max(0, startY))
            (endX, endY) = (min(w - 1, endX), min(h - 1, endY))
 
            # extract the face ROI, convert it from BGR to RGB channel
            # ordering, resize it to 224x224, and preprocess it
            face = frame[startY:endY, startX:endX]
            face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
            face = cv2.resize(face, (224, 224))
            face = img_to_array(face)
            face = preprocess_input(face)
            face = np.expand_dims(face, axis=0)
 
            # add the face and bounding boxes to their respective
            # lists
            faces.append(face)
            locs.append((startX, startY, endX, endY))
 
    # only make a predictions if at least one face was detected
    if len(faces) > 0:
        # for faster inference we'll make batch predictions on *all*
        # faces at the same time rather than one-by-one predictions
        # in the above `for` loop
        preds = maskNet.predict(faces)
 
    # return a 2-tuple of the face locations and their corresponding
    # locations
    return (locs, preds)
 
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-f", "--face", type=str,
    default="face_detector",
    help="path to face detector model directory")
ap.add_argument("-m", "--model", type=str,
    default="mask_detector.model",
    help="path to trained face mask detector model")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
    help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
 
# load our serialized face detector model from disk
print("[INFO] loading face detector model...")
prototxtPath = os.path.sep.join([args["face"], "deploy.prototxt"])
weightsPath = os.path.sep.join([args["face"],
    "res10_300x300_ssd_iter_140000.caffemodel"])
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)
 
# load the face mask detector model from disk
print("[INFO] loading face mask detector model...")
maskNet = load_model(args["model"])
 
# initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream...")
#vs = VideoStream(src=0).start()
vs = VideoStream(usePiCamera=True).start()
time.sleep(1.0)
 
# loop over the frames from the video stream
while True:
    # grab the frame from the threaded video stream and resize it
    # to have a maximum width of 400 pixels
    frame = vs.read()
    frame = imutils.resize(frame, width=400)
 
    # detect faces in the frame and determine if they are wearing a
    # face mask or not
    (locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)
 
    # loop over the detected face locations and their corresponding
    # locations
    for (box, pred) in zip(locs, preds):
        # unpack the bounding box and predictions
        (startX, startY, endX, endY) = box
        (incorrect, mask, nomask) = pred
 
        # determine the class label and color we'll use to draw
        # the bounding box and text
        # label = "Mask" if mask > withoutMask else "No Mask"
        # color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
 
        if (mask > nomask):
            label = "Mask"
            color = (0, 255, 0)
            buzzer.stop()
            red.off()
            green.on()
            
        elif (nomask > mask):
            label = "No Mask"
            color = (0, 0, 255)
            buzzer.start(10)
            time.sleep(1)
            green.off()
            red.on()
            
        elif (incorrect > nomask):
            label = "Incomplete"
            color = (0, 255, 255)
            buzzer.start(10)
            time.sleep(1)
            green.off()
            red.on()
            
 
 
        # include the probability in the label
        label = "{}: {:.2f}%".format(label, max(incorrect, mask, nomask) * 100)
 
        # display the label and bounding box rectangle on the output
        # frame
        cv2.putText(frame, label, (startX, startY - 10),
            cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
        cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)
 
    # show the output frame
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
 
    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break
 
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()

Answer 1

众所周知，深度学习机器模型在解析图像时通常很慢。你有没有试过做一个Opencv的haarcascade？也许可以尝试压缩帧的分辨率，教程在这里https://www.geeksforgeeks.org/how-to-compress-images-using-python-and-pil/