facemask_detection.py

# 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
import time
# import drone_config


def get_facenet_masknet():
    # 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"])
    prototxtPath = (
        '/Users/USER/Documents/DroneProjects/facemaskdetection/face_detector/deploy.prototxt')
    # weightsPath = os.path.sep.join([args["face"],
    #                                 "res10_300x300_ssd_iter_140000.caffemodel"])
    weightsPath = (
        '/Users/USER/Documents/DroneProjects/facemaskdetection/face_detector/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(
        '/Users/USER/Documents/DroneProjects/facemaskdetection/mask_detector.model')
    return(faceNet, maskNet, args)


def detect_and_predict_mask(frame, faceNet, maskNet, args):
    # 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[2]):
        # 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)

            # 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
        faces = np.array(faces, dtype="float32")
        preds = maskNet.predict(faces, batch_size=32)

    # return a 2-tuple of the face locations and their corresponding
    # locations
    return (locs, preds)