camera.py

import cv2
import tensorflow as tf
from keras.applications.mobilenet_v2 import preprocess_input
from keras.preprocessing.image import img_to_array
from 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 numpy as np

facec = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
#model = FacialExpressionModel("model.json", "model_weights.h5")
font = cv2.FONT_HERSHEY_SIMPLEX

class VideoCamera(object):
    def __init__(self):
        #self.video = cv2.VideoCapture(0)
        # load our serialized face detector model from disk
        self.prototxtPath = 'face_detector/deploy.prototxt'
        self.weightsPath = "face_detector/res10_300x300_ssd_iter_140000.caffemodel"
        self.faceNet = cv2.dnn.readNet(self.prototxtPath, self.weightsPath)
        # load the face mask detector model from disk
        self.maskNet = tf.keras.models.load_model("model.h5")
        # initialize the video stream and allow the camera sensor to warm up
        self.vs = VideoStream(src=0).start()
        time.sleep(2.0)

    def __del__(self):
        #self.video.release()
        self.vs.stop()

    def detect_and_predict_mask(self):
        # grab the dimensions of the frame and then construct a blob
        # from it
        frame=self.vs.read()
        (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
        self.faceNet.setInput(blob)
        detections = self.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 > 0.5:
                # 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 = self.maskNet.predict(faces)

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


    # returns camera frames along with bounding boxes and predictions
    def get_frame(self):
        frame = self.vs.read()
        # detect faces in the frame and determine if they are wearing a
        # face mask or not
        (locs, preds) = self.detect_and_predict_mask()

        # 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
            (mask, withoutMask) = 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)

            # include the probability in the label
            label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 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
        _, jpeg = cv2.imencode('.jpg', frame)
        return jpeg.tobytes()