human detect

# USAGE
# python pi_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel

from multiprocessing import Process, Queue
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import datetime
import time
import cv2

def classify_frame(net, inputQueue, outputQueue):
    print("[INFO] starting classify process...")
    while True:
        if not inputQueue.empty():
            frame = inputQueue.get()
            frame = cv2.resize(frame, (300, 300))
            blob = cv2.dnn.blobFromImage(frame, 0.007843, (300, 300), 127.5)

            net.setInput(blob)
            detections = net.forward()

            outputQueue.put(detections)
        time.sleep(2)

def write_frame(writeQueue, startQueue):
    print("[INFO] starting write process...")
    fourcc = cv2.VideoWriter_fourcc('M','J','P','G') #*'MJPG'
    out = cv2.VideoWriter('output.avi', fourcc, 20, (640, 480), True)

    while True:
        if not writeQueue.empty():
            frame = writeQueue.get()
            out.write(frame)
    out.release()

ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True, help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True, help="path to Caffe pre-trained model")
args = vars(ap.parse_args())

CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
    "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
    "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
    "sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

inputQueue = Queue(maxsize=1)
outputQueue = Queue(maxsize=1)
writeQueue = Queue(maxsize=1)
startQueue = Queue(maxsize=1)

detections = None
confidence_set = 0.8
count = 0

print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

print("[INFO] starting process...")
p = Process(target=classify_frame, args=(net, inputQueue, outputQueue,))
p.daemon = True
p.start()
w = Process(target=write_frame, args=(writeQueue, startQueue))
w.daemon = True
w.start()

print("[INFO] starting video stream...")
vs = cv2.VideoCapture(0)
fps = FPS().start()

global fW, fH, framerate
fW = vs.get(3)
print ("[INFO] fW:", fW)
fH = vs.get(4)
print ("[INFO] fH:", fH)
framerate = vs.get(5)
print ("[INFO] ramerate:", framerate)

while True:
    ret, frame = vs.read()
    if ret == True:
        if inputQueue.empty():
            inputQueue.put(frame)
        if not outputQueue.empty():
            detections = outputQueue.get()

        cv2.putText(frame, datetime.datetime.now().strftime("%c"), (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 1)

        if detections is not None:
            for i in np.arange(0, detections.shape[2]):
                confidence = detections[0, 0, i, 2]

                if confidence > confidence_set:

                    idx = int(detections[0, 0, i, 1])

                    label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)

                    if idx == 8 or idx == 12 or idx == 15:
                        print(label)
                        count = 100

        if count > 1:# счетчик для записи кадров после пропадания объекта из кадра
            writeQueue.put(frame)
            count -= 1
            print(count)
        cv2.imshow("Camera", frame)
        key = cv2.waitKey(1) & 0xFF
        if key == ord("q"):
            break
    else:
        break
    fps.update()

fps.stop()
vs.release()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
cv2.destroyAllWindows()