Измерение расстояния с помощью камеры Pi - PullRequest
Новая
       15

Измерение расстояния с помощью камеры Pi

0 голосов
/ 08 марта 2019

Я хочу использовать приведенный ниже код для измерения расстояния до объекта (человека), обнаруженного в потоке видео в реальном времени.

Ссылка на код: https://github.com/JamzyWang/OD/blob/master/computeDistance.py

Меня интересует, как мне обработать маркер в видеопотоке, поскольку я уже обнаружил человека, которого должен использовать в качестве маркера. Действительно ли эта функция кода нужна в моем случае? Или я должен просто начать с калибровки камеры.

И если я начну с калибровки камеры, которая в этом случае выполняется для предварительно загруженного изображения, это будет полезно

Пожалуйста, также найдите ниже код обнаружения человека, который я использовал: 

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

# import the necessary packages
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import cv2
import RPi.GPIO as GPIO
import time

GPIO.setmode(GPIO.BOARD)
LEDON = 18 # Connected to Physical pin 31 of Pi
#i=0
GPIO.setup(LEDON, GPIO.OUT) # LED Setup

# construct the argument parse and parse the arguments
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")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
    help="minimum probability to filter weak detections")
args = vars(ap.parse_args())

# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
    "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
    "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
    "sofa", "train", "tvmonitor"]

#IGNORING CLASSES
IGNORE = set(["background", "aeroplane", "bicycle", "bird", "boat",
              "bus", "car", "cat","chair", "cow", "diningtable",
          "dog", "horse", "motorbike", "pottedplant", "sheep",
          "sofa", "train", "tvmonitor"])

#CLASSES = ["chair", "person","bicycle" , "cow"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

# initialize the video stream, allow the cammera sensor to warmup,
# and initialize the FPS counter
print("[INFO] starting video stream...")
vs = VideoStream(usePiCamera=True).start() # usePiCamera = True #
time.sleep(2.0)
fps = FPS().start()

# 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)

    # grab the frame dimensions and convert it to a blob
    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),
        0.007843, (300, 300), 127.5)

    # pass the blob through the network and obtain the detections and
    # predictions
    net.setInput(blob)
    detections = net.forward()

    # loop over the detections
    for i in np.arange(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the prediction
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the `confidence` is
        # greater than the minimum confidence
        if confidence > args["confidence"]:
            # extract the index of the class label from the
            # `detections`, then compute the (x, y)-coordinates of
            # the bounding box for the object
            idx = int(detections[0, 0, i, 1])

                # if the predicted class label is in the set of classes
            # we want to ignore then skip the detection
            if CLASSES[idx] in IGNORE:
                continue

            #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")

            # draw the prediction on the frame
            label = "{}: {:.2f}%".format(CLASSES[idx],
                confidence * 100)
            cv2.rectangle(frame, (startX, startY), (endX, endY),
                COLORS[idx], 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(frame, label, (startX, y),
                cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)

            # Blow LED if Person is detected in frame
            if CLASSES[idx] == ("person"):
                               GPIO.output(LEDON, True) # LED ON
                               time.sleep(2)
                               GPIO.output(LEDON, False) # LED OFF


    # show the output frame
    Data = cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    ######
    #if Data == ("person"):
         #          GPIO.output(LEDON, True) # LED ON 


    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break

    # update the FPS counter
    fps.update()

# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()
...