real_time_object_detection.py

# USAGE
# python3.7 real_time_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel

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

# importing supporting files
from Ultrasonics import ultrasonic
from Suggestion import suggestions
import speech

# 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"]
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(src=0).start()
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])
            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)


            #To espeak remove multiline comment from beow lines.
            #print label
            print(CLASSES[idx])
            
            # print(suggestions.suggest(CLASSES[idx]) )

            # Speak the object name and suggest an action to him/her.
            text = CLASSES[idx] + " is in front of you."
            print(text)
            os.system('espeak "{}" --stdout | aplay'.format(text))
            if(suggestions.suggest(CLASSES[idx])!= ""):
                s = suggestions.suggest(CLASSES[idx])
                print("Suggetion: ", s)
                os.system('espeak "{}" --stdout | aplay'.format(s))
                # speech.speak(s)

            # calculating front distance
            dist = ultrasonic.distance(2, 3) # GPIO pin2 - trig, pin3 - echo
            print ("Measured Distance from front = %.1f cm" % dist)
            time.sleep(1)
            '''
            if(dist<40):
                glowLed(16) # GPIO pin
            '''

            # calculating left distance
            dist_left = ultrasonic.distance(17, 18) # GPIO pin - trig, pin - echo
            print("Measured Distance from left = %.1f cm" % dist_left)
            time.sleep(1)
            '''
            if(dist_left<40):
                glowLed(20) # GPIO pin
            '''

            # calculating right distance
            dist_right = ultrasonic.distance(26, 19) # GPIO pin2 - trig, pin3 - echo
            print("Measured Distance from right = %.1f cm" % dist_right)
            time.sleep(1)
            '''
            if(dist_right<40):
                glowLed(21) # GPIO pin
            '''
            
            # Notifying blind person about the availablity of space.
            d1 = "Distance available at front to you is " + str(dist)
            d2 = "Distance to your right and left is  " + str(dist_right) + str(dist_left) + "respectively"
            text1 = d1 + d2
            print(text1)
            # speech.speak(text1)
            

    # 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

    # 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()