For this Demo, we will use the same code, but we'll do a few tweakings. Here we are going to use OpenCV and the camera Module to use the live feed of the webcam to detect objects.

Add the OpenCV library and the camera being used to capture images. Just add the following lines to the import library section.

import cv2

cap = cv2.VideoCapture(0)

Next, we don't need to load the images from the directory and convert it to numPy array as OpenCV will take care of that for us

Remove This

for image_path in TEST_IMAGE_PATHS:

image = Image.open(image_path)

# the array based representation of the image will be used later in order to prepare the

# result image with boxes and labels on it.

image_np = load_image_into_numpy_array(image)

With

while True:

ret, image_np = cap.read()

We will not use matplotlib for final image show instead, we will use OpenCV for that as well. Now, for that,

Remove This

plt.figure(figsize=IMAGE_SIZE)

plt.imshow(image_np)

With

cv2.imshow('object detection', cv2.resize(image_np, (800,600)))

if cv2.waitKey(25) & 0xFF == ord('q'):

cv2.destroyAllWindows()

break

This code will use OpenCV that will, in turn, use the camera object initialized earlier to open a new window named "Object_Detection" of the size "800×600". It will wait for 25 milliseconds for the camera to show images otherwise, it will close the window.

Final Code with all the changes:

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

import cv2
cap = cv2.VideoCapture(0)

sys.path.append("..")

from utils import label_map_util

from utils import visualization_utils as vis_util

MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())

detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
while True:
ret, image_np = cap.read()
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)

cv2.imshow('object detection', cv2.resize(image_np, (800,600)))
if cv2.waitKey(25) 0xFF == ord('q'):
cv2.destroyAllWindows()
break