Real-time counter using Tensorflow object detection API - tensorflow

Question

Im currently working on real-time object detection using tensorflow API.I've gotten that figured out, but right now I would like to add in object counter. So, I'll have real-time object detection + counter.
The source code for object detection was taken from tensorflow ipynb tutorial and I added OpenCV for real-time detection. I've merged the real-time detection source code with the counter source code where initially it was for vehicle counting from this guy's repo.
So, my current output: No error and no output. But my webcam light flickers which shows it's being used so the opencv part is working. Could anyone take a look the code and help me figure what's wrong? It'd be a really great help. Thank you in advance.
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import csv
import time
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
import cv2
cap = cv2.VideoCapture(0)
# initialize .csv
with open('traffic_measurement.csv', 'w') as f:
writer = csv.writer(f)
csv_line = \
'Person Movement Direction'
writer.writerows([csv_line.split(',')])
# Variables to count persons
total_passed_person = 0
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# ## Object detection imports
# Here are the imports from the object detection module.
from utils import label_map_util
from utils import visualization_utils as vis_util
# # Model preparation
# What model to download.
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
# ## Download Model
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())
# ## Load a (frozen) Tensorflow model into memory.
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='')
# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we
know
that this corresponds to `airplane`. Here we use internal utility functions, but anything that
returns
a dictionary mapping integers to appropriate string labels would be fine
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)
# ## Helper code
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
# Detection
def object_detection_function():
total_passed_person = 0
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(input_frame, 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')
# for all the frames that are extracted from input video
while cap.isOpened():
(ret,frame) = cap.read()
if not ret:
print ('end of the video file...')
break
input_frame = frame
# 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.
(counter, csv_line) = \
vis_util.visualize_boxes_and_labels_on_image_array(
cap.get(1),
input_frame,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
total_passed_person = total_passed_person + counter
# insert information text to video frame
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(
input_frame,
'Detected Persons: ' + str(total_passed_person),
(10, 35),
font,
0.8,
(0, 0xFF, 0xFF),
2,
cv2.FONT_HERSHEY_SIMPLEX,
)
# when the vehicle passed over line and counted, make the color of ROI line green
if counter == 1:
cv2.line(input_frame, (0, 200), (640, 200), (0, 0xFF, 0), 5)
else:
cv2.line(input_frame, (0, 200), (640, 200), (0, 0, 0xFF), 5)
# insert information text to video frame
cv2.rectangle(input_frame, (10, 275), (230, 337), (180, 132, 109), -1)
cv2.putText(
input_frame,
'ROI Line',
(545, 190),
font,
0.6,
(0, 0, 0xFF),
2,
cv2.LINE_AA,
)
cv2.putText(
input_frame,
'-Movement Direction: ' + direction,
(14, 302),
font,
0.4,
(0xFF, 0xFF, 0xFF),
1,
cv2.FONT_HERSHEY_COMPLEX_SMALL,
)
if csv_line != 'not_available':
with open('traffic_measurement.csv', 'a') as f:
writer = csv.writer(f)
(direction) = \
csv_line.split(',')
writer.writerows([csv_line.split(',')])
cv2.imshow('object detection',cv2.resize(input_frame, (800,600)))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break