Custom-Object-Detection/Object Detection demo.py at master · Giscle/Custom-Object-Detection · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
"""
Credit to the Tensorflow Team for the Object Detection API
Written by Sagar Jaiswal

You need to have the Tensorflow Object Detection API installed for this code to work
This file needs to be stored in the Object Detection folder of Object Detection API
"""

from utils import label_map_util
from utils import visualization_utils as vis_util
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import cv2

sys.path.append("..")
cap = cv2.VideoCapture("input_video.mp4")
fps = 30
capSize = (640, 480)
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
out = cv2.VideoWriter()
success = out.open('output_video.mp4',fourcc,fps,capSize,True)

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_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
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)


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)


with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    while cap.isOpened():
      ret, image_np = cap.read()
      if ret == True:
          image_np_expanded = np.expand_dims(image_np, axis=0)
          image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
          boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
          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')
          (boxes, scores, classes, num_detections) = sess.run(
              [boxes, scores, classes, num_detections],
              feed_dict={image_tensor: image_np_expanded})
          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)
          out.write(image_np)
          if cv2.waitKey(25) & 0xFF == ord('q'):
              cv2.destroyAllWindows()
              break
      else:
          break

cap.release()
out.release()
cv2.destroyAllWindows()