/
SecondObject_detection_webcam.py
564 lines (471 loc) · 21.4 KB
/
SecondObject_detection_webcam.py
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
######## Webcam Object Detection Using Tensorflow-trained Classifier #########
#
# Author: Evan Juras
# Date: 1/20/18
# Description:
# This program uses a TensorFlow-trained classifier to perform object detection.
# It loads the classifier uses it to perform object detection on a webcam feed.
# It draws boxes and scores around the objects of interest in each frame from
# the webcam.
## Some of the code is copied from Google's example at
## https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb
## and some is copied from Dat Tran's example at
## https://github.com/datitran/object_detector_app/blob/master/object_detection_app.py
## but I changed it to make it more understandable to me.
# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from PIL import Image
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
#set PYTHONPATH=C:\tensorflow1\models;C:\tensorflow1\models\research;C:\tensorflow1\models\research\slim
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
# Number of classes the object detector can identify
NUM_CLASSES = 5
## Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# 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)
# Load the 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='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,1280)
ret = video.set(4,720)
img=Image.open('checkSize.jpg')
width, height = img.size
print(width)
print(height)
flagSide = 'left'
while(True):
# Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
ret, frame = video.read()
frame_expanded = np.expand_dims(frame, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: frame_expanded})
if len(classes[0] > 0):
listOf4Indexes = np.where(classes[0] == 4)
#print(listOf4Indexes)
# print(len(classes[0]))
# print(len(listOf4Indexes[0]))
# print('len(boxes)={} len(boxes[0])={} len(boxes[0][0]={}'.format(len(boxes),len(boxes[0]),len(boxes[0][0])))
c = np.zeros(shape=(1,len(classes[0])-len(listOf4Indexes[0])))
b = np.zeros((1,len(classes[0])-len(listOf4Indexes[0]),4))
s = np.zeros(shape=(1,len(classes[0])-len(listOf4Indexes[0])))
for FourIndex in listOf4Indexes:
# classes[0]=np.delete(classes[0],FourIndex
# boxes[0]=np.delete(boxes[0],FourIndex)
# scores[0]=np.delete(scores[0],FourIndex)
c[0]=np.delete(classes[0],FourIndex)
b[0]=np.delete(boxes,FourIndex,axis=1)
s[0]=np.delete(scores[0],FourIndex)
# print(len(c[0]))
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
np.squeeze(b),
np.squeeze(c).astype(np.int32),
np.squeeze(s),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.60)
#print(boxes[0][1])
if classes[0][0] == 2 and scores[0][0] > 0.96:
print('I see a Wallet')
if width * boxes[0][0][1] <= width/2:
flagSide = 'left'
#imageName = 'left-'+imageName
#print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
else :
flagSide = 'right'
#print('Wallet is on {} side'.format(flagSide))
#imageName = 'right-'+imageName
#print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
print('Wallet is on {} side'.format(flagSide))
# All the results have been drawn on the frame, so it's time to display it.
cv2.namedWindow('Object detector', cv2.WINDOW_NORMAL)
cv2.resizeWindow('Object detector',800,600)
cv2.imshow('Object detector', frame)
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
video.release()
cv2.destroyAllWindows()
#----------------------------------------------------------------------------------------------------------------------------------------------------------
MODEL_NAME = 'inferenceGraphs/inference_graphWithUnknown'
IMAGES_NAME = []
# Grab path to current working directory111
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
#taking new images for registering an object------------------------------------------
cam = cv2.VideoCapture(0)
cv2.namedWindow('test')
img_counter = 0
while True:
ret,frame = cam.read()
cv2.imshow("test",frame)
if not ret:
break
k = cv2.waitKey(1)
if k%256 == 27:
print("Escape hit...")
break
elif k%256 == 32:
img_name = "Took_Image_{}.jpg".format(img_counter)
cv2.imwrite(img_name,frame)
print("{} written!".format(img_name))
img_counter += 1
cam.release()
cv2.destroyAllWindows()
import pdb; pdb.set_trace()
#-----------------------------------------------------------------------------------
#creating augmented images----------------------------------------------------------
types = ('newImagesForAugment\*jpg','newImagesForAugment\*jpeg')
for files in types:
IMAGES_NAME.extend(glob.glob(files))
# Path to image
sess1 = tf.Session()
for singleImage in IMAGES_NAME:
img = pt.imread(singleImage)
tf_img = tf.convert_to_tensor(img)
brght_img = tf.image.flip_left_right(tf_img)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'output2.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite)
brght_img = tf.image.transpose_image(tf_img)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'transposed.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite)
brght_img = tf.image.rot90(tf_img)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'rot90.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite)
brght_img = tf.image.rot90(tf_img,k=3)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'rot90.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite) #central_crop
brght_img = tf.image.central_crop(tf_img,0.70)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'centralcropped.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite)
# brght_img = tf.contrib.image.rotate(tf_img, 30 * math.pi / 180, interpolation='BILINEAR')
# fileToSave = tf.image.encode_jpeg(brght_img)
# fname = tf.constant(singleImage.split('.')[0]+'30degrees.jpg')
# fwrite = tf.write_file(fname,fileToSave)
# result = sess1.run(fwrite)
src_im = Image.open(singleImage)
rotated = scipy.ndimage.rotate(src_im, 20, cval=210)
scipy.misc.imsave(singleImage.split('.')[0]+'rotatedTest.jpg', rotated)
img = pt.imread(singleImage.split('.')[0]+'rotatedTest.jpg')
tf_img = tf.convert_to_tensor(img)
brght_img = tf.image.central_crop(tf_img,0.60)
fileToSave = tf.image.encode_jpeg(brght_img)
fname = tf.constant(singleImage.split('.')[0]+'rotatedTest.jpg')
fwrite = tf.write_file(fname,fileToSave)
result = sess1.run(fwrite)
# angle = 45
# size = 200, 200
# dst_im = Image.new("RGBA", (196,283), "blue" )
# im = src_im.convert('RGBA')
# rot = im.rotate( angle, expand=1 ).resize(size)
# dst_im.paste( rot, (0, 0), rot )
# dst_im = dst_im.convert('RGB')
# dst_im.save(singleImage.split('.')[0]+'45bllue.jpg','JPEG')
# Number of classes the object detector can identify
#--------------------------------------------------------------------------------------------
#Object detection----------------------------------------------------------------------------
import pdb; pdb.set_trace()
NUM_CLASSES = 4
IMAGES_NAME = []
types = ('newImagesForAugment\*jpg','newImagesForAugment\*jpeg')
for files in types:
IMAGES_NAME.extend(glob.glob(files))
# Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# 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)
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='')
sess = tf.Session(graph=detection_graph)
for singleImage in IMAGES_NAME:
PATH_TO_IMAGE = os.path.join(CWD_PATH,singleImage)
# Load the Tensorflow model into memory.
im = Image.open(PATH_TO_IMAGE)
width, height = im.size
print(width)
print(height)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Load image using OpenCV and
# expand image dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
image = cv2.imread(PATH_TO_IMAGE)
image_expanded = np.expand_dims(image, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_expanded})
tempBoxes = np.copy(boxes)
# Draw the results of the detection (aka 'visulaize the results')
obj_count = 1
print(boxes)
print(boxes[0][0:obj_count][:])
boxes= boxes[0][0:obj_count][:]
#print(boxes[0])
i = 0
while i < len(boxes[0]):
if i % 2 == 0:
boxes[0][i] = (height * boxes[0][i]).astype(np.int32)
else:
boxes[0][i] = (width * boxes[0][i]).astype(np.int32)
i += 1
#print(classes)
#print(tempBoxes)
#print(singleImage)
#print(PATH_TO_IMAGE)
imageName = singleImage.split('\\')[1]
#print(imageName)
vis_util.visualize_boxes_and_labels_on_image_array(
image,
np.squeeze(tempBoxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.50)
#--------------------------------------------------------------------------------------
if classes[0][0] == 2 and scores[0][0] > 0.96:
print('I see a Wallet')
if boxes[0][1] <= width/2:
print('Wallet is on left side')
imageName = 'left-'+imageName
print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
else :
print('Wallet is on right side')
imageName = 'right-'+imageName
print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
#Saving new xml annotated image--------------------------------------------------------
# All the results have been drawn on image. Now display the image.
#cv2.imshow('Object detector', image)
filepath = os.path.join(singleImage.split('\\')[0]+'\\annotatedImages\\',imageName)
print(filepath)
cv2.imwrite(filepath,image)
root = ET.Element("annotation")
folder = ET.SubElement(root, "folder")
folder.text = singleImage.split('\\')[0]
filename = ET.SubElement(root, "filename")
filename.text = imageName
path = ET.SubElement(root, "path")
path.text = PATH_TO_IMAGE
source = ET.SubElement(root, "source")
ET.SubElement(source, "database").text = "Unknown"
size = ET.SubElement(root, "size")
ET.SubElement(size, "width").text = str(width)
ET.SubElement(size, "height").text = str(height)
ET.SubElement(size, "depth").text = "3"
segmented = ET.SubElement(root, "segmented")
segmented.text = "0"
objectTag = ET.SubElement(root, "object")
name = ET.SubElement(objectTag,"name")
name.text = "tempClass1"
pose = ET.SubElement(objectTag,"pose")
pose.text = "Unspecified"
truncated = ET.SubElement(objectTag,"truncated")
truncated.text = "0"
difficult = ET.SubElement(objectTag,"difficult")
difficult.text = "0"
bndbox = ET.SubElement(objectTag,"bndbox")
ET.SubElement(bndbox, "xmin").text = str(boxes[0][1])
ET.SubElement(bndbox, "ymin").text = str(boxes[0][0])
ET.SubElement(bndbox, "xmax").text = str(boxes[0][3])
ET.SubElement(bndbox, "ymax").text = str(boxes[0][2])
tree = ET.ElementTree(root)
finalFileName = 'newImagesForAugment\\'+imageName.split('.')[0] + '.xml'
tree.write(finalFileName)
#time.sleep(2)
#---------------------------------------------------------------------------------------------
# Press any key to close the image
#cv2.waitKey(0)
# Clean up
#cv2.destroyAllWindows()
import pdb; pdb.set_trace()
#---------------------------------------------------------------------------------------------------------------------------------------------------------
MODEL_NAME = 'inference_graph'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
#set PYTHONPATH=C:\tensorflow1\models;C:\tensorflow1\models\research;C:\tensorflow1\models\research\slim
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
# Number of classes the object detector can identify
NUM_CLASSES = 6
## Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# 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)
# Load the 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='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,1280)
ret = video.set(4,720)
img=Image.open('checkSize.jpg')
width, height = img.size
print(width)
print(height)
flagSide = 'left'
while(True):
# Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
ret, frame = video.read()
frame_expanded = np.expand_dims(frame, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: frame_expanded})
if len(classes[0] > 0):
listOf4Indexes = np.where(classes[0] == 4)
#print(listOf4Indexes)
# print(len(classes[0]))
# print(len(listOf4Indexes[0]))
# print('len(boxes)={} len(boxes[0])={} len(boxes[0][0]={}'.format(len(boxes),len(boxes[0]),len(boxes[0][0])))
c = np.zeros(shape=(1,len(classes[0])-len(listOf4Indexes[0])))
b = np.zeros((1,len(classes[0])-len(listOf4Indexes[0]),4))
s = np.zeros(shape=(1,len(classes[0])-len(listOf4Indexes[0])))
for FourIndex in listOf4Indexes:
# classes[0]=np.delete(classes[0],FourIndex
# boxes[0]=np.delete(boxes[0],FourIndex)
# scores[0]=np.delete(scores[0],FourIndex)
c[0]=np.delete(classes[0],FourIndex)
b[0]=np.delete(boxes,FourIndex,axis=1)
s[0]=np.delete(scores[0],FourIndex)
# print(len(c[0]))
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
np.squeeze(b),
np.squeeze(c).astype(np.int32),
np.squeeze(s),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.60)
#print(boxes[0][1])
if classes[0][0] == 2 and scores[0][0] > 0.96:
print('I see a Wallet')
if width * boxes[0][0][1] <= width/2:
flagSide = 'left'
#imageName = 'left-'+imageName
#print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
else :
flagSide = 'right'
#print('Wallet is on {} side'.format(flagSide))
#imageName = 'right-'+imageName
#print('width/2={} boxes[0][1]={}'.format(width/2,boxes[0][1]))
print('Wallet is on {} side'.format(flagSide))
# All the results have been drawn on the frame, so it's time to display it.
cv2.namedWindow('Object detector', cv2.WINDOW_NORMAL)
cv2.resizeWindow('Object detector',800,600)
cv2.imshow('Object detector', frame)
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
video.release()
cv2.destroyAllWindows()