-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathSocialDist_app.py
392 lines (340 loc) · 14.8 KB
/
SocialDist_app.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
import os
import math
from itertools import combinations
# comment out below line to enable tensorflow logging outputs
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import time
import tensorflow as tf
#gpu configuration
physical_devices = tf.config.experimental.list_physical_devices('GPU')
if len(physical_devices) > 0:
tf.config.experimental.set_memory_growth(physical_devices[0], True)
from absl import app,logging
import core.utils as utils
from core.yolov4 import filter_boxes
from tensorflow.python.saved_model import tag_constants
from core.config import cfg
from PIL import Image
import cv2
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
# deep sort imports
from deep_sort import preprocessing, nn_matching
from deep_sort.detection import Detection
from deep_sort.tracker import Tracker
from tools import generate_detections as gdet
#API imports
from flask_ngrok import run_with_ngrok
from flask import Flask, flash, request, redirect, url_for, render_template, Response
from werkzeug.utils import secure_filename
# customize API with the parameters
framework = 'tf'
weights = './checkpoints/yolov4-416'
size = 416
tiny = False
model = 'yolov4'
output = './static/outputs/output.avi'
output_format = 'XVID'
iou = 0.45
score = 0.50
dont_show = True
info = True
count = True
violations = []
track_cnt = 0
fps = 0
UPLOAD_FOLDER = './static/uploads'
ALLOWED_EXTENSIONS = {'gif', 'webm', 'mp4', 'mov', 'avi'}
app1 = Flask(__name__)
app1.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
run_with_ngrok(app1)
def allowed_file(filename):
return '.' in filename and \
filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
@app1.route('/', methods=['GET', 'POST'])
def upload_file():
global cap_stream1
global vid_stream1
if request.method == 'POST':
# check if the post request has the file part
if 'file' not in request.files:
flash('No file part')
return redirect(request.url)
file = request.files['file']
# If the user does not select a file, the browser submits an
# empty file without a filename.
if file.filename == '':
flash('No selected file')
return redirect(request.url)
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
vid_stream1 = os.path.join(app1.config['UPLOAD_FOLDER'], filename)
file.save(vid_stream1)
cap_stream1 = cv2.VideoCapture(vid_stream1)
return redirect(url_for('stream', file='show_vdo.html'))
#return "Uploaded successfully"
#return redirect(url_for('download_file', name=filename))
return '''
<!doctype html>
<title>uploading</title>
<h1>Please choose a video from Stanford Dataset</h1>
<form method=post enctype=multipart/form-data>
<input type=file name=file>
<input type=submit value=Upload>
</form>
'''
#cap = cv2.VideoCapture(vid)
def generate_frames(cap):
while True:
success, frame = cap.read()
if not success:
break
else:
ret, buffer = cv2.imencode('.jpg', frame)
frame = buffer.tobytes()
yield(b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + frame + b'\r\n')
def generate_output(f):
ret, buffer = cv2.imencode('.jpg', f)
_frame = buffer.tobytes()
yield(b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + _frame + b'\r\n')
@app1.route("/stream")
def stream():
return render_template('show_vdo.html')
@app1.route('/video')
def stream_video():
return Response(generate_frames(cap_stream1), mimetype='multipart/x-mixed-replace; boundary=frame')
@app1.route("/stream2")
def stream2():
return render_template('monitor.html', v=len(violations), track_cnt=str(track_cnt), _fp=fps)
@app1.route('/violations')
def main():
# Definition of the parameters
max_cosine_distance = 0.4
nn_budget = None
nms_max_overlap = 0.8
# initialize deep sort
model_filename = 'model_data/mars-small128.pb'
encoder = gdet.create_box_encoder(model_filename, batch_size=1)
# calculate cosine distance metric
metric = nn_matching.NearestNeighborDistanceMetric("cosine", max_cosine_distance, nn_budget)
# initialize tracker
tracker = Tracker(metric)
# load configuration for object detector
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
#STRIDES, ANCHORS, NUM_CLASS, XYSCALE = utils.load_config(FLAGS)
input_size = size
video_path = vid_stream1
# load tflite model if flag is set
if framework == 'tflite':
interpreter = tf.lite.Interpreter(model_path=weights)
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
print(input_details)
print(output_details)
# otherwise load standard tensorflow saved model
else:
saved_model_loaded = tf.saved_model.load(weights, tags=[tag_constants.SERVING])
infer = saved_model_loaded.signatures['serving_default']
# begin video capture
try:
vid = cv2.VideoCapture(int(video_path))
except:
vid = cv2.VideoCapture(video_path)
out = None
'''def fourcc(a,b,c,d):
return ((ord(a) & 255) + ((ord(b) & 255) << 8) + ((ord(c) & 255) << 16) + ((ord(d) & 255) << 24))'''
# get video ready to save locally if flag is set
if output:
# by default VideoCapture returns float instead of int
height = int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT))
width = int(vid.get(cv2.CAP_PROP_FRAME_WIDTH))
fps = int(vid.get(cv2.CAP_PROP_FPS))
codec = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter(output, codec, fps, (width, height))
frame_num = 0
#violations=[]
total_ped = []
# while video is running
while True:
return_value, frame = vid.read()
if return_value:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = Image.fromarray(frame)
else:
return 'Video has ended or failed, try a different video format!'
break
frame_num +=1
print('Frame #: ', frame_num)
frame_size = frame.shape[:2]
image_data = cv2.resize(frame, (input_size, input_size))
image_data = image_data / 255.
image_data = image_data[np.newaxis, ...].astype(np.float32)
start_time = time.time()
# run detections on tflite if flag is set
if framework == 'tflite':
interpreter.set_tensor(input_details[0]['index'], image_data)
interpreter.invoke()
pred = [interpreter.get_tensor(output_details[i]['index']) for i in range(len(output_details))]
# run detections using yolov3 if flag is set
if model == 'yolov3' and tiny == True:
boxes, pred_conf = filter_boxes(pred[1], pred[0], score_threshold=0.25,
input_shape=tf.constant([input_size, input_size]))
else:
boxes, pred_conf = filter_boxes(pred[0], pred[1], score_threshold=0.25,
input_shape=tf.constant([input_size, input_size]))
else:
batch_data = tf.constant(image_data)
pred_bbox = infer(batch_data)
for key, value in pred_bbox.items():
boxes = value[:, :, 0:4]
pred_conf = value[:, :, 4:]
boxes, scores, classes, valid_detections = tf.image.combined_non_max_suppression(
boxes=tf.reshape(boxes, (tf.shape(boxes)[0], -1, 1, 4)),
scores=tf.reshape(
pred_conf, (tf.shape(pred_conf)[0], -1, tf.shape(pred_conf)[-1])),
max_output_size_per_class=50,
max_total_size=50,
iou_threshold=iou,
score_threshold=score
)
# convert data to numpy arrays and slice out unused elements
num_objects = valid_detections.numpy()[0]
bboxes = boxes.numpy()[0]
bboxes = bboxes[0:int(num_objects)]
scores = scores.numpy()[0]
scores = scores[0:int(num_objects)]
classes = classes.numpy()[0]
classes = classes[0:int(num_objects)]
# format bounding boxes from normalized ymin, xmin, ymax, xmax ---> xmin, ymin, width, height
original_h, original_w, _ = frame.shape
bboxes = utils.format_boxes(bboxes, original_h, original_w)
# store all predictions in one parameter for simplicity when calling functions
pred_bbox = [bboxes, scores, classes, num_objects]
# read in all class names from config
class_names = utils.read_class_names(cfg.YOLO.CLASSES)
# by default allow all classes in .names file
#allowed_classes = list(class_names.values())
# custom allowed classes (uncomment line below to customize tracker for only people)
allowed_classes = ['pedestrian', 'biker']
# loop through objects and use class index to get class name, allow only classes in allowed_classes list
names = []
deleted_indx = []
for i in range(num_objects):
class_indx = int(classes[i])
class_name = class_names[class_indx]
if class_name not in allowed_classes:
deleted_indx.append(i)
else:
names.append(class_name)
names = np.array(names)
count = len(names)
if count:
cv2.putText(frame, "Objects being tracked: {}".format(count), (5, 35), cv2.FONT_HERSHEY_COMPLEX_SMALL, 2, (0, 255, 0), 2)
print("Objects being tracked: {}".format(count))
# delete detections that are not in allowed_classes
bboxes = np.delete(bboxes, deleted_indx, axis=0)
scores = np.delete(scores, deleted_indx, axis=0)
# encode yolo detections and feed to tracker
features = encoder(frame, bboxes)
detections = [Detection(bbox, score, class_name, feature) for bbox, score, class_name, feature in zip(bboxes, scores, names, features)]
#initialize color map
cmap = plt.get_cmap('tab20b')
colors = [cmap(i)[:3] for i in np.linspace(0, 1, 20)]
# run non-maxima supression
boxs = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
classes = np.array([d.class_name for d in detections])
indices = preprocessing.non_max_suppression(boxs, classes, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
# Call the tracker
tracker.predict()
tracker.update(detections)
#initializing a list of centers
centroids = []
# update tracks
for track in tracker.tracks:
if not track.is_confirmed() or track.time_since_update > 1:
continue
bbox = track.to_tlbr()
class_name = track.get_class()
x_min = int((bbox[0]))
y_min = int((bbox[1]))
x_max = int((bbox[2]))
y_max = int((bbox[3]))
x_center = int(x_min+((x_max-x_min)/2))
y_center = int(y_min+((y_max-y_min)/2))
_centroid = (x_center, y_center)
centroids.append(_centroid)
#total_ped+=1
#print(centroids)
if info:
tped=track.track_id
if not tped in total_ped:
total_ped.append(tped)
for centers in combinations(centroids, 2):
c1, c2 = centers
x1, y1 = c1
x2, y2 = c2
if social_dist(c1, c2)<=45:
cv2.circle(frame, (x1,y1), radius=7,color = (255,0,0), thickness=-1)
cv2.circle(frame, (x2,y2), radius=7,color = (255,0,0), thickness=-1)
if info:
print("Tracker ID: {}, Class: {}, BBox Coords (x_center. y_center): {}".format(str(track.track_id), class_name, (c1, c2)))
ped = track.track_id
if not ped in violations:
violations.append(ped)
'''else:
cv2.circle(frame, (x1,y1), radius=5,color = (0,255,0), thickness=-1)
#cv2.circle(frame, (x2,y2), radius=5,color = (0,255,0), thickness=-1)'''
#cv2.rectangle(frame,(0,0), (70,70 ), (255,255,255), -1)
cv2.rectangle(frame,(10,5),(315,70),(102, 102, 255), -1)
cv2.putText(frame, "violations: "+ str(len(violations)), (30,30), 0, 1, (255,255,255), 2)
cv2.putText(frame, "Total person: "+ str(track.track_id),(30,60), 0, 1, (255,255,255), 2)
track_cnt = track.track_id
# draw dot on screen
#color = (0,0,255)
#color = colors[int(track.track_id) % len(colors)]
#color = [i * 255 for i in color]
#cv2.rectangle(frame, (int(bbox[0]), int(bbox[1])), (int(bbox[2]), int(bbox[3])), color, 2)
#cv2.rectangle(frame, (int(bbox[0]), int(bbox[1]-30)), (int(bbox[0])+(len(class_name)+len(str(track.track_id)))*17, int(bbox[1])), color, -1)
#cv2.putText(frame, class_name + "-" + str(track.track_id),(int(bbox[0]), int(bbox[1]-10)),0, 0.75, (255,255,255),2)
# if enable info flag then print details about each track
'''if FLAGS.info:
print("Tracker ID: {}, Class: {}, BBox Coords (x_center. y_center): {}".format(str(track.track_id), class_name, (c1, c2)))
else:
cv2.circle(frame, (x1,y1), radius=5,color = (0,255,0), thickness=-1)
cv2.circle(frame, (x2,y2), radius=5,color = (0,255,0), thickness=-1)'''
# calculate frames per second of running detections
fps = 1.0 / (time.time() - start_time)
print("FPS: %.2f" % fps)
result = np.asarray(frame)
result = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
#cv2.putText(frame, "violations: "+ str(violations),(30,30), 0, 1, (0,255,0), 2)
if not dont_show:
cv2.imshow("Output Video", result)
# if output flag is set, save video file
if output:
out.write(result)
if cv2.waitKey(1) & 0xFF == ord('q'): break
cv2.destroyAllWindows()
#output_vid = './static/outputs/output.avi'
#cap_outout = cv2.VideoCapture(output_vid)
#return Response(generate_output(frame), mimetype='multipart/x-mixed-replace; boundary=frame')
#print( len(violations), str(track.track_id), fps)
return '''<!doctype html>
<p>{{len(violations)}} Violations found. Total {{track_cnt}} person tracked</p>'''
#claculate the social distances
def social_dist(center1, center2):
x1, y1 = center1
x2, y2 = center2
dist_ = math.sqrt((x2-x1)**2 + (y2-y1)**2)
return dist_
if __name__ == '__main__':
app1.run()