def predict_height():
if request.method == 'POST':
if 'file' not in request.files:
return 'Error: No file part, please try again'
file = request.files['file']
if file.filename == '':
return 'Error: No file name, please try again'
if file and allowed_file(file.filename):
K.clear_session()
img, result_df = object_detector([file.filename], [file])
if len(img) == 0:
return 'Error: Image could not be used.'
# format image for return in html
img = img[file.filename]
tag = create_tag(img)
# scale and clean data
scaler = load('models/scaler.joblib')
try:
result_df['banana_box'] = result_df[[
'banana_box_point1', 'banana_box_point2',
'banana_box_point3', 'banana_box_point4'
]].mean(axis=1)
result_df['person_box'] = result_df[[
'person_box_point1', 'person_box_point2',
'person_box_point3', 'person_box_point4'
]].mean(axis=1)
X = scaler.transform(result_df.drop(columns=['filename']))
except:
return '''
<!DOCTYPE html>
<img src={0} class="img-responsive" width='400'>
<p>Error: A prediction could not be made using this image
<br>
<i>Either a banana or person could not be detected.</i></p>'''.format(
tag)
# make final prediction with random forest
model = load('models/randomforest.joblib')
pred = model.predict(X)[0]
ft = int(pred // 12)
inch = round(pred % 12, 1)
return render_template('prediction_answer.html',
variable=[f'{ft} ft {inch} in', '', tag])
else:
return redirect(request.url)
return render_template('prediction.html',
Title='Height Prediction with Object Detection')
def process(args):
objects_detected = dict()
"""
#tracker_types = ['BOOSTING', 'MIL','KCF', 'TLD', 'MEDIANFLOW', 'GOTURN']
#tracker_type = tracker_types[2]
#tracker = None
if tracker_type == 'BOOSTING':
tracker = cv.TrackerBoosting_create()
if tracker_type == 'MIL':
tracker = cv.TrackerMIL_create()
if tracker_type == 'KCF':
tracker = cv.TrackerKCF_create()
if tracker_type == 'TLD':
tracker = cv.TrackerTLD_create()
if tracker_type == 'MEDIANFLOW':
tracker = cv.TrackerMedianFlow_create()
if tracker_type == 'GOTURN':
tracker = cv.TrackerGOTURN_create()
"""
predictor = object_detector(args.model, args.config)
stream = cv.VideoCapture(args.input if args.input else 0)
window_name = "Tracking in progress"
cv.namedWindow(window_name, cv.WINDOW_NORMAL)
cv.setWindowProperty(window_name, cv.WND_PROP_AUTOSIZE, cv.WINDOW_AUTOSIZE)
cv.moveWindow(window_name,10,10)
if args.output:
_, test_frame = stream.read()
height = test_frame.shape[0]
width = test_frame.shape[1]
fourcc = cv.VideoWriter_fourcc(*'XVID')
#out = cv.VideoWriter(args.output,fourcc, 20.0, (640,480))
out = cv.VideoWriter(args.output,fourcc, 20.0, (width,height))
failTolerance = 0
if args.classes:
with open(args.classes, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
else:
classes = list(np.arange(0,100))
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(stream, predictor, args.thr, classes)
while stream.isOpened():
grabbed, frame = stream.read()
if not grabbed:
break
timer = cv.getTickCount()
"""
#Did not use OpenCV's multitracker because of the restrivtive nature of its Python counterpart.
#If one tracker in the multitracker fails, there's no way to find out which tracker failed.
#There's no easy way to delete individual trackers in the multitracker object.
#Even when multitracker fails, bboxes will have old values, but 'ok' will be false
#if len(objects_list) > 0:
#ok, bboxes = multi_tracker.update(frame)
#bboxes = multi_tracker.getObjects()
#ok = multi_tracker.empty()
"""
print('Tracking - ',objects_list)
if len(objects_detected) > 0:
del_items = []
for obj,tracker in trackers_dict.items():
ok, bbox = tracker.update(frame)
if ok:
objects_detected[obj][0] = bbox
else:
print('Failed to track ', obj)
del_items.append(obj)
for item in del_items:
trackers_dict.pop(item)
objects_detected.pop(item)
fps = cv.getTickFrequency() / (cv.getTickCount() - timer)
if len(objects_detected) > 0:
drawPred(frame, objects_detected)
# Display FPS on frame
cv.putText(frame, "FPS : " + str(int(fps)), (100,50), cv.FONT_HERSHEY_SIMPLEX, 0.75, (50,170,50), 2)
else:
cv.putText(frame, 'Tracking Failure. Trying to detect more objects', (50,80), cv.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(stream, predictor, args.thr, classes)
# Display result
#If resolution is too big, resize the video
if frame.shape[1] > 1240:
cv.imshow(window_name, cv.resize(frame, (1240, 960)))
else:
cv.imshow(window_name, frame)
#Write to output file
if args.output:
out.write(frame)
k = cv.waitKey(1) & 0xff
#Force detect new objects if 'q' is pressed
if k == ord('q'):
print('Refreshing. Detecting New objects')
cv.putText(frame, 'Refreshing. Detecting New objects', (100,80), cv.FONT_HERSHEY_SIMPLEX, 0.75,(0,0,255),2)
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(stream, predictor, args.thr, classes)
# Exit if ESC pressed
if k == 27 : break
stream.release()
if args.output:
out.release()
cv.destroyAllWindows()
def process(args):
objects_detected = dict()
tracker_types = ['BOOSTING', 'MIL', 'KCF', 'TLD', 'MEDIANFLOW', 'GOTURN']
tracker_type = tracker_types[2]
tracker = None
"""
if tracker_type == 'BOOSTING':
tracker = cv.TrackerBoosting_create()
if tracker_type == 'MIL':
tracker = cv.TrackerMIL_create()
if tracker_type == 'KCF':
tracker = cv.TrackerKCF_create()
if tracker_type == 'TLD':
tracker = cv.TrackerTLD_create()
if tracker_type == 'MEDIANFLOW':
tracker = cv.TrackerMedianFlow_create()
if tracker_type == 'GOTURN':
tracker = cv.TrackerGOTURN_create()
"""
predictor = object_detector(args.model, args.config)
multi_tracker = cv.MultiTracker_create()
stream = cv.VideoCapture(args.input if args.input else 0)
window_name = "Tracking in progress"
cv.namedWindow(window_name, cv.WINDOW_NORMAL)
cv.setWindowProperty(window_name, cv.WND_PROP_AUTOSIZE, cv.WINDOW_AUTOSIZE)
cv.moveWindow(window_name, 10, 10)
if args.output:
_, test_frame = stream.read()
height = test_frame.shape[0]
width = test_frame.shape[1]
fourcc = cv.VideoWriter_fourcc(*'XVID')
out = cv.VideoWriter(args.output, fourcc, 20.0, (width, height))
failTolerance = 0
if args.classes:
with open(args.classes, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
else:
classes = list(np.arange(0, 100))
stream, objects_detected, objects_list, multi_tracker = intermediate_detections(
stream, predictor, multi_tracker, tracker, args.thr, classes)
while stream.isOpened():
grabbed, frame = stream.read()
if not grabbed:
break
timer = cv.getTickCount()
if len(objects_list) > 0:
ok, bboxes = multi_tracker.update(frame)
fps = cv.getTickFrequency() / (cv.getTickCount() - timer)
print(bboxes, ' --- ', ok)
if ok and len(bboxes) > 0:
drawPred(frame, bboxes, objects_detected)
# Display FPS on frame
cv.putText(frame, "FPS : " + str(int(fps)), (100, 50),
cv.FONT_HERSHEY_SIMPLEX, 0.75, (50, 170, 50), 2)
else:
cv.putText(frame,
'Tracking Failure. Trying to detect more objects',
(50, 80), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)
stream, objects_detected, objects_list, multi_tracker = intermediate_detections(
stream, predictor, multi_tracker, tracker, args.thr, classes)
# Display result
#If resolution is too big, resize the video
if frame.shape[1] > 1240:
cv.imshow(window_name, cv.resize(frame, (1240, 960)))
else:
cv.imshow(window_name, frame)
#Write to output file
if args.output:
out.write(frame)
k = cv.waitKey(1) & 0xff
#Force detect new objects if 'q' is pressed
if k == ord('q'):
print('Refreshing. Detecting New objects')
cv.putText(frame, 'Refreshing. Detecting New objects', (100, 80),
cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)
stream, objects_detected, objects_list, multi_tracker = intermediate_detections(
stream, predictor, multi_tracker, tracker, args.thr, classes)
# Exit if ESC pressed
if k == 27: break
stream.release()
if args.output:
out.release()
cv.destroyAllWindows()
def process(args):
objects_detected = dict()
cv.setUseOptimized(onoff=True)
tracker = cv.TrackerKCF_create()
predictor = object_detector(args.model, args.config)
stream = cv.VideoCapture(args.input if args.input else 0)
window_name = "Tracking in progress"
cv.namedWindow(window_name, cv.WINDOW_NORMAL)
cv.setWindowProperty(window_name, cv.WND_PROP_AUTOSIZE, cv.WINDOW_AUTOSIZE)
cv.moveWindow(window_name, 10, 10)
if args.output:
_, test_frame = stream.read()
height = test_frame.shape[0]
width = test_frame.shape[1]
fourcc = cv.VideoWriter_fourcc(*'XVID')
out = cv.VideoWriter(args.output, fourcc, 20.0, (width, height))
if args.classes:
with open(args.classes, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
else:
classes = list(np.arange(0, 100))
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(
stream, predictor, args.thr, classes)
while stream.isOpened():
grabbed, frame = stream.read()
if not grabbed:
break
timer = cv.getTickCount()
if len(objects_detected) > 0:
del_items = []
for objectt, tracker in trackers_dict.items():
positive, bbox = tracker.update(frame)
if positive:
objects_detected[objectt][0] = bbox
else:
print('Failed to track ', objectt)
del_items.append(objectt)
for item in del_items:
trackers_dict.pop(item)
objects_detected.pop(item)
fps = cv.getTickFrequency() / (cv.getTickCount() - timer)
if len(objects_detected) > 0:
drawPred(frame, objects_detected)
cv.putText(frame, "FPS : " + str(int(fps)), (100, 50),
cv.FONT_HERSHEY_SIMPLEX, 1.35, (50, 170, 50), 1)
else:
cv.putText(frame,
'Tracking Failure. Trying to detect more objects',
(50, 80), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(
stream, predictor, args.thr, classes)
cv.imshow(window_name, frame)
if args.output:
out.write(frame)
k = cv.waitKey(1) & 0xff
#Refresh detection by pressing 'q'
if k == ord('q'):
print('Refreshing. Detecting New objects')
cv.putText(frame, 'Refreshing. Detecting New objects', (100, 80),
cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)
stream, objects_detected, objects_list, trackers_dict = intermediate_detections(
stream, predictor, args.thr, classes)
#Save results and end program if 'e' pressed.
if k == ord('e'): break
stream.release()
if args.output:
out.release()
cv.destroyAllWindows()
