def read_video():
while True:
ret, image = cap.read()
if not ret:
continue
detector_ip.push(Inference(image.copy()))
detector_op.wait()
ret, inference = detector_op.pull()
if ret:
i_dets = inference.get_result()
trk_ip.push(Inference(i_dets))
def read():
while True:
ret, image = cap.read()
if not ret:
continue
image = image.copy()
stock_image_in.push(image)
# image = cv2.resize(image, (int(image.shape[1] / 2), int(image.shape[0] / 2)))
detector_ip.push(Inference(image))
detector_op.wait()
ret, inference = detector_op.pull()
if ret:
i_dets = inference.get_result()
trk_ip.push(Inference(i_dets))
def read_video():
# start = time.time()
while True:
ret, image = cap.read()
if not ret:
continue
detector_ip.push(Inference(image.copy()))
def detect_age_gender(trackers):
if not Tracker.__age_inference:
print("initializing Age Model")
Tracker.__age_inference = AgeApiRunner(SessionRunner())
detector_ip = Tracker.__age_inference.get_detector_ip()
detector_op = Tracker.__age_inference.get_detector_op()
for i, trk in enumerate(trackers):
trk_trail = trk.get_trail()
person = trk_trail.get_person()
if not trk.detect_age() or len(person.get_age_list()) >= 10 or len(person.get_gender_list()) >= 10 or trk.get_image() is None:
continue
# print("len of tracker", i, " " ,len(trk.get_patches()))
detector_ip.push(Inference(trk.get_image().copy()))
# ret, inference = detector_op.pull(True)
while True:
detector_op.wait()
ret, inference = detector_op.pull(True)
if ret:
# print(ret)
if inference.get_result().get_genders() is None or inference.get_result().get_ages() is None:
break
print(inference.get_result().get_genders())
print(inference.get_result().get_ages())
gender_confidence = inference.get_result().get_genders()[0][0]
gender = 'M' if gender_confidence < 0.5 else 'F'
age = int(inference.get_result().get_ages()[0])
# print(type())
trk.get_trail().get_person().add_age(age)
trk.get_trail().get_person().add_gender(gender, gender_confidence)
print("ages", trk.get_trail().get_person().get_age_list())
print("genders", trk.get_trail().get_person().get_gender_list())
break
def infer_yolo(timestamp, margin, points):
while True:
yolo_input.wait()
ret, image = yolo_input.pull(flush=True)
if not ret:
continue
# ret, flag = zone_image_update.pull()
# if ret and flag:
# cv2.imwrite('../../../Angular-Dashboard-master/src/assets/rack_image.jpg', image)
# print("After Update")
inference = Inference(image)
img_shape = image.shape
ret, point_set_dict = point_set.pull()
if ret:
point_set_dict["point_set_2"] = [
[0,
0.6 * margin], [img_shape[1] - 4.25 * margin, 0.6 * margin],
[img_shape[1] - 4.25 * margin, img_shape[0] - 0.6 * margin],
[0, img_shape[0] - 0.6 * margin]
]
print("updated points")
points = point_set_dict['point_set_2']
retail_an_object.rack_dict = point_set_dict
retail_an_object.global_init()
inference.get_meta_dict()['warp_points'] = retail_an_object.rack_dict
yolo_ip.push(inference)
yolo_op.wait()
ret, inference = yolo_op.pull()
ret1, zones = zone_detection_in_pipe.pull()
if ret:
i_dets = inference.get_result()
boxes = tracker_stock.update(i_dets)
image = i_dets.get_annotated(boxes)
if ret1 and not zones:
image = retail_an_object.print_shelfNo(image)
image = retail_an_object.misplacedBoxes(boxes, image)
image = retail_an_object.draw_empty_space(boxes, image)
flag = retail_an_object.change_of_state()
# cv2.rectangle(image, (margin, margin), (img_shape[1]-margin, img_shape[0]-margin), (0, 0, 255), 3)
current_time = time.time()
elapsed_seconds = (current_time - timestamp)
# print(elapsed_seconds)
if (elapsed_seconds > 3):
if flag == 1:
# pass
Thread(target=retail_an_object.postdata).start()
timestamp = time.time()
# print("left corner: ",points[0][1])
image = image[int(points[0][1] - margin / 2):int(points[2][1] +
margin / 2),
int(points[0][0]):int(points[2][0] + margin / 2), :]
stock_in_pipe.push(image)
cv2.imshow("retail_out", image)
cv2.waitKey(1)
def start_cam():
while True:
ret, image = cap.read()
if not ret:
continue
inference = Inference(image.copy(), return_pipe=ret_pipe)
detector.get_in_pipe().push_wait()
detector.get_in_pipe().push(inference)
def readvideo():
while True:
re, image = cap0.read()
if re:
ip0.push(Inference(image.copy()))
else:
break
time.sleep(0.025)
def extract_features(patch, ip, op):
patch[0] = cv2.equalizeHist(patch[0])
patch[1] = cv2.equalizeHist(patch[1])
patch[2] = cv2.equalizeHist(patch[2])
ip.push(Inference(patch, meta_dict={}))
op.wait()
ret, feature_inference = op.pull()
if ret:
return feature_inference.get_result()
def load():
# print("LOADED")
while True:
ret, image = cap.read()
print(ret)
if not ret:
continue
detector_ip.push(Inference(image.copy()))
# print("#################################")
sleep(0.05)
def read():
while True:
ret, image = cap.read()
if not ret:
continue
image = image.copy()
yolo_input.push(image)
# print("Image read count: ", count)
# count+=1
# image = cv2.resize(image, (int(image.shape[1] / 2), int(image.shape[0] / 2)))
detector_ip.push(Inference(image))
detector_op.wait()
ret, inference = detector_op.pull()
if ret:
i_dets = inference.get_result()
infer_idets = Inference(i_dets)
infer_idets.get_meta_dict()['zone_pipe'] = zone_pipe
trk_ip.push(infer_idets)
def read():
while True:
ret, image = cap.read()
# image = cv2.resize(image, (int(image.shape[1]/2), int(image.shape[0]/2)))
# if count == 100:
# detector_ip.close()
# print("breaking...")
# trk_ip.close()
# break
if not ret:
continue
detector_ip.push(Inference(image.copy()))
# print('waiting')
detector_op.pull_wait()
# print('done')
ret, inference = detector_op.pull()
if ret:
i_dets = inference.get_result()
trk_ip.push(Inference(i_dets))
def read():
lst = []
skip = 2
count = 0
while True:
count += 1
ret, image = cap.read()
if not ret or count % skip != 0:
continue
detector_ip.push_wait()
inference = Inference(image)
detector_ip.push(inference)
image = cv2.resize(image, tuple(image_shape[:2][::-1]))
image = np.expand_dims(image, axis=0)
# K.set_session(session)
extractor = ResNet50ExtractorAPI('rn50_api', True)
ip = extractor.get_in_pipe()
# op = extractor.get_out_pipe()
extractor.use_session_runner(session_runner)
session_runner.start()
extractor.run()
ret_pipe = Pipe()
# for i in range(1000):
i = 0
while True:
ret, image = cap.read()
if not ret:
continue
ip.push(Inference(image, ret_pipe, {}))
ret, feature_inference = ret_pipe.pull()
if ret:
print(feature_inference.get_result().shape)
else:
ret_pipe.wait()
session_runner.stop()
detection = TFObjectDetectionAPI(
PRETRAINED_faster_rcnn_inception_v2_coco_2018_01_28, image.shape, 'tf_api',
True)
detector_ip = detection.get_in_pipe()
detector_op = detection.get_out_pipe()
detection.use_session_runner(session_runner)
detection.use_threading()
session_runner.start()
detection.run()
frame_no = 0
while True:
ret, image = cap.read()
if not ret:
continue
detector_ip.push(Inference(image.copy()))
detector_op.wait()
ret, inference = detector_op.pull(True)
if ret:
i_dets = inference.get_result()
# print(i_dets.get_masks()[0].shape)
frame = i_dets.get_annotated()
cv2.imshow("annotated", i_dets.get_annotated())
# cv2.imshow("annotated", i_dets.extract_patch(0))
cv2.waitKey(1)
# person = i_dets.get_category('person')
# for i in range(i_dets.get_length()):
# if i_dets.get_classes(i) == 1 and i_dets.get_scores(i) > 0.7:
# cv2.imwrite("/home/uniquetrij/PycharmProjects/SecureIt/data/obj_tracking/outputs/patches/" + (
# str(frame_no).zfill(5)) + (str(i).zfill(2)) + ".jpg", i_dets.extract_patches(i))
print(frame_no)
def __job(self, inference):
self.__enc_in_pipe.push(
Inference(inference.get_data(),
meta_dict={'inference': inference},
return_pipe=self.__out_pipe))