def process_images(model_path, detection_class, detection_threshold,
max_processing_delay):
"""Starts Tensorflow and detects objects in the incoming images.
Args:
model_path (str): Filepath to the Tensorflow model to use.
detection_class (int): Detection classe to detect
detection_threshold (float): Detection threshold to apply to all Tensorflow detections.
max_processing_delay (float): Allowed delay before processing an incoming image.
"""
odapi = DetectorAPI(path_to_ckpt=model_path)
num_processed_skips = 0
if TENSORFLOW_PROCESS_BARRIER is None:
return
try:
TENSORFLOW_PROCESS_BARRIER.wait()
except BrokenBarrierError as exc:
print(f'Error waiting for Tensorflow processes to initialize: {exc}')
return False
while True:
entry = RAW_IMAGES_QUEUE.get()
for _, capture in entry.items():
if time.time() - capture['raw_image_time'] > max_processing_delay:
num_processed_skips += 1
continue # Skip image due to delay
image = capture['cv_image']
# process_start = time.time()
boxes, scores, classes, _ = odapi.process_frame(image)
# process_end = time.time()
confident_boxes = []
confident_object_classes = []
confident_scores = []
if len(boxes) == 0:
continue
for box, score, box_class in sorted(zip(boxes, scores, classes),
key=lambda x: x[1],
reverse=True):
# if score > detection_threshold:
if score > detection_threshold and box_class == detection_class:
confident_boxes.append(box)
confident_object_classes.append(COCO_CLASS_DICT[box_class])
confident_scores.append(score)
image = cv2.rectangle(image, (box[1], box[0]),
(box[3], box[2]), (255, 0, 0), 2)
capture['processed_image_time'] = time.time()
capture['boxes'] = confident_boxes
capture['classes'] = confident_object_classes
capture['scores'] = confident_scores
capture['cv_image'] = image
try:
PROCESSED_BOXES_QUEUE.put_nowait(entry)
except Full as exc:
print(f'PROCESSED_BOXES_QUEUE is full: {exc}')
def process_images(index, model_path, detection_classes, detection_threshold,
max_processing_delay):
"""Starts Tensorflow and detects objects in the incoming images.
Args:
index: Process index used for displaying number of skips only.
model_path: Filepath to the Tensorflow model to use.
detection_classes: List of detection classes to detect. Empty list means all classes
in the model are detected.
detection_threshold: Detection threshold to apply to all Tensorflow detections.
max_processing_delay: Allowed delay before processing an incoming image.
"""
odapi = DetectorAPI(path_to_ckpt=model_path)
num_processed_skips = 0
while True:
entry = RAW_IMAGES_QUEUE.get()
inline_print(0, RAW_IMAGES_QUEUE.qsize())
raw_time = entry['raw_image_time']
if time.time() - raw_time > max_processing_delay:
num_processed_skips = num_processed_skips + 1
inline_print(20 + index, str(num_processed_skips))
continue # Skip image due to delay
image = entry['image']
boxes, scores, classes, _ = odapi.process_frame(image)
for i in range(len(boxes)):
# Empty detection classes means detect everything
if not detection_classes or classes[i] in detection_classes:
if scores[i] > detection_threshold:
box = boxes[i]
image = cv2.rectangle(image, (box[1], box[0]),
(box[3], box[2]), (255, 0, 0), 2)
out_entry = {
'source': entry['source'],
'raw_image_time': entry['raw_image_time'],
'capture_image_time': entry['capture_image_time'],
'processed_image_time': time.time(),
'image': image
}
PROCESSED_IMAGES_QUEUE.put(out_entry)
inline_print(3, PROCESSED_IMAGES_QUEUE.qsize())
inline_print(
9,
str(out_entry['processed_image_time'] -
out_entry['capture_image_time']))