async def get_roi_contour(camera_id: str):
"""
Get the contour of the RoI
"""
validate_camera_existence(camera_id)
roi_file_path = ObjectsFilteringPostProcessor.get_roi_file_path(camera_id, settings.config)
roi_contour = ObjectsFilteringPostProcessor.get_roi_contour(roi_file_path)
if roi_contour is None:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"There is no defined RoI for {camera_id}")
return roi_contour.tolist()
def __init__(self, config, source: str, logger: str):
self.config = config
self.camera_id = self.config.get_section_dict(source)["Id"]
self.resolution = tuple([int(i) for i in self.config.get_section_dict("App")["Resolution"].split(",")])
self.birds_eye_resolution = (200, 300)
self.out = None
self.out_birdseye = None
self.live_feed_enabled = self.config.get_boolean(source, "LiveFeedEnabled")
self.track_hist = dict()
self.roi_file_path = ObjectsFilteringPostProcessor.get_roi_file_path(self.camera_id, self.config)
async def remove_roi_contour(camera_id: str, reboot_processor: Optional[bool] = True):
"""
Delete the defined RoI for a camera.
"""
validate_camera_existence(camera_id)
roi_file_path = ObjectsFilteringPostProcessor.get_roi_file_path(camera_id, settings.config)
if not validate_file_exists_and_is_not_empty(roi_file_path):
detail = f"There is no defined RoI for {camera_id}"
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=detail)
os.remove(roi_file_path)
success = restart_processor() if reboot_processor else True
return handle_response(None, success, status.HTTP_204_NO_CONTENT)
async def add_or_replace_roi_contour(camera_id: str, body: ContourRoI, reboot_processor: Optional[bool] = True):
"""
Define a RoI for a camera or replace its current one.
A RoI is defined by a vector of [x,y] 2-tuples, that map to coordinates in the image.
"""
validate_camera_existence(camera_id)
roi_file_path = ObjectsFilteringPostProcessor.get_roi_file_path(camera_id, settings.config)
dir_path = Path(roi_file_path).parents[0]
Path(dir_path).mkdir(parents=True, exist_ok=True)
roi_contour = np.array(body.contour_roi, dtype=int)
np.savetxt(roi_file_path, roi_contour, delimiter=',', fmt='%i')
restart_processor() if reboot_processor else True
return roi_contour.tolist()
def map_camera(camera_name, config, options=[]):
camera_dict = map_section_from_config(camera_name, config)
camera = config.get(camera_name)
camera_id = camera.get("Id")
image_string = None
if "withImage" in options:
image_string = get_camera_default_image_string(camera_id)
camera_dict["image"] = image_string
calibration_file_path = get_camera_calibration_path(settings.config, camera_id)
camera_dict["has_been_calibrated"] = validate_file_exists_and_is_not_empty(calibration_file_path)
roi_file_path = ObjectsFilteringPostProcessor.get_roi_file_path(camera_id, settings.config)
camera_dict["has_defined_roi"] = validate_file_exists_and_is_not_empty(roi_file_path)
in_out_file_path = InOutMetric.get_in_out_file_path(camera_id, settings.config)
camera_dict["has_in_out_border"] = validate_file_exists_and_is_not_empty(in_out_file_path)
return camera_dict
def update(self, cv_image, objects, post_processing_data, fps, log_time):
if not self.live_feed_enabled:
return
self.update_history(post_processing_data["tracks"])
distancings = post_processing_data.get("distances", [])
dist_threshold = post_processing_data.get("dist_threshold", 0)
birds_eye_window = np.zeros(self.birds_eye_resolution[::-1] + (3, ),
dtype="uint8")
class_id = int(
get_model_json_file_or_return_default_values(
self.config,
self.config.get_section_dict('Detector')['Device'],
self.camera_id)["variables"]["ClassID"])
roi_contour = ObjectsFilteringPostProcessor.get_roi_contour(
self.roi_file_path)
if roi_contour is not None:
color = (41, 127, 255) # #ff7f29 (255, 127, 41)
visualization_utils.draw_contour(cv_image, roi_contour, color)
output_dict = visualization_utils.visualization_preparation(
objects, distancings, dist_threshold)
category_index = {
class_id: {
"id": class_id,
"name": "Pedestrian",
}
} # TODO: json file for detector config
face_index = {
0: "YES",
1: "NO",
-1: "N/A",
}
# Assign object's color to corresponding track history
for i, track_id in enumerate(output_dict["track_ids"]):
self.track_hist[track_id][1].append(
output_dict["detection_colors"][i])
# Draw bounding boxes and other visualization factors on input_frame
visualization_utils.visualize_boxes_and_labels_on_image_array(
cv_image,
output_dict["detection_boxes"],
output_dict["detection_classes"],
output_dict["detection_scores"],
output_dict["detection_colors"],
output_dict["track_ids"],
category_index,
instance_masks=output_dict.get("detection_masks"),
use_normalized_coordinates=True,
line_thickness=3,
face_labels=output_dict["face_labels"],
face_index=face_index)
# TODO: Implement perspective view for objects
birds_eye_window = visualization_utils.birds_eye_view(
birds_eye_window, output_dict["detection_boxes"],
output_dict["violating_objects"])
# Put occupancy to the frame
# region
# -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_-
txt_fps = 'Occupancy = ' + str(len(objects))
# (0, 0) is the top-left (x,y); normalized number between 0-1
origin = (0.05, 0.93)
visualization_utils.text_putter(cv_image, txt_fps, origin)
# -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_-
# endregion
# visualize tracks
# region
# -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_-
visualization_utils.draw_tracks(cv_image,
self.track_hist,
radius=1,
thickness=1)
# -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_- -_-
# endregion
self.out.write(cv_image)
self.out_birdseye.write(birds_eye_window)