draw.group_bbox_and_tag

Description

Draws large bounding boxes with tags, over identified groups of bounding boxes.

class Node(config=None, **kwargs)

Draws large bounding boxes with tags over multiple object bounding boxes which have been identified as belonging to the same group.

The large_groups data type from dabble.check_large_groups, and the groups key of the obj_attrs data type from dabble.group_nearby_objs, are inputs for this node which identifies the different groups, and the group associated with each bounding box.

For better understanding, refer to the Group Size Checking use case.

Inputs

img (numpy.ndarray): A NumPy array of shape \((height, width, channels)\) containing the image data in BGR format.

bboxes (numpy.ndarray): A NumPy array of shape \((N, 4)\) containing normalized bounding box coordinates of \(N\) detected objects. Each bounding box is represented as \((x_1, y_1, x_2, y_2)\) where \((x_1, y_1)\) is the top-left corner and \((x_2, y_2)\) is the bottom-right corner. The order corresponds to bbox_labels and bbox_scores.

obj_attrs (Dict[str, Any]): A dictionary of attributes associated with each bounding box, in the same order as bboxes. Different nodes that produce this obj_attrs output type may contribute different attributes. draw.group_bbox_and_tag requires the groups attribute from dabble.group_nearby_objs.

large_groups (List[int]): A list of integers representing the group IDs of groups that have exceeded the size threshold.

Outputs

none: No outputs produced.

Configs

tag (str) – default = “LARGE GROUP!”.
The string message printed when a large group is detected.

Changed in version 1.2.0: draw.group_bbox_and_tag used to take in obj_tags (List[str]) as an input data type, which has been deprecated and now subsumed under obj_attrs. The same attribute is accessed by using the groups key of obj_attrs.