Bounding box handling in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a bounding box in object detection?

A bounding box is a rectangle that tightly encloses an object in an image, defined by coordinates usually as (x_min, y_min, x_max, y_max). It helps locate and identify objects.

beginner

How do you convert bounding boxes from (x, y, width, height) format to (x_min, y_min, x_max, y_max)?

You keep x_min = x, y_min = y, then calculate x_max = x + width - 1 and y_max = y + height - 1.

intermediate

What is Intersection over Union (IoU) in bounding box handling?

IoU measures how much two bounding boxes overlap. It is the area of overlap divided by the area of union of the two boxes. It helps evaluate detection accuracy.

intermediate

Why is Non-Maximum Suppression (NMS) used in bounding box handling?

NMS removes duplicate bounding boxes that detect the same object by keeping only the box with the highest confidence score and discarding others with high overlap.

beginner

How can bounding boxes be normalized for neural network input?

Bounding box coordinates can be divided by the image width and height to scale them between 0 and 1, making them independent of image size.

What does the bounding box format (x_min, y_min, x_max, y_max) represent?

A Center coordinates only

B Center coordinates and width/height

C Top-left and bottom-right corners of the box

D Width and height only

The format (x_min, y_min, x_max, y_max) defines the top-left and bottom-right corners of the bounding box.

What is the main purpose of Non-Maximum Suppression (NMS)?

A To remove overlapping boxes for the same object

B To increase the number of bounding boxes

C To resize images

D To normalize bounding box coordinates

NMS removes overlapping bounding boxes that detect the same object, keeping only the best one.

How is Intersection over Union (IoU) calculated?

A Difference between box widths

B Area of overlap divided by area of union

C Sum of areas of two boxes

D Distance between box centers

IoU is the ratio of the overlapping area to the combined area of two bounding boxes.

Why normalize bounding box coordinates before feeding to a model?

A To convert coordinates to pixels

B To remove bounding boxes

C To increase coordinate values

D To make coordinates relative to image size

Normalization scales coordinates between 0 and 1, making them independent of image size.

Which PyTorch tensor shape is typical for a batch of bounding boxes?

A [batch_size, num_boxes, 4]

B [4, num_boxes]

C [num_boxes, batch_size]

D [batch_size, 4]

Bounding boxes are usually stored as [batch_size, number_of_boxes, 4_coordinates].

Explain how Non-Maximum Suppression (NMS) works and why it is important in bounding box handling.

Think about how multiple boxes might detect the same object and how to keep only one.

Describe the process to calculate Intersection over Union (IoU) between two bounding boxes.

Imagine two rectangles overlapping and how much they share.