Custom object detection dataset in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ data_output

intermediate

Understanding dataset structure for object detection

You have a custom object detection dataset with images and annotations in COCO format. What is the number of unique object categories in the dataset?

Computer Vision

import json

with open('annotations.json') as f:
    data = json.load(f)

categories = data['categories']
num_categories = len(categories)
print(num_categories)

A 5

B 15

C 10

D 20

💡 Hint

Look at the 'categories' key in the COCO annotation file. Count how many category entries it has.

The 'categories' list in COCO format contains all unique object categories. Counting its length gives the number of categories.

❓ Predict Output

intermediate

Output of bounding box extraction code

Given the following code snippet that extracts bounding boxes from annotations, what is the output?

Computer Vision

annotations = [
    {'bbox': [10, 20, 30, 40], 'category_id': 1},
    {'bbox': [15, 25, 35, 45], 'category_id': 2},
    {'bbox': [50, 60, 70, 80], 'category_id': 1}
]

bboxes = [ann['bbox'] for ann in annotations if ann['category_id'] == 1]
print(bboxes)

A [[10, 20, 30, 40], [50, 60, 70, 80]]

B []

C [[10, 20, 30, 40]]

D [[15, 25, 35, 45]]

💡 Hint

Filter bounding boxes where category_id equals 1.

The list comprehension filters annotations with category_id 1 and collects their bounding boxes.

❓ visualization

advanced

Visualizing bounding boxes on an image

Which option correctly draws bounding boxes on an image using OpenCV for a given list of boxes?

Computer Vision

import cv2
import numpy as np

image = np.zeros((100, 100, 3), dtype=np.uint8)
bboxes = [[10, 10, 30, 30], [50, 50, 20, 20]]

for box in bboxes:
    x, y, w, h = box
    cv2.rectangle(image, (x, y), (x+w, y+h), (255, 0, 0), 2)

cv2.imwrite('output.png', image)

A Draw rectangles using cv2.rectangle with top-left and bottom-right corners calculated correctly.

B Draw rectangles using cv2.circle at (x, y) with radius w.

C Draw rectangles using cv2.line connecting (x, y) to (x+w, y+h) only.

D Draw rectangles using cv2.rectangle with (x, y) and (w, h) as corners directly.

💡 Hint

Bounding boxes are defined by top-left corner (x, y) and width and height (w, h). Use these to find corners.

cv2.rectangle requires top-left and bottom-right points. Bottom-right is (x+w, y+h). Other options misuse the API or draw incorrect shapes.

🔧 Debug

advanced

Identify the error in dataset loading code

What error will this code raise when loading a custom object detection dataset?

Computer Vision

import json

with open('annotations.json') as f:
    data = json.load(f)

images = data['images']
annotations = data['annotations']

image_id = images[0]['id']
image_annotations = [ann for ann in annotations if ann['image_id'] == image_id]

print(len(image_annotations))

A KeyError because 'images' key is missing in JSON

B TypeError because 'annotations' is not iterable

C IndexError because images list is empty

D No error, prints the number of annotations for the first image

💡 Hint

Check if the JSON file has 'images' and 'annotations' keys and they contain lists.

If the JSON file is correctly formatted in COCO style, the code runs without error and prints the count of annotations for the first image.

🚀 Application

expert

Calculate average bounding box area per category

Given a dataset with annotations, which option correctly computes the average bounding box area for each category?

Computer Vision

annotations = [
    {'bbox': [10, 20, 30, 40], 'category_id': 1},
    {'bbox': [15, 25, 35, 45], 'category_id': 2},
    {'bbox': [50, 60, 70, 80], 'category_id': 1},
    {'bbox': [5, 10, 15, 20], 'category_id': 2}
]

from collections import defaultdict

area_sum = defaultdict(float)
count = defaultdict(int)

for ann in annotations:
    _, _, w, h = ann['bbox']
    area = w * h
    area_sum[ann['category_id']] += area
    count[ann['category_id']] += 1

avg_area = {cat: area_sum[cat]/count[cat] for cat in area_sum}
print(avg_area)

A {1: 3500.0, 2: 1200.0}

B {1: 3400.0, 2: 937.5}

C {1: 2500.0, 2: 1200.0}

D {1: 3500.0, 2: 975.0}

💡 Hint

Calculate area as width * height for each bbox, sum by category, then divide by count.

Category 1 areas: 30*40=1200, 70*80=5600; sum=6800, average=3400.0. Category 2 areas: 35*45=1575, 15*20=300; sum=1875, average=937.5.