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.

Practice

1. What is the main purpose of creating a custom object detection dataset?

easy

A. To compress images for faster loading

B. To improve image resolution automatically

C. To generate random images for testing

D. To teach a computer to find specific objects in images

Solution

1. Step 1: Understand the goal of object detection datasets

   Custom object detection datasets are made to help computers learn to recognize and locate specific objects in images.

2. Step 2: Identify the correct purpose

   Among the options, only teaching a computer to find specific objects matches the goal of such datasets.

3. Final Answer:

   To teach a computer to find specific objects in images -> Option D

4. Quick Check:

   Custom dataset purpose = teach detection [OK]

Hint: Custom datasets train models to detect your objects [OK]

Common Mistakes:

• Confusing dataset purpose with image enhancement
• Thinking dataset creates images instead of labeling
• Assuming dataset compresses images

2. Which of the following is the correct format for an annotation line in a YOLO custom dataset label file?

easy

A. class_id x_center y_center width height (all normalized between 0 and 1)

B. image_width image_height class_id x y (pixel values)

C. class_name x_min y_min x_max y_max (absolute pixel coordinates)

D. class_id x_min y_min width height (normalized coordinates)

Solution

1. Step 1: Recall YOLO annotation format

   YOLO uses normalized coordinates with class_id, x_center, y_center, width, and height all between 0 and 1.

2. Step 2: Match options to YOLO format

   class_id x_center y_center width height (all normalized between 0 and 1) matches this format exactly; others use pixel values or different coordinate types.

3. Final Answer:

   class_id x_center y_center width height (all normalized between 0 and 1) -> Option A

4. Quick Check:

   YOLO labels use normalized center coords [OK]

Hint: YOLO labels use normalized center coordinates [OK]

Common Mistakes:

• Using pixel coordinates instead of normalized
• Confusing bounding box corners with center format
• Mixing class name with class id

3. Given this label file line for an image of size 640x480:
2 0.5 0.5 0.25 0.25
What are the pixel coordinates of the bounding box corners (x_min, y_min, x_max, y_max)?

medium

A. (200, 150, 360, 270)

B. (160, 120, 320, 240)

C. (240, 180, 400, 300)

D. (320, 240, 480, 360)

Solution

1. Step 1: Calculate center pixel coordinates

   x_center = 0.5 * 640 = 320, y_center = 0.5 * 480 = 240

2. Step 2: Calculate width and height in pixels

   width = 0.25 * 640 = 160, height = 0.25 * 480 = 120

3. Step 3: Calculate bounding box corners

   x_min = 320 - 160/2 = 240, y_min = 240 - 120/2 = 180
   x_max = 320 + 160/2 = 400, y_max = 240 + 120/2 = 300

4. Final Answer:

   (240, 180, 400, 300) -> Option C

5. Quick Check:

   Center ± half width/height = corners [OK]

Hint: Multiply normalized by image size, then subtract/add half box [OK]

Common Mistakes:

• Using width/height as full coordinates instead of half
• Mixing up x and y calculations
• Forgetting to multiply by image dimensions

4. You have a dataset folder with images and label files. The labels are missing for some images. What is the best way to fix this before training?

medium

A. Remove images without label files from the dataset

B. Create empty label files for those images

C. Rename images to match existing label files

D. Ignore missing labels and train anyway

Solution

1. Step 1: Understand dataset consistency needs

   Training requires each image to have a matching label file with annotations.

2. Step 2: Choose the best fix

   Removing images without labels avoids errors and ensures clean training data. Creating empty labels may confuse the model, renaming won't help if labels don't exist, ignoring missing labels causes errors.

3. Final Answer:

   Remove images without label files from the dataset -> Option A

4. Quick Check:

   Dataset must have matching image-label pairs [OK]

Hint: Keep only images with labels to avoid training errors [OK]

Common Mistakes:

• Creating empty label files that confuse training
• Ignoring missing labels causing crashes
• Renaming files without creating labels

5. You want to add a new object class to your existing custom dataset. Which steps should you follow to update your dataset correctly?

hard

A. Only add new images with the new class, no config changes needed

B. Add the new class to the class list, label new images with it, and update training config

C. Replace old class labels with the new class in all files

D. Add new class images but keep old labels unchanged without config update

Solution

1. Step 1: Update class list

   Add the new object class to your dataset's class list file so the model knows about it.

2. Step 2: Label new images with the new class

   Annotate images containing the new object using the new class id in label files.

3. Step 3: Update training configuration

   Modify your training config to include the new class count and class names.

4. Final Answer:

   Add the new class to the class list, label new images with it, and update training config -> Option B

5. Quick Check:

   Update classes, labels, and config for new objects [OK]

Hint: Update classes, label new data, and config for new objects [OK]

Common Mistakes:

• Not updating class list causing training errors
• Forgetting to label new objects
• Ignoring config updates leading to wrong class counts