Skip to Content

AI-900: What Is Object Detection in Computer Vision? Locating Objects in Images

Object detection is a computer vision capability that can locate and classify specific objects within an image, like vehicles, and return their bounding box coordinates. Learn how object detection differs from semantic segmentation, OCR, and image classification.

Table of Contents

Question

Returning a bounding box that indicates the location of a vehicle in an image is an example of which computer vision capability? Select the correct option.

A. Object detection.
B. semantic segmentation.
C. optical character recognizer (OCR).
D. Image classification.

Answer

A. Object detection.

Explanation

Object detection is a computer vision capability that enables AI models to locate and classify specific objects, like vehicles, within an image. When an object detection model processes an image, it analyzes the visual content to find any instances of the target object class.

For each detected object, the model returns:

  1. The object’s class or category (e.g. “car”, “truck”, “bus”, etc.)
  2. A bounding box indicating the object’s location in the image, usually in the form of pixel coordinates for the box’s corners

So in the example of locating vehicles, an object detection model would place a bounding box around each vehicle it finds in the image and label them with their specific class. This allows pinpointing the exact position and type of multiple target objects.

Object detection differs from the other options presented:

  • Semantic segmentation assigns a class label to every pixel in the image, effectively painting regions by category. It doesn’t output bounding boxes or separate individual objects.
  • Optical character recognition (OCR) focuses specifically on detecting and transcribing text in images, not locating arbitrary objects.
  • Image classification assigns a single category label to the entire image based on its primary subject. It doesn’t provide any location information for specific objects.

Therefore, object detection using bounding boxes is the correct computer vision capability for locating vehicles or other target objects within an image. Its ability to pinpoint multiple objects’ locations and classes distinguishes it from related techniques like segmentation, OCR, and classification.

Returning a bounding box that indicates the location of a vehicle in an image is a typical example of object detection. This capability identifies objects within an image and provides their positions, often using bounding boxes to show where they are located.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.