Table of Contents
Which computer vision type is used to locate cars in an image?
Prepare for your AI-900 exam by learning why object detection is the correct computer vision technique to determine the location of cars in an image. Understand its role in estimating distances and how it differs from image classification and face detection.
Question
You need to determine the location of cars in an image so that you can estimate the distance between them. Which type of computer vision should you use?
A. Face detection
B. Image classification
C. Object detection
D. Optical character recognition
Answer
C. Object detection
Explanation
The correct type of computer vision to use is C. Object detection. This is because the core requirement of the task is to “determine the location of cars,” which is the primary function of object detection.
Understanding Object Detection
Object detection is a computer vision technique that identifies and locates instances of objects within an image or video. For each object it finds, the model returns two key pieces of information:
- A class label: This identifies what the object is (e.g., “car”).
- A bounding box: These are the pixel coordinates that define a rectangle enclosing the object.
The bounding box coordinates provide the precise location data needed to fulfill the requirement. Once you have the locations of two or more cars, you can use those coordinates (along with camera perspective information) to estimate the distance between them.
Why Other Options Are Incorrect
A. Face detection: This is a specialized type of object detection that is trained specifically to find human faces. It would not be able to identify cars.
B. Image classification: This technique assigns a single label to the entire image. For example, it could tell you that the image contains cars, but it would not provide any information about where those cars are located in the image. Therefore, you cannot use it to estimate distances between them.
D. Optical character recognition (OCR): This is used to extract printed or handwritten text from an image. It is completely irrelevant for identifying physical objects like cars.
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.