AI-900 Practice Question: Describe features of computer vision workloads on Azure
What can Azure AI Vision's spatial analysis feature do?
⚠ Common exam trap
A common mix-up: candidates confuse spatial analysis with general computer vision features like OCR or 3D reconstruction, assuming it can handle any image or video analysis task, when it is specifically focused on people detection and movement in physical spaces from live or recorded camera feeds.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Analyze video to detect people's presence and movement in physical spaces
Azure AI Vision's spatial analysis feature is designed to analyze video streams from cameras to detect the presence and movement of people in physical spaces. It uses computer vision models to track individuals, count occupancy, and understand movement patterns in real-time, enabling applications like retail analytics or workplace safety.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Extract text from documents and images
Why it's wrong here
This option describes Optical Character Recognition (OCR), a computer vision task that extracts printed or handwritten text from images and documents using services like Azure's Computer Vision Read API. While OCR is a legitimate vision workload, it has nothing to do with spatial analysis, which operates on video streams to detect and track people in physical spaces over time.
- ✓
Analyze video to detect people's presence and movement in physical spaces
Why this is correct
Spatial analysis, available within Azure Computer Vision, ingests video frames and uses deep learning models to detect the presence of people, count them, track their movement paths, and monitor occupancy in real-world environments like stores or factories. It outputs temporal events (e.g., a person entering a zone or crossing a line), which enables retail analytics, safety monitoring, and facility management—matching this correct answer.
- ✗
Identify the 3D coordinates of objects in satellite imagery
Why it's wrong here
This describes geospatial or photogrammetric processing of satellite imagery, which reconstructs terrain or object coordinates in 3D space. Spatial analysis, by contrast, focuses on live or recorded video from cameras in physical spaces, detecting human presence and motion rather than deriving coordinates from overhead satellite data.
- ✗
Generate 3D models from 2D photographs
Why it's wrong here
This describes 3D reconstruction from photographs, a technique known as photogrammetry or structure-from-motion, which builds a 3D mesh from 2D images. Spatial analysis is unrelated to reconstructing scenes or objects; it analyzes people in video, tracking their presence and movement for behavioral insight, not for generating 3D models.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
Key term
Azure AI Vision
Azure AI Vision is a cloud-based service from Microsoft that uses pre-built machine learning models to extract information from images and videos, such as objects, text, faces, and scene descriptions.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.