AI-900 Practice Question: Describe features of computer vision workloads on Azure
What does Azure AI Vision's 'people detection' (spatial analysis) feature track?
⚠ Common exam trap
Many candidates confuse 'people detection' with facial recognition or attribute detection (like masks), but Azure AI Vision's spatial analysis is strictly about anonymous tracking and counting, not identification or detailed attribute analysis.
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
✓
Counting, tracking movement, and measuring occupancy of people in defined zones from video
Azure AI Vision's spatial analysis (people detection) tracks the movement of people in video feeds, counting individuals and measuring how long they stay in defined zones. It does not identify specific people, detect masks or safety equipment, or measure body dimensions. This feature is designed for occupancy monitoring and flow analysis in physical spaces.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Identifying the names of specific people in video footage
Why it's wrong here
Identifying a specific person by name in video requires face recognition — comparing a detected face against a known database of individuals, or performing face verification. Spatial analysis deliberately anonymizes people: it never extracts facial features, and it discards tracking history after aggregation, so it cannot match anyone to an identity. The correct Azure service for this task is Azure Face API (with person/group matching) or a custom face recognition pipeline, not the spatial analysis feature tested here.
- ✓
Counting, tracking movement, and measuring occupancy of people in defined zones from video
Why this is correct
Spatial analysis in Azure Computer Vision is specifically designed to detect persons in video frames, track their movement across a scene over time, and compute aggregate metrics such as zone occupancy, queue length, entry/exit counts, and dwell time. It operates on anonymous bounding boxes and centroids, never on individual identities, so it answers 'how many people are here and where are they moving' rather than 'who is here.' This makes it the stated purpose of the feature, and the correct description of what spatial analysis natively delivers.
- ✗
Detecting whether people are wearing masks or safety equipment
Why it's wrong here
Mask and safety-equipment detection requires recognizing specific visual attributes on a person, such as color, shape, and part of the body (e.g., a mask over the face or a hard hat on the head). Spatial analysis does not classify clothing or accessories; it only counts and tracks anonymous people as moving objects. To detect PPE, you would train a custom object-detection or classification model (for example, via Azure Custom Vision) and run it separately, because the built-in spatial analysis model has no concept of safety equipment.
- ✗
Measuring individual people's heights and body dimensions
Why it's wrong here
Measuring a person's height or body dimensions requires metric spatial reasoning, typically using depth sensors, stereo cameras, or external calibration combined with skeletal keypoint estimation. Spatial analysis works with ordinary monocular video and outputs a 2D bounding box or centroid per detected person, not 3D skeletal joint positions or real-world measurements. Without depth information and camera intrinsic calibration, estimating metric height or body dimensions from a single video feed is unreliable, so this capability is outside the scope of spatial analysis.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
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.
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.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.