How to Quickly Count Customers in Live Retail Video?

You work for a company that captures live video footage of checkout areas in their retail stores. You need to use the live video footage to build a model to detect the number of customers waiting for service in near real time. You want to implement a solution quickly and with minimal effort. How should you build the model?

Use the Vertex AI Vision Occupancy Analytics model. Source Reference Answer
Use the Vertex AI Vision Person/vehicle detector model.
Train an AutoML object detection model on an annotated dataset by using Vertex AutoML.
Train a Seq2Seq+ object detection model on an annotated dataset by using Vertex AutoML.

Community Votes

100%

100% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests your ability to match business constraints like speed and effort to the appropriate cloud AI service, while avoiding the trap of over-engineering with custom AutoML workflows.

Leveraging pre-built Vertex AI models enables rapid deployment without custom training overhead. The community unanimously recommends Occupancy Analytics for its purpose-built design and zero-code implementation.

Option B is frequently selected because the Person/Vehicle Detector can identify individuals, but it lacks the native occupancy counting and queue optimization features required for minimal-effort deployment.

Community Discussion (7 comments)

tardigradum 👍 1 Selected: A

It makes sense to use Vertex AI Vision Occupancy to reduce the effort of obtaining a model that identifies the number of people in a video, although I am hesitant about the fact that it says 'BUILD a model' and strictly speaking, no model is actually built with that option.

Prakzz 👍 1 Selected: B

https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/vehicle-detector Occupancy analytics has other features too like zone detection, dwell time, and more, which is not needed in this scenario.

fitri001 👍 4 Selected: A

A. Use the Vertex AI Vision Occupancy Analytics model: This is a pre-built model specifically designed for analyzing occupancy in videos. It's ideal for this scenario as it requires minimal configuration and can likely be deployed quickly.

guilhermebutzke 👍 4 Selected: A

My Answer: A: Vertex AI Vision Occupancy Analytics is a pre-trained model specifically designed to count people in live video streams. This removes the need for expensive and time-consuming data labeling and training, making it ideal for quick implementation. **Vertex AI Vision Person/Vehicle Detector model detects individual people and vehicles, not specifically focusing on occupancy counting. It would require further processing to estimate the number of waiting customers. Option C and D requires labeling data and training, which adds effort and time. https://cloud.google.com/vision-ai/docs/overview

ddogg 👍 2 Selected: A

A. Use the Vertex AI Vision Occupancy Analytics model. Here's why: Pre-trained and optimized: Occupancy Analytics is a pre-trained and optimized model specifically designed for counting people in video footage, aligning perfectly with your task. This eliminates the need for extensive data collection, annotation, and training, saving time and effort. Near real-time performance: The model is designed for low latency and near real-time inference, providing results quickly with minimal delay, important for live video analysis. Minimal configuration: Compared to training your own model, this option requires minimal configuration within the Vertex AI console, allowing for a quicker setup and deployment.

b1a8fae 👍 1 Selected: B

All you need is counting the number of customers in the video stream. I would say no need to have the extra functionalities of occupancy analytics, person/vehicle is enough for this use case. https://cloud.google.com/vision-ai/docs/person-vehicle-model

winston9 👍 3 Selected: A

https://codelabs.developers.google.com/vertex-ai-vision-queue-detection#0

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Expert Analysis

Why the Answer Is Correct

Vertex AI Vision Occupancy Analytics is a fully managed, pre-trained model specifically engineered for detecting and counting people in video streams. It directly addresses the requirement for near real-time performance while minimizing development effort, as no data labeling or model training is needed. The solution handles complex scenarios like overlapping individuals and varying lighting out of the box.

Why the Other Options Are Wrong

Custom AutoML approaches (C and D) require significant time for data collection, annotation, and training, violating the "quickly and minimal effort" constraint. The Person/Vehicle Detector (B) identifies bounding boxes for objects but does not natively optimize for occupancy counting or queue management without additional custom logic and tuning.

Community Comment Notes

Candidates consistently highlight that pre-built models are ideal for immediate deployment scenarios. Comment [3] provides a valuable codelab reference demonstrating queue detection implementation. Comment [5] raises a valid semantic point about "building" versus "using," but exam strategy prioritizes meeting business constraints over literal wording. Comments [6] and [7] incorrectly favor B, overlooking that Occupancy Analytics includes zone detection and dwell time which streamline queue analysis.

Official Reference

Exam Strategy

Focus on matching keywords like "quickly," "minimal effort," and "pre-built" to select managed services over custom training solutions. Always evaluate whether a specialized analytics API or model exists before defaulting to generic object detection or AutoML workflows.

Related Analysis

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide