Master Thesis – Performance Validation of Edge AI Video Analytics

Category

Computer Vision, Artificial Intelligence, Edge AI, Deep Learning, Statistics, Automation

Scope

One or two students completing a 30-credit Master thesis each

Background

Edge AI video analytics enables object detection and event generation directly on cameras, providing actionable insights in real time for applications such as security, safety, business intelligence, and operational efficiency.

Annotated datasets are widely used when developing deep learning models, but they are not available in edge deployments, where cameras continuously monitor live scenes. In addition, analytics performance can be affected by environmental conditions, camera installation, and system load. This variability makes it challenging to evaluate performance systematically under real-world conditions.

As a result, there is a growing need for standardized methods to test, benchmark, and validate end-to-end video analytics systems operating at the edge.

Goal

The objective of this thesis is to develop a framework for the automated validation of Edge AI video analytics systems. The project will investigate how live video and controlled test environments can be used to measure analytics performance, and how the results relate to real-world deployments.

The outcome will be a prototype framework for automated testing, data collection, and performance analysis of end-to-end video analytics systems.

The work may involve:

• Reviewing existing AI benchmarking and validation methods
• Defining a methodology for standardized system testing
• Developing software for automated test execution and data collection
• Applying statistical methods to analyze performance variability
• Documenting the results and providing recommendations for future validation frameworks

The project combines knowledge of computer vision and machine learning with software engineering and applied statistics.

Who are you?

We’re looking for one or two Master’s students with strong analytical skills and an interest in AI-driven systems.

Your studies may be in a field such as:

• Computer Science
• Robotics and Automation
• Data Science
• Applied Mathematics

You may also have experience or an interest in one or more of these areas:

• Computer Vision
• Machine Learning or Deep Learning
• Statistics and Data Analysis
• Software Engineering

OK, I am interested! What do I do now?

You are valuable to us – how nice that you are interested in one of our proposals! There are a few things for you to keep in mind when applying.

• Applications are accepted in both Swedish and English, and you apply via the proposal advert.
• The announced thesis is open only to students affiliated with a Swedish University/College either directly or via an exchange program.
• When the thesis proposal states that it includes two students working together, we would like you to apply in pairs. In these cases, send one application each but make sure to clearly state in your application who your co-applicant is. If you have any questions regarding this, please do not hesitate to contact us.
• Please attach your CV and University/College grade summary.

Who to contact for any questions regarding the position!

• Supervisor: Giuseppe Bianco, giuseppe.bianco@axis.com
• Manager: Carl Wiberg, carl.wiberg@axis.com