You should be comfortable navigating open-ended research questions, making independent design decisions, and working collaboratively as a thesis pair and with our team.
We'd love to hear that you have:
A foundation in machine learning, computer vision and statistics
Programming experience in Python and/or C/C++
Familiarity with 3D data processing
An interest in algorithm design with real-world constraints in mind
Bonus points for:
Experience with Rust
Working knowledge of 3D sensors or embedded systems
Experience with simulation environments for 3D sensor data
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.
We would like you to apply in pairs. Please 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!
Katja Palmkvist (katja.palmkvist@axis.com)
Type of Employment
Thesis Worker (Fixed Term)
Posting End Date
2026-07-10
Certain roles at Axis require background checks, which means applicable verifications will be done in these recruitments. Notice will be provided before we take any action.
About Axis Communications
Let´s create a smarter, safer world
For more information about Axis, please visit our website www.axis.com .
Listen to Get To Know Axis - Podcast
Benefits
Vision insurancePerformance bonus
Additional Information
Job Title
Master Thesis - 3D Surveillance Analytics
Job Description
Category
Computer Vision, Deep Learning, Image Processing
Scope
Two students completing a Master's Thesis (30 hp each).
Background
At Axis Communications, we are pushing the boundaries of surveillance technology beyond traditional video. As part of this effort, we are exploring how 3D sensors can be used in static surveillance setups - think traffic intersections or perimeter monitoring.
A key challenge in this domain is to get actionable insights from the raw sensor data: separating relevant events from the static environment and correctly classifying different objects, with the end goal of having a complete analytics pipeline for automated alarm decisions. While such perception problems are well-studied for 2D video, they remain less explored for static 3D surveillance sensors.
This thesis will investigate a specific topic within the 3D sensor analytics pipeline - pushing the state of the art while keeping computational load low enough for embedded applications.
Goals
Survey the relevant literature to establish reference points and identify promising directions within the chosen problem area.
Investigate and develop methods to address a specific challenge within the 3D sensor analytics pipeline.
Explore techniques to reduce computational cost with embedded hardware constraints in mind.
Evaluate methods quantitatively on synthetic and real-world sensor data, and qualitatively on real sensor recordings.
Document the development process, findings, and results in a comprehensive thesis.
Axis · Sweden