Axis enables a smarter and safer world by creating network solutions that provide insights for improving security and new ways of doing business. As the industry leader in network video, Axis offers products and services for video surveillance and analytics, access control, and audio systems. Axis has more than 3,000 dedicated employees in over 50 countries and collaborates with partners worldwide to deliver customer solutions.
Category
Probability theory, Automatic Control
Scope
2 students completing 30 credits (20 weeks) each.
Background
In a retail store it is of great value to be able to keep track of product placement and misplacement, something that today mostly is done manually. With a mobile camera platform that moves around in a store we can build a map using simultaneous localization and mapping (SLAM). This have been done many times before, e.g. [1].
At subsequent wandering of the platform we can detect differences in the environment from the map that was built the times before. This is normally considered an unwanted defect which means that the map should be updated to reflect the current state of the environment.
In this thesis we want to look at the differences (deltas) in the map as interesting data containing information about what parts of the environment that has changed. In a store environment this might mean that a shelf is now empty instead of full, the products have been moved around or that something was dropped on the ground.
[1] “Minimum hardware SfM/SLAM for sparse data point mapping of retail stores”
Goal
Differentiating between noise and interesting environment change is the main focus of this thesis. The map delta (change in the map) could be detection noise or actual information of interest. If the mobile camera platform is controllable; calculate a suitable path to obtain the needed information to minimize the noise in the specific area of change.
The result of detecting a changed environment could be presented to an operator as a pair of before-and-after images of the area of change together with a position marker on the map.
Depending on the interest and expertise of the students the thesis can focus on different areas of the problem. The camera platform could be one of the following:
Current state-of-the-art SLAM algorithms could be reused to focus on the map delta problem or the robot control problem to gain the best information.
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.
28-02-2024
Ange nedan vart du önskar arbeta och glöm inte bort att ange din e-postadress!