30hp - Open Vocabulary Object Detection and Tracking

Introduction:
Thesis work is an excellent way to get closer to Scania and build relationships for the future. Many of today's employees began their Scania career with their degree project.

Background:
Open vocabulary object detection means that the object detector can detect unseen classes. If the object detector also can perform tracking, it would be able to track unseen classes. Datasets for autonomous driving typically have a limited set of classes that are very traffic scene oriented like car, pedestrian, traffic sign, traffic light, lane, etc. However, in rare situation, classes outside this limited set could be important to detect and track. This thesis aims at evaluating the feasibility of open vocabulary object detection and tracking for autonomous driving.

Objective:

Investigate this suggested set of research questions:

• How complex are such networks compared to conventional object detection and tracking?
• What is the performance compared to conventional object detection and tracking?
• How to train open vocabulary capable deep neural networks for object detection and tracking and which data is needed?

Job description:

The Master’s Thesis will most likely include the following

• Survey of open vocabulary object detection and tracking for both 2d and 3d.
• Selecting a number of deep neural networks to be used in the experiments.
• Selecting which data to be used for training.
• Performing experiments on automotive data.

Education/program/focus:

Indicate education, program or focus: Masters program on computer science with a focus on AI

Number of students: 1
Start date for the thesis work: January 2026
Estimated time required: 6 months

Contact persons and supervisors:

Thomas Gustafsson, Expert Engineer, 
thomas.gustafsson@scania.com,

Ajinkya Khoche, Industrial PhD, 
ajinkya.khoche@scania.com

Application:
Your application must include a CV, personal letter and transcript of grades

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.