Thesis: Image-based object segmentation on embedded camera systems*
Thesis: Image-based object segmentation on embedded camera systems*
Waldkirch (bei Freiburg), DE, 79183
Waldkirch (bei Freiburg), DE, 79183
Summer Semester 2025 - fixed-term for 3-6 months
In logistics, the precise assignment of detected features in an image (e.g., barcodes) to the corresponding objects (e.g., packages) plays a crucial role. Currently, only the positions of the features in the image are known, but not the positions of the objects themselves. This leads to challenges in object-feature matching, especially when multiple objects are positioned closely together in an image.
To improve the accuracy of this assignment, the object region in the image needs to be identified. By correlating the object region with the position of the detected feature, the accuracy of the assignment can be significantly enhanced.
The goal of this project is to integrate a demonstrator on an embedded camera system, capable of segmenting and localizing individual objects in real-time using image sequences from material flows.
YOUR TASKS:
- You analyze and compare different approaches from traditional image processing and AI-based segmentation for object recognition
- You implement a solution on an embedded camera system
- You evaluate the developed solution in a real-world application environment
YOUR PROFILE:
- You are studying Computer Science, Computer Vision, Machine Learning, or a related field
- You have basic knowledge of optics or physics
- You have programming experience in languages such as Python, Matlab, Lua, or C++
- You work independently and in a structured manner, with a quick grasp of new concepts
- You possess strong teamwork and communication skills
YOUR APPLICATION:
- We are looking forward to your online application
- Sarah Disch
- Job-ID 36396
- All applications will be treated confidentially
*At SICK, we see people, not gender.
We put great emphasis on diversity, reject discrimination and do not think in categories such as gender, ethnicity, religion, disability, age or sexual identity.
Stichworte: Intern, Internship, Abschlussarbeit
Summer Semester 2025 - fixed-term for 3-6 months
In logistics, the precise assignment of detected features in an image (e.g., barcodes) to the corresponding objects (e.g., packages) plays a crucial role. Currently, only the positions of the features in the image are known, but not the positions of the objects themselves. This leads to challenges in object-feature matching, especially when multiple objects are positioned closely together in an image.
To improve the accuracy of this assignment, the object region in the image needs to be identified. By correlating the object region with the position of the detected feature, the accuracy of the assignment can be significantly enhanced.
The goal of this project is to integrate a demonstrator on an embedded camera system, capable of segmenting and localizing individual objects in real-time using image sequences from material flows.
YOUR TASKS:
- You analyze and compare different approaches from traditional image processing and AI-based segmentation for object recognition
- You implement a solution on an embedded camera system
- You evaluate the developed solution in a real-world application environment
YOUR PROFILE:
- You are studying Computer Science, Computer Vision, Machine Learning, or a related field
- You have basic knowledge of optics or physics
- You have programming experience in languages such as Python, Matlab, Lua, or C++
- You work independently and in a structured manner, with a quick grasp of new concepts
- You possess strong teamwork and communication skills
YOUR APPLICATION:
- We are looking forward to your online application
- Sarah Disch
- Job-ID 36396
- All applications will be treated confidentially
*At SICK, we see people, not gender.
We put great emphasis on diversity, reject discrimination and do not think in categories such as gender, ethnicity, religion, disability, age or sexual identity.
Stichworte: Intern, Internship, Abschlussarbeit