Image Analysis with Microcomputer

• design a stand alone image analysis system
• optimize the electro optical front-end
• research and design an adequate algorithm for the basic measurement problem
• perform an exhaustsive scene analysis
• perform an adequate noise source analysis
• design and implement a digital version of the algorithm
• perform the relevant Software/Hardware analysis
• implement and verify the selected analysis algorithm
• plan, implement and evaluate a verification of the selected method
• evaluate the actually implemented method(s) against alternative solutions.

In the first 10 weeks, the principle of image formation in optical systems and the physics of photoabsorption and electron transport in semiconductors (with emphasis on CCD and APS technology). The students will also be introduced to analogue and digital processing of electronic image information and the use and optimal use of SW libraries.

In the last part of the course, the focus is on applying and embedding image analysis in real-world applications. Examples of fields addressed are object classification and recognition applied in vision-based navigation in 2D and 3D scenes and automatic detection and recognition of targets. Throughout, the focus is on usability through robustness and autonomy.

30020/30021, Complex functions and Microcomputer systems.

Lectures and exercises, followed by a larger special assignment for each student team.

The theory will be presented during the first 10 weeks of the course.
During the last 10 weeks, overlapping the theory, the students will work in small teams on a special assignment (real-world application).

Maximum: 40.

Please be aware that this course has a limited number of seats available. If there are too many applicants, a pool will be created for the remainder of the qualified applicants, and they will be selected at random. You will be informed 8 days before the start of the course, whether you have been allocated a spot.