Improving our Smart Camera System
Over the last two years we have developed a smart camera prototype based around the Tegra X1 platform, being able to segment/classify every pixel in an image using convolutional neural networks. However, in the mean time we have developed several new approaches to process the acquired images faster based on the mostly static scenery and a second, multispectral camera module.
Now we would like to include those in our prototype, and otherwise improve it by building a more compact system, adding communication capabilities to transmit suspicious cases to a remote computer and/or to add additional sensors (GPS, microphone). We would also like to port everything to the latest OS for the Tegra X1 board to get best performance transferring data from the sensor to the processor.
Since this is a very broad engineering project, please just come talk to me if you think it might be interesting and we can quickly discuss all the options that can be done.
Status: In Progress
- Looking for 1-2 semster project students or 1-4 students for a group project.
- Supervision: Lukas Cavigelli
- Some experience programming (Computer Science 1+2 or equivalent)
- Motivation to optimize real systems
- 10% Theory / Literature Research
- 70% Implementation
- 20% Evaluation
Detailed Task Description
A detailed task description will be created before the start of the project together with the student(s) and tailored to their interests and knowledge.
Meetings & Presentations
The students and advisor(s) agree on weekly meetings to discuss all relevant decisions and decide on how to proceed. Of course, additional meetings can be organized to address urgent issues. At the end of the project, you have to present/defend your work during a 15 min. presentation and 5 min. of discussion as part of the IIS colloquium.\
- The EDA wiki with lots of information on the ETHZ ASIC design flow (internal only) 
- The IIS/DZ coding guidelines