Projekt

Deep Learning & AI for Target Detection in Radar

Udbyder

Vejleder

Sted

København og omegn

Problem
In radar processing a common method for detecting signals in noise is the CFAR1 method. This method is good for simple targets in ideal environments but presents problems when rain clutter and jet engine modulations are present. The goal of this project is to create a detection scheme based on an adaptive algorithm.             

Challenge
The student(s) should create a framework for training and evaluating an advanced discriminator to detect a complex target in a difficult environment.

Solutions should be investigated using different optimization criteria with and without an ability to effect the measurement situation.

The evaluation will primarily be traditional performance metrics like probability of detection and false alarm rate. Time permitting the solutions should be evaluated for processing requirements on either CPU or GPUs.

Example of tasks

  1. Literature study of neural network detection
  2. Proof of concept implementation
  3. Network “training” on Weibel data
  4. Offline and live test
  5. Performance comparison


Contact Person
Henrik Stenby Andresen
E-mail:
hsa@weibel.dk
Phone: +45 4816 9761

Practical details
Place of work: Weibel HQ and/or place of study.


Birte Kronbak Andersen is not the project supervisor, she just put the project idea in the Project Bank for Weibel. But a supervisor can most likely be found at DTU Space.

I samarbejde med

Weibel

Søg i opslag

OM DTU

DTU er et teknisk eliteuniversitet med international rækkevidde og standard. Vores mission er at udvikle og nyttiggøre naturvidenskab og teknisk videnskab til gavn for samfundet. 10.000 studerende uddanner sig her til fremtiden, og 5.700 medarbejdere har hver dag fokus på uddannelse, forskning, myndighedsrådgivning og innovation, som bidrager til øget vækst og velfærd.

Find os her

Anker Engelunds Vej 1
Bygning 101A
2800 Kgs. Lyngby


45 25 25 25

dtu@dtu.dk

CVR-nr. 30 06 09 46

Liste over EAN Numre

Job på DTU

Se alle jobs
 

loading..