Interference Object Detection using TensorFlow Lite and Transfer Learning for Android Devices
Ladda ner
Publicerad
Författare
Typ
Examensarbete för masterexamen
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
With the rapid evolution of machine learning and artificial intelligence faster and
more robust network architectures are developed. This is possible due to the increase
in computational power, improved algorithms and the creation of large scale
annotated datasets. Re-purposing these state of the art networks using transfer
learning allows for customized models to be created and applied to niche problems.
In this paper, we create an object detection application able to detect interference
points in anechoic testing chambers. The application runs detection on a mobile device
using networks created with TensorFlow Lite. Utilizing the detection result the
application can give advice on how to improve the installation in the testing chamber
and can thus enforce a baseline for how installations are conducted increasing
the repeatability of tests. The end product is an android application running on a
mobile device able to detect interference points in 13 FPS for two different testing
chambers. The two object detection networks used achieved a mean average precision
score of 0.8765 and 0.8650 and a average recall score of 0.7212 and 0.6997
respectively.
Beskrivning
Ämne/nyckelord
Android Studio, Anechoic Chamber, Machine Learning, Object Detection, Single Shot Detector, TensorFlow, TensorFlow Lite, Transfer Learning