Attention on the road!
Publicerad
Författare
Typ
Examensarbete för masterexamen
Program
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
Autonomous driving and advanced driver-assistance systems require the perception
of the surrounding environment. A subtask in perception is the detection and classification
of objects in the environment, commonly referred to as object detection.
To aid in this task an autonomous system is outfitted with a sensor suite which
commonly include camera, LiDAR and radar sensor modalities.
The contribution of this work is the construction of a novel object detection pipline
using a sensor suite of five radar sensors which are capable of detecting objects
in a complete field of view. The model constructed is an end-to-end deep learning
model which utilizes graph convolutions over radar points to generate a contextualized
representation of the sensor data.
It is shown that the model presented is able detect the most commonly occurring
classes in the dataset and performs particularly well on objects in motion. It is explored
why the model performs poorly on the uncommon classes which stems from
limitations in the non-maximum suppression algorithm as well as the low efficacy of
the object classifier.
Beskrivning
Ämne/nyckelord
Object detection, Radar, Automotive, Geometric deep learning, Attention, nuScenes.