Deep Learning based Turn Light Detection at Road Intersections for Autonomous Driving
Abstract: Autonomous driving promises to revolutionise transportation by making it more eﬃcient, cheaper, safer and climate friendlier. Bringing autonomous vehicles onto roads requires eﬀectively sensing the surrounding environment and integrating derived information into a safe and eﬃcient driving policy. This involves, amongst others, capturing the intent of other traﬃc participants as signalled by turn lights. Contributing to the development of autonomous systems as part of the publicly funded MEC-View project at Bosch, this thesis aims at detecting turn signals with an emphasis on oncoming vehicles at road intersections. Speciﬁcally, using images taken from cameras attached to side mirrors of an autonomous vehicle, a Convolutional LSTM Neural Network detects and classiﬁes turn signals of approaching vehicles during both day and night time. As such, this work diﬀers in important aspects from existing literature. Results obtained from experiments and detailed analyses of test cases indicate that the devised model performs competitively despite data scarcity and strong label imbalance, with a weighted F1 score of 80.8%. Hence, this thesis lays promising ground work in the domain of autonomous driving and identiﬁes potential future improvements.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)