Institutional Repository of Vilnius University
Objektų aptikimas skirtingomis aplinkos sąlygomis naudojantis giliaisiais neuroniniais tinklais /
Abstract
dc:descriptionThis paper examines the problem of what training data should be used for a neural network that detects objects and could be used in an autonomous vehicle. An experiment was made to determine whether only data of good environmental conditions could be used for training and how accurately objects could be detected in poor environmental conditions. It was found that using only good environmental data for training the detection accuracy of objects in poor environmental conditions, and especially during poor time of day, is significantly lower, but it can be improved by using data augmentations during training.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Stongvilas, Žygimantas,
- Contributors dc:contributor
-
- Dapkūnas, Boleslovas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107115636&prefLang=en_US