|
Эта публикация цитируется в 6 научных статьях (всего в 6 статьях)
ОБРАБОТКА ИЗОБРАЖЕНИЙ, РАСПОЗНАВАНИЕ ОБРАЗОВ
Road images augmentation with synthetic traffic signs using neural networks
A. S. Konushin, B. V. Faizov, V. I. Shakhuro Lomonosov Moscow State University, Faculty of Mechanics and Mathematics
Аннотация:
Traffic sign recognition is a well-researched problem in computer vision. However, the state of the art methods works only for frequent sign classes, which are well represented in training datasets. We consider the task of rare traffic sign detection and classification. We aim to solve that problem by using synthetic training data. Such training data is obtained by embedding synthetic images of signs in the real photos. We propose three methods for making synthetic signs consistent with a scene in appearance. These methods are based on modern generative adversarial network (GAN) architectures. Our proposed methods allow realistic embedding of rare traffic sign classes that are absent in the training set. We adapt a variational autoencoder for sampling plausible locations of new traffic signs in images. We demonstrate that using a mixture of our synthetic data with real data improves the accuracy of both classifier and detector.
Ключевые слова:
traffic sign classification, synthetic training samples, neural networks, image recognition, image transforms, neural network compositions
Поступила в редакцию: 30.12.2020 Принята в печать: 19.04.2021
Образец цитирования:
А. С. Конушин, Б. В. Фаизов, В. И. Шахуро, “Road images augmentation with synthetic traffic signs using neural networks”, Компьютерная оптика, 45:5 (2021), 736–748
Образцы ссылок на эту страницу:
https://www.mathnet.ru/rus/co962 https://www.mathnet.ru/rus/co/v45/i5/p736
|
Статистика просмотров: |
Страница аннотации: | 22 | PDF полного текста: | 12 | Список литературы: | 9 |
|