Classification of rare traffic signs

Компьютерная оптика

卷:44

Anton Konushin¹  Boris Faizov²  Vladislav Shakhuro²  Vadim Sanzharov² 

[1] Gubkin RSU of Oil and Gas;

[2] Lomonosov Moscow State University, Moscow, Russia;

关键词: traffic sign classification;    synthetic training samples;    neural networks;    image recognition;    image transforms;    neural network compositions;   

DOI  :  10.18287/2412-6179-CO-601

来源: DOAJ

【 摘 要 】

The paper studies the possibility of using neural networks for the classification of objects that are few or absent at all in the training set. The task is illustrated by the example of classification of rare traffic signs. We consider neural networks trained using a contrastive loss function and its modifications, also we use different methods for generating synthetic samples for classification problems. As a basic method, the indexing of classes using neural network features is used. A comparison is made of classifiers trained with three different types of synthetic samples and their mixtures with real data. We propose a method of classification of rare traffic signs using a neural network discriminator of rare and frequent signs. The experimental evaluation shows that the proposed method allows rare traffic signs to be classified without significant loss of frequent sign classification quality.

【 授权许可】

Unknown