arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.12902cs.CVcs.LGstat.ML
收藏

基于符号-真实图像转换GANs的交通标志识别数据增强

Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition

Hochschule Bonn-Rhein-Sieg(波恩-莱茵-锡格应用技术大学);German Research Center for Artificial Intelligence(德国人工智能研究中心)

Nour Soufi, Matias Valdenegro-Toro

摘要:

交通标志识别是许多先进驾驶辅助系统的重要组成部分,也是完全自动驾驶所必需的。计算性能通常是使用大规模神经网络用于此目的的瓶颈。SqueezeNet是一个很好的候选交通标志的高效图像分类,但在我们的实验中,它没有达到高精度,我们认为这是由于缺乏数据,需要数据增强。生成对抗网络可以学习经验数据的高维分布,从而生成新的数据点。在本文中,我们应用pix 2 pix GANs架构来生成新的交通标志图像,并评估这些图像在数据增强中的使用。由于条件GANs中的模式坍塌,我们有动机使用pix 2 pix将符号图像转换为真实图像。通过我们的实验,我们发现使用GAN的数据增强可以将圆形交通标志的分类准确率从92.1%提高到94.0%,将三角形交通标志的分类准确率从93.8%提高到95.3%,总体提高了2%。然而,一些传统的增强技术可以优于GAN数据增强,例如圆形交通标志的对比度变化(95.5%)和三角形交通标志的位移(96.7%)。我们的负面结果表明,虽然GANs可以天真地用于数据增强,但它们并不总是最佳选择,这取决于问题和数据的可变性。

英文摘要:

Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data points. In this paper we apply pix2pix GANs architecture to generate new traffic sign images and evaluate the use of these images in data augmentation. We were motivated to use pix2pix to translate symbolic sign images to real ones due to the mode collapse in Conditional GANs. Through our experiments we found that data augmentation using GAN can increase classification accuracy for circular traffic signs from 92.1% to 94.0%, and for triangular traffic signs from 93.8% to 95.3%, producing an overall improvement of 2%. However some traditional augmentation techniques can outperform GAN data augmentation, for example contrast variation in circular traffic signs (95.5%) and displacement on triangular traffic signs (96.7 %). Our negative results shows that while GANs can be naively used for data augmentation, they are not always the best choice, depending on the problem and variability in the data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑