Traffic Accident Data Generation Based on Improved Generative Adversarial Networks
Open Access
Abstract
For urban traffic, traffic accidents are the most direct and serious risk to people’s lives, and rapid recognition and warning of traffic accidents is an important remedy to reduce their harmful effects. However, research scholars are often confronted with the problem of scarce and difficult-to-collect accident data resources for traffic accident scenarios. Therefore, in this paper, a traffic data generation model based on Generative Adversarial Networks (GAN) is developed. To make GAN applicable to non-graphical data, we improve the generator network structure of the model and used the generated model to resample the original data to obtain new traffic accident data. By constructing an adversarial neural network model, we generate a large number of data samples that are similar to the original traffic accident data. Results of the statistical test indicate that the generated samples are not significantly different from the original data. Furthermore, the experiments of traffic accident recognition with several representative classifiers demonstrate that the augmented data can effectively enhance the performance of accident recognition, with a maximum increase in accuracy of 3.05% and a maximum decrease in the false positive rate of 2.95%. Experimental results verify that the proposed method can provide reliable mass data support for the recognition of traffic accidents and road traffic safety.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (WUT: 2021VI042)
- National Key R&D Program of China (2018YFB1600600)
- National Natural Science Foundation of China (52072288)
This publication has 25 references indexed in Scilit:
- A novel sparse representation model for pedestrian abnormal trajectory understandingExpert Systems with Applications, 2019
- His-GAN: A histogram-based GAN model to improve data generation qualityNeural Networks, 2019
- Understanding Individualization Driving States via Latent Dirichlet Allocation ModelIEEE Intelligent Transportation Systems Magazine, 2019
- How Generative Adversarial Networks and Their Variants WorkACM Computing Surveys, 2019
- GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classificationNeurocomputing, 2018
- 3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained NetworkIEEE Transactions on Medical Imaging, 2018
- Densely Connected Convolutional Networks2017
- Machine Learning and Data Mining Methods in Diabetes ResearchComputational and Structural Biotechnology Journal, 2017
- Discretization: An Enabling TechniqueData Mining and Knowledge Discovery, 2002
- Regression Models and Life-TablesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1972