ARAGAN: A dRiver Attention estimation model based on conditional Generative Adversarial Network

被引:4
作者
Araluce, Javier [1 ]
Bergasa, Luis M. [1 ]
Ocana, Manuel [1 ]
Barea, Rafael [1 ]
Lopez-Guillen, Elena [1 ]
Revenga, Pedro [1 ]
机构
[1] Univ Alcala UAH, Elect Dept, Alcala De Henares, Spain
来源
2022 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV) | 2022年
关键词
D O I
10.1109/IV51971.2022.9827175
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Predicting driver's attention in complex driving scenarios is becoming a hot topic due to it helps the design of some autonomous driving tasks, optimizing visual scene understanding and contributing knowledge to the decision making. We introduce ARAGAN, a driver attention estimation model based on a conditional Generative Adversarial Network (cGAN). This architecture uses some of the most challenging and novel deep learning techniques to develop this task. It fuses adversarial learning with Multi-Head Attention mechanisms. To the best of our knowledge, this combination has never been applied to predict driver's attention. Adversarial mechanism learns to map an attention image from an RGB traffic image while mapping the loss function. Attention mechanism contributes to the deep learning paradigm finding the most interesting feature maps inside the tensors of the net. In this work, we have adapted this concept to find the saliency areas in a driving scene. An ablation study with different architectures has been carried out, obtained the results in terms of some saliency metrics. Besides, a comparison with other state-of-the-art models has been driven, outperforming results in accuracy and performance, and showing that our proposal is adequate to be used on real-time applications. ARAGAN has been trained in BDDA and tested in BDDA and DADA2000, which are two of the most complex driver attention datasets available for research.
引用
收藏
页码:1066 / 1072
页数:7
相关论文
共 50 条
[41]   A tropical cyclone intensity prediction model using conditional generative adversarial network [J].
Hong, Xu ;
Hu, Liang ;
Kareem, Ahsan .
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS, 2023, 240
[42]   A Conditional Generative Adversarial Network Based Approach for Network Slicing in Heterogeneous Vehicular Networks [J].
Falahatraftar, Farnoush ;
Pierre, Samuel ;
Chamberland, Steven .
TELECOM, 2021, 2 (01) :141-154
[43]   Conditional Generative Adversarial Network-Based Image Denoising for Defending Against Adversarial Attack [J].
Zhang, Haibo ;
Sakurai, Kouichi .
IEEE ACCESS, 2021, 9 :169031-169043
[44]   Attention-Based Generative Adversarial Network Model for RC Column Backbone Curve Identification [J].
Gai, Tongtong ;
Yu, Dehu ;
Zeng, Sen ;
Yang, Shujuan ;
Lin, Jerry Chun-Wei .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2025, 21 (01) :455-464
[45]   An Enhanced Generative Adversarial Network Prediction Model Based on LSTM and Attention for Corrosion Rate in Pipelines [J].
Long, Pujun ;
Liang, Mi ;
Chen, Hongjian ;
Yang, Qin .
IEEE ACCESS, 2025, 13 :50260-50273
[46]   Trajectory Prediction using Conditional Generative Adversarial Network [J].
Barbie, Thibault ;
Nishida, Takeshi .
PROCEEDINGS OF THE 2017 INTERNATIONAL SEMINAR ON ARTIFICIAL INTELLIGENCE, NETWORKING AND INFORMATION TECHNOLOGY (ANIT 2017), 2017, 150 :193-197
[47]   Conditional generative adversarial network for gene expression inference [J].
Wang, Xiaoqian ;
Dizaji, Kamran Ghasedi ;
Huang, Heng .
BIOINFORMATICS, 2018, 34 (17) :603-611
[48]   Imbalanced data prediction model based on self-attention mechanism and generative adversarial network [J].
Li, Hui ;
Zhang, Fengxin ;
Pi, Dechang ;
Ding, Dongyan .
INTELLIGENT DATA ANALYSIS, 2025,
[49]   Face Identification Using Conditional Generative Adversarial Network [J].
Jameel, Samer Kais ;
Majidpour, Jafar ;
Al-Talabani, Abdulbasit K. ;
Qadir, Jihad Anwar .
COMPUTER JOURNAL, 2023, 66 (07) :1687-1697
[50]   SpeakerGAN: Speaker identification with conditional generative adversarial network [J].
Chen, Liyang ;
Liu, Yifeng ;
Xiao, Wendong ;
Wang, Yingxue ;
Xie, Haiyong .
NEUROCOMPUTING, 2020, 418 :211-220