标题: Multi-task driver gaze estimation in real world driving scenes
作者: Wu, XM (Wu, Xinmei); Li, L (Li, Lin); Zhou, G (Zhou, Gang); Wu, QL (Wu, Qilong); Zuo, XK (Zuo, Xinkai); Zhu, HH (Zhu, Haihong); He, S (He, Shen)
来源出版物: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 卷: 160 文献号: 111892 DOI: 10.1016/j.engappai.2025.111892 Published Date: 2025 NOV 23 子辑: B
摘要: Driver gaze estimation task is pivotal for safe driving. However, challenges persist when dealing with changing illumination, eyeglasses, adjacent zones, or personal behavior and appearance. To tackle these problems, we introduce a driver gaze estimation approach, including gaze zone and direction estimation. We propose a global facial feature extraction convolutional neural network (gCNN) embedded with attention network for driver gaze zone estimation. The incorporation of attention mechanisms in different dimensions (channel or spatial) at various stages facilitates the network in efficiently capturing overall generic features in early stages and concrete representations in later stages. This network is also applied to extract facial features in gaze direction estimation task. While a local eye feature extraction convolutional neural network (LeCNN) is proposed for fine-grained eye features extraction. The facial and eye features, as well as head pose, are concatenated and fused to regress the finer gaze direction. The experimental results show that the network achieves an error of 2.43 degrees and 4.36 degrees on MPIIFaceGaze and EyeDIAP datasets, respectively, outperforming the prior arts. Furthermore, in driver gaze zone estimation task, our method achieves accuracy of 98.87 % on Laboratory for Intelligent and Safe Automobiles (LISA) Gaze dataset, with 3.91 % improvement over prior arts. It also achieves a compatible performance of 82.80 % on Driver Gaze in the Wild (DGW) dataset.
作者关键词: Advanced driver assistance; Eye gaze estimation; Gaze zone estimation; Attention mechanism; Transfer learning
KeyWords Plus: REGION
地址: [Wu, Xinmei; Li, Lin; Zhou, Gang; Wu, Qilong; Zhu, Haihong] Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Peoples R China.
[Wu, Xinmei] Zhejiang Agr & Forestry Univ, Coll Math & Comp Sci, Hangzhou, Peoples R China.
[Zuo, Xinkai] Changjiang Spatial Informat Technol Engn Co Ltd, Wuhan, Peoples R China.
[He, Shen] Wuhan Metro Grp Co Ltd, Wuhan, Peoples R China.
通讯作者地址: Li, L (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan, Peoples R China.
电子邮件地址: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]
影响因子：8
