欢迎访问《汽车安全与节能学报》,

汽车安全与节能学报 ›› 2022, Vol. 13 ›› Issue (2): 325-332.DOI: 10.3969/j.issn.1674-8484.2022.02.013

• 智能驾驶与智慧交通 • 上一篇    下一篇

基于双流自适应图卷积神经网络的行人过街意图识别

胡远志(), 蒋涛, 刘西, 施友宁   

  1. 汽车零部件先进制造技术教育部重点实验室(重庆理工大学),重庆400054,中国
  • 收稿日期:2021-11-19 修回日期:2022-02-16 出版日期:2022-06-30 发布日期:2022-07-01
  • 作者简介:胡远志(1977—),男(汉),湖南,教授。E-mail: yuanzhihu@cqut.edu.cn

Pedestrian-crossing intention-recognition based on dual-stream adaptive graph-convolutional neural-network

HU Yuanzhi(), JIANG Tao, LIU Xi, SHI Youning   

  1. Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education (Chongqing University of Technology), Chongqing 400054, China
  • Received:2021-11-19 Revised:2022-02-16 Online:2022-06-30 Published:2022-07-01

摘要:

对城市道路上的自动驾驶车辆,提出了一种判别行人过街意图的识别方法。该方法利用双流、时空自适应图卷积神经网络(2s-AGCN),联系了行人骨架的动力学与行人过街意图;以时空图卷积神经网络(ST-GCN)的动作识别为基础,加入自适应图卷积神经网络结构(AGCN);在骨骼的长度和方向上,设计了双流网络,将2个网络输出的 Softmax 分数融合,来预测行人过街意图。根据自动驾驶联合注意力公开数据集(JAAD),进行了仿真实验。结果表明:本文的2s-AGCN行人过街意图识别方法的准确率达到了89.36%,比ST-GCN神经网络的结果高3.36%。因此,该方法识别准确率较高。

关键词: 自动驾驶车辆, 驾驶安全, 行人过街意图, 图卷积神经网络(GCN)

Abstract:

A recognition method was proposed to judge pedestrians’ intention to cross street for autonomous vehicles on urban roads. The method utilized a two-stream, spatiotemporally adaptive graph-convolutional neural-network (named 2s-AGCN) with linking the dynamics of pedestrian skeletons and pedestrian crossing intention; Added the adaptive graph convolutional neural-network (AGCN) structure based on the action recognition of the spatiotemporal graph convolutional neural network (ST-GCN); A dual-stream neural-network was designed in terms of the length and direction of the bones for fusing the Softmax scores output by the two networks to predict pedestrian crossing intention. Simulation experiments were carried out based on the Joint Attention in Autonomous Driving public Dataset (JAAD). The results shown that the accuracy of this 2s-AGCN method reaches 89.36%, which is 3.36% higher than the accuracy of the ST-GCN. Therefore, the recognition accuracy of this method is high.

Key words: autonomous vehicles, driving safety, pedestrian crossing intention, graph convolution neural-network (GCN)

中图分类号: