计算机工程与应用2025，Vol.61Issue(21)：214-224,11.DOI:10.3778/j.issn.1002-8331.2407-0554
基于多特征交互融合的行人过街意图预测
Pedestrian Crossing Intention Prediction Based on Multi-Feature Interaction Fusion
摘要
Abstract
Pedestrian intention prediction is very important for the development of safe advanced driver assistance sys-tems.Traditional methods mainly use graph convolutional network and recursive architecture to process human pose data.These methods have limitations in feature fusion and rely on the integrity of pedestrian pose information extraction,result-ing in lower accuracy when pedestrians are obscured.In order to solve the above problems,a multi-feature interactive fusion pedestrian crossing intention prediction module(PEPR-Net)is proposed,which uses head pose and introduces skel-eton heat map information to improve the accuracy of prediction when pedestrians are blocked,and bridge the comple-mentary gap between non-Euclidean bone point information and other features.On this basis,a multi-feature interactive hybrid fusion module is proposed,which uses cascade cross attention fusion method to process pixel information and cascade hybrid fusion structure to process non-pixel information.Finally,a new asymmetric bidirectional gated cycle module(UBA-GRU)is introduced for feature fusion,and the optimal fusion strategy is used to achieve the best predictive performance of F1 score and accuracy(ACC).A large number of ablation experiments are performed on the PIE dataset,and performance analysis shows that PEPR-Net achieves 91%accuracy.The results are expected to provide more accurate pedestrian intent predictions for autonomous driving systems.关键词
自动驾驶辅助系统/多特征交互融合/意图预测/注意力机制/骨架热力图Key words
autonomous driving assistance system/multi-feature interactive fusion/pedestrian intention/attention mecha-nism/skeleton heat map分类
信息技术与安全科学引用本文复制引用
杨智勇,郭洁铷,郭子杭,许沁欣..基于多特征交互融合的行人过街意图预测[J].计算机工程与应用,2025,61(21):214-224,11.基金项目
重庆市自然科学基金(cstc2021ycjh-bgzxm0088) （cstc2021ycjh-bgzxm0088）
重庆市教育委员会科学技术研究计划项目(KJZD-M202303401) （KJZD-M202303401）
重庆市高校创新研究群体(CXQT21032). （CXQT21032）
