EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation

Qu, Fang; Zhou, Pengzhan; He, Yuepeng; Gao, Kaixin; Luo, Youyu; Feng, Xin; Liu, Yu; Guo, Songtao

doi:10.24963/ijcai.2025/200

EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation

Fang Qu, Pengzhan Zhou, Yuepeng He, Kaixin Gao, Youyu Luo, Xin Feng, Yu Liu, Songtao Guo

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1793-1801.

https://doi.org/10.24963/ijcai.2025/200

Keywords

Computer Vision: CV: Action and behavior recognition
Computer Vision: CV: Efficiency and Optimization
Computer Vision: CV: Biometrics, face, gesture and pose recognition

Abstract

Present Advanced Driving Assistance System (ADAS) responds to the dangerous crossing of pedestrians after the occurrence of the incident, occasionally causing severe accidents due to the stringent response window. Inference of pedestrian crossing intention may help vehicles operate in advance and enhance the safety of the vehicle by predicting the crossing probability. Recent studies usually ignore the demand of real-time forecast that required in the realistic driving scenario, and mainly focus on improving the model representation capacity on public datasets by increasing modality and observation time. Consequently, a new framework named EfficientPIE is proposed to predict the pedestrian crossing intention in real time with sole observation of the incident. To achieve reliable predictions, we propose incremental learning based on intention domain to relieve forgetting and promote performance with a progressive perturbation method. Our EfficientPIE outperforms all the SOTA models on two datasets PIE and JAAD, running nearly 7.4x faster than the previously fastest model. Our code is available at https://github.com/heinideyibadiaole/EfficientPIE.

Fang Qu, Pengzhan Zhou, Yuepeng He, Kaixin Gao, Youyu Luo, Xin Feng, Yu Liu, and Songtao Guo. 2025. EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1793–1801. https://doi.org/10.24963/ijcai.2025/200

@inproceedings{ijcai2025p200,
  title     = {EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation},
  author    = {Qu, Fang and Zhou, Pengzhan and He, Yuepeng and Gao, Kaixin and Luo, Youyu and Feng, Xin and Liu, Yu and Guo, Songtao},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {1793--1801},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/200},
  url       = {https://doi.org/10.24963/ijcai.2025/200},
}

TY  - CPAPER
TI  - EfficientPIE: Real-Time Prediction on Pedestrian Crossing Intention with Sole Observation
AU  - Qu, Fang
AU  - Zhou, Pengzhan
AU  - He, Yuepeng
AU  - Gao, Kaixin
AU  - Luo, Youyu
AU  - Feng, Xin
AU  - Liu, Yu
AU  - Guo, Songtao
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 1793
EP  - 1801
DO  - 10.24963/ijcai.2025/200
UR  - https://doi.org/10.24963/ijcai.2025/200
ER  -