Type of Publication

Journal Articles

Date:

7 /

2024

Status

Published

DOI:

10.1109/TAI.2024.3421175

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

Featured in:

IEEE Transactions on Artificial Intelligence

Authors:

Zihan Jiang, Yiqun Ma, Bingyu Shi, Xin Lu, Jian Xing, Nuno Gonçalves and Bo Jin

Abstract

This paper introduces a novel model for low-quality pedestrian trajectory prediction, the Social Non-stationary Transformers (NSTransformers), that merges the strengths of NSTransformers and Spatio-Temporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a Generative Adversarial Network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction’s diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction.

Citation
Zihan Jiang, Yiqun Ma, Bingyu Shi, Xin Lu, Jian Xing, Nuno Gonçalves and Bo Jin, “Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction,” in IEEE Transactions on Artificial Intelligence 1(01) 2024. DOI: 10.1109/TAI.2024.3421175.

Related Content

Researcher Coordinator, VIS TEAM Leader
Post-Doc Researcher
No tagged content to show
No tagged content to show
No tagged content to show

RECENT PUBLICATIONS

MorFacing: A Benchmark for Estimation Face Recognition Robustness to Face Morphing Attacks

Authors: Iurii Medvedev and Nuno Gonçalves
Featured in: IEEE International Joint Conference on Biometrics (IJCB 2024)

Face Liveness Detection Competition (LivDet-Face)

Authors: Lambert Igene, Afzal Hossain, Stephanie Schuckers, Mohammad Zahir Uddin Chowdhury, Humaira Rezaie, Ayden Rollins, Jesse Dykes, Rahul Vijaykumar, Sebastien Marcel, Juan Tapia, Carlos Aravena, Daniel Schulz, Nima Karimian and Anafsheh Adami, Diogo Nunes, João Marcos, Nuno Gonçalves, Lovro Sikošek, Borut Batagelj, Nima Schei, David Pabon, Manuela Tiedemann, Vasiliy Pryadchenko, Aleksandr Alenin, Alhasan Alkhaddour, Anton Pimenov, Artem Tregubov, Igor Avdonin, Maxim Lazantsev and Mikhail Pozigun
Featured in: IEEE International Joint Conference on Biometrics Competitions, 2024

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

Authors: Zihan Jiang, Yiqun Ma, Bingyu Shi, Xin Lu, Jian Xing, Nuno Gonçalves and Bo Jin
Featured in: IEEE Transactions on Artificial Intelligence

suggested news

Laser engraving of precious metal artifacts (UniqueMark® deterministic...
UniqueMark® and UniQode® Glitter patent published
Paper about protecting facial recognition systems against morphing...

RECENT PROJECTS

FACING2 – Face Image Understanding
VISUAL-ID – Unique Visual Identities in Graphics, Images and Faces
UniqueMark

Institute of Systems and Robotics Department of Electrical and Computers Engineering University of Coimbra