Sequence-Preserving Dual-FoV Defense for Traffic Sign and Light Recognition in Autonomous Vehicles
Open Access
Abstract
For Autonomous Vehicles (AVs), recognizing traffic lights and signs is critical for safety because perception errors directly affect navigation decisions. Real-world disturbances such as glare, rain, dirt, and graffiti, as well as digital adversarial attacks, can lead to dangerous misclassifications. Current research lacks (i) temporal continuity (stable detection across consecutive frames to prevent flickering misclassifications), (ii) multi-field-of-view (FoV) sensing, and (iii) integrated defenses against both digital and natural degradation. This paper presents two principal contributions: (1) a three-layer defense framework integrating feature squeezing, inference-time temperature scaling (softmax = 3 without distillation training), and entropy-based anomaly detection with sequence-level temporal voting; (2) a 500 sequence dual-FoV benchmark (30k base frames, 150k with perturbations) from aiMotive, Waymo, Udacity, and Texas sources across four operational design domains. The unified defense stack achieves 79.8% mAP on a 100-sequence test set (6k base frames, 30k with perturbations), reducing attack success rate from 37.4% to 18.2% (51% reduction) and high-risk misclassifications by 32%. Cross-FoV validation and temporal voting enhance stability under lighting changes (+3.5% mAP) and occlusions (+2.7% mAP). Defense improvements (+9.5–9.6% mAP) remain consistent across native 3D (aiMotive, Waymo) and projected 2D (Udacity, Texas) annotations. Preliminary recapture experiments (n = 15 scenarios) show 2.5% synthetic–physical ASR gap (p = 0.18), though larger validation is needed. Code, models, and dataset reconstruction tools are publicly available.
Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- QHSA-ViT: A Quantum Discrete-Fourier-Transform-Based Hierarchical Self-Attention Fusion Vision Transformer for Traffic Sign Recognition in Intelligent Vehicular NetworksIEEE Internet of Things Journal, 2025
- An Adaptive Hierarchical Framework With Contrastive Aggregation for Traffic Sign ClassificationIEEE Open Journal of Intelligent Transportation Systems, 2025
- Time-aware and task-transferable adversarial attack for perception of autonomous vehiclesPattern Recognition Letters, 2024
- Detection of adversarial attacks based on differences in image entropyInternational Journal of Information Security, 2023
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous VehiclesIEEE Internet of Things Journal, 2021
- Multi-Source Adversarial Sample Attack on Autonomous VehiclesIEEE Transactions on Vehicular Technology, 2021
- Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models2019
- Robust Physical-World Attacks on Deep Learning Visual Classification2018
- Universal Adversarial Perturbations2017