arXiv subjects

Shaozu Ding

Publications and source records attributed to Shaozu Ding.

4 recordsLinked to original sources

arXiv2026

Inter-3D VQA: A Roadside Multimodal Benchmark for 3D Spatiotemporally Grounded Visual Question Answering

Recent advances in visual question answering (VQA) and multimodal large language models (MLLMs) have enabled natural-language reasoning over traffic scenes. However, existing benchmarks are largely built from ego-vehicle views or 2D roadside videos, limiting their ability to evaluate 3D-grounded reasoning over real-world distances, trajectories, infrastructure topology, and safety-critical interactions. We introduce Inter-3D VQA, a large-scale roadside multimodal benchmark for 3D spatiotemporally grounded VQA at intersections. Built from synchronized point clouds and multi-view images, Inter-3D VQA contains 407K QA pairs covering lane-level positions, object relationships, motion patterns, and near-miss-oriented interaction reasoning. We further propose Inter-Geo, an MLLM baseline that integrates object- and scene-level aligned LiDAR representations, and Inter-Metrics, a unified evaluation framework for textual consistency, numerical accuracy, and semantic correctness. Experiments show that Inter-Geo outperforms image-based VLMs, especially on grounded spatial and temporal reasoning tasks. Our benchmark and codes are available at https://github.com/ASU-Suo-Lab/Inter-3D-VQA .

cs.CV↗

arXiv2026

RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception

LiDAR has increasingly been integrated into traffic cameras to expand coverage and mitigate occlusion in roadside cooperative perception. However, how unimodal and camera-LiDAR fusion architectures behave under variations in LiDAR point sparsity induced by sensor configurations and scene-dependent sensing conditions remains underexplored. We introduce RESOLVE, a large-scale real-world benchmark dataset featuring multi-resolution roadside LiDAR and synchronized camera-LiDAR sensing for systematic evaluation of unimodal and fusion-based architectures in roadside 3D detection and tracking. RESOLVE contains over 100k images and 26k point cloud frames with 220k manually annotated bounding boxes, captured at a real-world urban intersection across diverse lighting and weather conditions and spanning 10 classes of traffic participants. In particular, RESOLVE enables controlled evaluation across three LiDAR resolution levels while keeping all other sensing and environmental factors fixed. This allows fair cross-architecture comparisons under point cloud distribution shifts resulting from resolution variations, sensing distance, and training-inference resolution mismatches. Results from extensive benchmark experiments reveal insights into how multimodal fusion can compensate for LiDAR point sparsity, offering clues for designing cost-efficient roadside multimodal perception. The dataset and benchmark codes are available at https://github.com/ASU-Suo-Lab/RESOLVE.

cs.CV↗

arXiv2025

Vehicular Communication Security: Multi-Channel and Multi-Factor Authentication

Secure and reliable communications are crucial for Intelligent Transportation Systems (ITSs), where Vehicle-to-Infrastructure (V2I) communication plays a key role in enabling mobility-enhancing and safety-critical services. Current V2I authentication relies on credential-based methods over wireless Non-Line-of-Sight (NLOS) channels, leaving them exposed to remote impersonation and proximity attacks. To mitigate these risks, we propose a unified Multi-Channel, Multi-Factor Authentication (MFA) scheme that combines NLOS cryptographic credentials with a Line-of-Sight (LOS) visual channel. Our approach leverages a challenge-response security paradigm: the infrastructure issues challenges and the vehicle's headlights respond by flashing a structured sequence containing encoded security data. Deep learning models on the infrastructure side then decode the embedded information to authenticate the vehicle. Real-world experimental evaluations demonstrate high test accuracy, reaching an average of 95% and 96.6%, respectively, under various lighting, weather, speed, and distance conditions. Additionally, we conducted extensive experiments on three state-of-the-art deep learning models, including detailed ablation studies for decoding the flashing sequence. Our results indicate that the optimal architecture employs a dual-channel design, enabling simultaneous decoding of the flashing sequence and extraction of vehicle spatial and locational features for robust authentication.

cs.CR↗

arXiv2025

High and Low Resolution Tradeoffs in Roadside Multimodal Sensing

Balancing cost and performance is crucial when choosing high- versus low-resolution point-cloud roadside sensors. For example, LiDAR delivers dense point cloud, while 4D millimeter-wave radar, though spatially sparser, embeds velocity cues that help distinguish objects and come at a lower price. Unfortunately, the sensor placement strategies will influence point cloud density and distribution across the coverage area. Compounding the first challenge is the fact that different sensor mixtures often demand distinct neural network architectures to maximize their complementary strengths. Without an evaluation framework that establishes a benchmark for comparison, it is imprudent to make claims regarding whether marginal gains result from higher resolution and new sensing modalities or from the algorithms. We present an ex-ante evaluation that addresses the two challenges. First, we realized a simulation tool that builds on integer programming to automatically compare different sensor placement strategies against coverage and cost jointly. Additionally, inspired by human multi-sensory integration, we propose a modular framework to assess whether reductions in spatial resolution can be compensated by informational richness in detecting traffic participants. Extensive experimental testing on the proposed framework shows that fusing velocity-encoded radar with low-resolution LiDAR yields marked gains (14 percent AP for pedestrians and an overall mAP improvement of 1.5 percent across six categories) at lower cost than high-resolution LiDAR alone. Notably, these marked gains hold regardless of the specific deep neural modules employed in our frame. The result challenges the prevailing assumption that high resolution are always superior to low-resolution alternatives.

cs.RO↗