The Internet of Things (IoT) is transforming intelligent transportation systems by connecting roadside cameras, edge computing units, vehicles, and traffic infrastructure into a shared sensing and decision-making ecosystem. However, transmitting raw traffic video over vehicle-to-everything (V2X) links is bandwidth-intensive, while deploying large multimodal models directly on resource-constrained vehicles is often impractical. To address these limitations, this article proposes VISTA (Vision-Informed Semantic Traffic Awareness), a multimodal vision-language edge-intelligence framework that combines predictive video representation learning with lightweight language-based reasoning to provide communication-efficient traffic situational awareness. In the proposed architecture, roadside surveillance units employ the Video Joint Embedding Predictive Architecture (V-JEPA) and an attentive-pooler module to convert traffic video clips into compact future-scene embeddings. These embeddings are transmitted through V2X links to vehicle-mounted systems, where a TinyLlama small language model, enhanced with a custom visual adapter, interprets the embeddings alongside natural-language (NL) traffic queries. VISTA enables vehicles to obtain interpretable traffic information, reason about upcoming scene dynamics, and identify potential collision risks without receiving raw video streams. Experimental results in a digital-twin urban traffic environment show that VISTA achieves 97.77% accuracy and an 89% F1 score for future collision prediction while reducing the communication payload by several orders of magnitude compared with raw RGB video transmission. These results demonstrate the feasibility of embedding-based multimodal intelligence for low-latency, communication-efficient, and safety-oriented IoT-enabled transportation systems.
翻译:暂无翻译