Abstract
Road-condition classification is a key enabler for intelligent transportation, cooperative safety, and autonomous driving. This paper proposes an enhanced analytical and cooperative V2V framework for inferring road and environmental states in real time. Vehicles exchange feature vectors containing traction, braking anomalies, visibility metrics, weather intensity, and density estimations. A mathematical model for weighted cooperative fusion is introduced, and five road-condition scoring functions are formulated. Analytical proofs for convergence, noise-resilience, and low-latency operation are provided [1]. A simulation scenario is presented with expected performance results. Accuracy, latency, and false-positive rate improvements are demonstrated through embedded figures. The findings confirm that cooperative V2V fusion greatly enhances classification reliability and responsiveness, making the framework suitable for next-generation vehicular networks.