Vehicle Localization in IoV Environments: A Vision-LSTM Approach with Synthetic Data Simulation

Vehicles, Год журнала: 2025, Номер 7(1), С. 12 - 12

Опубликована: Янв. 31, 2025

With the rapid development of Internet Vehicles (IoV) and autonomous driving technologies, robust accurate visual pose perception has become critical for enabling smart connected vehicles. Traditional deep learning-based localization methods face persistent challenges in real-world vehicular environments, including occlusion, lighting variations, prohibitive cost collecting diverse datasets. To address these limitations, this study introduces a novel approach by combining Vision-LSTM (ViL) with synthetic image data generated from high-fidelity 3D models. Unlike traditional reliant on costly labor-intensive data, datasets enable controlled, scalable, efficient training under environmental conditions. enhances feature extraction classification performance through its matrix-based mLSTM modules advanced aggregation strategy, effectively capturing both global local information. Experimental evaluations independent target scenes distinct features structured indoor environments demonstrate significant gains, achieving matching accuracies 91.25% 95.87%, respectively, outperforming state-of-the-art These findings underscore innovative advantages integrating highlighting potential to overcome reduce costs, enhance accuracy reliability vehicle applications such as navigation perception.

Язык: Английский

Synergy optimization of energy management strategy for extended-range electric vehicles incorporating road noise perception

Energy, Год журнала: 2025, Номер unknown, С. 136783 - 136783

Опубликована: Май 1, 2025

Язык: Английский