Global Navigation Satellite System (GNSS) environment recognition is important for enhancing positioning reliability and context awareness in complex urban and natural scenes. However, existing methods predominantly rely on signal features and necessitate extensive labeled datasets, compromising their robustness in label-scarce scenarios. To address this, we propose a large language model (LLM)-assisted, few-sample GNSS environment recognition framework. Our approach leverages LLM-generated physical-semantic soft labels for knowledge distillation during training and incorporates a lightweight test-time adaptation (TTA) strategy during inference. Experimental results demonstrate that with only 1% of labeled training data, the proposed method outperforms the baseline by 6% in classification accuracy.
A Spectral Decoupling Adaptive Modulation module enhances low-frequency semantics and high-frequency details in the frequency domain, while a Hierarchical Spatial Dependency Modeling module captures local consistency and global semantic dependencies.
Wei Zhao, Yingchao Dong, Lingchao Wang et al.· International Journal of Adv...· 0 citations
This paper develops the first Vision-Language Model (VLM)-based framework for GNSS spoofing detection for autonomous vehicles by fusing front-camera visual data with in-vehicle sensor readings against GNSS-derived maneuvers.
Mohammed Aldeen, Muhammad Sami Irfan, Sagar Dasgupta et al.· arXiv.org· 0 citations
A DeGIN (Deep GPS Increment Network) is proposed, which is a hybrid CNN-BiLSTM architecture for predicting GNSS position correction increments in latitude and longitude during signal outages, and achieves higher accuracy and better generalization than conventional baselines and recent deep learning approaches.
Khalid M. Nasr, Sherif Mostafa, Ali Maher et al.· GPS Solutions· 0 citations
A hybrid model combining a convolutional neural network (CNN) and a long short-term memory (LSTM) network provides a better balance between positioning accuracy and practical GPU training efficiency than PrNet under the evaluated conditions.
Qiang Guo, Zeng-Ke Li, Meng Sun et al.· Measurement science and tech...· 0 citations
A visual foundation model-based multilabel perception framework that leverages existing on-board surveillance videos without requiring additional sensors or manual annotation is proposed, enabling zero-shot recognition of diverse environmental elements.
Shize Huang, Yimin Shen, Qianhui Fan et al.· Journal of Transportation En...· 0 citations
A lightweight object detection framework, termed MDCF-YOLO, which achieves a superior accuracy-efficiency trade-off compared to state-of-the-art lightweight object detectors and exhibits similarly competitive performance on the AI-TOD dataset, further validating its effectiveness and generalization capability in UAV re...
Peng-Fei Dai, Liang Chen, Ting Fan et al.· Cluster Computing· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
