Multi-modal fusion indoor localization enabled by significant information gain is a crucial approach to ensure both accuracy and robustness. However, pronounced feature heterogeneity across modalities originating from distinct sources, and even intra-modality heterogeneity arising from multi-scale issues, can lead to severe ambiguity in location semantics, thereby severely constraining the localization accuracy of existing fusion methods. To address these challenges, we propose an accurate multi-modal fusion localization framework (FDLoc) that leverages frequency feature decomposition and dual-grained feature fusion to reduce intra- and inter-modality heterogeneity between magnetic and Wi-Fi modalities. First, we invoke Wavelet Packet Transforms to decompose the raw bimodal features in the frequency domain for explicitly representing their scale differences, and design a temporal-frequency attention to guide finegrained modeling of multi-scale features within each modality; by using nonlinear feature transformations, we further align the features of two modalities and adaptively fuse them across modalities, resulting in fused features with consistent semantic representation. Second, we incorporate contextual information from the localization process by employing a pretrained region prediction network to learn grid-level probability distribution, and use these coarse-grained region features to constrain the localization model for consistent positional convergence. Finally, we fuse the coarse- and fine-grained location semantic features using a gated network to achieve accurate location prediction. Experimental evaluations in typical indoor scenarios show that FDLoc consistently outperforms existing methods, with an average accuracy improvement of approximately 51 %.

Using ambient magnetic for indoor localization has been a research focus in recent years. However, intricate magnetic feature patterns in complicated indoor ambiance, with particular emphasis on the multi-scale dynamics arising from diverse user motion states, further hinder localization accuracy and universality. To address these challenges, this paper originally proposes a novel mixed-frequency magnetic data representation learning-based framework (MixLoc) for accurate and universal localization. Our core idea is to systematically model the multi-scale dynamics-affected pedestrian indoor localization as a location-semantic learning problem based on mixed-frequency magnetic data. First, we propose a data augmentation method to automatically construct a mixed-frequency magnetic dataset. Then, we propose a novel encoder to learn temporal and spatial representations from these data and extract subtle differences among multi-scale sequences. Finally, a novel localization model is proposed to accurately infer locations by capturing significant global and local features from both temporal and spatial representations. The evaluation results based on comprehensive experiments show that the accuracy of MixLoc increases about 42% compared to other state-of-the-art approaches.