# A Block-Sparse Bayesian Learning Algorithm with Dictionary Parameter Estimation for Multi-Sensor Data Fusion

arXiv: https://arxiv.org/abs/2503.12913 · HTML: https://mlsanity.com/paper/2503.12913/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2025.

## Built on by (most cited first, 1 of 1)

- [General Pruning Criteria for Fast SBL](https://mlsanity.com/paper/2509.21572/) (2025)

## Abstract (arXiv)

We propose an sparse Bayesian learning (SBL)-based method that leverages group sparsity and multiple parameterized dictionaries to detect the relevant dictionary entries and estimate their continuous parameters by combining data from multiple independent sensors. In a MIMO multi-radar setup, we demonstrate its effectiveness in jointly detecting and localizing multiple objects, while also emphasizing its broader applicability to various signal processing tasks. A key benefit of the proposed SBL-based method is its ability to resolve correlated dictionary entries-such as closely spaced objects-resulting in uncorrelated estimates that improve subsequent estimation stages. Through numerical simulations, we show that our method outperforms the newtonized orthogonal matching pursuit (NOMP) algorithm when two objects cross paths using a single radar. Furthermore, we illustrate how fusing measurements from multiple independent radars leads to enhanced detection and localization performance.