Millimeter-wave (mmWave) radar is widely used for vehicle detection in adverse weather conditions due to its robustness against environmental interference. However, the sparsity of mmWave radar data and the lack of height information significantly limit its broader applicability. To address these challenges, we propose MVDFusion, a multi-modal vehicle detection framework that integrates LiDAR and radar data for robust perception in foggy environments. The proposed framework is designed to fully exploit LiDAR information to compensate for the limitations of sparse radar data. Specifically, two key modules are developed: a radar height query module to enhance height estimation, and a radar–LiDAR query fusion module to improve feature representation. This design enables deep feature-level integration of mmWave radar and LiDAR data. Extensive experiments on the Oxford Radar RobotCar dataset demonstrate that MVDFusion achieves superior performance and robustness under foggy conditions. In particular, it outperforms existing state-of-the-art methods at intersection-over-union thresholds of 0.5, 0.65, and 0.8, achieving detection accuracies of 95.8%, 94.2%, and 81.5%.
This paper presents a preconditioner-based parallel-in-time (PinT) method for solving the quasi-static Biot’s consolidation model in poroelasticity, a problem characterized by stiff coupling and saddle-point structures. To address the computational challenges of the resulting large-scale linear systems, we design two physics-based Schur-complement approximation preconditioners that ensure robust Krylov convergence. Crucially, the method achieves a pipelined space-time architecture by introducing an inverted time-stepping mechanism: Instead of sequential time marching, time steps are traversed in the inner loop, while the outer loop applies an iterative solve across the entire space-time trajectory. This structure relaxes the strict dependency on fully converged solutions at each time step, enabling approximate solutions to be iteratively refined in parallel. Implemented as a pipelined wavefront scheme with strictly nearest-neighbor communication, the algorithm achieves strong scalability. Algorithmic verification conducted on systems with up to 200 thousand degrees of freedom demonstrates stable convergence and sustained strong scaling with up to 128 cores. The proposed approach maintains the accuracy of the underlying finite element discretization while alleviating the “time bottleneck,” making it highly effective for large-scale, long-duration poroelastic simulations.