Extended-Target Classification and Localization for Near-Field ISAC

TL;DR

This paper introduces a novel joint classification and localization framework for extended targets in near-field ISAC, leveraging a dual-branch inference with attention and structured supervision to improve accuracy and efficiency.

Contribution

It proposes a dual-branch inference framework with cross-task attention and structured supervision for extended target classification and localization in near-field ISAC.

Findings

Cross-task attention benefits classification accuracy.

Uncertainty-aware regression improves localization performance.

The framework achieves optimal joint operation with fewer sensing tones.

Abstract

Near-field integrated sensing and communication (ISAC) enables object-level sensing from distance-dependent array responses, yet most existing near-field methods still rely on point-target models and realistic extended targets remain largely unexplored. In this paper, joint target classification and range-azimuth localization are studied from channel responses of realistic extended targets. A dual-branch inference framework is proposed. Semantic and geometric branches are used for classification and localization, respectively. Cross-task attention is introduced after task-specific encoding so that complementary cues can be exchanged without forcing full feature sharing from the input stage. To improve localization on the same backbone, uncertainty-aware regression and a physics-guided structured objective are adopted, including planar consistency, peak-response regularization, and geometry-coupling constraints. Training and evaluation data are generated from full-wave electromagnetic scattering simulations of voxelized vehicle targets with randomized heading angles, material contrasts, and placements. The compared variants show that cross-task attention mainly benefits classification, while uncertainty-aware and structured supervision are needed to recover strong localization performance on the same backbone. Under the adopted shared-OFDM benchmark, the proposed framework reaches the best joint operating point with fewer sensing tones for the same target performance region.