Dec 2026· IEEE Robotics and Automation Letters· Vol 11, pp. 13829-13836· 0 citations· 44 references
TL;DR
A hierarchical context-detail enhancement (HCDE) framework to address challenges in local detail representation and long-range context modeling of 4D millimeter-wave radar, and designs a radar attribute-aware encoding (RAE) module to enable local detail modeling.
Abstract
As an emerging sensor for autonomous driving, 4D millimeter-wave radar has attracted increasing attention due to its all-weather robustness and cost-effectiveness. However, existing 4D radar-based detection frameworks still face challenges in local detail representation and long-range context modeling. To address these challenges, we propose a hierarchical context-detail enhancement (HCDE) framework. In the encoding stage, we design a radar attribute-aware encoding (RAE) module to enable local detail modeling. Specifically, RAE exploits the spatial coordinates, velocity, and intensity of radar points to establish neighborhood constraints and perform multi-feature space encoding, providing augmented local representations under sparse radar observations. Furthermore, in the bird's-eye-view (BEV) space, we present a dual-stream BEV enhancement (DSBE) module. The local branch reinforces structure, whereas the dynamic branch adaptively models long-range spatial context. Extensive experiments on the View-of-Delft (VoD) and TJ4DRadSet benchmarks demonstrate the effectiveness of the proposed framework.
While the fusion of 4D millimeter-wave radar and camera holds significant potential for 3D object detection in autonomous driving, the extreme sparsity of radar points and the deficiency of depth information in images lead to severe cross-modal spatial misalignment. Existing two-stage methods might suffer from the irre...
Yu-Zhe Song, De-Xing Lin, Jian Chen et al.· 0 citations
This review provides a task-oriented perspective on the transition from sparse object perception to dynamic spatial understanding and summarizes the task coverage, input data, annotations, and evaluation protocols of existing datasets, clarifying the empirical support for different research directions.
Xu-Min Wu, Jun-Lin Zhou, Ji-Lin Mei et al.· 0 citations
LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object detection in complex driving environments. However, sparse radar observations and differences in spatial sampling between the two modalities complicate reliable cross-mod...
Gang Ma, Sen-Jie Hu, Jun-Jie Liu et al.· arXiv.org· 0 citations
4D radar-camera fusion has attracted increasing attention for reliable 3D perception under adverse weather conditions. However, existing methods either lose valuable radar information by using sparse point clouds, or suffer from high computation when processing raw tensors directly. To address these challenges, this pa...
Li-Wei Luo, Xia Wu· IEEE Robotics and Automation...· 0 citations
Millimeter-wave radar is highly valuable for all-weather autonomous driving perception due to its excellent environmental robustness and range-velocity measuring capability. However, it inherently suffers from severe point cloud sparsity, high noise, and insufficient semantic information, which makes it challenging to...
Jian Dong, Hui-Ying Xu, Hong-Bo Li et al.· Measurement science and tech...· 0 citations
This work proposesours, an aerial-image detector built on the YOLO12 architecture, which combines a triple-path high-frequency enhancement convolution module (TriPathHFConv), receptive-field coordinate-attention convolution (RFCAConv), and a Mamba-based global-context module.
Hao Wang· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.