Aug 2026· Italian National Conference on Sensors· Vol 26, pp. 5276· 0 citations· 20 references
Medicine
TL;DR
This study will provide reliable fundamental support for the training and verification of 4D imaging radar perception algorithms, vehicle decision-making and planning in complex scenarios, and multi-sensor fusion technologies.
Abstract
The latest generation of 4D imaging radar demonstrates significant potential in autonomous driving environmental perception, leveraging its capability to provide target elevation data and dense point clouds. This paper introduces a complete method for constructing a multimodal 4D imaging radar dataset for three-dimensional traffic scenes. It illustrates the hardware and software configurations of the data-acquisition vehicle. Methods including multi-sensor coordination, parameter calibration, timestamp synchronization and spatial datum synchronization are proposed. And eight typical three-dimensional traffic scenarios are designed, such as rainy weather environments, dense heterogeneous targets, enclosed tunnels, high-speed cut-in of multiple vehicles, multi-layered stereoscopic structures and edge working condition reproduction. In addition, this paper puts forward a frame-by-frame processing method for high-resolution images and point cloud data collected by the high-definition camera-LiDAR-4D imaging radar collaborative system. A large model-based 3D annotation method for multiple types of targets is proposed, generating a spatio-temporal sequence-optimized four-dimensional annotation sequence, and finally constructs a complete and high-quality multimodal 4D imaging radar dataset for three-dimensional traffic scenes. The results show that the constructed dataset enables the synchronization of timestamps and spatial coordinate systems. The large model can achieve high-precision 3D annotation for the four predefined target types. The dataset contains 11,400 frames of data from high-definition cameras, LiDAR, and 4D imaging radar, with 131,642 labels. This study will provide reliable fundamental support for the training and verification of 4D imaging radar perception algorithms, vehicle decision-making and planning in complex scenarios, and multi-sensor fusion technologies.
To address the challenges of insufficient feature representation and the difficulty of detecting sparse and distant objects in UAV-borne LiDAR point clouds—which exhibit significantly lower point density than terrestrial/mobile LiDAR scans—this paper proposes an enhanced detection algorithm built upon the PointPillars framework. First, a coordinate attention mechanism is incorporated to enhance the network’s ability to capture spatial geometric information. Furthermore, the backbone network is redesigned with a dual-path structure and a feature modulation fusion module, enabling adaptive integration of multi-scale features. Experimental evaluations conducted on a custom simulated UAV-borne LiDAR point cloud dataset demonstrate that the proposed method achieves 85.35% 3D mAP and 88.26% BEV mAP, corresponding to absolute improvements of 21.61 and 7.85 percentage points compared with the original PointPillars model. In addition, the proposed approach demonstrates consistent performance on the publicly available KITTI benchmark through preliminary cross-dataset validation. The results indicate that the proposed method can effectively improve the detection accuracy and robustness of LiDAR-based 3D object detection in complex environments.
Yu Zhai, Sen Xie, Wenhao Li et al.· Electronics· 0 citations
Four-dimensional (4D) Radar is a powerful sensing modality capable of detecting surrounding three-dimensional (3D) objects under diverse weather conditions and providing Doppler-based motion information. However, raw 4D Radar signals contain significant clutter from road surfaces, guardrails, and surrounding vehicles, along with multipath-induced ghost reflections and the receiver's inherent noise floor. Consequently, preprocessing algorithms designed to remove such invalid measurements often make the Radar data excessively sparse. Moreover, the Doppler measurements provided by 4D Radar describe only the radial component of an object's velocity, limiting their ability to recover the full motion state. In this paper, we introduce a stereo 4D Radar-based 3D object detection framework that exploits the geometric disparity between left and right Radars to estimate the absolute velocity of objects and achieve more robust perception through the fusion of their complementary features. The effectiveness of the proposed framework is validated on our in-house stereo 4D Radar dataset, demonstrating performance gains of 8.82 points in AP 3D and 9.0 points in AP BEV over state-of-the-art mono 4D Radar baselines. These results demonstrate that absolute velocity estimation combined with stereo geometry-aware feature fusion leads to substantial improvements in 3D object detection.
Seung-Hyun Song, Dong-Hee Paek, Woong-Chan Byun et al.· 0 citations
A vector map containing lane information is essential to perform global or local path planning for autonomous driving. Vector maps, also termed high-definition (HD) maps, are typically developed using high-cost LiDAR or a combination of cameras and deep learning. In this article, the first complete real-time vector map simultaneous localization and mapping (SLAM) system using the emerging 4-D radar and low-cost cameras is proposed. First, a dynamic object removal mask (DORM)-based visual-4-D radar odometry is proposed, which incorporates a velocity-adaptive and distance-dependent radius function to ensure robust performance in dynamic urban environments. By considering both the object’s absolute velocity and its distance from the sensor, our method effectively suppresses dynamic features while preserving distant static landmarks. The experimental results indicate that the proposed method outperforms state-of-the-art LiDAR SLAM and other techniques in dynamic scenarios. Second, a two-stage loop detection method is suggested using the vector map generated by the inverse perspective mapping (IPM) and the 4-D radar $Z$ projection image. Experimental validation demonstrates that odometry drift is reduced through pose graph optimization-based loop closure. A demonstration video related to this work is available at the following link: https://youtu.be/pPb2ze24F30
Aiming at the complex scene characteristics of dense substation equipment, metal reflection, and strong electromagnetic interference, and the problems of insufficient accuracy, texture loss, and poor robustness of traditional single or double sensor 3D reconstruction, this paper proposes a 3D reconstruction method of visual Lidar inertial fusion. This method develops a handheld multi-sensor acquisition device suitable for substation scenes to realize the spatial-time synchronization and tightly coupled fusion optimization of lidar, camera, and inertial data, and improves the pose estimation accuracy through factor graph optimization and error smoothing. The actual substation experiment shows that the proposed method can generate a three-dimensional model with high-precision geometric structure and real texture.
Le Ren, Guixin Zhang, Zhaoting Hou et al.· Journal of Physics, Conferen...· 0 citations
Differential tomographic synthetic aperture radar (D-TomoSAR) has emerged as a powerful technique for 3-D reconstruction and deformation monitoring of urban buildings. However, most existing spaceborne SAR tomography studies have only used single-polarization channels, leaving the advantages of multipolarization information inherent to dual-polarimetric data insufficiently exploited. To address this limitation, this letter proposes a polarimetric phase-optimized D-TomoSAR method for building reconstruction and deformation monitoring, utilizing dual-polarimetric spaceborne SAR data acquired by the PAZ satellite. The proposed approach employs the exhaustive search polarization optimization (ESPO) algorithm to enhance polarimetric signal quality and integrates a compressive sensing (CS) framework based on orthogonal matching pursuit (OMP) for the joint estimation of 3-D scatterer elevations and temporal deformation rates. Experimental results demonstrate that the proposed method significantly improves monitoring point density, point cloud reconstruction quality, and noise suppression compared with conventional single-polarization approaches, validating the applicability and practical potential of PAZ dual-polarimetric SAR (PolSAR) data for D-TomoSAR-based urban infrastructure monitoring.
Leixin Zhang, Feng Zhao, J. Mallorquí et al.· IEEE Geoscience and Remote S...· 0 citations
Abstract. Semantic classification is a fundamental step in Mobile Laser Scanning (MLS) point clouds processing, and remains a non-trivial task. In this work, we propose a classification framework based on a 3D Sparse Convolutional Neural Network (SparseCNN) for efficient processing of large-scale MLS data. A coarse-to-fine two-stage pipeline is introduced, where an essential model performs a classification for the entire scene, followed by a refinement stage for detailed ground-surface classes. To enhance robustness under diverse acquisition conditions, both point-wise and scene-wise data augmentation strategies are employed during the training, including rotation, jittering, density perturbation, noise injection, and patch swapping. To account for environmental and sensor variations, wavelength-specific models are trained for both urban and highway scenes. Experimental results on urban and highway datasets demonstrate strong performance, achieving over 90% accuracy for major classes, while ablation studies show that radiometric features are critical for distinguishing material dependent classes, such as traffic signs, and that the proposed augmentation strategies improve performance for challenging object categories, such as pedestrian, which is dynamic and structurally ambiguous.
Nan-Feng Li, H. Teufelsbauer, F. Pöppl et al.· The International Archives o...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
