Camera and millimeter-wave (MMW) radar fusion is essential for accurate and robust autonomous driving systems. With the advancement of radar technology, next-generation high-resolution automotive radar, i.e., 4D radar, has emerged. In addition to the target range, azimuth, and Doppler velocity measurements of traditional radar, 4D radar provides elevation measurement to create a denser “point cloud.” In this study, we propose a camera and 4D radar fusion network called RCFusion, which achieves multimodal feature fusion under a unified bird’s-eye view (BEV) space to accomplish 3D object detection tasks. In the camera stream, multi-scale feature maps are obtained by the image backbone and feature pyramid network; they are then converted into orthographic feature maps by an orthographic feature transform. Next, enhanced and fine-grained image BEV features are obtained via a designed shared attention encoder. Meanwhile, in the 4D radar stream, a newly designed component named Radar PillarNet efficiently encodes the radar features to generate radar pseudo-images, which are fed into the point cloud backbone to create radar BEV features. An interactive attention module is proposed for the fusion stage, which outputs a valid fusion of the two-modal BEV features. Finally, a generic detection head predicts the object classes and locations. The proposed RCFusion is validated on the TJ4DRadSet and View-of-Delft datasets. The experimental results and analysis show that the proposed method can effectively fuse camera and 4D radar features to achieve robust detection performance.

Hand gesture recognition technology plays an important role in human-computer interaction and in-vehicle entertainment. Under in-vehicle conditions, it is a great challenge to design gesture recognition systems due to variable driving conditions, complex backgrounds, and diversified gestures. In this paper, we propose a gesture recognition system based on frequency-modulated continuous-wave (FMCW) radar and transformer for an in-vehicle environment. Firstly, the original range-Doppler maps (RDMs), range-azimuth maps (RAMs), and range-elevation maps (REMs) of the time sequence of each gesture are obtained by radar signal processing. Then we preprocess the obtained data frames by region of interest (ROI) extraction, vibration removal algorithm, background removal algorithm, and standardization. We propose a transformer-based radar gesture recognition network named RGTNet. It fully extracts and fuses the spatial-temporal information of radar feature maps to complete the classification of various gestures. The experimental results show that our method can better complete the eight gesture classification tasks in the in-vehicle environment. The recognition accuracy is 97.56%.

Odometry is a crucial technology for the autonomous positioning of intelligent vehicles. While estimating the odometry from LiDAR and cameras has progressed recently, it remains to be seen how to estimate the odometry from a 4D radar, an emerging sensor with unique advantages over cameras and LiDAR. In this study, a deep-learning-based 4D radar odometry method, named 4DRO-Net, is proposed. The method employs a coarse-to-fine hierarchical optimization technique based on a sliding window to estimate and refine an autonomous vehicle's pose in an iterative manner. A feature-extraction network for 4D radar point clouds is proposed to achieve efficient learning of sparse point clouds. An initial pose-generation module is constructed to obtain the initial pose, which is used to warp the first point cloud and bridge the distance to the second point cloud. A velocity-aware attention cost volume module is then developed to correlate the warped first point cloud with the second point cloud to obtain point-motion information. The velocity information of the radar points is used to learn the attention weights to increase the robustness of the motion information estimation. Motion information is used to regress the corrected pose, which is then used to refine the initial pose to obtain a more accurate final pose. The superior performance and effectiveness of our 4D radar odometry method are demonstrated on both the View-of-Delft and an in-house dataset.

3D object detection and occupancy prediction are critical tasks in autonomous driving, attracting significant attention. Despite the potential of recent vision-based methods, they encounter challenges under adverse conditions. Thus, integrating cameras with next-generation 4D imaging radar to achieve unified multi-task perception is highly significant, though research in this domain remains limited. In this paper, we propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction, enabling comprehensive environmental perception. Specifically, we introduce a novel Coarse Voxel Queries Generator that integrates geometric priors from 4D radar with semantic features from images to initialize voxel queries, establishing a robust foundation for subsequent Transformer-based refinement. To leverage temporal information, we design a Dual-Branch Temporal Encoder that processes multi-modal temporal features in parallel across BEV and voxel spaces, enabling comprehensive spatio-temporal representation learning. Furthermore, we propose a Cross-Modal BEV-Voxel Fusion module that adaptively fuses complementary features through attention mechanisms while employing auxiliary tasks to enhance feature quality. Extensive experiments on the OmniHD-Scenes, View-of-Delft (VoD), and TJ4DRadSet datasets demonstrate that Doracamom achieves state-of-the-art performance in both tasks, establishing new benchmarks for multi-modal 3D perception. Code and models can be available at https: //github.com/TJRadarLab/Doracamom.

This paper presents a target tracking algorithm based on 4D millimeter-wave radar point cloud information for autonomous driving applications, which addresses the limitations of traditional 2 + 1D radar systems by using higher resolution target point cloud information that enables more accurate motion state estimation and target contour information. The proposed algorithm includes several steps, starting with the estimation of the ego vehicle’s velocity information using the radial velocity information of the millimeter-wave radar point cloud. Different clustering suggestions are then obtained using a density-based clustering method, and correlation regions of the targets are obtained based on these clustering suggestions. The binary Bayesian filtering method is then used to determine whether the targets are dynamic or static targets based on their distribution characteristics. For dynamic targets, Kalman filtering is used to estimate and update the state of the target using trajectory and velocity information, while for static targets, the rolling ball method is used to estimate and update the shape contour boundary of the target. Unassociated measurements are estimated for the contour and initialized for the trajectory, and unassociated trajectory targets are selectively retained and deleted. The effectiveness of the proposed method is verified using real data. Overall, the proposed target tracking algorithm based on 4D millimeter-wave radar point cloud information has the potential to improve the accuracy and reliability of target tracking in autonomous driving applications, providing more comprehensive motion state and target contour information for better decision making.

The rapid advancement of deep learning has intensified the need for comprehensive data for use by autonomous driving algorithms. High-quality datasets are crucial for the development of effective data-driven autonomous driving solutions. Next-generation autonomous driving datasets must be multimodal, incorporating data from advanced sensors that feature extensive data coverage, detailed annotations, and diverse scene representation. To address this need, we present OmniHD-Scenes, a large-scale multimodal dataset that provides comprehensive omnidirectional high-definition data. The OmniHD-Scenes dataset combines data from 128-beam LiDAR, six cameras, and six 4D imaging radar systems to achieve full environmental perception. The dataset comprises 1501 clips, each approximately 30-s long, totaling more than 450 K synchronized frames and more than 5.85 million synchronized sensor data points. We also propose a novel 4D annotation pipeline. To date, we have annotated 200 clips with more than 514 K precise 3D bounding boxes. These clips also include semantic segmentation annotations for static scene elements. Additionally, we introduce a novel automated pipeline for generation of the dense occupancy ground truth, which effectively leverages information from non-key frames. Alongside the proposed dataset, we establish comprehensive evaluation metrics, baseline models, and benchmarks for 3D detection and semantic occupancy prediction. These benchmarks utilize surround-view cameras and 4D imaging radar to explore cost-effective sensor solutions for autonomous driving applications. Extensive experiments demonstrate the effectiveness of our low-cost sensor configuration and its robustness under adverse conditions.