Multi-sensor fusion represents a primary approach for enhancing environmental perception in intelligent transportation scenes. Among diverse fusion strategies, Bird’s-Eye View (BEV) perspective-based fusion methods have emerged as a prominent research focus owing to advantages such as unified spatial representation. However, current BEV fusion methods still face challenges with insufficient robustness in cross-modal alignment and weak perception of dynamic objects. To address these challenges, this paper proposes a Bidirectional Complementary Cross-Attention Module (BCCA), which achieves deep fusion of image and point cloud features by adaptively learning cross-modal attention weights, thereby significantly improving cross-modal information interaction. Secondly, we propose a Temporal Adaptive Fusion Module (TAFusion). This module effectively incorporates temporal information within the BEV space and enables efficient fusion of multi-modal features across different frames through a two-stage alignment strategy, substantially enhancing the model’s ability to perceive dynamic objects. Based on the above, we integrate these two modules to propose the Dual Temporal and Transversal Attention Network (DTTANet), a novel camera and LiDAR fusion framework. Comprehensive experiments demonstrate that our proposed method achieves improvements of 1.42% in mAP and 1.26% in NDS on the nuScenes dataset compared to baseline networks, effectively advancing the development of 3D object detection technology for intelligent transportation scenes.

In autonomous driving, adverse weather (rain, fog, night) degrades camera images (blur, missing details, low contrast) and introduces crossmodal fusion challenges: feature dimension mismatch and modal noise interference between LiDAR and camera. To address these issues, this paper first proposes a Fourier Regularized Inverse Convolution (FRIC) module. Using Fourier inverse filtering and a learnable upsampling mechanism, FRIC suppresses image blur and noise, restoring highquality visual features for subsequent fusion. Second, aiming at feature mismatch and modal noise under complex weather, a Heterogeneous Collaborative Enhancement (HCE) fusion module is introduced. It constructs a dualattention mechanism (spatial attention and coordinate attention) to capture complementary highlevel and lowlevel features, thereby weakening weatherinduced noise and enhancing key object representations. Based on FRIC and HCE, a multisensor fusion network integrating LiDAR and camera is built. The network fuses restored visual data with multilevel features to solve core difficulties of multimodal three dimensional (3D) object detection in complex weather and boost detection performance. Extensive experiments on nuScenes demonstrate that compared to the baseline, our method improves mean average precision (mAP) by 1.4% and the nuScenes Detection Score (NDS) by 1.1%. Specifically, nighttime mAP increases by 2.8% and rainyday mAP by 3.8%. These results verify the effectiveness of the proposed approach, providing reliable technical support for allweather perception in autonomous driving and related fields. The code is available at https://github.com/yushi123469/RHCE.git.

With the rapid advancement of intelligent driving, LiDAR and cameras provide complementary geometric and semantic information. Therefore, fusing these two sensors is a mainstream approach for 3D object detection. However, existing methods still face two key challenges: effectively exploiting complementary information among candidate boxes during post-processing and balancing detection accuracy with computational efficiency. To address these challenges, we first propose an aggregated Euclidean distance weighted box fusion (AED-WBF) method, which aggregates complementary information from multiple candidate boxes during post-processing to improve bounding-box selection and localization accuracy. We further develop a hybrid deformable half-conv (HDHC) module that jointly enhances global and local feature representations through hierarchical offset prediction and local neighborhood attention. By integrating half-conv with a separable self-attention mechanism, HDHC reduces computational complexity while maintaining detection accuracy. Based on AED-WBF and HDHC, we construct EAEPNet, an efficient multilevel LiDAR–camera fusion network for 3D object detection. Extensive experiments are conducted on the KITTI and nuScenes datasets. On the KITTI test set, EAEPNet improves the mean average precision (mAP) by 2.73% over the baseline network. On nuScenes, EAEPNet achieves a mAP of 72.5% and an nuScenes detection score (NDS) of 74.4% on the validation set, as well as a mAP of 73.2% and an NDS of 75.3% on the test set. These results validate the effectiveness of EAEPNet in multi-sensor 3D object detection and spatial measurement. Its strong performance across multiple datasets further demonstrates its potential for intelligent driving and real-time high-precision spatial measurement. The code is available at: https://github.com/juanmao73/EAEPNet .