Lidars and cameras are critical sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, accurate and robust fusion methods are still under exploration due to non-homogenous representations. In this paper, we find that the complementary roles of point clouds and images vary with depth. An important reason is that the point cloud appearance changes significantly with increasing distance from the Lidar, while the image's edge, color, and texture information are not sensitive to depth. To address this, we propose a fusion module based on the Depth Attention Mechanism (DAM), which mainly consists of two operations: gated feature generation and point cloud division. The former adaptively learns the importance of bimodal features without additional annotations, while the latter divides point clouds to achieve differential fusion of multi-modal features at different depths. This fusion module can enhance the representation ability of original features for different point sets and provide more comprehensive features by using the dual splicing strategy of concatenation and index connection. Additionally, considering point density as a feature and its negative correlation with depth, we build an Adaptive Threshold Generation Network (ATGN) to generate the depth threshold by extracting density information, which can divide point clouds more reasonably. Experiments on the KITTI dataset demonstrate the effectiveness and competitiveness of our proposed models.

In terms of urban rail transit network vulnerability, most studies have focused on the network topology characteristics and travel cost changes after network incidents and analyzed rail transit network independently. The neglects of passenger flow distributions on the network and alternative public transport modes under rail network disruptions would either underestimate or overestimate the vulnerability of rail transit network, and thus lead to inaccurate results and decisions. This study presents an accessibility-based measurement for urban rail transit network vulnerability analysis and explicitly accounts for rail passenger flow characteristics, travel cost changes, and alternative transit modes. It is shown that the proposed approach is capable of measuring the consequences on rail network, and the advantages of the accessibility method are demonstrated and compared. The methodology is applied to the urban rail transit network of Shenzhen, China within a multi-modal public transport network. Results reveal that the consequences of disruptions on network accessibility are obviously different for stations with different passenger flow characteristics, and some undisrupted stations are found to be vulnerable under surrounding station failures. The proposed methodology offers reliable measurements on rail transit network vulnerability and implications for decision-making under rail network disruptions.

Autonomous driving has received much attention in the last decade as a key component of intelligent transportation, and vehicle detection serves as a fundamental task for autonomous driving. Although recent learning-based methods have achieved great advances in terms of accuracy, these methods are usually computationally expensive and cannot be deployed on resource-limited devices. To address this limitation, in this paper, we aim to develop an efficient yet highly accurate vehicle detection method by tailoring a network quantization method. Due to the small objects and diverse scenarios in the real world, we introduce learnable scale parameters for network quantization to achieve flexible adaption. Ablation study is conducted to demonstrate the effectiveness of our method. In addition, extensive experiments are conducted on the UA-DETRAC and KITTI datasets for performance evaluation. Compared to previous generic network quantization methods, our method produces significantly better performance. Moreover, our quantized network surpasses previous lightweight vehicle detection methods in terms of both accuracy and efficiency, establishing a new baseline for vehicle detection.

Traffic sign detection is a research hotspot in advanced assisted driving systems, given the complex background, light transformation, and scale changes of traffic sign targets, as well as the problems of slow result acquisition and low accuracy of existing detection methods. To solve the above problems, this paper proposes a traffic sign detection method based on a lightweight multiscale feature fusion network. Since a lightweight network model is simple and has fewer parameters, it can greatly improve the detection speed of a target. To learn more target features and improve the generalization ability of the model, a multiscale feature fusion method can be used to improve recognition accuracy during training. Firstly, MobileNetV3 was selected as the backbone network, a new spatial attention mechanism was introduced, and a spatial attention branch and a channel attention branch were constructed to obtain a mixed attention weight map. Secondly, a feature-interleaving module was constructed to convert the single-scale feature map of the specified layer into a multiscale feature fusion map to realize the combined encoding of high-level semantic information and low-level semantic information. Then, a feature extraction base network for lightweight multiscale feature fusion with an attention mechanism based on the above steps was constructed. Finally, a key-point detection network was constructed to output the location information, bias information, and category probability of the center points of traffic signs to achieve the detection and recognition of traffic signs. The model was trained, validated, and tested using TT100K datasets, and the detection accuracy of 36 common categories of traffic signs reached more than 85%, among which the detection accuracy of five categories exceeded 95%. The results showed that, compared with the traditional methods of Faster R-CNN, CornerNet, and CenterNet, traffic sign detection based on a lightweight multiscale feature fusion network had obvious advantages in the speed and accuracy of recognition, significantly improved the detection performance for small targets, and achieved a better real-time performance.

Freeway bottleneck areas are prone to congestion and have high accident risk. A variable speed limit provides technical support for alleviating congestion and improving traffic safety in such areas. The existing variable speed limit rules in the related literature have a single focus, and most of them do not give specific quantitative speed limits. In this study, a variable speed limit system suitable for freeway bottleneck areas was constructed. Variable speed limit rules under different levels of traffic congestion and adverse weather conditions were designed, and the parameters for freeways were defined. Then, the VISSIM microscopic traffic simulation software was used to build two bottleneck scenarios of a tunnel area and a merging area for simulation tests. The research shows that in these two scenarios, reasonable speed limits can effectively reduce roadway delays and improve the operational efficiency of bottleneck areas in certain traffic flow ranges (e.g., a medium flow of around 900 pcu/h/lane). Unreasonable speed limits in low flow inhibit freeway efficiency more significantly. When congestion has already formed with high flow, different speed limits have a limited effect on efficiency improvement. The research results reported in this paper can provide a theoretical reference for the design and practical application of variable speed limit systems in freeway bottleneck areas. This provides a certain contribution to sustainable traffic development.

The printed circuit board (PCB) is the core control unit of electromechanical equipment. In order to determine the influence of the coupling vibration caused by vehicle–road interaction on the PCB reliability of roadside electromechanical equipment, first, the dynamic load of the vehicle tire is solved by establishing the dynamic model of a vehicle road. Then, the acceleration response data generated by road vibration are obtained by solving the road finite element model. Finally, the power density spectrum of the acceleration response is taken as input excitation, and the deformation response of the PCB under vehicle–road coupling vibration is analyzed. The experimental results show that when the vehicle is driving close to the roadside, the vibration caused by vehicle–road coupling will lead to a large deformation of the PCB, and the deformation value reaches 0.170 mm, which can cause structural damage to the PCB. This shows that the vehicle–road coupling vibration can affect the reliability of the roadside electromechanical equipment; thus, the optimal design of the PCB layout is created. After optimization, the first-order modal frequency of the PCB is increase by 5.4%, which reduces the risk of the components breaking away from the PCB substrate.