Composition optimization of the asphalt mixture of pavement is one effective measures to reduce the harm of traffic noise. To improve the noise reduction effect of porous asphalt mixture (PAM) and promote the recycling of crumb rubber in highway engineering, the preparation parameters of high-viscosity modified asphalt for PAM were optimized in this study, and the mixture gradation was optimized based on the unbalance force and contact force of mixed aggregate. The effects of crumb rubber content and particle size on the damping performance and dynamic shear modulus of the mixture were studied. The effects of different preparation parameters on the performance of the PAM were comprehensively evaluated based on the orthogonal test, and preparation parameters of PAM were recommended. The results show that with the increase of crumb rubber content, the damping ratio of the mixed aggregate increases gradually. The addition of crumb rubber is conducive to improving the damping performance and toughness of the PAM, but it has an adverse impact on the bearing capacity. Under the condition of low strain, the damping ratio of the mixed aggregate containing 2–5 mm crumb rubber is 1.2–5 times that of the mixed aggregate containing 0.6–1 mm crumb rubber. The recommended optimum content of crumb rubber in PAM is 4%, and the optimum particle size of alternative aggregate is 2.36–4.75 mm. The significant factors affecting Marshall stability are rubber particle content, asphalt aggregate ratio, mixing temperature, compaction times, and forming temperature. The rational utilization of crumb rubber in PAM is of positive significance to promoting the green development of highway construction and the harmless treatment of waste resources.

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.

For analyzing the traffic anomaly within dashcam videos from the perspective of ego-vehicles, the agent should spatial-temporally localize the abnormal occasion and regions and give a semantically recounting of what happened. Most existing formulations concentrate on the former spatial-temporal aspect and mainly approach this goal by training normal pattern classifiers/regressors/dictionaries with large-scale availably labeled data. However, anomalies are context-related, and it is difficult to distinguish the margin of abnormal and normal clearly. This paper proposes a progressive unsupervised driving anomaly detection and recounting (D&R) framework. The highlights are three-fold: (1) We formulate driving anomaly D&R as a temporal-spatial-semantic (TSS) model, which achieves a coarse-to-fine focusing and generates convincing driving anomaly D&R. (2) This work contributes an unsupervised D&R without any training data while performing an effective performance. (3) We novelly introduce the traffic saliency, isolation forest, visual semantic causal relations of driving scene to effectively construct the TSS model. Extensive experiments on a driving anomaly dataset with 106 video clips (temporal-spatial-semantically labeled carefully by ourselves) demonstrate superior performance over existing techniques.

The separation of battery charging and swapping processes enables highway operators to more flexibly manage the recharging of depleted batteries at battery swapping stations (BSSs), while also leveraging renewable energy (RE) resources to lower electricity costs. However, previous studies have not addressed the connection between BSS recharging strategies and the demand for fully charged batteries, which is determined by EV swapping schemes. To address this gap, the paper proposes a joint optimization approach for scheduling EVs and managing BSSs, considering RE generation along the highway. Specifically, a spatial-temporal network model is developed to represent the transportation-energy characteristics of EVs, incorporating BSS selection and battery swapping processes. Additionally, a BSS management model is formulated to plan the recharging of depleted batteries and ensure the availability of fully charged batteries to meet the swapping demands of EVs. The Lagrange relaxation algorithm is employed to handle the interaction between EV scheduling and BSS operations. A case study shows that this method effectively coordinates EV swapping schemes with BSS recharging strategies, resulting in a 17.3% improvement in RE generation utilization and a reduction in grid electricity consumption by RMB 1753.8.

The highway transportation system exhibits immense potential for adaptive functioning due to its distinctive operational attributes. This capability permits to harness more renewable energy, leading to a reduction in energy consumption costs. In this article, an integrative energy system optimization model is introduced from the standpoint of highway service zone operators. To simulate the behavior of electric vehicles on highways, an expanded network flow model is formulated considering driving, queueing, and charging actions. This model comprehensively integrates dimensions of time, space, and the state of charge of the vehicles. Consequently, the proposed model is proficient in representing the spatiotemporal and flexible operational traits inherent to electric vehicles. Through a series of numerical case studies executed on a real-world highway system, the effectiveness of the proposed model is demonstrated. These findings substantiate the potential utility and efficacy of our model in enhancing the operation optimization of energy systems within highway transportation systems.

Regard for the facts that the low accuracy and low real-time of the artificial observation to determine the road icing condition, and it is difficult to forecast icing situation, according to the main factors influencing the road-icing, and the electrical characteristics reflected by the pavement ice layer, this paper presents an innovative system, that is, ice-forecasting of the highway’s dangerous section. The system bases on road surface water salinity measurements and pavement temperature measurement to calculate the freezing point of water and temperature change trend, and then predicts the occurrence time of road icing; using capacitance measurements to verdict the road surface is frozen or not; This paper expounds the method of using single chip microcomputer as the core of the control system and described the business process of the system.