Search

Nowadays, the commercial potential of live e-commerce is being continuously explored, and machine vision algorithms are gradually attracting the attention of marketers and researchers. During live streaming, the visuals can be effectively captured by algorithms, thereby providing additional data support. This paper aims to consider the diversity of live streaming devices and proposes an extremely lightweight and high-precision model to meet different requirements in live streaming scenarios. Building upon yolov5s, we incorporate the MobileNetV3 module and the CA attention mechanism to optimize the model. Furthermore, we construct a multi-object dataset specific to live streaming scenarios, including anchor facial expressions and commodities. A series of experiments have demonstrated that our model realized a 0.4% improvement in accuracy compared to the original model, while reducing its weight to 10.52%.

The vehicle-road collaborative intelligence approach has become an industry consensus. It can efficiently tackle the technical hurdles and reduce the performance requirements and costs of on-board perception and computing devices. There is a need for in-depth quantitative studies to optimize the allocation of vehicle-road intelligent capabilities for collaborative intelligence. However, current research tends to focus more on qualitative analysis, and there is little research on the redistribution of vehicle and roadside intelligent capabilities. In this paper, we present a model for distributing perception and computing capabilities between vehicle-side and roadside, ensuring to meet the needs of various autonomous driving levels. Meanwhile, the collaborative intelligence approach will also introduce the costs of intelligent infrastructure deployment, energy, and maintenance. Different roads have varying scene characteristics and usage intensities. It is necessary to conduct a cost-effectiveness analysis of the intelligent deployment of different road types. A vehicle-road cost allocation model is developed based on the lifecycle traveled distance of vehicles and the lifecycle traffic flow of various roads to evaluate the function-cost effectiveness. Our study presents several vehicle-road intelligent schemes that meet the needs of various autonomous driving levels and selects Beijing for case analysis. The results indicate that primary intelligent infrastructure can reduce the lifecycle cost of the vehicle-side intelligent scheme for intermediate autonomous driving from ¥65,301 to ¥37,703, and advanced intelligent infrastructure can reduce the lifecycle cost for advanced autonomous driving from ¥126,938 to ¥42,180. Considering the distributed cost of vehicle-side and roadside, urban roads in Beijing have higher function-cost effectiveness compared to highways, especially urban expressways, which are expected to generate 43.3 times the vehicle-function-cost benefits after the advanced intelligent upgrades. The corresponding research findings can serve as a reference for city managers to make decisions on intelligent road deployment.

Technical route decision making of intelligent driving has always been the focus of attention of automotive enterprises and even the industry. Firstly, this study combs the main technical routes of intelligent driving at different levels from three dimensions: development strategy, intelligence allocation and sensor combination. Then, the methodology of technical component combination is designed to disassemble different technical routes into corresponding technical component combinations. Finally, an improved evaluation model of total cost of ownership of intelligent driving is developed and the total cost of ownership of intelligent driving system under different technical routes is compared. For the development strategy, even if the function superposition can follow some research and development achievements of low-level intelligent driving, scenario-driven is still the option with lower cost and better sustainability. For intelligence allocation, collaborative intelligence can effectively reduce the cost of the vehicle compared with single-vehicle intelligence by up to 46%, but the cost reduction depends on the original on-board hardware. For sensor combination, the multi-source fusion always has the cost advantage compared with vision-only, but the advantage is more obvious in the medium-level and high-level stage of single-vehicle intelligence.

The Measurement-While-Drilling (MWD) system, composed of a tri-axial magnetometer and a tri-axial accelerometer, is widely used in the Horizontal Directional Drilling machine in coal mines. This system can provide attitude information of each measuring point in the borehole, which will eventually allow the trajectory of the borehole to be drawn. The attitude information, however, showed a low-level accuracy, due to the sensor’s imperfection and mounting errors. The accuracy worsened when low-cost sensors were employed, as they had higher random noise. Therefore, an exploration of ways to eliminate the sensor imperfection and mounting tolerance as well as to suppress the noise is needed. In this paper, a feasible calibration approach was designed to address these issues. This new approach combined three foundational calibration algorithms, including the ellipsoidal fitting method, the planar fitting method, and the inner product invariance method. The traditional ellipsoidal fitting method and planar fitting method were optimized by using the recursive least square criterion and omitting the steps of sample data acquisition, respectively. In addition, the noise suppression method was involved in our approach to improve the calibration accuracy. The numerical simulation results showed that the number of sampling points decreased significantly, but the accuracy of the azimuthal angle and the pitch angle fully met the engineering requirements. The experimental results showed that the pitch angle error was reduced by less than 0.5°, and the azimuth error was also reduced by less than 2.5°. It should be noted that this new approach could be implemented without the help of other expensive auxiliary equipment.

There are big differences between the driving behaviors of intelligent connected vehicles (ICVs) and traditional human-driven vehicles (HVs). ICVs will be mixed with HVs on roads for a long time in the future. Different intelligent functions and different driving styles will affect the condition of traffic flow, thereby changing traffic efficiency and emissions. In this paper, we focus on China’s expressways and secondary motorways, and the impacts of the ‘single-lane automatic driving system’ (SLADS) on traffic delay, road capacity and carbon dioxide (CO2) emissions were studied under different ICV penetration rates. Driving styles were regarded as important factors for scenario analysis. We found that with higher volume input, SLADS has an optimizing effect on traffic efficiency and CO2 emissions generally, which will be more significant as the ICV penetration rate increases. Additionally, enhancing the aggressiveness of driving behavior appropriately is an effective way to amplify the benefits of SLADS.