Jianguo Zhu’s research while affiliated with China High Speed Transmission and other places

Pavement damage detection is essential for subsequent road maintenance decisions. However, recent detection networks have low accuracy and fail to detect most diseases on the road, which means that testing is very inefficient. Therefore, this study uses the unmanned aerial vehicle (UAV) road damage database and describes a multi-level attention mechanism called Multi-level Attention Block (MLAB) to strengthen the utilization of essential features by the You Only Look Once version 3 (YOLO v3). Adding MLAB between the backbone and feature fusion parts effectively increases the mAP value of the proposed network to 68.75%, while the accuracy of the original network is only 61.09%. The network is able to detect longitudinal cracks, transverse cracks, repairs, and potholes with high accuracy, and significantly improves the accuracy of alligator cracks and oblique cracks. The findings of this study will accelerate the application of non-destructive automatic road damage detection.

With the rapid development of intelligent transportation, it is of great significance to improve road traffic safety and traffic efficiency by tracking road users in real time. In this paper, a roadside multi-source data acquisition platform is designed based on two main sensors, lidar and camera, to perform time synchronization between lidar data and camera data. The point cloud data and image data of the same frame are the research objects. Based on Zhang Zhengyou’s calibration method and the plane target model theory, the camera internal parameters and the joint external parameters of the lidar and camera are respectively calibrated to obtain the internal and external parameter matrix. The error is 0.09 pixels, and the external parameter calibration error is 0.22 pixels. The registration test of lidar and camera under different roadside layout conditions is designed to verify the adaptability of the registration method. When the camera is arranged and installed, the distance between the horizontal and vertical directions should not exceed 90 cm.

Tunnels account for an increasing proportion of highways. Due to the semi-closed structure of tunnels, signal communication is difficult in tunnels. This review analyzes the signal data transmission requirements of intelligent network management systems, such as lighting systems, wind protection systems, fire protection systems, and vehicle and pedestrian positioning systems in tunnels. The selection of signal coverage and transmission methods are also discussed. The advantages and disadvantages of various networking methods are analyzed. This paper summarizes the wireless signal transmission, wired signal transmission and signal transmission modes of different tunnel types.