Multi-sensor space-time synchronization and traffic scheduling device and method based on vehicle-road cooperation

Abstract

The invention discloses a multi-sensor space-time synchronization and traffic scheduling device and method based on vehicle-road cooperation, relates to the technical field of road traffic, changes the data aggregation mode of subsystems, restrains the distributed subsystems under the same time axis, and provides preconditions for data fusion of multi-sensing equipment. Through carrying a multi-sensor space-time synchronization and traffic driving scheduling device based on a vehicle-road cooperation global area network, hard touch exposure control of a camera and cooperation of the camera and a light supplement lamp in different light environments are realized, and a frame synchronization guarantee is provided for perception data fusion of a mechanical laser radar and the camera. And the reliability of the sensing data source in different light environments is ensured, and the effective recall rate of the sensing data is enhanced. Through carrying a multi-sensor space-time synchronization and traffic driving scheduling device based on a vehicle-road cooperation global network, traffic light state information can be uploaded to a cloud server through a network interface, and scheduling information of a node unit with a control right can also be received, thereby realizing traffic flow scheduling.

Description

technical field [0001] The invention relates to the technical field of road traffic, in particular to a multi-sensor time-space synchronization and traffic dispatching device and method based on vehicle-road coordination. Background technique [0002] Time synchronization and network port data aggregation are important guarantees for the full-speed construction of the Vehicle-Infrastructure Cooperative All-Area Network. Such as figure 1 As shown, at present, the technical features are as follows: the data flow of the sensing devices of the on-board unit and the roadside unit is transmitted to the computing unit, and the time when the computing unit captures the data is used as the time reference to realize data fusion; NTP is performed on devices with network ports. Or PTP synchronization and data flow convergence; mechanical laser radar and camera data fusion is based on feature extraction to achieve data fusion; the effective recall rate of camera perception data is affe...

AI Technical Summary

Problems solved by technology

[0003] The above technologies have the following disadvantages: data fusion takes the time point when the computing unit acquires the data as the fusion benchmark, and lacks data time validity guarantee, because the data may be delayed due to link transmission delay, or may be delayed due to the calculation unit Busy and unable to receive data in time

In addition, the direct deployment of computing units on the side of the roadside unit has high environmental adaptability and security requirements for the computing unit, and is incompatible with the data flow of sensing devices on other interfaces. The perception device interface puts forward requirements, which makes it incompatible with the existing vehicle-mounted units and roadside unit perception devices; there are mature synchronization protocols based on the LAN, but the requirements for the perception device must be able to access the LAN and support ptp Synchronization or ntp synchronization has caused other existing sensing devices to be unable to access; the hardware frame synchronization of the mechanical lidar and the camera cannot be realized, and the training and compensation of the data set are required on the algorithm side, which increases the computing power load and algorithm accuracy Requirements; in order to increase the effective recall rate of camera perception data at night, on the one hand, additional computing power is required for training, and on the other hand, it is necessary to rely on long-term supplementary light at night, which will cause light pollution; it is not compatible with traffic signals in various regions. Higher requirements are put forward for the network scheduling of the transportation system in which the regional boundary line participates in the vehicle-road collaborative global network

Images