Method for detecting vehicle cross-lane driving behaviors in dynamic flat scale weighing area

Abstract

The invention discloses an automobile cross-lane driving behavior detection method in a dynamic flat plate scale weighing area. The method comprises the steps: establishing a road vehicle dynamic weight measurement area building information model; performing cross-lane behavior detection, analyzing the images acquired by the cameras on the two sides, detecting a vehicle target, and if the centralpoint of a vehicle bounding box in an image frame acquired by the camera on one side is located on the longitudinal central line of the image, selecting the images acquired by the cameras on the two sides at the moment corresponding to the image frame, and triggering wheel landing point detection; projecting the wheel landing point to the building information model of the dynamic weighing area; analyzing the number of vehicles and the front-back position relation of the vehicles according to the position relation of the wheel landing points in the ground coordinate system of the building information model of the dynamic weighing area to obtain the corresponding relation between different vehicle tires and the peak value of the weight curve of the flat scale, and calculating the vehicle weighing result according to the corresponding relation. According to the invention, an accurate weight measurement result can still be obtained when an automobile crosses a road.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and vehicle dynamic weighing, in particular to a method for detecting the cross-lane driving behavior of vehicles in the weighing area of ​​a dynamic flat scale. Background technique [0002] Vehicle dynamic weighing, that is, the vehicle can get the weight of the vehicle directly from the scale without stopping. The same lane on the road often uses two or more flat scales for vehicle weight measurement. For one-way multi-lane roads, multiple weighbridges need to be placed, and two weighbridges in the same lane can be used as a group to obtain the axle load of the vehicle. On multi-lane roads, if the driver crosses the road in the weighing area, the weight obtained by the weighbridge will be inaccurate, and the driver of the overloaded vehicle often cheats in this way to avoid punishment. In this case, it is necessary to identify the behavior of the vehicle and analyze and process the wei...

AI Technical Summary

Problems solved by technology

This solution requires a large number of flat-plate weighing instruments to fill the road plane. At the same time, when there are multiple vehicles on the road, it is difficult to match the order of the weighing instruments to match the same vehicle, and the weighing results cannot be obtained.

CN101870293B Detects the crossing behavior of the vehicle, and judges whether the intersection point between the extension line of the lane line and the bottom of the image is within the imaging of the vehicle, and is oriented towards active and safe driving of the vehicle. The conditions of use and judgment standards are very limited, and it cannot be applied to the scene of dynamic weight measurement

There are also some solutions that use whether the vehicle and the lane line intersect to judge the behavior of crossing or pressing the line. It is necessary to design an algorithm to detect the vehicle and the lane line. Not only is the method cumbersome, but the reliability of the judgment result is also poor.

Images