Vehicle Type Recognition

According to the newly revised "Classification of Toll Road Vehicle Toll Vehicles" issued by the Ministry of Transport of the People's Republic of my country, starting from January 1, 2020, the classification of toll roads across the country will be further unified, standardized and perfected to realize fast non-stop toll collection. Therefore, the importance and accuracy of vehicle model recognition are once again on the agenda.

1. Analysis of vehicle identification application technology

According to JT/T489-2019 "People's Republic of China Transportation Industry Standards", toll road vehicles are classified into three series: passenger cars, trucks, and special operation vehicles, mainly relying on the two key parameters of vehicle length and axle to achieve separation.

At present, the technology used in vehicle recognition is very extensive. The main vehicle detection modules are: camera, light curtain, single-line scan lidar, solid-state area array lidar, and single-point measurement lidar. The functions that can be realized by each technical solution are limited, and the specific functions are shown in the following table.

Note: In the actual application process, the difficulties we need to overcome are not only the advantages and disadvantages of the technology itself, but also the overall installation and implementation.

Comprehensive factors such as labor difficulty, occupation of police force, maintenance and service life, etc.

The whole lidar vehicle detection system is divided into two parts, as shown above

Part A: Lidar model recognition module. By installing structural parts, fix two HPS-167U-L (or model HPS-167U) lidars at an angle of 40° -50°, one vertical downwards, and one inclined downwards. The entire module can be directly installed on the top of the toll station, under the flyover or under the traffic light pole through the mounting hole, and connected to the main system through the data line. This part is the main module to identify the vehicle type.

Part B: Axle recognition module (assisted vehicle recognition, the result is more accurate). It consists of a HPS-167U-L lidar and a mounting structure, which is installed on the roadside of the toll station for axle statistics. This part is used as a functional complement module of the vehicle identification scheme, and customers can selectively install it according to their own needs.

2. Introduction of Lidar Model Recognition System

The car model recognition system based on Hypersen's lidar technology develops automatic matching of car model information by collecting key parameters such as car length, car height, and axles to assist in tolling decisions. The system includes three modules: lidar ranging module + control module + tooling module. The system can be customized and developed according to customer requirements.

3. How to use the vehicle identification system

After the system is installed on the gantry, the vehicle height information can be directly measured by the lidar installed in the vertical direction, and then the vehicle speed can be calculated by the time difference between the vehicle triggering the two lidars. Finally, combined with the data measured by the vertical radar, the contour information of the vehicle can be restored. The detection flow chart is as follows:

Through the neural network algorithm to complete the vehicle identification work, the original data is matched and identified. 

After the identification test is completed, the main control board transmits the test result directly to the customer main control system through the data line. The transmission content includes data such as vehicle type, vehicle height, vehicle length, vehicle speed and number of vehicle types.

Install the HYPERSEN model recognition host computer, you can receive, display, save data, save debugging information, reset tooling and other operations.