Vehicle type detection method based on multi-sensor fusion
A technology of multi-sensor fusion and vehicle detection, applied in traffic flow detection, instruments, measurement devices, etc., can solve the problems of single, inaccurate identification results, etc., and achieve the effect of simple operation and low cost
Active Publication Date: 2022-03-18
招商局重庆公路工程检测中心有限公司
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the deficiencies in the existing technology, the present invention proposes a vehicle vehicle detection method based on multi-sensor fusion to solve the technical problem that the prior art uses a single detection method to identify the vehicle model, and the identification result is not accurate enough
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0048] This embodiment provides a vehicle detection method based on multi-sensor fusion. The multi-sensors include: a laser radar sensor, a geomagnetic sensor and a video sensor. The selection of the above three sensors is not limited, and it can be implemented in an achievable manner in the prior art; For example: the WLR-711 series laser rangefinder of Wanji can be used as the lidar sensor, the Wantus Sirui PD06 can be used as the geomagnetic sensor, and the vehicle detection camera DS-2C47EWD-LZS of Hikvision can be used as the video sensor.
[0049] The vehicle detection method based on multi-sensor fusion, its process is as follows: figure 1 As shown, the details are as follows:
[0050] Step 1. Collect vehicle data through lidar sensors, geomagnetic sensors, and video sensors, and obtain vehicle height features, vehicle magnetic field features, vehicle edge features, and vehicle texture features based on the vehicle data.
[0051] In a specific embodiment, such as fig...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a vehicle type detection method based on multi-sensor fusion, and the method comprises the following steps: collecting vehicle data through a laser radar sensor, a geomagnetic sensor and a video sensor, and obtaining a vehicle height feature, a vehicle magnetic field feature, a vehicle edge feature and a vehicle texture feature according to the vehicle data; determining a vehicle type detection model according to the vehicle height characteristics; if the vehicle height is 1.6-3 m, selecting the vehicle type detection model as a probabilistic neural network model; if the height of the vehicle is smaller than 1.6 m or larger than 3 m, the vehicle type detection model is selected as a support vector machine model; and inputting the vehicle height features, the vehicle magnetic field features, the vehicle edge features and the vehicle texture features into a vehicle type detection model, and detecting the vehicle type. According to the invention, the technical problem that the identification result is not accurate enough when a single detection means is adopted to identify the vehicle type in the prior art can be solved.
Description
technical field [0001] The invention relates to the technical field of vehicle vehicle detection, in particular to a vehicle vehicle detection method based on multi-sensor fusion. Background technique [0002] Vehicle detection is one of the research directions for realizing intelligent transportation system. Existing vehicle detection methods usually use video / image recognition methods or microwave detection methods. The method based on video / image recognition has high requirements on image quality and environment, and it is difficult to achieve accurate vehicle detection in environments with many interferences and poor light (such as in rainy and snowy weather); It is not applicable when there are many types of vehicles and the vehicle speeds on the road are inconsistent. [0003] Therefore, there is an urgent need for a vehicle type detection method that can overcome the defects of vehicle type identification based on video / image recognition methods and microwave detect...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/015G08G1/01G08G1/042G01D21/02
CPCG08G1/015G08G1/0125G08G1/042G01D21/02
Inventor 韩坤林龚加兴缪庆旭孙铁元邢春超桑晓玉刘文韬张朋刘大洋李仁富张胜雨伍仙桥唐皎
Owner 招商局重庆公路工程检测中心有限公司