Automobile collision fuel oil leakage detection method based on image recognition
A technology of image recognition and leak detection, which can be used to detect the appearance of fluid at the leak point, vehicle test, vehicle impact test, etc. It can solve the problems of hidden safety hazards in vehicle production, prone to missed judgments, and long judgment cycles. Achieve the effect of improving test safety, improving accuracy and reducing test cost
Active Publication Date: 2021-10-19
JIANGLING MOTORS
View PDF16 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The existing fuel leakage detection method mainly collects collision images through cameras, and manually distinguishes them, which is inefficient and takes a long period of discrimination, which is prone to missed judgments and poses safety hazards to subsequent vehicle production.
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 Construction
[0036] The present invention is described in detail below with reference to accompanying drawing and embodiment:
[0037] The present invention uses the AI algorithm to search for similarities between two pictures, and compare and analyze the feature points. If it reaches more than 90%, it will be the same or similar by default. Realize image comparison based on open-source algorithms for full-image and partial image comparison.
[0038] attached Figure 1-7 It can be seen that a method for detecting fuel leakage in a car collision based on image recognition includes the following steps:
[0039] S100. Rigidly connect the body-in-white and the tackle through fixed tooling; the lower surface of the body-in-white must be 400mm higher than the upper surface of the tackle;
[0040] S101. Pigment coating on the surface of the fuel system; the painted pigments are in the shape of a well, grid or dotted lines or dots;
[0041] S102. Fill the fuel tank with liquid, the amount of ...
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 relates to an automobile collision fuel oil leakage detection method based on image recognition, which comprises the following steps of: the surface of a fuel oil system is coated with a pigment, the surface of a fuel system is subjected to mesh division; after the fuel system is collided, the fuel system is displaced and deformed, the positions of components forming the fuel system are firstly change, the surfaces of the components forming the fuel system are also changed, and the rectangular frame forming the coating is also deformed; meanwhile, the color of liquid stored in the fuel tank is obviously different from the color of pigment coated on the surface of the fuel system, after the fuel system leaks, the color of a grid coated on the surface of the fuel system is obviously changed, an image collected by the camera system is greatly changed with an original image, and when the image recognition system recognizes the image, leakage of the fuel system is easier to judge, the leakage of the fuel system is easier to judge, and the fuel leakage recognition efficiency and accuracy of the system are improved.
Description
technical field [0001] The invention relates to the technical field of automobile collision detection, in particular to a method for detecting fuel leakage in automobile collision based on image recognition. Background technique [0002] Due to its own structural design characteristics of traditional fuel light buses, the fuel filler is generally located under the B-pillar of the vehicle body. In the event of a traffic accident, the fuel filler and its surrounding components are vulnerable to impact or inertial impact, resulting in fuel leakage, which has a serious impact on personal safety. This requires automakers to take this risk into consideration during fuel system development. [0003] However, using the vehicle collision test method to detect and determine whether the above risks do not meet the actual design requirements, on the one hand, the time does not allow, and the physical inspection will be done after the prototype vehicle is released. If there is still fue...
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): G01M3/12G01M17/007G01M7/08
CPCG01M3/12G01M17/0078G01M7/08
Inventor 邬杰徐莉侯聚英刘豪李文凤
Owner JIANGLING MOTORS