Vehicle identification method and terminal equipment
A car logo and vehicle technology, applied in the field of car logo recognition, can solve the problems of inability to recognize vehicles without license plates, low recognition robustness, etc., and achieve high recognition result accuracy, strong recognition robustness, and small model size. Effect
Inactive Publication Date: 2020-02-07
DONGGUAN ZKTECO ELECTRONICS TECH
View PDF8 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of this, the embodiment of the present invention provides a vehicle logo recognition method and terminal equipment to solve the problem of low robustness of car logo recognition by artificial feature extraction and inability of deep learning to recognize vehicles without license plates in the prior art. The problem with the logo
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
[0044] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
[0045] In order to illustrate the technical solutions of the present invention, specific examples are used below to illustrate.
[0046] figure 1 It is a schematic diagram of the implementation flow of a vehicle identification method provided by the embodiment of the present invention, and is described in detail as follows.
[0047]Step 101, acquire a plurality of pictures of vehicles to be dete...
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 method is suitable for the technical field of image processing. The invention provides a vehicle identification method and terminal equipment. The vehicle identification method comprises the following steps: roughly positioning vehicle logo positions of pictures of a plurality of vehicles to be detected; then, adopting a lightweight CNN detection network model to carry out accurate positioningon the position of the vehicle logo; preprocessing the accurate positioning result, training a preset lightweight convolutional neural network (CNN) model by using the preprocessed second training sample, and determining the trained neural network model as a target neural network model according to the second test sample; and inputting the second to-be-detected image into the target neural network model to obtain a vehicle logo recognition result, thereby solving the problems that the robustness of vehicle logo recognition based on artificial feature extraction in the prior art is relativelylow and the vehicle logo of a vehicle without a license plate cannot be recognized through deep learning.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a vehicle identification recognition method and a terminal device. Background technique [0002] With the continuous growth of the number of vehicles and traffic volume, illegal and criminal acts that hinder traffic order, such as car decks, multiple licenses for one vehicle, multiple vehicles with one license plate, and unlicensed vehicles, have become particularly prominent. , through the traditional recognition method based on manually designed features, or the deep learning method based on convolutional neural network (Convolutional Neural Network, CNN) to extract features. However, in the above car logo recognition scheme, the traditional algorithm is artificially designed. In practical applications, the recognition model is not robust and is easily affected by problems such as camera installation angles and environmental lighting changes, resulting in u...
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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/54G06V2201/08G06N3/045
Inventor 周庆标古川南李治农
Owner DONGGUAN ZKTECO ELECTRONICS TECH