A method and system for retrieving a fake-licensed vehicle
A technology for decked cars and vehicles, which is applied in special data processing applications, instruments, and electronic digital data processing, etc., can solve the problems that decked cars cannot achieve accurate retrieval and verification, and achieve the effect of ensuring accuracy and running speed balance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] figure 1 It is a schematic flow chart of this embodiment, a method for retrieving a decked vehicle, comprising:
[0040] Step 101, pre-training a model for vehicle filtering, where the model includes a vehicle type model, a color model, a sub-brand model, a license plate information model, and a feature area classification model;
[0041] The license plate retrieval method disclosed in this embodiment adopts the target detection model of deep learning. Since deep learning has a powerful feature learning ability, it can improve the accuracy and efficiency of target detection. Specifically, in this embodiment, classical models such as vgg and resnet are used for optimization, while meeting the requirements of accuracy and speed.
[0042] In this embodiment, model training is performed on vehicle images collected from cameras at public security traffic checkpoints to obtain a variety of filtering models, where the filtering models include vehicle type models, color models...
Embodiment 2
[0061] This embodiment is essentially an improvement of embodiment 1, specifically the improvement proposed in step 106. In order to ensure the integrity of the description, all the steps of embodiment 2 are described below. It should be noted that this embodiment Steps 201 to 205 are the same as steps 101 to 105 in the embodiment.
[0062] figure 2 It is a schematic flow chart of this embodiment, a method for retrieving a decked vehicle, comprising:
[0063] Step 201, pre-training a model for vehicle filtering, where the model includes a vehicle type model, a color model, a sub-brand model, a license plate information model, and a feature area classification model;
[0064] The license plate retrieval method disclosed in this embodiment adopts the target detection model of deep learning. Since deep learning has a powerful feature learning ability, it can improve the accuracy and efficiency of target detection. Specifically, in this embodiment, classical models such as vgg ...
Embodiment 3
[0086] image 3 It is a schematic diagram of the structure of this embodiment, a retrieval system for licensed vehicles, including:
[0087] The training unit 301 is used to pre-train a model for vehicle filtering, where the model includes a vehicle type model, a color model, a sub-brand model, a license plate information model, and a feature area classification model;
[0088] The obtaining unit 302 is used to obtain the first image of the target vehicle information to be retrieved, and extract the vehicle license plate number information of the first image; the first removal unit 303 is used to remove the vehicle license plate number information of the first image, and obtain the second image, Extracting vehicle type information, vehicle color information, vehicle sub-brand information, and feature extraction area information of the second image;
[0089] The second removal unit 304 is used to remove the license plate number information of the original test set vehicle of t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com