A fast retrieval method and system for bayonet image vehicles based on deep learning

A technology of deep learning and bayonet, applied in the field of rapid retrieval method and system of bayonet images based on deep learning, can solve problems such as high accuracy, difficult training, large vehicle feature vector, etc., achieve high accuracy and reduce similarity The effect of degree calculation

Active Publication Date: 2020-01-10
ENJOYOR COMPANY LIMITED
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Among the current vehicle retrieval methods, one is to use traditional machine learning to extract different feature vectors for identification, and the other is to use deep learning neural networks for feature extraction. Usually, traditional machine learning algorithms are not as accurate as deep learning; most of the current methods It is to use the classification model to train the network and then extract the feature layer for identification. In this way, the feature vector of the vehicle is generally large. Since the vehicle features need to be compared with all the vehicle features in the database, the bayonet pictures stored in the traffic system of the big cities often have more than The number of pictures in the billion level, this retrieval method obviously cannot meet the actual situation. In addition, the deeper the neural network layer, the higher the recognition accuracy rate is generally. However, its training is also more difficult.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A fast retrieval method and system for bayonet image vehicles based on deep learning
  • A fast retrieval method and system for bayonet image vehicles based on deep learning
  • A fast retrieval method and system for bayonet image vehicles based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] Example: such as figure 1 As shown, a fast retrieval system for bayonet image vehicles based on deep learning includes a picture acquisition module, a feature extraction module, a picture index module, and a picture upload module; the picture acquisition module, feature extraction module, picture index module, picture Upload modules are connected sequentially. The image acquisition module is in the form of a web page, directly select the image to be retrieved, and then the image is acquired, and the trained model is used to extract the 128*1-dimensional feature vector, and the k-tree index is used for retrieval, and the top ten most similar images are returned and displayed . Among them, the image acquisition module and the image upload module both use python's flask module, and the feature extraction module uses the inception_resnet_v2 model. Here, the Inception_resnet_v2 network of GoogleNet is used, such as figure 2 As shown, the network combines the advantages 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

No PUM Login to view more

Abstract

The present invention relates to a fast retrieval method and system for bayonet image vehicles based on deep learning. The present invention uses a deep neural network to extract vehicle feature information, and extracts vehicle features based on the inception_resnet_v2 network, which realizes network weight sharing and effectively avoids A large number of repeated calculations, the loss function is trained with triplet samples, and directly generates a 128-dimensional vector. In the stage of retrieving pictures, the present invention uses feature clustering to index features and improve query speed. The invention can speed up the extraction speed of image features and fast real-time response, and at the same time can effectively inspect and hunt down illegal vehicles such as fake license plates and fake license plate vehicles.

Description

technical field [0001] The present invention relates to the field of intelligent transportation, in particular to a method and system for fast retrieval of bayonet image vehicles based on deep learning. Background technique [0002] In the field of intelligent transportation, intelligent traffic monitoring is a very important development direction at present. At present, my country has deployed a large number of electronic police and checkpoint systems on urban roads. These systems can capture high-definition pictures of vehicles in real time, and identify and analyze the license plate number, as well as some vehicle model information (such as vehicle size, color, etc.). However, in the currently used bayonet monitoring system, the license plate number recognition still has a misrecognition and missed recognition rate of about 10%. More importantly, it will not be possible to identify illegal vehicles with license plates or deliberately concealed photos. Therefore, by usin...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/53G06K9/62G06N3/04G06N3/08
CPCG06F16/583G06N3/08G06N3/045G06F18/23213
Inventor 王辉田玉兰陈涛李建元温晓岳
Owner ENJOYOR COMPANY LIMITED
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products