Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Vehicle model data set establishing method serving for deep learning

An establishment method, deep learning technology, applied in the fields of electrical digital data processing, still image data retrieval, special data processing applications, etc. problems, to achieve the effect of improving the recognition ability, improving the recognition rate, and improving the accuracy

Inactive Publication Date: 2017-06-20
成都容豪电子信息科技有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The recognition accuracy rate of existing vehicle identification systems is generally not high, which is mainly caused by improper classification methods when the data set is established. The recognition accuracy is not high

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
  • Vehicle model data set establishing method serving for deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. For simplicity, some technical features known to those skilled in the art are omitted from the following description.

[0016] A method for establishing a car model data set serving deep learning is provided, including the following steps:

[0017] S1. Collect multi-angle pictures of various models of cars. The pictures can be collected from the Internet or taken by yourself; each model of car has at least 7 different angles of pictures, including but not limited to the following angles, Front, left front, right, side, back, left back, right back, etc.;

[0018] S2. Establish a tree structure for the above-mentioned multi-angle pictures according to the four-level classification method of "car brand-car model-car model-car year".

[0...

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 invention provides a vehicle model data set establishing method serving for deep learning. The method comprises the following steps: S1, collecting multi-angle pictures of vehicles in various models, each vehicle model at least has seven kinds of pictures in different angles; S2, according to a classification method of vehicle brand-vehicle type-vehicle model-vehicle year, establishing a tree structure of the pictures; S3, dividing the pictures of each vehicle year into two parts, using one part of the pictures to establish a training set file, and using the other part to establish a test set file; S4, establishing a training set file label file and a test set file label file, to establish a data set. The vehicle pictures are established into the tree structure according to the method of vehicle brand-vehicle type-vehicle model-vehicle year. The method is beneficial for improving identification capacity of a system on vehicles, and obviously improving identification precision. The pictures of the data set are multi-angle pictures of the vehicles, being helpful for perfecting models and improving identification rate.

Description

technical field [0001] The invention relates to the technical field of data classification, in particular to a method for establishing a car model data set serving deep learning. Background technique [0002] The recognition accuracy rate of existing vehicle identification systems is generally not high, which is mainly caused by improper classification methods when the data set is established. The recognition accuracy is not high. [0003] Therefore, there is an urgent need for a method to correctly and effectively construct a car data set, so as to improve the recognition accuracy. Contents of the invention [0004] The object of the present invention is to provide a method for establishing a car model data set serving deep learning, which can well solve the above problems. [0005] In order to meet the above-mentioned requirements, the technical solution adopted by the present invention is to provide a method for establishing a car model data set serving deep learning,...

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 Applications(China)
IPC IPC(8): G06F17/30G06K9/62
CPCG06F16/51G06V2201/08G06F18/214
Inventor 邓建华罗兴成杨容申瑞涵胡健彭欢易歆马可染周可意刘成
Owner 成都容豪电子信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products