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

Pre-labeling method based on target detection and storage medium

A technology for target detection and labeling models, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of poor adaptability of training models and high labor costs, improve rapid adaptability, and ensure effectiveness and efficiency. , the effect of reducing the likelihood

Pending Publication Date: 2022-08-05
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above problems, the present invention provides a pre-labeling method and storage medium based on target detection, which solves the problems of high labor costs and poor adaptability of training models in actual scenarios.

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
  • Pre-labeling method based on target detection and storage medium
  • Pre-labeling method based on target detection and storage medium
  • Pre-labeling method based on target detection and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] Example: see Figure 1-Figure 6 ,

[0034] A pre-labeling method based on target detection, comprising the following steps,

[0035] S1. Perform data screening on small-scale original data. Including but not limited to using frame drawing to improve the degree of scene changes, establishing scene libraries through automatic scene classification, actively identifying abnormal scenes and supplementing corner cases, etc., to reduce the data to be labeled.

[0036] S2. Label the original data that has been screened for data as training data. Using the data identified from S1, data preprocessing such as data cleaning and de-distortion are firstly performed, and then the image 2D frame labeling is performed as training data.

[0037] S3. Use the training data to train the basic target detection model, obtain a depth model, and differentiate the depth model into a pre-labeled model and a sensor model. Deep learning algorithms include but are not limited to convolutional ne...

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 discloses a pre-labeling method based on target detection and a storage medium, and the method comprises the following steps: S1, carrying out the data discrimination of small-scale original data; s2, labeling the original data subjected to data discrimination to serve as training data; s3, training a basic target detection model by adopting the training data to obtain a depth model, and differentiating the depth model into a pre-labeling model and a sensor model; s4, performing pre-labeling on subsequent large-scale original data through the pre-labeling model to form labeled training data; and S5, inputting the labeled training data into the pre-labeling model and the sensor model, and carrying out model lifting training. According to the method, the problems that the labor cost of common target detection labeling is too high and the adaptive capacity of a training model is poor in an actual scene are solved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and automatic driving, and more particularly relates to a pre-marking method and storage medium based on target detection. Background technique [0002] Artificial intelligence is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and produce a new type of intelligent machine that can respond in a manner similar to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making. Research i...

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): G06V10/774G06V10/778G06V10/82G06V20/56G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/045G06F18/217G06F18/214
Inventor 卢天翔吴锐张琪
Owner CHONGQING CHANGAN AUTOMOBILE CO LTD
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