Screening method and device of blind area detection training set, server and storage medium

A screening method and training set technology, which is applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of time-consuming, labor-intensive standards, and inconsistencies in training sets, so as to improve recognition accuracy, reduce costs, and optimize model parameters. Effect

Active Publication Date: 2021-10-15
TIANJIN SOTEREA AUTOMOTIVE TECH LMITED CO
View PDF13 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention aims to propose a screening method, device, server and storage medium for a blind spot detection training set, so as to solve the problem that the training set of a convolutional neural network for blind spot detection in the prior art can only be manually marked. Time-consuming and labor-intensive technical issues with inconsistent standards

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
  • Screening method and device of blind area detection training set, server and storage medium
  • Screening method and device of blind area detection training set, server and storage medium
  • Screening method and device of blind area detection training set, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 It is a schematic flow chart of the screening method for the blind spot detection training set provided in Embodiment 1 of the present invention. The screening method for the blind spot detection training set provided in the embodiment of the present invention is applicable to the case of screening the image training set for blind spot detection, especially It is used to screen the blind spot detection convolutional neural network image training set, the screening method of the blind spot detection training set can be performed by a screening device for the blind spot detection training set, see figure 1 , the screening method of the blind spot detection training set, comprising:

[0035] S110, input the image to the semantic segmentation neural network.

[0036] Usually, for blind spot detection, images are collected by an image acquisition device installed at a specific position on the vehicle, and the collected images are discriminated through a convolution...

Embodiment 2

[0049] Figure 4 It is a schematic flow chart of the screening method for the blind spot detection training set provided by Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiment. Specifically, the output matrix is ​​mapped to the basic image template, and further optimization is as follows: calculate A relative characteristic ratio of each element in the output matrix in the output matrix, generating a relative matrix according to the relative characteristic ratio; generating a characteristic image according to the relative matrix and the output image.

[0050] see Figure 4 , the screening method of the blind spot detection training set, comprising:

[0051] S210, input the image into the semantic segmentation neural network.

[0052] S220. Acquire an output matrix of the feature recognition deconvolution layer in the semantic segmentation neural network, where the output matrix is ​​used to represent the feature intensity corresp...

Embodiment 3

[0064] Image 6 It is a schematic flow chart of the screening method of the blind spot detection training set provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above embodiments. Specifically, the method can also add the following steps: obtaining the semantic segmentation neural network input the image into the target detection neural network; determine the coordinate position corresponding to the target recognition result according to the output result of the semantic segmentation neural network; determine the region of interest according to the coordinate position. see Image 6 , the screening method of the blind spot detection training set, comprising:

[0065] S310, inputting the image into the semantic segmentation neural network.

[0066] S320. Obtain an output matrix of the semantic segmentation neural network feature recognition deconvolution layer.

[0067] S330. Project the output matrix to a basic image template ...

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 screening method and device for a blind area detection training set, a server and a storage medium. The method comprises the steps: inputting an image into a semantic segmentation neural network; acquiring an output matrix of a feature recognition deconvolution layer in the semantic segmentation neural network, wherein the output matrix is used for representing feature intensity corresponding to each pixel of the output image; mapping the output matrix to a basic image template to form a feature image, wherein the basic image template is used for highlighting the intensity of feature intensity; and calculating an image feature value mean value of a preset region of interest in the feature image, comparing the feature value mean value with a preset mean value threshold value, and when the feature value mean value is not greater than the preset mean value threshold value, determining that the image is added into a blind area detection training set. A unified, objective and visual prediction result of a data set can be obtained, and targets with poor feature extraction and uncertainty can be added to next training.

Description

technical field [0001] The invention belongs to the technical field of computer image recognition, and in particular relates to a screening method, device, server and storage medium of a blind spot detection training set. Background technique [0002] Automobile blind spot detection is an intelligent safety technology for automobiles, which can intelligently identify pedestrians and other vehicles in the blind spot of the vehicle through the intelligent monitoring camera and other auxiliary equipment (radar, alarm, display screen, etc.) installed on the car, and According to this, a prompt is issued, thereby eliminating the blind spot of sight and improving driving safety. [0003] At present, vehicle blind spot detection usually uses cameras to capture corresponding images, and uses convolutional neural networks to identify various targets appearing in the images. [0004] In the process of realizing the present invention, the inventor found the following technical problem...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 徐显杰李涛
Owner TIANJIN SOTEREA AUTOMOTIVE TECH LMITED CO
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap