False detection image determination method and device, equipment and medium

A determination method and a technology of images to be detected, applied in the field of machine learning, can solve the problem of low generalization of the determination method of false detection images

Pending Publication Date: 2020-09-08
ZHEJIANG DAHUA TECH CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] Embodiments of the present invention provide a method, device, device, and medium for determining a false det

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
  • False detection image determination method and device, equipment and medium
  • False detection image determination method and device, equipment and medium
  • False detection image determination method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] figure 1 It is a process schematic diagram of a method for determining a falsely detected image provided by an embodiment of the present invention, and the process includes the following steps:

[0064] S101: Based on the pre-trained feature extraction network model, determine a first feature vector of the image to be detected.

[0065] A method for determining a falsely detected image provided by an embodiment of the present invention is applied to an image acquisition device, and may also be applied to other electronic devices, such as PCs, mobile terminals, and other devices.

[0066] In the embodiment of the present invention, in order to determine whether the image to be detected is a false detection image, it is necessary to determine the first feature vector of the image to be detected.

[0067] Specifically, in the embodiment of the present invention, the image to be detected is input into the pre-trained feature extraction network model, and the image to be de...

Embodiment 2

[0082] In order to determine whether the image to be detected is a false detection image, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the neural network model based on the determined similarity and the pre-trained neural network model for the image to be detected The recognition result of determining whether the image to be detected is a false detection image, including:

[0083] identifying a maximum value among said similarities;

[0084] If the maximum value is greater than a preset threshold, determine that the image to be detected is a falsely detected image;

[0085] If the maximum value is not greater than the preset threshold, when the recognition result of the image to be detected based on the pre-trained neural network model is a background image, it is determined that the image to be detected is a false detection image.

[0086] In order to determine whether the image to be detected is a false detection image, in the...

Embodiment 3

[0098] In order to determine the feature vectors in the background target feature pool, on the basis of the above-mentioned embodiments, in the embodiment of the present invention, the process of determining the background target feature pool includes:

[0099] Determine the background image in the saved image based on the pre-trained neural network model;

[0100] Determine the second feature vector of each background image based on the pre-trained feature extraction network model;

[0101] Adding each of the determined second feature vectors to the background target feature pool.

[0102] In order to determine the feature vectors in the feature pool of the background target, some images are collected and saved in the embodiment of the present invention. Preferably, the saved image is an image of a target area framed by a detection frame, which is detected by a detection method in the prior art. Since the background image may be mistakenly detected as the target image in th...

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 false detection image determination method and device, equipment and a medium. The method comprises the steps of: based on a pre-trained feature extraction network model, determing a first feature vector of the to-be-detected image, determining the similarity between the first feature vector and each feature vector in a stored background target feature pool, and determining whether the to-be-detected image is a false detection image according to the determined similarity and a pre-trained neural network model recognition result of the to-be-detected image. According to the method, the network model is extracted through the pre-trained features; a first feature vector of the to-be-detected image is determined, therefore, the similarity with the feature vectors in the background target feature pool is determined; therefore, the corresponding similarity can be detected for any image, the recognition result of the to-be-detected image according to the similarity and the pre-trained neural network model is ensured, the accuracy of the determined false detection image is improved, and the generalization of the false detection image determination method is improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, and in particular to a method, device, device and medium for determining false detection images. Background technique [0002] With the development of intelligent technology, intelligent security systems are becoming more and more popular, and the alarm function is an important function of the intelligent security system. The image acquisition device of the intelligent security system tracks the target of concern. When the target of concern crosses the designated warning line Trigger the alarm function of the intelligent security system. At present, the mainstream methods for target tracking include deep learning, correlation filtering and other methods. When the image acquisition device of the intelligent security system tracks the target, it will make a judgment based on the collected target image containing the target. In the prior art, no matter which method is used to trac...

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
IPC IPC(8): G06K9/46G06K9/62G06N3/08
CPCG06N3/08G06V10/462G06F18/22
Inventor 鲁逸峰郑春煌邬国栋
Owner ZHEJIANG DAHUA TECH CO LTD
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