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

Image sample generation method, specific scene target detection method and system thereof

An image sample and target detection technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of difficult labeling and large amount of data, and achieve the effect of high realism, simple algorithm and high labeling accuracy

Active Publication Date: 2020-05-12
ZHEJIANG PECKERAI TECH CO LTD
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide an image sample generation method for deep learning and its system, and a specific scene target detection method for the technical defects involved in the background technology, so as to solve the problem of deep learning training sample data collection and labeling For difficult and large data problems, use simple algorithms to quickly provide effective training samples for the detection of contraband, and can flexibly adapt to target detection tasks in different scenarios, so as to improve the performance of target detection tasks in the security inspection process using deep learning methods efficiency and accuracy

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
  • Image sample generation method, specific scene target detection method and system thereof
  • Image sample generation method, specific scene target detection method and system thereof
  • Image sample generation method, specific scene target detection method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Embodiment 1: In order to solve the above technical problems, as figure 1 As shown, the present invention proposes a method for generating image samples based on deep learning, including: S1: Obtain a real-shot security inspection image of a target scene to form a scene data set.

[0038]Specifically, the target scenarios include airports, railway stations, bus stations, government buildings, embassies, conference centers, exhibition centers, hotels, shopping malls, large-scale events, post offices, schools, logistics industry, industrial testing, express delivery transit, etc. Items that need to be checked in the place, such as luggage, express parcels, bags, bags, goods, etc. If the target is contraband (such as guns, explosives, etc.), the target scene refers to the container where the contraband is located, that is, a place that can be used to store contraband. Usually, the type of scene is related to the place. For example, luggage is the main scene in places such...

Embodiment 2

[0060] Embodiment 2: An image sample generation system based on deep learning, including: a scene data set, a target data set, a preprocessing module, an image preprocessing module to be fused, an image fusion module, and a sample library generated.

[0061] Specifically, the scene data set is composed of the real-shot security inspection images of the target scene described in Embodiment 1, and the target data set is composed of the marked target images described in Embodiment 1.

[0062] Composed of X-ray images of items, the X-ray images of items can be collected using X-ray security inspection equipment; the items include luggage, express parcels, oversized cargo, etc.

[0063] As an embodiment of the present invention, the scene data set and the data in the target data set are preprocessed, and the processing methods include but not limited to one or more of pixel gray value processing, denoising, background difference, and de-artifact kind. As a preferred embodiment of ...

Embodiment 3

[0076] Embodiment 3: Corresponding to the above-mentioned image sample generation method based on deep learning, according to an embodiment of the present invention, a specific scene target detection method is also provided, including:

[0077] Step 1: Acquire the security inspection image of the item, and preprocess the image; wherein, the preprocessing method includes but not limited to one or more of image normalization, denoising, background difference, and de-artifacting.

[0078] A normalization operation is performed on the image with a preset size, 500*500 is taken as an example in this embodiment.

[0079] The Gaussian smoothing algorithm is used to denoise the image. The value of each point of the Gaussian smoothed image is obtained by weighted average of itself and other pixel values ​​in the field; the specific operation is to use a template to scan each point in the image. One pixel, the value of the center pixel of the template is replaced by the weighted average...

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 an image sample generation method for deep learning, a specific scene target detection method and a system thereof. The image sample generation method comprises the following steps: obtaining a real shot security check image of a target scene based on security check place analysis so as to obtain a target security check image with a label; determining a to-be-fused image and processing the to-be-fused image by a new fusion algorithm to obtain a new sample. A large number of target images in a real scene do not need to be shot on site; the real shot image in the complexenvironment does not need to be marked manually; the algorithm is simple, a new sample image with place pertinence can be flexibly and rapidly generated; through comparison, it is found that the new sample obtained through the method is almost consistent with the actually shot image containing the detection target, a more vivid effect is especially displayed in a color image mode, the labeling accuracy is high, and the efficiency and accuracy of a target detection task in the intelligent security check method are improved.

Description

technical field [0001] The invention belongs to the technical field of security inspection, and in particular relates to an image sample generation method for deep learning, a system thereof, and a specific scene target detection method. Background technique [0002] X-ray is a kind of electromagnetic radiation with a shorter wavelength than visible light. It has stronger solid and liquid penetrating ability than visible light, and can even penetrate a certain thickness of steel plate. When X-rays pass through an object, the internal structures of objects with different material compositions, different densities and different thicknesses can absorb X-rays to varying degrees. The greater the density and thickness, the more rays are absorbed; the smaller the density and thickness, the less rays are absorbed , the pixel value of the generated image represents the density value of the object, so the intensity of rays transmitted from the object can reflect the internal structure...

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): G06T7/00G06T5/00G06K9/62
CPCG06T7/0004G06T2207/10116G06T2207/20081G06T2207/20084G06T2207/30108G06F18/241G06T5/70G06V10/82G06V10/764G06V20/52G06V10/774G06V10/806G06V10/454G06V10/56G06V10/751G06T7/70G06V10/44G06T5/50G06T7/0008G06T2207/20221
Inventor 李一清周凯
Owner ZHEJIANG PECKERAI TECH 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com