Method and system for monitoring and detecting target based on fuzzy algorithm

A technology of fuzzy algorithm and detection method, applied in the target monitoring and detection system based on fuzzy algorithm, in the field of target monitoring and detection based on fuzzy algorithm, can solve problems such as poor reliability, and achieve real-time detection, fast calculation speed, and improved reliability. Effect

Active Publication Date: 2012-07-25
上海智觉光电科技有限公司
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The Chinese Patent Publication No. CN102152457A discloses an embedded plastic mold protection device based on histogram matching, which does not involve target recognition and detection. Other schemes such as Chinese Patent Publication Nos. CN2712620U and CN201960720U all use non-photoelectric image detection methods For mold protection, poor reliability

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
  • Method and system for monitoring and detecting target based on fuzzy algorithm
  • Method and system for monitoring and detecting target based on fuzzy algorithm
  • Method and system for monitoring and detecting target based on fuzzy algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] see figure 1 , the present invention discloses a target monitoring and detection method based on a fuzzy algorithm, and the method can be used to detect whether mold protector plastic parts and mold cavities appear (of course, the present invention can also be used in other fields), including the following steps:

[0072] [Step S1] Obtain the target image and the background image. After preliminary processing, they are stored in linear order.

[0073] [Step S2] Extract the differential feature parameters between the target image and the background image; divide the current screen into several small ROIs, and use the differential algorithm to calculate the image gray level difference between the background and the plastic part target, and the background and the cavity target in the small ROI . Extract the features of suspected targets and non-target areas. The feature extraction algorithm uses gray level accumulation, or uses feature quantity extraction and establishes...

Embodiment 2

[0097] The mold protection system first needs to capture three standard images of mold clamping, plastic parts, and mold cavity as the reference template for identification. The reference template image is stored in a preset directory. Every time the system is started, it is read into the memory and converted into two-dimensional data And do 4 / 8 alignment according to the number of CPU bits. In the gap between the detection work of the mold protection system, each snapshot must be subject to target recognition detection, including the following steps:

[0098] The first step is to extract the characteristic parameters of the difference between the target and the background image, use the difference algorithm to calculate the image gray difference between the background and the plastic part target, and the background and the mold cavity target, extract the feature detection operator of the suspected target and the non-target area, and feature extraction The algorithm can use gr...

Embodiment 3

[0108] see figure 1 , the method for identifying and detecting the appearance of mold protector plastic parts and mold cavity targets provided by the present invention can be subdivided into the following steps:

[0109] In Step 1, digital images of the background, molded part, and cavity are captured.

[0110] Step 2, obtaining the digital image of the current frame.

[0111] In step 3, the current picture is divided into small ROI areas, and the digital images of the background, plastic parts and mold cavity are differentiated in each ROI area, and the differences between various images in the ROI are extracted.

[0112] Step 4, calculate the difference parameters according to the ROI. Before the statistics, you can directly calculate the gray value difference. It is also possible to perform feature extraction before the statistics, and after the feature vector is established, the feature vector of the statistical difference. The different statistical parameters are only ...

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 method and a system for monitoring and detecting a target based on a fuzzy algorithm. The method comprises the following steps of: acquiring a target image and a background image; extracting differential characteristic parameters between the target image and the background image; dividing the current picture into a plurality of small regions of interest (ROI), and calculating image gray difference between a background and a plastic target as well as between the background and a die cavity target in the small ROI by using a difference algorithm; detecting target similarity; counting target occurrence parameter values in each small ROI according to the extracted differential characteristic parameters, and respectively accumulating target and non-target characteristic parameters in respective small ROI during counting; judging the target; and performing decision possibility judgment of target non-occurrence and target occurrence according to the counted parameter values of the target. By the method and the system, the calculation amount is reduced, the calculation speed is high, and the requirement for real-time detection is ensured; and the counted parameters are judged by adopting fuzzy mathematics, so that the reliability of target identification and detection is improved, and the contradiction between the speed and the effectiveness is effectively solved.

Description

technical field [0001] The invention belongs to the technical field of photoelectric mold protection, and relates to a target monitoring and detection method, in particular to a target monitoring and detection method based on a fuzzy algorithm; meanwhile, the invention also relates to a target monitoring and detection system based on a fuzzy algorithm. Background technique [0002] Injection molds are the most important molding equipment for injection molding products, and their quality is directly related to the quality of products. Moreover, since the mold occupies a large proportion of the production cost of the injection molding processing enterprise, its service life directly affects the cost of the injection molding product. Therefore, improving the quality of injection molds, maintaining and maintaining them through photoelectric technology, and prolonging their service life are important issues for injection molded product processing companies to reduce costs and inc...

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): B29C45/76B29C45/84
Inventor 游旭新
Owner 上海智觉光电科技有限公司
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