Production line object part motion detection and tracking method based on videos

A motion detection, production line technology, applied in image data processing, instrumentation, computing, etc., can solve problems such as missed detection, and achieve the effect of reducing missed detection rate, increasing robustness, and improving reliability

Active Publication Date: 2015-01-21
南京曼新智能科技有限公司
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can get a good detection effect by using a simple background model when the scene is relatively simple, but in complex and changeable scenes, there will be too many missed detections

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
  • Production line object part motion detection and tracking method based on videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] As shown in the figure, it is a video-based motion detection and tracking method for production line item parts, which is implemented by the following software modules: image acquisition, Gaussian filtering, foreground segmentation, item identification, particle filter, item feature extraction and model Update, background image extraction and background model update, output object image position.

[0020] When performing detection and tracking, follow the steps below:

[0021] 1) Image acquisition: a single digital camera is used to acquire the images of the production line running without load and the actual running production line images; the camera used for image acquisition is connected to the industrial computer through a 1394 digital acquisition card, and the camera is installed above the production line. The downward angle of 30°~90° in the direction;

[0022] 2) Background generation: Gaussian filtering is performed on the acquired no-load running image for a f...

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 relates to a production line object part motion detection and tracking method based on videos, and belongs to the field of automatic production lines. A single digital camera is adopted for acquiring conveying images of production line objects, modeling is conducted through background subtraction and object characteristics, and then image segmentation of moving objects and a production line background is achieved. In the normal operating process of a production line, through background subtraction, a background region of the production line and a moving object part region are determined, and modeling is conducted through surface characteristics and contour characteristics of the products. In the assembly process of the production line, a Gaussian model of background images is continuously updated, and object parts on the production line are better segmented and are not affected by external environment interference. Meanwhile, motion trails of the objects are matched in multiple images, and therefore the multiple objects can be continuously tracked. By the adoption of the method, the calculation reliability of the positions of the product parts in continuous motion can be improved, the objects can be accurately tracked, and the requirements for product assembly automation can be met.

Description

technical field [0001] The invention relates to an automatic production line, in particular to a method for detecting and locating moving objects by using images. Background technique [0002] With the development of computer technology and field bus technology, machine vision has become increasingly mature. It has become an indispensable part of modern industrial automation production and is widely used in industries such as automobiles, food, medicine, chemicals, mechanical processing, and electronic devices. As the price of computer hardware decreases, production lines equipped with vision systems can effectively replace multiple human operators. At the same time, the new production line can flexibly carry out various tasks. For different applications, it is only necessary to update or upgrade the software of the vision system to meet new requirements. Due to fatigue, it is difficult for manual operators of traditional production lines to ensure continuous and accurate ...

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): G06T7/20G06T5/00G06T7/215
CPCG06T7/215G06T2207/10016G06T2207/30108
Inventor 董远强朱文俊
Owner 南京曼新智能科技有限公司
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