Machine Vision Burst Imaging for Deviation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In continuous manufacturing processes, existing machine vision systems struggle to detect deviations in moving objects and machine malfunctions effectively, often requiring higher frequency and resolution imaging to accurately monitor products and machinery, which current systems cannot provide efficiently.
Innovation Solution
A method and system that utilize a machine vision system with at least one image sensor and an acoustic sensor, capable of capturing images at a first frequency and switching to a higher frequency 'image burst' mode upon deviation detection, with the trigger signal defining the duration, frequency, and resolution of the burst, and optionally involving a second image sensor or acoustic data analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the image capturing frequency is increased to detect deviations more accurately, then the detection precision is improved, but the data processing load and system complexity increase
Solution Approach 1:
The system implements periodic action by switching between normal imaging mode and burst mode imaging. During normal operation, images are captured at a standard frequency. When a deviation is detected, the system temporarily increases the imaging frequency to capture multiple images in rapid succession (burst mode), then returns to normal mode. This periodic adjustment of imaging frequency allows high-precision detection when needed while maintaining low system complexity during normal operation.
Solution Approach 2:
The system applies dynamics by making the image capturing frequency adjustable and adaptive rather than fixed. The imaging frequency dynamically changes based on operational conditions - operating at a lower frequency during normal conditions and switching to a higher frequency during deviation detection events. This dynamic adjustment resolves the contradiction by allowing the system to optimize between precision and complexity based on real-time needs.
2Speed
If the image capturing frequency is increased to monitor moving objects more effectively, then the detection speed is improved, but the data transmission and processing burden increases
Solution Approach 1:
The system uses periodic action to capture images at high frequency only during brief burst periods when deviations are detected, rather than continuously. This generates a limited set of high-value image data that requires minimal transmission and processing, while still achieving fast detection when needed. The periodic nature of burst mode imaging ensures that large volumes of data are not continuously generated.
Solution Approach 2:
The system extracts only the essential image data needed for deviation detection by using targeted burst mode imaging. Instead of continuously capturing and transmitting all images, the system identifies critical moments when deviations occur and extracts only the relevant high-frequency image sequences for analysis. This extraction approach reduces the overall data volume while maintaining detection effectiveness.
3Reliability
If multiple image sensors are used to improve monitoring coverage, then the detection reliability is improved, but the device complexity and cost increase
Solution Approach 1:
The system applies multi-functionality by enabling a single image sensor to perform multiple roles through burst mode operation. The same sensor that captures normal images also captures high-frequency deviation images when triggered. This eliminates the need for separate dedicated sensors for different functions, maintaining detection reliability while avoiding the complexity and cost of multiple sensors.
Solution Approach 2:
The system uses self-service by having the existing image sensor system trigger and execute burst mode imaging autonomously when deviations are detected. The sensor system monitors its own operation and automatically increases imaging frequency when needed, without requiring additional external sensors or complex control systems. This self-service approach maintains reliability while minimizing added complexity.
Data Source
Figure 1~2
Figure 3
AI summary
The invention relates to a method, comprising capturing an image of an object to be monitored at a first image capturing frequency by an image sensor of a machine vision system, transmitting said captured image data to an image data processing device and analysing said received image data by said image data processing device, and wherein if the image data is detected to comprise a deviation, a trigger signal is transmitted for triggering an image sensor for reconfiguring it to capture an image burst and for transmitting the captured image burst data to said image data processing device for further analysis. The invention further relates to a machine vision system and a computer program product performing the method.