Container Orientation via Learned Sequential Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing container orientation systems are costly, complex, and require specialized personnel for setup, especially when adapting to changes in container shape or geometry, and are sensitive to container contents, particularly in transparent containers.
Innovation Solution
A device and process using a single fixed illuminator and recording device with a learning mechanism that automatically learns the container's lateral surface through multiple sequential images, processing similarity functions to determine orientation without requiring geometric parameters or expert intervention, utilizing CMOS sensors and a synchronization strategy to minimize system complexity and cost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple vision systems are used to detect the entire lateral surface of containers, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The lateral surface detection is divided into multiple angular positions (N positions around the carousel). Instead of using multiple simultaneous vision systems, the system segments the detection task into sequential observations at different angular positions as the container rotates, achieving complete surface detection with a single vision system.
Solution Approach 2:
The system adds the time dimension and rotational movement to the detection process. By observing the container at multiple angular positions during its rotation-revolution movement, the system reconstructs the entire lateral surface from a single fixed viewing point, transforming a spatial problem into a temporal-spatial solution.
2Adaptability or versatility
If optical sensors are used to measure container profile, then adaptability to container shape changes is improved, but measurement precision deteriorates due to noisy signals
Solution Approach 1:
Instead of directly measuring the container profile with sensors that produce noisy signals, the system creates optical images (copies) of the container at multiple angular positions. These image copies are then processed and combined to reconstruct the complete lateral surface, providing both adaptability to shape changes and high measurement precision through visual information.
3Device complexity
If a single viewing point is used for detection, then device complexity is reduced, but measurement precision deteriorates due to limited observation angle
Solution Approach 1:
The system maintains continuous observation of the container throughout its rotation-revolution movement. By capturing images at multiple angular positions continuously as the container passes through the detection zone, the single viewing point achieves complete surface coverage and high measurement precision through the continuity of the detection process.
4Adaptability or versatility
If traditional vision systems are used, then adaptability to container shape changes is improved, but ease of operation deteriorates due to complex setup requirements
Solution Approach 1:
The system performs self-calibration and automatic adaptation to different container formats through the learning mechanism. The vision system automatically learns the container characteristics and adjusts its detection parameters without requiring manual setup or expert intervention, making the system easy to operate while maintaining high adaptability to various container shapes.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables precise, low-cost container orientation with a single viewing point, insensitive to container positioning and contents, and operable by non-qualified personnel, achieving high-speed orientation without complex setup or parameter entry.
Implementation Method 1
a fixed illuminator for illuminating the container and a single fixed recording device for recording multiple sequential images of the container during its movement of rotation-revolution
Data Source
AI summary
A device and a process for the orientation of containers with a carousel rotating about a vertical axis with a circumferential plurality of rotating seats imparting a rotation to each container causing a rotation-revolution. A recording device with illuminator recording multiple sequential images of the container during rotation-revolution. A controller adapted learn the lateral surface of said container in a number of positions. Learning each of the N positions said container is positioned with a random initial orientation, and during rotation a number of images are recorded. The controller acquires one current image, processes a similarity function representing the similarity between each current image and the images recorded in the same position in said learning step, calculates the similarity functions and the angle corresponding to the maximum value of this sum is used for the orientation of said container.