Vending Machine Planogram Determination via Machine Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the inventory of products in vending machines are slow, expensive, and prone to errors due to manual planogram recording and auditing, especially when dealing with small, distorted, and visually complex consumer-packaged goods.
Innovation Solution
The use of machine vision technologies with a series of novel steps, including creating a database of reference images, comparing images using color vectors, feature detection, and pruning algorithms to accurately identify products in vending machine slots, employing techniques like Gaussians in a color space and multiple feature extraction algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual planogram recording and auditing methods are used, then the process is simple to implement, but the speed is slow and error rate is high
Solution Approach 1:
The patent replaces manual mechanical recording processes with an automated machine vision system that uses digital imaging, color vector analysis, and feature detection algorithms to identify and record planogram data, thereby increasing both speed and accuracy simultaneously
Solution Approach 2:
The system enables self-service by allowing the vending machine to automatically capture images and perform product identification without requiring manual intervention from drivers, using onboard imaging devices and processing algorithms to autonomously determine planogram status
2Measurement precision
If prior art machine vision techniques are used, then automation is achieved, but accuracy is poor due to distorted and obscured CPG images
Solution Approach 1:
The patent segments the complex image processing task into distinct stages: color vector extraction, feature detection, candidate generation, and verification. This segmentation allows each component to be optimized independently, improving accuracy while managing complexity through modular processing
Solution Approach 2:
The system changes parameters by extracting color vectors and feature descriptors that are invariant to common distortions such as rotation, scaling, and partial obscuration. This parameter transformation allows accurate identification despite variations in image quality caused by distorted or obscured CPG packaging
3Measurement precision
If comprehensive feature detection algorithms are used, then identification accuracy is improved, but computational cost and processing time increase
Solution Approach 1:
The patent performs preliminary action by pre-computing color vectors and feature descriptors for all reference products and storing them in a database. During actual planogram determination, these pre-computed features are quickly compared against captured images, significantly reducing processing time while maintaining high accuracy through the use of prepared reference data
Data Source
AI summary
A method is described for the automatic determination of a planogram in a vending machine using image processing. Novel steps include the use of a Gaussian map in a two-dimensional color space, such as the HS plane, to create high-dimensionally color vectors for all and for selected portions of images. Multiple feature detection/extraction algorithms are run between multiple idealized reference images for a product and one image from one vending machine coil location. The large resulting candidate feature list is pruned in a series of steps using both color and gray-scale color vectors and small area image matching around features. Remaining candidate features are ranked by a RANSAC outlier removal step, with the top ranked product then being the correct product in that coil in the planogram. Steps are repeated for all coils in a vending machine.