Dual-Imager Self-Checkout Tracking via Steering Mirror
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-based systems for detecting and tracking objects in environments, such as retail stores, face challenges in capturing high-resolution images of moving objects over large areas without the need for expensive active illumination, which can interfere with other components and be impractical due to varying object positions.
Innovation Solution
The implementation of a dual-imager system with a targeting imager for wide-angle, high-resolution imaging and a steerable scanning imager, utilizing a steering mirror to adjust the field of view based on object characteristics, allowing for high-resolution imaging of selected objects while reducing relative motion and eliminating the need for extensive high-resolution capture of the entire field of view.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a high-resolution camera is mounted in the ceiling to cover a large area, then the field of view is increased, but the resolution becomes insufficient to identify small objects
Solution Approach 1:
The patent divides the imaging system into two separate cameras: a first camera with a wide field of view for detecting object presence and position, and a second camera with a narrow field of view for capturing high-resolution images of selected objects. This segmentation allows each camera to be optimized for its specific function, resolving the contradiction between field of view and resolution.
Solution Approach 2:
Different parts of the imaging system have different qualities: the first camera provides wide-area coverage with lower resolution requirements, while the second camera provides high-resolution imaging for specific local areas. This local quality differentiation allows the system to achieve both wide field of view and high resolution where needed.
2Measurement precision
If a fast shutter speed is used to capture moving objects sharply, then image quality is improved, but expensive active illumination systems are required
Solution Approach 1:
The system performs preliminary detection of moving objects using the first camera with wide field of view before activating the second camera for high-resolution imaging. This preliminary action allows the system to prepare and select targets in advance, enabling sharp capture of moving objects without requiring expensive active illumination systems.
3Area of stationary object
If the field of view is increased to cover more area, then the coverage is improved, but the relative motion between objects and field of view increases
Solution Approach 1:
The patent employs dynamic tracking where the second camera focuses on specific objects of interest rather than maintaining a fixed wide field of view. This dynamic approach allows the system to maintain high-resolution imaging of moving objects while the first camera continues to provide wide-area coverage, effectively managing the contradiction between coverage area and relative motion.
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
This approach enables efficient, high-resolution object tracking and identification in retail environments, including self-checkout systems and loss prevention, without the need for costly illumination systems and improves the assessment of shopping patterns or detection of shoplifting.
Implementation Method 1
A field of view of a scanning imager or camera is directed or caused to track one or more objects via a steering mirror
Data Source
AI summary
Systems and methods for providing self-checkout systems that utilize a scanning imager or camera which includes a selectively steerable field of view. A tracking subsystem may include a targeting imager or camera that captures data (e.g., 3-dimensional data) that characterizes objects in an environment, for instance a retail environment. Images captured by one or more targeting imagers may be used to determine characteristics of objects. The characteristics may be used to generate an object model, which is a collection of properties about an object in the field of view. The tracking subsystem directs the field of view of the relatively higher resolution scanning imager with a relatively narrow field of view to track one or more objects so that images of the objects may be captured. The images are processed to identify the identification of the objects so that the objects may be added to a transaction list to complete a purchase process.