Intelligent Shopping Cart Tracking for Abnormal Item Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent shopping carts lack accuracy in detecting abnormal shopping behaviors, such as missing barcode scans or improper item placement, due to issues with commodity stacking and interference.
Innovation Solution
The method involves acquiring code scanning data and video-frame image data, segmenting commodities, tracking their trajectories, determining motion directions and distances, and using preset thresholds to detect abnormal behaviors by combining these data types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If commodity stacking is allowed in the shopping cart basket area, then the shopping cart can hold more commodities and improve shopping efficiency, but the stacked commodities cause mutual shielding and interference that reduces detection accuracy
Solution Approach 1:
The patent divides the basket area into multiple detection zones (first basket area and second basket area) with different detection thresholds. The first basket area uses a first threshold while the second basket area uses a second threshold, allowing the system to adapt to different stacking conditions in different regions of the basket.
Solution Approach 2:
The patent dynamically adjusts detection parameters based on the stacking state of commodities. When commodities are stacked, the system changes the detection threshold parameters to account for the reduced visibility and interference, thereby maintaining detection accuracy despite the increased quantity of commodities.
2Ease of operation
If self-service code scanning is implemented, then the shopping process is simplified and cashier interaction is reduced, but abnormal behaviors such as missing scans become harder to detect
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors the correlation between code scanning data and commodity trajectory data. When a discrepancy is detected (e.g., a commodity is placed in the basket without being scanned), the system generates an abnormal behavior indication and can prompt the user to complete the scanning process.
Solution Approach 2:
The patent combines multiple data types (code scanning data, video-frame image data, trajectory tracking data) to create a composite detection system. This multi-source data fusion allows the system to reliably detect abnormal behaviors while maintaining the simplicity of self-service scanning.
3Reliability
If trajectory tracking is used to monitor commodity motion, then abnormal behaviors can be detected, but the complexity of processing video-frame image data increases
Solution Approach 1:
The patent segments the video-frame image data processing into distinct stages: initial commodity detection, trajectory tracking, motion state determination, and abnormal behavior detection. This segmentation allows each stage to be optimized independently and reduces the overall processing complexity.
Solution Approach 2:
The patent performs preliminary commodity detection and segmentation before trajectory tracking. By pre-identifying commodities and their initial positions in the video frames, the system reduces the computational burden during the subsequent trajectory tracking and analysis stages.
Data Source
AI summary
An abnormal shopping behavior detection method and apparatus for an intelligent shopping cart, and the shopping cart are disclosed in the present disclosure. The method includes: acquiring code scanning data of commodities and video-frame image data of a basket area during a shopping behavior of a user; segmenting the commodities in an image of each frame in the video-frame image data of the basket area, to obtain image data of each target commodity in the basket area; tracking a trajectory of each target commodity; determining a motion direction and a motion distance of the tracked trajectory of each target commodity; determining an indicative state of whether each target commodity is put in or taken out of the shopping cart; and detecting an abnormal shopping behavior of the user.