Image analysis – Applications – Target tracking or detecting
Reexamination Certificate
1998-02-06
2001-05-22
Au, Amelia M. (Department: 2623)
Image analysis
Applications
Target tracking or detecting
C235S383000
Reexamination Certificate
active
06236736
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a point-of-sale system for retail environments, and more particularly to a system and method for detecting and analyzing motion patterns of individuals at a self-service checkout point-of-sale.
2. Description of the Prior Art
In the retail industry, labor is the number one expense after cost of goods sold. Employees working as “checkout personnel” or “cashiers” are the single largest category of labor. This is particularly true for those retailers in the food segment. On average, the retailer must have three or more cashiers trained for every checkout lane in a food store.
One problem for retailers is the cost associated with the recruiting, hiring, training, scheduling, managing, etc. of cashiers. This cost is exacerbated in that turnover in the food segment can easily exceed 100% annually, especially in metropolitan areas. It is not uncommon for food retailers to have significantly fewer cashiers on hand in a retail establishment than is optimally required.
The constant recruiting, hiring, training, and scheduling of cashiers consumers significant management time and expense. Scheduling alone can make or break a retailer's performance on any given day and significantly impact customer service. By scheduling too many cashiers, the retailer has excess capacity and a higher cost of sales for the day. By scheduling too few cashiers, checkout queues grow long with angry customers who may not return due to poor customer service. Other customers may enter the store and go elsewhere due to the long lines. Checkout problems are typically the leading consumer dissatisfaction issue for retailers.
Self Checkout (SCO) Terminals offer benefits to both the retailer and the consumer. For the retailer, SCO terminals reduce the retailer's need for cashiers, thereby reducing the costs associated with them. Since SCO terminals are rarely closed, the job of predicting and scheduling cashier demand is made easier. For the consumer, SCO terminals offer the perception of faster checkout, privacy, control, etc., and a significantly enhanced shopping experience.
Thus, in theory, replacing traditional cashier assisted checkout with self checkout makes great business sense. However, the cashier performs several roles for the retailer in addition to itemizing and tendering groceries. One significant role is that of security—ensuring that the consumers pay for all the groceries that they take out of the store. A SCO terminal can enable the consumer to take the cashier's place in itemizing and tendering. But the concern remains how to ensure that the consumer pays for all the items taken out of the store.
Loss prevention specialists know that the probability of theft increases when someone believes an opportunity exists to deceive without an offsetting risk of detection/consequence. By removing the cashier, the consumer is no longer faced with a significant method of detection.
Typical SCO solutions have used technologies that are not consumer friendly, are perceived as non-trusting, fail to support the consumer throughout the transaction, and have placed added operational issues on the retailer.
There is therefore a significant need in the art for a system and method for providing security for self checkout environments in a way that is effective and efficient, but is also acceptable to the consumer.
SUMMARY OF INVENTION
The present invention operates to process a sequence of input images received from one or more cameras monitoring a self-checked checkout workstation in, for example, a retail environment. In a preferred embodiment, the present invention may operate to collect data that may be useful in analyzing user interaction with a self-checkout workstation or terminal.
The present invention is directed to a system and method for detecting hand movement patterns with respect to a checkout terminal, such as a self-service check-out terminal, by monitoring the scene of the self-service checkout terminal and generating a sequence of video frames representing activity in the scene. The image information in the video frames is processed by a processor, such as a computer to identify regions of a video frame representing a hand; track hand movement with respect to the scanner over a plurality of video frames and generating tracking information representative thereof; and generate event information descriptive of user activity at the self-service checkout terminal based on the tracking information.
The present invention may generate output after performing the above steps. By combining the results of the above steps with the various zones defined in the image, the present invention may generate a series of event records (stored in a file) corresponding to actions taking place at the self check out terminal. For example, an event record may correspond to an empty hand passing over the scanner (including its direction of movement), a product passing over the scanner (including its direction of movement), etc.
The above and other objects and advantages of the present invention will become more readily apparent when reference is made to the following description, taken in conjunction with the following drawings.
REFERENCES:
patent: 5115888 (1992-05-01), Schneider
patent: 5426282 (1995-06-01), Humble
patent: 5494136 (1996-02-01), Humble
patent: 5594469 (1997-01-01), Freeman et al.
patent: 5801766 (1998-09-01), Alden
patent: 5883968 (1999-03-01), Welch et al.
patent: 6002808 (1999-12-01), Freeman
Ko et al. “Extracting the hand region with the aid of a tracking facility” Electronics Letters vol. 32 pp. 1561-1563, Aug. 1996.*
Ayer et al. “Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding” IEEE Proc. of 5th International Conference on Computer Vision pp. 777-784, Jun. 1995.*
Sawasaki et al. “Design and implementation of high speed visual tracking system for real time motion analysis” Proc. of teh 13th International Conf. on Pattern Recognition, vol. 3, pp. 478-483, Aug. 1996.*
“Deformable Contours: Modeling, Extraction, Detection and Classification” by Kok Fung Lai, 1994.
“Vision Tutor” Version 1.1 Lecture Guide Ch. 5-6, from Amerinex Artificial Intelligence, Inc. 1995, pp. 5-1-6-90.
“Reduction of color space dimensionality by moment-preserving thresholding and its application for edge detection in color images” by Chen-Kuei Yang et al., in Pattern Recognition Letters, 1996, pp. 481-490.
“Automatic Feature Point Extraction and Tracking in Image Sequences for Unknown Camera Motion” by Qinfen Zheng and Rama Chellappa, IEEE Proc. 4th International Conference on Computer Vision, 1993, pp. 335-339.
“Object Tracking Using Curvilinear Features” by J.G. Landowski and R.S. Loe, SPIE vol. 974 Applications of Digital Image Processing XI (1988), pp. 353-360.
“Detection and Tracking of Facial Features by Using Edge Pixel Counting and Deformable Circular Template Matching” by De Silva, Aizawa and Hatori, IEICE Trans. Inf. & Syst. vol. E78-D, No. 9, Sep. 1995, pp. 1195-1207.
“Moving Object Tracking Using Local Windows” by Celenk and Reza, IEEE International Symposium on Intelligent Control 1988, pp. 180-185.
“Estimating Three-Dimenstional Motion Parameters of a Rigid Planar Patch” by Tsai and Huang, IEEE Pattern Recognition and Image Processing, 1981, pp. 94-118.
“Tracking Human Movements Using Finite Element Methods” by Wen-hung Liao, May 20, 1994.
“Object Tracking Through Adaptive Correlation” by Montera, Rogers, Ruck and Oxley, SPIE vol. 1959 Optical Pattern Recognition IV (!993), pp. 314-320.
“Object Tracking Through Adaptive Correlation” by Montera, Rogers, Ruck and Oxley, vo. 33, No. 1, Optical Engineering, Jan. 1994, pp. 294-302.
“Tracking Multiple Features Using Relaxation” by Jim Z.C. Lai, Pattern Recognition, vol. 26, No. 12, pp. 1827-1837, 1993.
“3D Structure and Motion Estimation from 2D Image Sequences” by Tan, Baker and Sullivan, Image and Vision Computing, vol. 11, No. 4, May 1993, pp. 203-210.
“Object Tracking With a Moving Camera” by Burt,
Crabtree Ralph N.
Huang Jianzhong
Kim Junhoy
Au Amelia M.
NCR Corporation
Needle & Rosenberg P.C.
Wu Jingge
LandOfFree
Method and apparatus for detecting movement patterns at a... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for detecting movement patterns at a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for detecting movement patterns at a... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2493498