Method and system for analyzing shopping behavior using multiple sensor tracking
View Patent ↗The present invention is a method and system for automatically analyzing the behavior of a person and a plurality of persons in a physical space based on measurement of the trip of the person and the plurality of persons on input images. The present invention captures a plurality of input images of the person by a plurality of means for capturing images, such as cameras. The plurality of input images is processed in order to track the person in each field of view of the plurality of means for capturing images. The present invention measures the information for the trip of the person in the physical space based on the processed results from the plurality of tracks and analyzes the behavior of the person based on the trip information. The trip information can comprise coordinates of the person's position and temporal attributes, such as trip time and trip length, for the plurality of tracks. The physical space may be a retail space, and the person may be a customer in the retail space. The trip information can provide key measurements as a foundation for the behavior analysis of the customer along the entire shopping trip, from entrance to checkout, that deliver deeper insights about the customer behavior. The focus of the present invention is given to the automatic behavior analytics applications based upon the trip from the extracted video, where the exemplary behavior analysis comprises map generation as visualization of the behavior, quantitative category measurement, dominant path measurement, category correlation measurement, and category sequence measurement.
1. A method for automatically analyzing the behavior of at least a person in a physical space based on measurement of the trip of the person, comprising the following steps of:
a) capturing a plurality of input images of the person by a plurality of means for capturing images,
b) processing the plurality of input images in order to track the person in each field of view of the plurality of means for capturing images,
c) finding information for the trip of the person in the physical space based on the processed results from the plurality of tracks, and
d) analyzing the behavior of the person based on the trip information,
wherein the trip information comprises coordinates of positions and temporal attributes of the plurality of tracks for the person.
2. The method according to claim 1 , wherein the method further comprises steps of:
a) repeating steps a) through d) in claim 1 for each person in a plurality of persons, and
b) measuring the behavior of the plurality of persons by aggregating the trip information for each person.
3. The method according to claim 1 , wherein the method further comprises a step of extracting statistical data from the trip information,
wherein the data comprises a traffic distribution, a shopping distribution, a shopping conversion, a category-level traffic distribution, a category-level shopping distribution, and a category-level shopping conversion.
4. The method according to claim 3 , wherein the method further comprises a step of generating layers of information based on the statistical data,
wherein the layers comprise a layer for traffic distribution, a layer for shopping distribution, a layer for shopping conversion, a layer for category-level traffic distribution, a layer for category-level shopping distribution, and a layer for category-level shopping conversion.
5. The method according to claim 4 , wherein the method further comprises a step of generating a map utilizing at least one layer from the layers of information,
wherein a combination of the layers can generate a map that represents complex behavior analyses.
6. The method according to claim 3 , wherein the method further comprises a step of generating a map based on the extracted statistical data,
whereby the map comprises a traffic distribution map, a shopping distribution map, a shopping conversion map, a category-level traffic distribution map, a category-level shopping distribution map, and a category-level shopping conversion map.
7. The method according to claim 3 , wherein the method further comprises a step of processing the behavior analysis based on the statistical data,
wherein the behavior analysis comprises map generation, quantitative category measurement, dominant path measurement, category correlation measurement, and category sequence measurement.
8. The method according to claim 7 , wherein the method further comprises a step of processing a category-level path analysis for the quantitative category measurement.
9. The method according to claim 7 , wherein the method further comprises a step of calculating a decision pattern of the person based on the dominant path measurement, whereby neighboring regions for the path direction can be defined either at point-level or at polygon-level depending on the predefined granularity of the neighboring region.
10. The method according to claim 7 , wherein the method further comprises a step of calculating an optimal distance between categories based on the category correlation measurement.
11. The method according to claim 7 , wherein the method further comprises a step of calculating the order of categories based on the category sequence measurement, whereby the order of categories shows the order of a customer's shopping engagement.
12. The method according to claim 1 , wherein the method further comprises a step of analyzing the stopping power based on the temporal attributes,
whereby the temporal attributes comprise trip time and trip length.
13. The method according to claim 1 , wherein the method further comprises a step of augmenting the trip information by domain-specific knowledge,
whereby the step of applying the domain-specific knowledge comprises:
a) a step of adding behavioral attributes, calculated by the analysis of the tracking of the person, to the trip information, and
b) a step of removing irrelevant data from the trip information.
14. The method according to claim 1 , wherein the method further comprises a step of utilizing a rule application module for analyzing the trip information and processing the behavior analysis,
whereby the rule application module comprises information unit verification technologies.
15. An apparatus for automatically analyzing the behavior of at least a person in a physical space based on measurement of the trip of the person, comprising:
a) means for capturing a plurality of input images of the person by a plurality of means for capturing images,
b) means for processing the plurality of input images in order to track the person in each field of view of the plurality of means for capturing images,
c) means for finding information for the trip of the person in the physical space based on the processed results from the plurality of tracks, and
d) means for analyzing the behavior of the person based on the trip information,
wherein the trip information comprises coordinates of positions and temporal attributes of the plurality of tracks for the person.
16. The apparatus according to claim 15 , wherein the apparatus further comprises:
a) means for repeatedly using means a) through d) in claim 15 for each person in a plurality of persons, and
b) means for measuring the behavior of the plurality of persons by aggregating the trip information for each person.
17. The apparatus according to claim 15 , wherein the apparatus further comprises means for extracting statistical data from the trip information,
wherein the data comprises a traffic distribution, a shopping distribution, a shopping conversion, a category-level traffic distribution, a category-level shopping distribution, and a category-level shopping conversion.
18. The apparatus according to claim 17 , wherein the apparatus further comprises means for generating layers of information based on the statistical data,
wherein the layers comprise a layer for traffic distribution, a layer for shopping distribution, a layer for shopping conversion, a layer for category-level traffic distribution, a layer for category-level shopping distribution, and a layer for category-level shopping conversion.
19. The apparatus according to claim 18 , wherein the apparatus further comprises means for generating a map utilizing at least one layer from the layers of information, wherein a combination of the layers can generate a map that represents complex behavior analyses.
20. The apparatus according to claim 17 , wherein the apparatus further comprises means for generating a map based on the extracted statistical data,
whereby the map comprises a traffic distribution map, a shopping distribution map, a shopping conversion map, a category-level traffic distribution map, a category-level shopping distribution map, and a category-level shopping conversion map.
21. The apparatus according to claim 17 , wherein the apparatus further comprises means for processing the behavior analysis based on the statistical data,
wherein the behavior analysis comprises map generation, quantitative category measurement, dominant path measurement, category correlation measurement, and category sequence measurement.
22. The apparatus according to claim 21 , wherein the apparatus further comprises means for processing a category-level path analysis for the quantitative category measurement.
23. The apparatus according to claim 21 , wherein the apparatus further comprises means for calculating a decision pattern of the person based on the dominant path measurement,
whereby neighboring regions for the path direction can be defined either at point-level or at polygon-level, depending on the predefined granularity of the neighboring region.
24. The apparatus according to claim 21 , wherein the apparatus further comprises means for calculating an optimal distance between categories based on the category correlation measurement.
25. The apparatus according to claim 21 , wherein the apparatus further comprises means for calculating the order of categories based on the category sequence measurement,
whereby the order of categories shows the order of a customer's shopping engagement.
26. The apparatus according to claim 15 , wherein the apparatus further comprises means for analyzing the stopping power based on the temporal attributes,
whereby the temporal attributes comprise trip time and trip length.
27. The apparatus according to claim 15 , wherein the apparatus further comprises means for augmenting the trip information by domain-specific knowledge,
whereby the means for applying the domain-specific knowledge comprises:
a) means for adding behavioral attributes, calculated by the analysis of the tracking of the person to the trip information, and
b) means for removing irrelevant data from the trip information.
28. The apparatus according to claim 15 , wherein the apparatus further comprises means for utilizing a rule application module for analyzing the trip information and processing the behavior analysis,
whereby the rule application module comprises information unit verification technologies.