CN113506132A - Method and device for determining offline attention degree - Google Patents
Method and device for determining offline attention degree Download PDFInfo
- Publication number
- CN113506132A CN113506132A CN202110764670.0A CN202110764670A CN113506132A CN 113506132 A CN113506132 A CN 113506132A CN 202110764670 A CN202110764670 A CN 202110764670A CN 113506132 A CN113506132 A CN 113506132A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- store
- pedestrians
- attention
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0245—Surveys
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
Abstract
The embodiment of the invention discloses a method and a device for determining offline attention, relates to the field of computer vision, and can solve the problem that the attention of a physical store cannot be automatically evaluated in the prior art. The method mainly comprises the following steps: recognizing the pedestrian posture in the pedestrian image and tracking the travel track of the pedestrian; determining the traveling direction of the pedestrian relative to the physical store according to the traveling track; identifying pedestrians according to a preset pedestrian identification technology, and determining the number of the pedestrians in the traveling direction; determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of the pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction; and/or determining the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture. The embodiment of the invention can be applied to the attention degree evaluation scene of the entity stores such as the entity stores, the entity advertisement screens/walls and the like.
Description
Technical Field
The invention relates to the field of computer vision, in particular to a method and a device for determining offline attention.
Background
In order to determine whether a store, an advertisement (including an advertisement screen or an advertisement wall), and the like, which are held by a merchant, are popular so that the merchant can adjust the business strategy, the attention of a consumer to the store or the advertisement is often required to be evaluated. However, currently, store or advertisement attention assessment is focused mainly on the line, and is assessed by the on-line click volume and the collection number. An effective scheme is not provided at present aiming at the automatic evaluation of the attention degree of stores, advertisement screens or advertisement walls of offline entities.
Disclosure of Invention
The invention provides a method and a device for determining offline attention, which are used for automatically determining the attention of physical stores such as physical stores, physical advertisement screens/walls and the like. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for determining offline attention, where the method includes:
recognizing the pedestrian posture in the pedestrian image and tracking the travel track of the pedestrian;
determining the traveling direction of the pedestrian relative to the physical store according to the traveling track;
identifying pedestrians according to a preset pedestrian identification technology, and determining the number of the pedestrians in the advancing direction;
determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction;
and/or determining the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture.
Optionally, determining a traveling direction of the pedestrian relative to the brick-and-mortar store according to the traveling track includes:
if the advancing direction comprises a store entering direction and a store exiting direction, determining whether the advancing direction of the pedestrian relative to the physical store is the store entering direction or the store exiting direction according to the advancing track and the store entering and exiting judgment reference line;
and if the traveling direction comprises the left traveling and the right traveling of the pedestrian outside the physical store, determining whether the pedestrian travels left or right outside the physical store according to the traveling track and the left and right traveling judgment reference line.
Optionally, if the travel direction includes a store-entering direction and a store-exiting direction, determining a degree of attention of a pedestrian to the physical store in the physical store according to the travel direction, the number of pedestrians in the travel direction, and a video frame sequence value corresponding to the pedestrian in the travel direction, including:
aiming at the same pedestrian, calculating the residence time of the pedestrian in the entity store according to the video frame sequence value corresponding to the pedestrian when entering the store, the video frame sequence value corresponding to the pedestrian when leaving the store and the sampling frequency of a camera;
and determining the sum of residence time of all pedestrians corresponding to the number of the pedestrians in the physical store as the attention degree of the pedestrians to the physical store in the physical store.
Optionally, if the traveling direction includes that the pedestrian travels left and right outside the brick-and-mortar store, determining the attention of the pedestrian to the brick-and-mortar store outside the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture, includes:
determining an attention angle of the pedestrian outside the physical store to the physical store according to an included angle between a straight line where key points of left and right shoulders of the pedestrian are located in the pedestrian posture and a store entering and exiting judgment reference line and the advancing track;
for the same pedestrian, determining the attention time of the pedestrian to the physical store in the advancing direction according to the video frame number corresponding to the pedestrian in the advancing direction, the attention angle determined by the pedestrian in each video frame corresponding to the advancing direction, and the sampling frequency of a camera;
respectively calculating the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the left travelling direction and the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the right travelling direction, and determining the sum of the attention time in the left travelling direction and the attention time in the right travelling direction as the attention degree of the pedestrians to the physical store outside the physical store.
Optionally, determining, according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture, a degree of attention of a pedestrian to the brick-and-mortar store outside the brick-and-mortar store, includes:
calculating the attention f of the pedestrian to the physical store outside the physical store according to the following formulaoutdoor：
Wherein il represents the ith pedestrian traveling leftwards, jl represents the video frame sequence value corresponding to the ith pedestrian traveling leftwards in the leftward traveling direction, ir represents the ith pedestrian traveling rightwards, jr represents the video frame sequence value corresponding to the ith pedestrian traveling rightwards in the rightward traveling direction, p represents the sampling frequency of the camera, and theta represents the attention angle of the pedestrian to the physical store outside the physical store;
il is 0 or more and nl is less than or equal to, nl represents the number of pedestrians in the left traveling direction;
0 ≦ ir ≦ nr, nr representing the number of pedestrians in the rightward traveling direction;
0≤jl≤mli，mlia video frame number indicating the i-th pedestrian traveling to the left in the leftward traveling direction;
0≤jr≤mri，mriindicates that the ith pedestrian moving to the right is moving toVideo frame number in right direction of travel.
Optionally, identifying the pedestrian according to a preset pedestrian identification technology, and determining the number of the pedestrians in the traveling direction includes:
if the traveling direction comprises a store entering direction and a store exiting direction, matching store entering pedestrians and store exiting pedestrians according to a preset pedestrian re-identification model, and determining the number of the pedestrians in the store entering direction or the store exiting direction;
if the advancing direction comprises leftward advancing and rightward advancing of the pedestrian outside the physical store, tracking the pedestrian according to a preset tracking algorithm, and determining the quantity of the pedestrians advancing leftward and rightward outside the physical store.
Optionally, the method further includes:
and weighting the attention of the pedestrian to the physical store in the physical store and the attention of the pedestrian to the physical store outside the physical store to obtain the total attention of the pedestrian to the physical store.
In a second aspect, an embodiment of the present invention provides an apparatus for determining offline attention, where the apparatus includes:
the recognition and tracking unit is used for recognizing the pedestrian posture in the pedestrian image and tracking the travel track of the pedestrian;
the first determining unit is used for determining the traveling direction of the pedestrian relative to the physical store according to the traveling track;
a second determination unit for identifying pedestrians according to a preset pedestrian identification technology and determining the number of pedestrians in the traveling direction;
the device further comprises a third determining unit and/or a fourth determining unit;
the third determining unit is used for determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction;
the fourth determination unit is configured to determine the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture.
Optionally, the first determining unit includes:
a first traveling direction determining module, configured to determine, when the traveling direction includes a store entering direction and a store exiting direction, whether the traveling direction of the pedestrian relative to the brick-and-mortar store is the store entering direction or the store exiting direction according to the traveling track and the store entering and exiting determination reference line;
and a second travel direction determination module, configured to determine, when the travel directions include left travel and right travel of the pedestrian outside the brick-and-mortar store, whether the pedestrian travels left or right outside the brick-and-mortar store according to the travel trajectory and the left-and-right travel determination reference line.
Optionally, the second determining unit includes:
the calculation module is used for calculating the residence time of the pedestrian in the physical store according to the video frame sequence value corresponding to the pedestrian entering the store, the video frame sequence value corresponding to the pedestrian exiting the store and the sampling frequency of the camera for the same pedestrian when the travelling direction comprises a store entering direction and a store exiting direction;
and the first attention degree determining module is used for determining the sum of residence time of all pedestrians corresponding to the number of the pedestrians in the physical store as the attention degree of the pedestrians to the physical store in the physical store.
Optionally, the third determining unit includes:
the attention angle determining module is used for determining an attention angle of the pedestrian to the physical store outside the physical store according to an included angle between a straight line where key points of left and right shoulders of the pedestrian are located in the pedestrian gesture and an in-out judgment reference line and the travel track when the travel direction comprises left travel and right travel of the pedestrian outside the physical store;
the attention time determining module is used for determining attention time of the pedestrian to the physical store in the advancing direction according to the number of video frames corresponding to the pedestrian in the advancing direction, the attention angle determined by each video frame corresponding to the pedestrian in the advancing direction and the sampling frequency of a camera for the same pedestrian;
and the second attention determining module is used for respectively calculating the sum of the attention time of all pedestrians corresponding to the number of pedestrians in the left traveling direction to the physical store and the sum of the attention time of all pedestrians corresponding to the number of pedestrians in the right traveling direction to the physical store, and determining the sum of the attention time in the left traveling direction and the attention time in the right traveling direction as the attention of the pedestrians to the physical store outside the physical store.
Optionally, the third determining unit is configured to calculate the attention f of the pedestrian to the brick-and-mortar store outside the brick-and-mortar store according to the following formulaoutdoor：
Wherein il represents the ith pedestrian traveling leftwards, jl represents the video frame sequence value corresponding to the ith pedestrian traveling leftwards in the leftward traveling direction, ir represents the ith pedestrian traveling rightwards, jr represents the video frame sequence value corresponding to the ith pedestrian traveling rightwards in the rightward traveling direction, and p represents the sampling frequency theta of the camera represents the attention angle of the pedestrian to the physical store outside the physical store
Il is 0 or more and nl is less than or equal to, nl represents the number of pedestrians in the left traveling direction;
0 ≦ ir ≦ nr, nr representing the number of pedestrians in the rightward traveling direction;
0≤jl≤mli，mlia video frame number indicating the i-th pedestrian traveling to the left in the leftward traveling direction;
0≤jr≤mri，mriindicating the number of video frames in the rightward traveling direction of the i-th pedestrian traveling rightward.
Optionally, the second determining unit is configured to, when the traveling direction includes a store-in direction and a store-out direction, match a pedestrian entering the store with a pedestrian exiting the store according to a preset pedestrian re-identification model, and determine the number of pedestrians in the store-in direction or the store-out direction; when the traveling direction comprises left traveling and right traveling of the pedestrian outside the physical store, tracking the pedestrian according to a preset tracking algorithm, and determining the quantity of the pedestrians traveling left and right outside the physical store.
Optionally, the apparatus further comprises:
and the weighting unit is used for weighting the attention degree of the pedestrian to the physical store in the physical store and the attention degree of the pedestrian to the physical store outside the physical store to obtain the total attention degree of the pedestrian to the physical store.
In a third aspect, an embodiment of the present invention provides a storage medium having stored thereon executable instructions, which when executed by a processor, cause the processor to implement the method of the first aspect.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of the first aspect.
As can be seen from the above, the method and apparatus for determining offline attention provided by the embodiments of the present invention can first recognize the pedestrian posture in the pedestrian image and track the travel track of the pedestrian, then determine the travel direction of the pedestrian relative to the brick-and-mortar store according to the travel track, and identifies pedestrians according to a preset pedestrian identification technology, determines the number of pedestrians in each traveling direction, and when the attention degree of an area in a physical store needs to be evaluated, can be calculated according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrians in the traveling direction, when the attention degree in the preset range outside the physical store needs to be evaluated, can be calculated according to the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture, when the total attention degree inside and outside the physical store needs to be evaluated, the total attention degree can be obtained by weighting the two attention degrees. Therefore, by applying the embodiment of the invention, the in-store attention degree can be automatically evaluated not only for the physical stores (such as supermarkets, drug stores, restaurants and other physical stores) containing the internal space, but also for the physical stores without the internal space (such as advertisement screens, advertisement walls and the like), and the function of evaluating the attention degree for any type of off-line physical stores is realized. And aiming at the entity store containing the internal space, the attention degrees in the store and outside the store can be comprehensively considered, so that the accuracy of the attention degree evaluation is further improved. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
The innovation points of the embodiment of the invention comprise:
1. and the attention degree of the pedestrian to the physical store in the store and/or the attention degree of the pedestrian to the physical store outside the store are/is automatically evaluated by combining a target tracking technology, a pedestrian recognition technology and a pedestrian gesture recognition technology. Specifically, the attention degree of the pedestrian to the entity store in the store is determined through the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction, which are obtained through the technology; the degree of attention of the pedestrian to the physical store outside the store is determined by the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture obtained by the above-described technique.
2. When the attention degree of the pedestrian to the physical store in the store is determined, the residence time of the pedestrian in the physical store is calculated according to the video frame sequence value corresponding to the same pedestrian when the pedestrian enters the store, the video frame sequence value corresponding to the same pedestrian when the pedestrian leaves the store and the sampling frequency of the camera. When the attention degree of the pedestrian to the physical store outside the store is determined, the attention time of the pedestrian to the physical store in the traveling direction is determined according to the video frame number corresponding to the same pedestrian in the traveling direction, the attention angle determined by the pedestrian in each video frame corresponding to the traveling direction, and the sampling frequency of the camera.
3. And judging the traveling direction of the pedestrian relative to the physical store by combining the traveling track and the judgment reference line.
4. By weighting the two attention degrees, the total attention degree more conforming to the actual attention degree is obtained.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be understood that the drawings in the following description are merely exemplary of some embodiments of the invention. For a person skilled in the art, without inventive effort, further figures can be obtained from these figures.
Fig. 1 is a schematic flow chart of a method for determining offline attention according to an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a method for determining a reference line according to an embodiment of the present invention;
FIG. 3 is an exemplary diagram for determining an angle of interest according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus for determining offline attention according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The invention provides a method and a device for determining offline attention, which are used for automatically determining the attention of physical stores such as physical stores, physical advertisement screens/walls and the like. The method provided by the embodiment of the invention can be applied to any electronic equipment with computing capability, and the electronic equipment can be a terminal or a server. In one implementation, the electronic device may be a camera integrated with the method, or may be another electronic device independent of the camera, and the attention assessment function is implemented by interacting with the camera. In one implementation, the functional software implementing the method may exist in the form of separate client software, or may exist in the form of a plug-in to currently associated client software.
The following provides a detailed description of embodiments of the invention.
Fig. 1 is a schematic flow chart of a method for determining offline attention according to an embodiment of the present invention. The method may comprise the steps of:
s101: recognizing the pedestrian gesture in the pedestrian image, and tracking the travel track of the pedestrian.
In evaluating the attention of the pedestrian located outside the store to the brick-and-mortar store, since the attention reflected when the pedestrian views the brick-and-mortar store in different postures is different, for example, a pedestrian who stays on the advertisement screen in front is more interested in the advertisement screen and the attention is higher than a pedestrian who views the advertisement screen at a glance on the side when passing by, the posture of the pedestrian needs to be considered in evaluating the attention of the pedestrian to the brick-and-mortar store outside the store. The pedestrian posture of the embodiment of the invention mainly comprises a pedestrian head key point and a plurality of shoulder key points, wherein the head key point can be one or more, the shoulder key points comprise a left shoulder key point and a right shoulder key point, and the left/right side key points can be one or more. In one implementation, a first-stage or two-stage head-shoulder detection model based on deep learning and a head-shoulder detection model based on a deep learning regression method may be trained in advance, then the head and shoulders in the video frame image are detected by using the head-shoulder detection model, and then the head and shoulder key points, such as a head top center point and two left and right shoulder edge key points, are determined by using the head-shoulder detection model.
In addition, in order to accurately evaluate the attention degree inside and outside the brick-and-mortar store, it is necessary to know information such as whether each pedestrian enters or exits the brick-and-mortar store, and a walking direction outside the store. To acquire such information, a pedestrian may be tracked using a target tracking technique to obtain a travel trajectory of the pedestrian. The target Tracking technology includes, but is not limited to, KCF (kernel Correlation Filters) algorithm, TLD (Tracking-Learning-Detection) algorithm, and MediaFlow algorithm.
It should be noted that the brick-and-mortar stores involved in the embodiment of the present invention may include not only brick-and-mortar stores having an internal space (e.g., brick-and-mortar stores such as supermarkets, drug stores, restaurants, etc.), but also brick-and-mortar stores having no internal space (e.g., advertisement screens, advertisement walls, etc.).
S102: and determining the traveling direction of the pedestrian relative to the physical store according to the traveling track.
The traveling directions related to the embodiment of the invention comprise a store-entering direction and a store-exiting direction, and the pedestrian travels leftwards and rightwards outside the physical store. The pedestrian tracking method has the advantages that the pedestrian can be tracked to obtain the travelling track of the pedestrian, the position information of the pedestrian at each time point can be obtained from the travelling track, and whether the pedestrian crosses into the physical store or out of the physical store and whether the pedestrian travels leftwards or rightwards when walking outside the physical store can be determined by analyzing the position information of the pedestrian.
In one embodiment, whether the pedestrian is in the store-entering direction or the store-exiting direction with respect to the brick-and-mortar store may be determined based on the travel track of the pedestrian and the store-entering and store-exiting determination reference line. The in-out store judgment reference line can be a straight line where a doorway of the physical store is located, and can also be other reference lines which can judge whether pedestrians cross in or out of the physical store. When a plurality of doorways of the physical store are provided, different in-out store judgment reference lines can be set for different doorways.
In one embodiment, whether the pedestrian travels to the left or to the right outside the brick-and-mortar store may be determined based on the travel locus of the pedestrian and the left-right travel determination reference line. The left-hand travel and the right-hand travel may be relative positional relationships, and may be determined by, for example, standing at an angle of the pedestrian when the pedestrian walks toward the brick and mortar store, or standing at an angle of the camera capturing the pedestrian outward. The left-right travel judgment reference line may be an outward central axis of a doorway of the physical store, or may be another reference line capable of judging that a pedestrian travels leftwards or rightwards, for example, the reference line may be a central axis of a field of view shot by the camera to the outside of the physical store. When there are a plurality of doorways of the physical store, different left and right travel judgment reference lines can be set for different doorways.
For example, as shown in fig. 2, the doorway of the physical store is a revolving door, a top-view camera is mounted on the ceiling of the doorway, the in-out store judgment reference line may be AB, and the left-right travel judgment reference line may be CD.
S103: and identifying pedestrians according to a preset pedestrian identification technology, and determining the number of the pedestrians in the advancing direction.
For the pedestrians who are located outside the physical store and concern about the physical store, the camera can capture the walking condition of the same pedestrian in real time, the pedestrians outside the physical store can be tracked by the aid of a preset tracking algorithm, and the number of the pedestrians walking leftwards and the number of the pedestrians walking rightwards are counted.
For a pedestrian entering a store concerned with the physical property in the physical property store, due to the limited shooting range of the camera, after the pedestrian enters the store, the pedestrian may exceed the shooting range of the camera, and after the pedestrian stays in the store for a period of time, the pedestrian leaves the store. Thus, it is impossible to recognize whether a pedestrian who leaves the brick-and-mortar store and a pedestrian who enters the brick-and-mortar store belong to the same pedestrian only by the tracking technology. In this case, in order to improve the accuracy of pedestrian recognition, the pedestrian re-recognition model may be used to match the store-entering image and the store-exiting image, so as to locate the video frames corresponding to the same pedestrian and count the number of pedestrians in the store-entering direction or the store-exiting direction.
The pedestrian re-identification model is not limited in the embodiment of the invention, and only needs to be capable of identifying whether the store-entering pedestrian and the store-exiting pedestrian are the same pedestrian. For example, the pedestrian re-recognition model may be a neural network model trained based on features such as contour features, color features, and poses of the pedestrian target, and it may be determined whether two pedestrians are the same pedestrian by recognizing the contour features, the color features, and the poses of the pedestrians.
S104: determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction; and/or determining the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture.
The degree of attention of a pedestrian to an entity store in the entity store is mainly related to the residence time of the pedestrian in the entity store and the number of pedestrians, so that the residence time of all pedestrians in the entity store can be calculated from the direction of entrance/exit of the store, the number of pedestrians in the entrance/exit of the store, and the corresponding video frame sequence values when the pedestrian enters/exits the store, and the sum of the residence times can be used as the degree of attention of the pedestrian to the entity store in the store.
The degree of attention of a pedestrian to an entity store outside the entity store is mainly related to how much the pedestrian pays attention to the entity store and the number of pedestrians in which posture, so the degree of attention of the pedestrian to the entity store outside the store can be determined according to the direction of entrance/exit of the pedestrian, the number of pedestrians in the direction of entrance/exit of the store, and the posture of the pedestrian.
It should be added that the installation mode of the camera for collecting the pedestrian video sequence may be a top view mode, the lens plane is parallel to the ground, or other installation modes, as long as the pedestrian posture related in the embodiment of the present invention can be captured according to the video frame, and the accuracy of other parameters related in the attention degree evaluation is not affected.
The method for determining the offline attention provided by the embodiment of the invention can firstly identify the pedestrian gesture in the pedestrian image and track the travel track of the pedestrian, then determine the travel direction of the pedestrian relative to the entity store according to the travel track, identify the pedestrian according to the preset pedestrian identification technology and determine the number of the pedestrian in each travel direction, when the attention of the area in the entity store needs to be evaluated, the method can be obtained by calculation according to the travel direction, the number of the pedestrians in the travel direction and the corresponding video frame sequence value of the pedestrian in the travel direction, and when the attention in the preset range outside the entity store needs to be evaluated, the method can be obtained by calculation according to the travel direction, the number of the pedestrians in the travel direction and the pedestrian gesture. Therefore, by applying the embodiment of the invention, the in-store attention degree can be automatically evaluated not only for the physical stores (such as supermarkets, drug stores, restaurants and other physical stores) containing the internal space, but also for the physical stores without the internal space (such as advertisement screens, advertisement walls and the like), and the function of evaluating the attention degree for any type of off-line physical stores is realized.
In another embodiment of the present invention, the specific implementation manner of the step "determining the attention degree of the pedestrian to the brick-and-mortar store within the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and the corresponding video frame sequence value of the pedestrian in the traveling direction" may be: aiming at the same pedestrian, calculating the residence time of the pedestrian in the entity store according to the video frame sequence value corresponding to the pedestrian when the pedestrian enters the store, the video frame sequence value corresponding to the pedestrian when the pedestrian leaves the store and the sampling frequency of the camera; and determining the sum of residence time of all pedestrians corresponding to the number of the pedestrians in the physical store as the attention degree of the pedestrians to the physical store in the physical store.
Specifically, the following formula can be adopted for calculation:
wherein f isindoorIndicating the pedestrian's interest in the brick-and-mortar store,
indicating the corresponding video frame sequence value when the ith pedestrian leaves the store,
indicates the ith pedestrianWhen a user enters a store, i is more than or equal to 0 and less than or equal to n, n is the number of people entering the store or the number of people leaving the store, and p represents the sampling frequency of the camera.
For example, if the sampling frequency of the camera is 25 frames/second, the video frame sequence value corresponding to the first pedestrian entering the store is 1, and the video frame sequence value corresponding to the first pedestrian leaving the store is 251, then the residence time of the pedestrian in the store is 10 seconds, and the residence times of all pedestrians are calculated and summed up, so that the attention of the pedestrian in the physical store to the physical store in the evaluation period can be calculated.
It should be noted that the evaluation period in the embodiment of the present invention may be a state in which all the pedestrians entering the store have already exited the store, so that the number of the pedestrians entering the store is the same as the number of the pedestrians exiting the store, and the residence time of each pedestrian entering the store in the store can be accurately counted.
In another embodiment of the present invention, the specific implementation manner of the step "determining the attention of the pedestrian to the brick-and-mortar store outside the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture" may be:
(1) and determining the attention angle of the pedestrian outside the physical store to the physical store according to the included angle between the straight line of the key points of the left shoulder and the right shoulder of the pedestrian in the pedestrian gesture and the in-out store judgment reference line and the advancing track.
As shown in fig. 3, for each pedestrian outside the brick-and-mortar store, two included angles (an acute angle and an obtuse angle) between a straight line where key points of left and right shoulders of the pedestrian are located and a store-entering judgment reference line can be obtained, and then the included angle related to the brick-and-mortar store concerned by the pedestrian is determined by combining the travel track of the pedestrian. For example, the left pedestrian in the figure defines an included angle θjlThe right pedestrian defines an included angle thetajr。
(2) And for the same pedestrian, determining the attention time of the pedestrian to the physical store in the traveling direction according to the video frame number corresponding to the pedestrian in the traveling direction, the attention angle determined by the pedestrian corresponding to each video frame in the traveling direction and the sampling frequency of the camera.
The angle of the pedestrian paying attention to the physical store may be different from one frame to another, so that the attention time of the pedestrian to the physical store needs to be calculated according to the attention angle and the sampling frequency of the pedestrian to each frame. In one embodiment, the cosine of the attention angle of each frame can be summed, and then the attention time of the pedestrian to the brick-and-mortar store can be calculated by combining the sampling frequency.
(3) And respectively calculating the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the leftward traveling direction and the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the rightward traveling direction, and determining the sum of the attention time in the leftward traveling direction and the attention time in the rightward traveling direction as the attention degree of the pedestrians to the physical store outside the physical store.
In one embodiment, the attention f of the pedestrian to the physical store outside the physical store can be calculated according to the following formulaoutdoor：
Wherein il represents the ith pedestrian traveling leftwards, jl represents the video frame sequence value corresponding to the ith pedestrian traveling leftwards in the leftward traveling direction, ir represents the ith pedestrian traveling rightwards, jr represents the video frame sequence value corresponding to the ith pedestrian traveling rightwards in the rightward traveling direction, p represents the sampling frequency of the camera, and theta represents the attention angle of the pedestrian to the physical store outside the physical store;
il is 0 or more and nl is less than or equal to, nl represents the number of pedestrians in the left traveling direction;
0 ≦ ir ≦ nr, nr representing the number of pedestrians in the rightward traveling direction;
0≤jl≤mli，mlia video frame number indicating the i-th pedestrian traveling to the left in the leftward traveling direction;
0≤jr≤mri，mriindicating the number of video frames in the rightward traveling direction of the i-th pedestrian traveling rightward.
It is necessary to supplement that, when a certain pedestrian walks on the left-right traveling judgment reference line all the time, the video frames corresponding to the pedestrian can be randomly divided into a certain traveling direction for calculation, so as to avoid repeated calculation.
In another embodiment of the present invention, for a brick-and-mortar store including an interior space, there is a large error between the in-store attention (i.e., the attention of a pedestrian to the brick-and-mortar store in the brick-and-mortar store) and the actual attention of the brick-and-mortar store, where the in-store attention is only taken as the attention of the brick-and-mortar store, or the in-store attention and the out-of-store attention (i.e., the attention of a pedestrian to the brick-and-mortar store outside the brick-and-mortar store) are directly added as the attention of the brick-and-mortar store. In order to further improve the accuracy of the evaluation of the attention of the physical store, the weights of the in-store attention degree and the out-of-store attention degree are determined according to the importance degrees of the in-store and out-of-store attention physical stores, and then the two attention degrees are weighted, so that the attention degree with higher accuracy is finally obtained.
The total attention can be calculated using the following formula: f ═ α findoor+(1-α)foutdoorWherein f isindoorIndicating in-store attention, foutdoorThe method may include determining corresponding weights for different types of brick and mortar stores in association, and when the interest needs to be evaluated for a certain brick and mortar store, determining the type of the brick and mortar store first, and then searching for the weight corresponding to the type to calculate the interest.
Corresponding to the foregoing method embodiment, an embodiment of the present invention provides an apparatus for determining offline attention, where as shown in fig. 4, the apparatus may include:
a recognition tracking unit 21 for recognizing a pedestrian posture in the pedestrian image and tracking a traveling locus of the pedestrian;
a first determination unit 22, configured to determine a traveling direction of the pedestrian relative to the brick-and-mortar store according to the traveling track;
a second determination unit 23 for identifying pedestrians according to a preset pedestrian recognition technology, and determining the number of pedestrians in the traveling direction;
the apparatus further comprises a third determining unit 24 and/or a fourth determining unit 25;
the third determining unit 24 is configured to determine a degree of attention of a pedestrian to the brick-and-mortar store within the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and a video frame sequence value corresponding to the pedestrian in the traveling direction;
the fourth determination unit 25 is configured to determine the attention of the pedestrian to the brick-and-mortar store outside the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture.
In another embodiment of the present invention, the first determining unit 22 includes:
a first traveling direction determining module, configured to determine, when the traveling direction includes a store entering direction and a store exiting direction, whether the traveling direction of the pedestrian relative to the brick-and-mortar store is the store entering direction or the store exiting direction according to the traveling track and the store entering and exiting determination reference line;
and a second travel direction determination module, configured to determine, when the travel directions include left travel and right travel of the pedestrian outside the brick-and-mortar store, whether the pedestrian travels left or right outside the brick-and-mortar store according to the travel trajectory and the left-and-right travel determination reference line.
In another embodiment of the present invention, the second determining unit 23 includes:
the calculation module is used for calculating the residence time of the pedestrian in the physical store according to the video frame sequence value corresponding to the pedestrian entering the store, the video frame sequence value corresponding to the pedestrian exiting the store and the sampling frequency of the camera for the same pedestrian when the travelling direction comprises a store entering direction and a store exiting direction;
and the first attention degree determining module is used for determining the sum of residence time of all pedestrians corresponding to the number of the pedestrians in the physical store as the attention degree of the pedestrians to the physical store in the physical store.
In another embodiment of the present invention, the third determining unit 24 includes:
the attention angle determining module is used for determining an attention angle of the pedestrian to the physical store outside the physical store according to an included angle between a straight line where key points of left and right shoulders of the pedestrian are located in the pedestrian gesture and an in-out judgment reference line and the travel track when the travel direction comprises left travel and right travel of the pedestrian outside the physical store;
the attention time determining module is used for determining attention time of the pedestrian to the physical store in the advancing direction according to the number of video frames corresponding to the pedestrian in the advancing direction, the attention angle determined by each video frame corresponding to the pedestrian in the advancing direction and the sampling frequency of a camera for the same pedestrian;
and the second attention determining module is used for respectively calculating the sum of the attention time of all pedestrians corresponding to the number of pedestrians in the left traveling direction to the physical store and the sum of the attention time of all pedestrians corresponding to the number of pedestrians in the right traveling direction to the physical store, and determining the sum of the attention time in the left traveling direction and the attention time in the right traveling direction as the attention of the pedestrians to the physical store outside the physical store.
In another embodiment of the present invention, the third determining unit 24 is configured to calculate the attention f of the pedestrian to the brick-and-mortar store outside the brick-and-mortar store according to the following formulaoutdoor：
Wherein il represents the ith pedestrian traveling leftwards, jl represents the video frame sequence value corresponding to the ith pedestrian traveling leftwards in the leftward traveling direction, ir represents the ith pedestrian traveling rightwards, and jr represents the video frame sequence value corresponding to the ith pedestrian traveling rightwards in the rightward traveling direction; theta represents the attention angle of the pedestrian to the physical store outside the physical store;
il is 0 or more and nl is less than or equal to, nl represents the number of pedestrians in the left traveling direction;
0 ≦ ir ≦ nr, nr representing the number of pedestrians in the rightward traveling direction;
0≤jl≤mli，mlia video frame number indicating the i-th pedestrian traveling to the left in the leftward traveling direction;
0≤jr≤mri，mriindicating the number of video frames in the rightward traveling direction of the i-th pedestrian traveling rightward.
In another embodiment of the present invention, the second determining unit 22 is configured to, when the traveling direction includes an entering direction and an exiting direction, match the entering pedestrian and the exiting pedestrian according to a preset pedestrian re-recognition model, and determine the number of pedestrians in the entering direction or the exiting direction; when the traveling direction comprises left traveling and right traveling of the pedestrian outside the physical store, tracking the pedestrian according to a preset tracking algorithm, and determining the quantity of the pedestrians traveling left and right outside the physical store.
In another embodiment of the present invention, the apparatus further comprises:
and the weighting unit is used for weighting the attention degree of the pedestrian to the physical store in the physical store and the attention degree of the pedestrian to the physical store outside the physical store to obtain the total attention degree of the pedestrian to the physical store.
Based on the above method embodiments, another embodiment of the present invention provides a storage medium having stored thereon executable instructions, which when executed by a processor, cause the processor to implement the method as described above.
Based on the foregoing method embodiment, another embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as described above.
The system and apparatus embodiments correspond to the method embodiments, and have the same technical effects as the method embodiments, and for the specific description, refer to the method embodiments. The device embodiment is obtained based on the method embodiment, and for specific description, reference may be made to the method embodiment section, which is not described herein again. Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for determining offline attention, the method comprising:
recognizing the pedestrian posture in the pedestrian image and tracking the travel track of the pedestrian;
determining the traveling direction of the pedestrian relative to the physical store according to the traveling track;
identifying pedestrians according to a preset pedestrian identification technology, and determining the number of the pedestrians in the advancing direction;
determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction;
and/or determining the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the pedestrian posture.
2. The method of claim 1, wherein determining a direction of travel of the pedestrian relative to the brick-and-mortar store from the travel trajectory comprises:
if the advancing direction comprises a store entering direction and a store exiting direction, determining whether the advancing direction of the pedestrian relative to the physical store is the store entering direction or the store exiting direction according to the advancing track and the store entering and exiting judgment reference line;
and if the traveling direction comprises the left traveling and the right traveling of the pedestrian outside the physical store, determining whether the pedestrian travels left or right outside the physical store according to the traveling track and the left and right traveling judgment reference line.
3. The method according to claim 1, wherein if the traveling direction includes an entering direction and an exiting direction, determining the attention degree of the pedestrian to the brick-and-mortar store in the brick-and-mortar store according to the traveling direction, the number of pedestrians in the traveling direction, and the corresponding video frame sequence value of the pedestrian in the traveling direction comprises:
aiming at the same pedestrian, calculating the residence time of the pedestrian in the entity store according to the video frame sequence value corresponding to the pedestrian when entering the store, the video frame sequence value corresponding to the pedestrian when leaving the store and the sampling frequency of a camera;
and determining the sum of residence time of all pedestrians corresponding to the number of the pedestrians in the physical store as the attention degree of the pedestrians to the physical store in the physical store.
4. The method of claim 1, wherein determining a pedestrian's interest level outside the brick-and-mortar store for the brick-and-mortar store based on the travel direction, the number of pedestrians in the travel direction, and the pedestrian gesture if the travel direction includes left and right travel of a pedestrian outside the brick-and-mortar store comprises:
determining an attention angle of the pedestrian outside the physical store to the physical store according to an included angle between a straight line where key points of left and right shoulders of the pedestrian are located in the pedestrian posture and a store entering and exiting judgment reference line and the advancing track;
for the same pedestrian, determining the attention time of the pedestrian to the physical store in the advancing direction according to the video frame number corresponding to the pedestrian in the advancing direction, the attention angle determined by the pedestrian in each video frame corresponding to the advancing direction, and the sampling frequency of a camera;
respectively calculating the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the left travelling direction and the sum of the attention time of all pedestrians to the physical store corresponding to the number of pedestrians in the right travelling direction, and determining the sum of the attention time in the left travelling direction and the attention time in the right travelling direction as the attention degree of the pedestrians to the physical store outside the physical store.
5. The method of claim 4, wherein determining a pedestrian's interest level outside the brick-and-mortar store for the brick-and-mortar store based on the travel direction, the number of pedestrians in the travel direction, and the pedestrian pose comprises:
calculating the attention f of the pedestrian to the physical store outside the physical store according to the following formulaoutdoor：
Wherein il represents the ith pedestrian traveling leftwards, jl represents the video frame sequence value corresponding to the ith pedestrian traveling leftwards in the leftward traveling direction, ir represents the ith pedestrian traveling rightwards, jr represents the video frame sequence value corresponding to the ith pedestrian traveling rightwards in the rightward traveling direction, p represents the sampling frequency of the camera, and theta represents the attention angle of the pedestrian to the physical store outside the physical store;
il is 0 or more and nl is less than or equal to, nl represents the number of pedestrians in the left traveling direction;
0 ≦ ir ≦ nr, nr representing the number of pedestrians in the rightward traveling direction;
0≤jl≤mli，mlia video frame number indicating the i-th pedestrian traveling to the left in the leftward traveling direction;
0≤jr≤mri，mriindicating the number of video frames in the rightward traveling direction of the i-th pedestrian traveling rightward.
6. The method of claim 1, wherein identifying pedestrians according to a preset pedestrian identification technique, determining the number of pedestrians in the direction of travel, comprises:
if the traveling direction comprises a store entering direction and a store exiting direction, matching store entering pedestrians and store exiting pedestrians according to a preset pedestrian re-identification model, and determining the number of the pedestrians in the store entering direction or the store exiting direction;
if the advancing direction comprises leftward advancing and rightward advancing of the pedestrian outside the physical store, tracking the pedestrian according to a preset tracking algorithm, and determining the quantity of the pedestrians advancing leftward and rightward outside the physical store.
7. The method of any one of claims 1-6, further comprising:
and weighting the attention of the pedestrian to the physical store in the physical store and the attention of the pedestrian to the physical store outside the physical store to obtain the total attention of the pedestrian to the physical store.
8. An offline attention determination device, comprising:
the recognition and tracking unit is used for recognizing the pedestrian posture in the pedestrian image and tracking the travel track of the pedestrian;
the first determining unit is used for determining the traveling direction of the pedestrian relative to the physical store according to the traveling track;
a second determination unit for identifying pedestrians according to a preset pedestrian identification technology and determining the number of pedestrians in the traveling direction;
the device further comprises a third determining unit and/or a fourth determining unit;
the third determining unit is used for determining the attention degree of the pedestrian to the physical store in the physical store according to the traveling direction, the number of pedestrians in the traveling direction and the corresponding video frame sequence value of the pedestrian in the traveling direction;
the fourth determination unit is configured to determine the attention of the pedestrian to the physical store outside the physical store according to the traveling direction, the number of pedestrians in the traveling direction, and the pedestrian posture.
9. A storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 7.
10. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110764670.0A CN113506132B (en) | 2021-07-06 | 2021-07-06 | Method and device for determining offline attention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110764670.0A CN113506132B (en) | 2021-07-06 | 2021-07-06 | Method and device for determining offline attention |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113506132A true CN113506132A (en) | 2021-10-15 |
| CN113506132B CN113506132B (en) | 2023-08-01 |
Family
ID=78011820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110764670.0A Active CN113506132B (en) | 2021-07-06 | 2021-07-06 | Method and device for determining offline attention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506132B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006133915A (en) * | 2004-11-02 | 2006-05-25 | National Institute Of Advanced Industrial & Technology | User interest analysis system, user interest analysis method, user interest analysis program, and recording medium therefor |
| JP2007181071A (en) * | 2005-12-28 | 2007-07-12 | Shunkosha:Kk | Apparatus and method for evaluating attention paid to contents |
| JP2009116510A (en) * | 2007-11-05 | 2009-05-28 | Fujitsu Ltd | Attention degree calculation device, attention degree calculation method, attention degree calculation program, information providing system and information providing device |
| JP2011233120A (en) * | 2010-04-30 | 2011-11-17 | Nippon Telegr & Teleph Corp <Ntt> | Advertising effectiveness indicator measuring apparatus, method of advertising effectiveness indicator measuring and program |
| JP2012168632A (en) * | 2011-02-10 | 2012-09-06 | Advanced Telecommunication Research Institute International | Pedestrian state classification device and program |
| US20180024631A1 (en) * | 2016-07-21 | 2018-01-25 | Aivia, Inc. | Interactive Display System with Eye Tracking to Display Content According to Subject's Interest |
| CN107679899A (en) * | 2017-09-26 | 2018-02-09 | 北京智云联众科技有限公司 | The content put-on method and device of a kind of advertisement screen |
| CN108230102A (en) * | 2017-12-29 | 2018-06-29 | 深圳正品创想科技有限公司 | A kind of commodity attention rate method of adjustment and device |
| CN109002778A (en) * | 2018-06-29 | 2018-12-14 | 上海小蚁科技有限公司 | Concern amount determines method and device, storage medium, terminal |
| CN109087133A (en) * | 2018-07-24 | 2018-12-25 | 广东金熙商业建设股份有限公司 | A kind of behavior guidance analysis system and its working method based on context aware |
| CN109448026A (en) * | 2018-11-16 | 2019-03-08 | 南京甄视智能科技有限公司 | Passenger flow statistical method and system based on head and shoulder detection |
| CN208689391U (en) * | 2018-07-23 | 2019-04-02 | 上海沛宇信息科技有限公司 | In conjunction with the commodity attention rate sensing system of electronics price tag |
| CN110309710A (en) * | 2019-05-20 | 2019-10-08 | 特斯联（北京）科技有限公司 | Content based on recognition of face pays close attention to big data processing method, apparatus and system |
| CN110399835A (en) * | 2019-07-26 | 2019-11-01 | 北京文安智能技术股份有限公司 | A kind of analysis method of personnel's residence time, apparatus and system |
| CN111353461A (en) * | 2020-03-11 | 2020-06-30 | 京东数字科技控股有限公司 | Method, device and system for detecting attention of advertising screen and storage medium |
| CN111401382A (en) * | 2019-12-04 | 2020-07-10 | 浙江凯耀照明有限责任公司 | Method for automatically detecting camera range and desk lamp using same |
| JP2020150519A (en) * | 2019-03-15 | 2020-09-17 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | Attention degree calculating device, attention degree calculating method and attention degree calculating program |
| CN111951058A (en) * | 2020-08-24 | 2020-11-17 | 珠海格力电器股份有限公司 | Commodity attention analysis method, device and system based on electronic price tags |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
-
2021
- 2021-07-06 CN CN202110764670.0A patent/CN113506132B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006133915A (en) * | 2004-11-02 | 2006-05-25 | National Institute Of Advanced Industrial & Technology | User interest analysis system, user interest analysis method, user interest analysis program, and recording medium therefor |
| JP2007181071A (en) * | 2005-12-28 | 2007-07-12 | Shunkosha:Kk | Apparatus and method for evaluating attention paid to contents |
| JP2009116510A (en) * | 2007-11-05 | 2009-05-28 | Fujitsu Ltd | Attention degree calculation device, attention degree calculation method, attention degree calculation program, information providing system and information providing device |
| JP2011233120A (en) * | 2010-04-30 | 2011-11-17 | Nippon Telegr & Teleph Corp <Ntt> | Advertising effectiveness indicator measuring apparatus, method of advertising effectiveness indicator measuring and program |
| JP2012168632A (en) * | 2011-02-10 | 2012-09-06 | Advanced Telecommunication Research Institute International | Pedestrian state classification device and program |
| US20180024631A1 (en) * | 2016-07-21 | 2018-01-25 | Aivia, Inc. | Interactive Display System with Eye Tracking to Display Content According to Subject's Interest |
| CN107679899A (en) * | 2017-09-26 | 2018-02-09 | 北京智云联众科技有限公司 | The content put-on method and device of a kind of advertisement screen |
| CN108230102A (en) * | 2017-12-29 | 2018-06-29 | 深圳正品创想科技有限公司 | A kind of commodity attention rate method of adjustment and device |
| CN109002778A (en) * | 2018-06-29 | 2018-12-14 | 上海小蚁科技有限公司 | Concern amount determines method and device, storage medium, terminal |
| CN208689391U (en) * | 2018-07-23 | 2019-04-02 | 上海沛宇信息科技有限公司 | In conjunction with the commodity attention rate sensing system of electronics price tag |
| CN109087133A (en) * | 2018-07-24 | 2018-12-25 | 广东金熙商业建设股份有限公司 | A kind of behavior guidance analysis system and its working method based on context aware |
| CN109448026A (en) * | 2018-11-16 | 2019-03-08 | 南京甄视智能科技有限公司 | Passenger flow statistical method and system based on head and shoulder detection |
| JP2020150519A (en) * | 2019-03-15 | 2020-09-17 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | Attention degree calculating device, attention degree calculating method and attention degree calculating program |
| CN110309710A (en) * | 2019-05-20 | 2019-10-08 | 特斯联（北京）科技有限公司 | Content based on recognition of face pays close attention to big data processing method, apparatus and system |
| CN110399835A (en) * | 2019-07-26 | 2019-11-01 | 北京文安智能技术股份有限公司 | A kind of analysis method of personnel's residence time, apparatus and system |
| CN111401382A (en) * | 2019-12-04 | 2020-07-10 | 浙江凯耀照明有限责任公司 | Method for automatically detecting camera range and desk lamp using same |
| CN111353461A (en) * | 2020-03-11 | 2020-06-30 | 京东数字科技控股有限公司 | Method, device and system for detecting attention of advertising screen and storage medium |
| CN111951058A (en) * | 2020-08-24 | 2020-11-17 | 珠海格力电器股份有限公司 | Commodity attention analysis method, device and system based on electronic price tags |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 何金枝;梁丽莎;侯科宇;徐威;周晋;: "线下鞋类门店产品关注度数据采集系统的设计及实证研究", 皮革科学与工程, no. 01, pages 73 - 76 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113506132B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luber et al. | People tracking in rgb-d data with on-line boosted target models | |
| Ge et al. | Vision-based analysis of small groups in pedestrian crowds | |
| US7450735B1 (en) | Tracking across multiple cameras with disjoint views | |
| US8098888B1 (en) | Method and system for automatic analysis of the trip of people in a retail space using multiple cameras | |
| Treptow et al. | Real-time people tracking for mobile robots using thermal vision | |
| CN111860282A (en) | Subway section passenger flow volume statistics and pedestrian retrograde motion detection method and system | |
| US20090319560A1 (en) | System and method for multi-agent event detection and recognition | |
| US20090231436A1 (en) | Method and apparatus for tracking with identification | |
| Simonnet et al. | Re-identification of pedestrians in crowds using dynamic time warping | |
| Treptow et al. | Active people recognition using thermal and grey images on a mobile security robot | |
| CN103310190A (en) | Facial image sample acquiring and optimizing method based on heterogeneous active vision network | |
| CN110874583A (en) | Passenger flow statistics method and device, storage medium and electronic equipment | |
| CN110399835B (en) | Analysis method, device and system for personnel residence time | |
| US9977970B2 (en) | Method and system for detecting the occurrence of an interaction event via trajectory-based analysis | |
| Prokaj et al. | Tracking many vehicles in wide area aerial surveillance | |
| Bertoni et al. | Perceiving humans: from monocular 3d localization to social distancing | |
| Choi et al. | New preceding vehicle tracking algorithm based on optimal unbiased finite memory filter | |
| CN113326719A (en) | Method, equipment and system for target tracking | |
| CN111311766A (en) | Roadside parking intelligent charging system and method based on license plate recognition and tracking technology | |
| Cielniak et al. | Data association and occlusion handling for vision-based people tracking by mobile robots | |
| CN115546705B (en) | Target identification method, terminal device and storage medium | |
| Guan et al. | Multi-person tracking-by-detection with local particle filtering and global occlusion handling | |
| EP2259221A1 (en) | Computer system and method for tracking objects in video data | |
| Mittal et al. | Pedestrian detection and tracking using deformable part models and Kalman filtering | |
| Wei et al. | Subject centric group feature for person re-identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |