CN111401305A - 4S store customer statistical method and device and electronic equipment - Google Patents
4S store customer statistical method and device and electronic equipment Download PDFInfo
- Publication number
- CN111401305A CN111401305A CN202010269319.XA CN202010269319A CN111401305A CN 111401305 A CN111401305 A CN 111401305A CN 202010269319 A CN202010269319 A CN 202010269319A CN 111401305 A CN111401305 A CN 111401305A
- Authority
- CN
- China
- Prior art keywords
- customer
- image
- store
- identified
- customers
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a 4S store customer statistical method, a device and electronic equipment, wherein the method comprises the following steps: acquiring an in-store image of a 4S store, performing pedestrian detection on the in-store image by utilizing an OpenPose algorithm to obtain a pedestrian detection result, extracting body joint points and bone point trend information of a customer in the in-store image when the customer is determined to be in the in-store image based on the pedestrian detection result, and connecting the body joint points of the customer according to the body joint points and bone point trend information of the customer to obtain a bone frame of the customer; processing the skeleton frame of the customer to obtain a posture graph of the customer; and counting the passenger flow data in the 4S shop based on the posture graph of the customer in the in-shop image. By the 4S store customer statistical method and device and the electronic equipment, the identification rate of customers in the store is improved, and the accuracy of the statistical passenger flow data is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a 4S store customer statistical method and device, electronic equipment and a computer-readable storage medium.
Background
At present, an Automobile Sales Service 4S shop (automatic Sales Service 4S) is an Automobile Sales enterprise integrating vehicle Sales (Sale), spare and accessory (spare), after-Sales Service (Service), and information feedback (Survey). The 4S store typically provides services such as purchasing new cars and maintaining the cars. Different vehicle brands can have different target client groups, and in order to determine target clients which accord with the sold vehicles from the group of people who enter the 4S store, the 4S store needs to count the clients who enter the store.
In order to count the customers entering the store, the 4S store may install a plurality of cameras in the store, collect images in the store, process the collected images in the store through a face recognition algorithm to recognize the customer face images in the store, and count the customers entering the store through the recognized customer face images.
However, due to lighting conditions in the store, the shooting angle when people face is shot, different makeup looks of customers when people come at different times, and the fact that some customers go to the 4S store and are always in a low head, the face images of the customers in the store shot by the camera are unclear, and the unclear face images of the customers cannot be used for identifying and counting the number of the customers.
Disclosure of Invention
In order to solve the existing technical problem, embodiments of the present invention provide a method and an apparatus for 4S store customer statistics, an electronic device, and a computer-readable storage medium.
In a first aspect, an embodiment of the present invention provides a 4S store customer statistics method, including:
acquiring an in-store image of a 4S store, performing pedestrian detection on the in-store image by utilizing an OpenPose algorithm, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
processing the skeleton frame of the customer to obtain a posture graph of the customer;
and counting the passenger flow data in the 4S shop based on the posture graph of the customer in the in-shop image.
In a second aspect, an embodiment of the present invention provides a 4S store customer statistics apparatus, including:
the system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for acquiring an in-store image in a 4S store, utilizing an OpenPose algorithm to detect pedestrians in the in-store image, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
the second processing module is used for processing the skeleton frame of the customer to obtain a posture graph of the customer;
and the counting module is used for counting the passenger flow data in the 4S shop based on the attitude map of the customer in the in-shop image.
In a third aspect, an embodiment of the present invention provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the steps in the method for 4S-shop customer statistics according to the first aspect are implemented.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the 4S store customer statistics method according to any one of claims 1 to 4.
In the solutions provided in the first to fourth aspects of the embodiments of the present invention, an openpos algorithm is used to perform pedestrian detection on the in-store image to obtain a skeleton frame of a customer in the in-store image, and the skeleton frame of the customer is processed to obtain a posture diagram of the customer, and statistics is performed on the passenger flow data in the 4S store based on the posture diagram of the customer in the in-store image; compared with a mode of counting the customer flow entering the store by adopting a face recognition technology in the related technology, the method can obtain the attitude map of the customer based on the OpenPose algorithm even if the obtained face image of the customer is unclear, so that the customer flow data in the 4S store can be counted by the attitude map of the customer, the conditions required by the customer flow counting are reduced, the recognition rate of the customer in the store is greatly improved, and the accuracy of the counted customer flow data is increased.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the background art of the present invention, the drawings required to be used in the embodiments or the background art of the present invention will be described below.
Fig. 1 is a flowchart illustrating a customer statistics method for a 4S store according to embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram illustrating a 4S store customer statistics apparatus according to embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for performing a 4S store customer statistics method according to an embodiment of the present invention.
Detailed Description
For clarity and conciseness of description of embodiments of the present invention, a brief introduction to the relevant concepts or technologies is first given:
the OpenPose algorithm, namely a real-time multi-person 2D posture estimation algorithm, is an open source library developed based on a convolutional neural network and supervised learning and taking caffe as a framework. Gesture recognition such as human body action, facial expression, finger motion can be realized.
The gait sequence-based cross visual angle gait recognition algorithm (GaitSet) is used for recognizing pedestrians according to a plurality of continuous pedestrian gait images.
Currently, an automobile sales Service 4S store is an automobile sales enterprise integrating vehicle sales (Sale), spare parts (spare), after-sales Service (Service), and information feedback (Survey). The 4S store typically provides services such as purchasing new cars and maintaining the cars. Different vehicle brands can have different target client groups, and in order to determine target clients which accord with the sold vehicles from the group of people who enter the 4S store, the 4S store needs to count the clients who enter the store.
In order to count the customers entering the store, the 4S store may install a plurality of cameras in the store, collect images in the store, process the collected images in the store through a face recognition algorithm to recognize the customer face images in the store, and count the customers entering the store through the recognized customer face images.
However, due to lighting conditions in the store, the shooting angle when people face is shot, different makeup looks of customers when people come at different times, and the fact that some customers go to the 4S store and are always in a low head, the face images of the customers in the store shot by the camera are unclear, and the unclear face images of the customers cannot be used for identifying and counting the number of the customers.
Based on this, the present embodiment provides a 4S shop customer statistical method, an apparatus, an electronic device, and a computer-readable storage medium, where the openpos algorithm is used to perform pedestrian detection on the in-shop image to obtain a skeleton frame of a customer in the in-shop image, and process the skeleton frame of the customer to obtain a posture diagram of the customer, and perform statistics on the passenger flow data in the 4S shop based on the posture diagram of the customer in the in-shop image; the conditions required by customer flow statistics are reduced, the recognition rate of customers in the store is greatly improved, and the accuracy of the passenger flow data obtained through statistics is increased.
Those skilled in the art will appreciate that embodiments of the present invention can be implemented as a 4S store customer statistics method, apparatus, electronic device, and computer-readable storage medium. Thus, embodiments of the invention may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, embodiments of the invention may also be embodied in the form of a computer program product in one or more computer-readable storage media having computer program code embodied in the medium.
The computer-readable storage media described above may take any combination of one or more computer-readable storage media. The computer-readable storage medium includes: an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium include: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only Memory (ROM), an erasable programmable read-only Memory (EPROM), a Flash Memory, an optical fiber, a compact disc read-only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any combination thereof. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device, or apparatus.
The computer program code embodied on the computer readable storage medium may be transmitted using any appropriate medium, including: wireless, wire, fiber optic cable, Radio Frequency (RF), or any suitable combination thereof.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the C language or similar programming languages.
Embodiments of the present invention are described below with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices, and computer-readable storage media according to embodiments of the invention.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner. Thus, the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The embodiments of the present invention will be described below with reference to the drawings.
Example 1
The embodiment provides a 4S store customer statistical method, and an execution subject is a server.
The server may adopt any computing device capable of implementing the 4S store customer statistical method by using the openpos algorithm in the prior art, and details are not repeated here.
Here, in order to realize the 4S store customer statistics by using the OpenPose algorithm, the OpenPose algorithm needs to be trained before the OpenPose algorithm is used, in the OpenPose algorithm training process, triple joint loss may be calculated by using feature values corresponding to different samples, a large number of pedestrian walking posture pictures are input for training, network parameters are optimized, and finally, the OpenPose algorithm model that can be used in this embodiment is obtained.
Fig. 1 shows a flowchart of a customer statistics method for a 4S store according to an embodiment of the present invention. As shown in fig. 1, the method comprises the following specific steps:
In step 100, the in-store image is captured by an image capturing device installed in a 4S store.
The in-store image is an image for showing each area in the 4S store.
The process of utilizing the OpenPose algorithm to detect the pedestrians of the images in the store and extracting the body joint point information and the bone point trend information of the customer in the images in the store is realized by the pedestrian detection function of the OpenPose algorithm, and is not repeated here.
After the fact that the customer exists in the in-store image is determined, the OpenPose algorithm uses a convolutional neural network to respectively extract body joint points and bone point trend information of the customer in the in-store image, and the body joint points of the customer are connected according to the body joint points and the bone point trend information of the customer to obtain a bone frame of the customer. The specific process is realized by the pedestrian gesture recognition function of the openpos algorithm, and is not described herein again.
Here, the body joint point includes: joint points of 6 arms, joint points of 2 trunks, joint points of 5 heads, joint points of 6 legs and joint points of 6 feet.
And the skeleton point trend information is used for indicating the positions of the body joint points and the connection relation among the body joint points.
When the obtained skeleton frame of the customer is incomplete, the openpos algorithm still connects the joint points which are already identified to obtain a relatively complete skeleton frame.
And 102, processing the skeleton frame of the customer to obtain a posture graph of the customer.
In the related art, after the skeleton frame of the customer is obtained from the in-store image by using the openpos algorithm, the walking posture of the customer is detected by continuously using the skeleton frame of the customer, but some customers are far away from the camera, so that the image of the customer in the in-store image shot by the camera is small, and the skeleton frame of the customer obtained after the processing by using the openpos algorithm is small; if the smaller skeleton frame of the customer is processed in the subsequent walking posture identification process, the walking posture of the customer may not be accurately determined. Then, in order to accurately determine the walking posture of the customer, the above step 102 may perform the following steps (1) to (2):
(1) when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
(2) and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
In the step (1), when the pixel value of the skeleton frame of the customer is smaller than the pixel threshold, it is described that the obtained skeleton frame of the customer is relatively fine and needs to be thickened.
The server may use any drawing technique to perform the thickening process on the skeleton frame of the customer, which is not described herein. In the step (2), the GaitSet algorithm is used to perform gait recognition processing on the skeleton frame of the customer after the thickening processing, and the process of obtaining the posture diagram of the customer is the prior art and is not described herein again.
The attitude map of the customer can be, but is not limited to: an image of a standing, sitting, or walking position of the customer in a 4S store.
As can be seen from the above contents of steps (1) to (2), before the posture recognition is performed, the skeleton frame of the customer whose pixel value is smaller than the pixel threshold is thickened, so as to obtain the skeleton frame of the customer whose thickness is appropriate, and the skeleton frame of the customer whose thickness is appropriate is processed in the subsequent walking posture recognition process.
After the posture diagram of the customer is obtained in step 102, the following step 104 may be continuously executed to count the passenger flow data in the 4S store based on the posture diagram of the customer in the in-store image.
And 104, counting the passenger flow data in the 4S shop based on the attitude map of the customer in the in-shop image.
In the related art, the customer is identified by directly using the attitude map of the customer, but since the image area of the in-store image in which the attitude map of the customer is located is colored in addition to the attitude map of the customer, the color of the attitude map of the customer in the in-store image and the color of the image area around the customer may be close to each other, so that when the server identifies the customer, the attitude map of the customer in the in-store image and the image area around the attitude map are used as the attitude map of the customer to identify the customer, the posture of the customer cannot be correctly identified, the customer identification fails, and the problem of inaccurate passenger flow data statistics is caused. In order to avoid identifying the customer in the in-store image as the customer posture map together with the image area around the posture map, and improve the accuracy of identifying the customer by the customer posture, in the 4S store customer statistical method proposed in this embodiment, step 104 may specifically execute the following steps (1) to (4):
(1) filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
(2) when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
(3) processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
(4) and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
In the step (1), the server may adopt any existing drawing software, and fill the customer's posture diagram with the first color, and fill the image area in the in-store image except for the customer's posture diagram with the second color, which is not described herein again.
The neutral color comprises: white, grey and black.
In one embodiment, the first color is white and the second color is gray or black.
In another embodiment, the first color is gray or black and the second color is white.
In the step (2), the customer image database may be stored in a server for storing customer images of each of all customers who arrive at the store.
And the customer image is used for representing the images of various postures of the customers arriving at the store, which are acquired by the image acquisition equipment.
For any customer, at least one customer image of the customer is stored in the customer image database.
In order to conveniently query all customer images of the same customer from the customer image database, after the customer images are stored in the customer image database, the server can establish the corresponding relation between the customer identification and the storage address of the customer image in the customer image database. Therefore, all the customer images of the same customer are associated with the customer identifier of the customer by the corresponding relation between the customer identifier and the storage address of the customer image. Then all customer images of the same customer can be queried by the customer identification.
Specifically, in order to perform similarity determination between the customer image and the customer image to be recognized, the server may perform the following steps (21) to (23):
(21) acquiring a customer identifier from a corresponding relation between the customer identifier stored in a customer image database and a storage address of a customer image to form a customer identifier set;
(22) selecting any customer identifier from the customer identifier set, and reading the customer image of the customer corresponding to the customer identifier according to the storage address of the customer image corresponding to the selected customer identifier;
(23) and (3) deleting the selected customer identifier from the customer identifier set, and then turning to the step (3) to continue to execute the step of processing the acquired customer image and the to-be-identified customer image and determining the similarity between the to-be-identified customer image and the customer image.
After the step of the step (4) is executed, the following step (24) is continuously executed:
(24) judging whether the customer identification set has a customer identification, if so, determining that a customer image which is not subjected to similarity judgment with the customer image to be identified exists in a customer image database, and executing a step (22); if not, determining that all the customer images in the customer image database are subjected to similarity judgment with the customer image to be identified, and ending the process.
In the step (3), in order to process the customer image to be recognized and the customer image and determine the similarity between the customer image to be recognized and the customer image, the following steps (31) to (34) may be specifically performed:
(31) respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
(32) calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
(33) when the Euclidean distance is smaller than or equal to a distance threshold value, determining that the to-be-identified customer image is similar to the to-be-identified customer image, and obtaining a judgment result that the to-be-identified customer image is a customer image of a customer who has arrived at a store;
(34) when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
In the step (31), the server may use any existing image processing algorithm to respectively extract the first image feature of the customer image and the second image feature of the customer image to be identified, and a specific process is the prior art and is not described herein again.
In the step (32), a specific process of calculating the euclidean distance between the customer image and the customer image to be identified is the prior art, and is not described herein again.
In the step (33), after obtaining a determination result that the customer image to be recognized is a customer image of a customer who has arrived at the store, the server may obtain a customer identifier of the customer associated with the customer image to be recognized, store the customer image to be recognized in the customer image database as a customer image of the customer associated with the customer image to be recognized, obtain a storage address where the customer image is stored, form a correspondence relationship between the customer identifier and the storage address of the customer image based on the obtained customer identifier and the storage address where the customer image is stored, and store the formed correspondence relationship between the customer identifier and the storage address of the customer image in the customer image database.
And the distance threshold is cached in the server.
In the step (4), the passenger flow data in the 4S store is used to indicate the number of customers entering the 4S store in one statistical period.
One statistical period, which may be, but is not limited to, the following time period: one day, one week, and half a month.
And after the customer corresponding to the customer image to be identified is determined as a new customer, the server performs incremental operation on the passenger flow data in the 4S store to obtain updated passenger flow data in the 4S store.
In one embodiment, the incremental operation is an addition operation on the passenger flow data in the 4S store.
Further, after the customer corresponding to the customer image to be recognized is determined as a new customer of the store, the server generates a new customer identification, stores the customer image indicating the customer to be recognized as the newly generated customer identification in the customer image database, then obtains a storage address for storing the customer image, forms a corresponding relationship between the newly generated customer identification and the storage address of the customer image, and finally stores the formed corresponding relationship between the customer identification and the storage address of the customer image in the customer image database.
It can be seen from the above description that the identification of the customer in the 4S store by human body walking posture analysis has good fault tolerance, and the identification and judgment can be performed no matter where the customer looks or not back to the image acquisition equipment. However, the theoretical gait recognition algorithm has a great disadvantage that if the detected pedestrian wears overcoat, a backpack or the like, the postures of the two legs during walking cannot be recognized well, and great misjudgment occurs. The problem can be solved by using the method for recognizing the human body posture by using the OpenPose algorithm.
In summary, in the 4S shop customer statistical method proposed in this embodiment, the openpos algorithm is used to perform pedestrian detection on the in-shop image to obtain a skeleton frame of a customer in the in-shop image, and process the skeleton frame of the customer to obtain a posture diagram of the customer, and statistics is performed on the passenger flow data in the 4S shop based on the posture diagram of the customer in the in-shop image; compared with a mode of counting the customer flow entering the store by adopting a face recognition technology in the related technology, the method can obtain the attitude map of the customer based on the OpenPose algorithm even if the obtained face image of the customer is unclear, so that the customer flow data in the 4S store can be counted by the attitude map of the customer, the conditions required by the customer flow counting are reduced, the recognition rate of the customer in the store is greatly improved, and the accuracy of the counted customer flow data is increased.
Example 2
The present embodiment proposes a 4S store customer counting apparatus for executing the 4S store customer counting method proposed in embodiment 1 above.
Referring to a schematic structural diagram of a 4S customer statistic device shown in fig. 2, the present embodiment provides a 4S customer statistic device, including:
the system comprises a first processing module 200, a second processing module and a third processing module, wherein the first processing module is used for acquiring an in-store image in a 4S store, detecting pedestrians on the in-store image by using an OpenPose algorithm, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
a second processing module 202, configured to process a skeleton frame of the customer to obtain a posture diagram of the customer;
a statistics module 204, configured to perform statistics on the passenger flow data in the 4S store based on the posture diagram of the customer in the in-store image.
Specifically, the statistical module 204 is specifically configured to:
filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
Specifically, the statistical module is configured to process the customer image to be identified and the customer image, and determine a similarity between the customer image to be identified and the customer image, and includes:
respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
The second processing module is specifically configured to:
when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
In summary, the 4S shop customer statistics apparatus proposed in this embodiment performs pedestrian detection on the in-shop image by using the openpos algorithm to obtain a skeleton frame of a customer in the in-shop image, processes the skeleton frame of the customer to obtain a posture diagram of the customer, and performs statistics on the passenger flow data in the 4S shop based on the posture diagram of the customer in the in-shop image; compared with a mode of counting the customer flow entering the store by adopting a face recognition technology in the related technology, the method can obtain the attitude map of the customer based on the OpenPose algorithm even if the obtained face image of the customer is unclear, so that the customer flow data in the 4S store can be counted by the attitude map of the customer, the conditions required by the customer flow counting are reduced, the recognition rate of the customer in the store is greatly improved, and the accuracy of the counted customer flow data is increased.
Example 3
The embodiment of the present invention further provides an electronic device, which includes a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the processes of the embodiment of the 4S store customer statistics method are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition.
Specifically, referring to fig. 3, the embodiment of the present invention further provides an electronic device, which includes a bus 71, a processor 72, a transceiver 73, a bus interface 74, a memory 75, and a user interface 76.
In an embodiment of the present invention, the electronic device further includes: a computer program stored on the memory 75 and executable on the processor 72, the computer program when executed by the processor 72 performing the steps of:
acquiring an in-store image of a 4S store, performing pedestrian detection on the in-store image by utilizing an OpenPose algorithm, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
processing the skeleton frame of the customer to obtain a posture graph of the customer;
and counting the passenger flow data in the 4S shop based on the posture graph of the customer in the in-shop image.
Optionally, the computer program when executed by the processor 72 may further implement the steps of:
counting the 4S in-store passenger flow data based on the posture graph of the customer in the in-store image, including:
filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
The processing the customer image to be identified and the customer image to determine the similarity of the customer image to be identified and the customer image comprises the following steps:
respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
The processing the skeletal frame of the customer to obtain the posture graph of the customer comprises:
when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
A transceiver 73 for receiving and transmitting data under the control of the processor 72.
In FIG. 3, a bus architecture (represented by bus 71), bus 71 may include any number of interconnected buses and bridges, bus 71 connecting various circuits including one or more processors, represented by processor 72, and memory, represented by memory 75.
The Processor 72 may be an Integrated Circuit chip having Signal Processing capability, and in the implementation process, the steps of the above method embodiments may be implemented by an Integrated logic Circuit in hardware of the Processor or instructions in the form of software, and the above Processor may include a general purpose Processor, a Central Processing Unit (CPU), a Network Processor (NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Complex Programmable logic device (Complex Programmable CP L) analog device, a P L D), a Programmable logic Array (Programmable L analog Array, a P L a), a Microcontroller Unit (MCU) or other Programmable logic device, a discrete Gate, a transistor, a discrete component, or a single core Processor, or multiple core processors.
The processor 72 may be a microprocessor or any conventional processor. The steps of the method disclosed in connection with the embodiments of the present invention may be directly performed by a hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a Random Access Memory (RAM), a flash Memory (flash Memory), a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), a register, and other readable storage media known in the art. The readable storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The bus 71 may also connect various other circuits such as peripherals, voltage regulators, or power management circuits to one another, and a bus interface 74 provides an interface between the bus 71 and the transceiver 73, as is well known in the art. Therefore, the embodiments of the present invention will not be further described.
The transceiver 73 may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. For example: the transceiver 73 receives external data from other devices, and the transceiver 73 is used to transmit data processed by the processor 72 to other devices. Depending on the nature of the computer system, a user interface 76 may also be provided, such as: touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, stylus.
It should be understood that in embodiments of the present invention, memory 75 may further include memory remotely located from processor 72, which may be connected to a server via a network, one or more portions of which may be AN ad hoc network (ad hoc network), AN intranet (intranet), AN extranet (extranet), a Virtual Private Network (VPN), a local area network (L AN), a wireless local area network (W L AN), a Wide Area Network (WAN), a Wireless Wide Area Network (WWAN), a Metropolitan Area Network (MAN), the Internet (Internet), the Public Switched Telephone Network (PSTN), the plain old telephone service network (POTS), a cellular telephone network, a wireless fidelity (Wi-Fi) network, and combinations of two or more of the foregoing networks, for example, cellular telephone network and wireless network may be a Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA) system, Worldwide Interoperability for Microwave Access (WiMAX) system, General Packet Radio Service (GPRS) system, Wideband Code Division Multiple Access (WCDMA) system, Long term evolution (L TE) system, frequency division multiple Access (L TE) system, TE 64, UMTS enhanced Mobile Telecommunications (OTC) system, UMTS — extended Mobile Telecommunications (6778), UMTS — Broadband Telecommunications (RS) system, UMTS — extended Mobile Telecommunications, UMTS — Broadband Telecommunications, UMTS — Telecommunications (6778, etc.
It will be appreciated that memory 75 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Wherein the nonvolatile memory includes: read-only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), or Flash Memory.
By way of exemplary and not limiting illustration, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), Double Data rate Synchronous Dynamic Random Access Memory (Double Data Rate SDRAM, DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), Synchronous link Dynamic Random Access Memory (Synchlink DRAM, S L DRAM), and direct bus Random Access Memory (DirectRAM). The Memory 75 of the electronic device described in this embodiment of the invention includes, but is not limited to, the above and any other suitable types of Memory.
In an embodiment of the present invention, memory 75 stores the following elements of operating system 751 and application programs 752: an executable module, a data structure, or a subset thereof, or an expanded set thereof.
Specifically, the operating system 751 comprises various system programs, such as: a framework layer, a core library layer, a driver layer, etc. for implementing various basic services and processing hardware-based tasks. Applications 752 include various applications such as: media Player (Media Player), Browser (Browser), for implementing various application services. A program implementing the method of an embodiment of the present invention may be included in the application 752. The application programs 752 include: applets, objects, components, logic, data structures, and other computer system executable instructions that perform particular tasks or implement particular abstract data types.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements each process of the 4S store customer statistics method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
In particular, the computer program may, when executed by a processor, implement the steps of:
acquiring an in-store image of a 4S store, performing pedestrian detection on the in-store image by utilizing an OpenPose algorithm, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
processing the skeleton frame of the customer to obtain a posture graph of the customer;
and counting the passenger flow data in the 4S shop based on the posture graph of the customer in the in-shop image.
Optionally, the computer program when executed by the processor may further implement the steps of:
counting the 4S in-store passenger flow data based on the posture graph of the customer in the in-store image, including:
filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
Processing the customer image to be identified and the customer image, and determining the similarity between the customer image to be identified and the customer image, wherein the steps comprise:
respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
Processing the skeletal frame of the customer to obtain a posture diagram of the customer, comprising:
when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
The computer-readable storage medium includes: permanent and non-permanent, removable and non-removable media may be tangible devices that retain and store instructions for use by an instruction execution apparatus. The computer-readable storage medium includes: electronic memory devices, magnetic memory devices, optical memory devices, electromagnetic memory devices, semiconductor memory devices, and any suitable combination of the foregoing. The computer-readable storage medium includes: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), non-volatile random access memory (NVRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic tape cartridge storage, magnetic tape disk storage or other magnetic storage devices, memory sticks, mechanically encoded devices (e.g., punched cards or raised structures in a groove having instructions recorded thereon), or any other non-transmission medium useful for storing information that may be accessed by a computing device. As defined in embodiments of the present invention, the computer-readable storage medium does not include transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses traveling through a fiber optic cable), or electrical signals transmitted through a wire.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed in the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating the interchangeability of hardware and software. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer program instructions. The computer program instructions comprise: assembly instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as: smalltalk, C + + and procedural programming languages, such as: c or a similar programming language.
The computer program instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g., from one website, computer, server, or data center via wire (e.g., coaxial cable, twisted pair cable, fiber optics, digital subscriber line (DS L)) or wireless (e.g., infrared, wireless, microwave) to another website, computer, server, or data center.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing embodiments of the method of the present invention, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, electronic device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to solve the problem to be solved by the embodiment of the invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be substantially or partially contributed by the prior art, or all or part of the technical solutions may be embodied in a software product stored in a storage medium and including instructions for causing a computer device (including a personal computer, a server, a data center, or other network devices) to execute all or part of the steps of the methods of the embodiments of the present invention. And the storage medium includes various media that can store the program code as listed in the foregoing.
In summary, the electronic device and the computer-readable storage medium provided in this embodiment perform pedestrian detection on the in-store image by using an openpos algorithm to obtain a skeleton frame of a customer in the in-store image, process the skeleton frame of the customer to obtain a posture diagram of the customer, and perform statistics on the 4S in-store passenger flow data based on the posture diagram of the customer in the in-store image; compared with a mode of counting the customer flow entering the store by adopting a face recognition technology in the related technology, the method can obtain the attitude map of the customer based on the OpenPose algorithm even if the obtained face image of the customer is unclear, so that the customer flow data in the 4S store can be counted by the attitude map of the customer, the conditions required by the customer flow counting are reduced, the recognition rate of the customer in the store is greatly improved, and the accuracy of the counted customer flow data is increased.
The above description is only a specific implementation of the embodiments of the present invention, but the scope of the embodiments of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present invention, and all such changes or substitutions should be covered by the scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A4S store customer statistical method is characterized by comprising the following steps:
acquiring an in-store image of a 4S store, performing pedestrian detection on the in-store image by utilizing an OpenPose algorithm, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
processing the skeleton frame of the customer to obtain a posture graph of the customer;
and counting the passenger flow data in the 4S shop based on the posture graph of the customer in the in-shop image.
2. The method of claim 1, wherein the counting of the 4S in-store traffic data based on the posture graph of the customer in the in-store image comprises:
filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
3. The method of claim 2, wherein processing the customer image to be identified and the customer image to determine a similarity of the customer image to be identified and the customer image comprises:
respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
4. The method of claim 1, wherein processing the skeletal frame of the customer to obtain a pose graph for the customer comprises:
when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
5. A 4S store customer statistics apparatus, comprising:
the system comprises a first processing module, a second processing module and a third processing module, wherein the first processing module is used for acquiring an in-store image in a 4S store, utilizing an OpenPose algorithm to detect pedestrians in the in-store image, extracting body joint points and skeleton point trend information of a customer in the in-store image, and connecting the body joint points of the customer according to the body joint points and the skeleton point trend information of the customer to obtain a skeleton frame of the customer;
the second processing module is used for processing the skeleton frame of the customer to obtain a posture graph of the customer;
and the counting module is used for counting the passenger flow data in the 4S shop based on the attitude map of the customer in the in-shop image.
6. The apparatus of claim 5, wherein the statistics module is specifically configured to:
filling the attitude map of the customer in the in-store image by using a first color, and filling an image area except the attitude map of the customer in the in-store image by using a second color to obtain a customer image to be identified; wherein the first color and the second color are different neutral colors;
when a customer image which is not subjected to similarity judgment with the customer image to be identified exists, acquiring a customer image which is not subjected to similarity judgment with the customer image to be identified from a customer image database;
processing the acquired customer image and the to-be-identified customer image, and determining the similarity between the to-be-identified customer image and the customer image;
and when the images of the customers to be identified are determined to be not similar to the images of the customers according to the similarity, determining the customers corresponding to the images of the customers to be identified as new shop customers, and updating the passenger flow data in the 4S shop.
7. The apparatus of claim 6, wherein the statistical module for processing the customer image to be identified and the customer image to determine the similarity between the customer image to be identified and the customer image comprises:
respectively extracting a first image feature of the customer image and a second image feature of the customer image to be identified;
calculating Euclidean distances between the customer image and the customer image to be identified according to the first image feature and the second image feature;
when the Euclidean distance is greater than a distance threshold, determining that the customer image to be identified is dissimilar to the customer image.
8. The apparatus of claim 5, wherein the second processing module is specifically configured to:
when the pixel value of the skeletal frame of the customer is smaller than a pixel threshold value, performing thickening processing on the skeletal frame of the customer;
and performing gait recognition processing on the thickened skeleton frame of the customer by using a GaitSet algorithm to obtain a posture diagram of the customer.
9. An electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, characterized in that the computer program, when executed by the processor, implements the steps of the 4S store customer statistics method according to any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the 4S store customer statistics method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269319.XA CN111401305B (en) | 2020-04-08 | 2020-04-08 | 4S store customer statistical method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269319.XA CN111401305B (en) | 2020-04-08 | 2020-04-08 | 4S store customer statistical method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401305A true CN111401305A (en) | 2020-07-10 |
| CN111401305B CN111401305B (en) | 2021-06-04 |
Family
ID=71413710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010269319.XA Expired - Fee Related CN111401305B (en) | 2020-04-08 | 2020-04-08 | 4S store customer statistical method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401305B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592320A (en) * | 2021-06-16 | 2021-11-02 | 成都世纪光合作用科技有限公司 | Dining intention identification method and device and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150016A (en) * | 2013-02-20 | 2013-06-12 | 兰州交通大学 | Multi-person motion capture system fusing ultra wide band positioning technology with inertia sensing technology |
| CN103426020A (en) * | 2013-08-14 | 2013-12-04 | 北京凯森世纪科技发展有限公司 | Exclusive infrared passenger flow counter |
| CN108510491A (en) * | 2018-04-04 | 2018-09-07 | 深圳市未来媒体技术研究院 | Blur the filter method of skeleton critical point detection result under background |
| CN207946826U (en) * | 2018-03-30 | 2018-10-09 | 广东华电网维信息科技有限公司 | A kind of system of registering based on dynamic human face identification |
| CN108960211A (en) * | 2018-08-10 | 2018-12-07 | 罗普特（厦门）科技集团有限公司 | A kind of multiple target human body attitude detection method and system |
| CN109272347A (en) * | 2018-08-16 | 2019-01-25 | 苏宁易购集团股份有限公司 | A kind of statistical analysis technique and system of shops's volume of the flow of passengers |
| CN109460702A (en) * | 2018-09-14 | 2019-03-12 | 华南理工大学 | Passenger's abnormal behaviour recognition methods based on human skeleton sequence |
| US20190122424A1 (en) * | 2017-10-23 | 2019-04-25 | Fit3D, Inc. | Generation of Body Models and Measurements |
| CN109726672A (en) * | 2018-12-27 | 2019-05-07 | 哈尔滨工业大学 | It is a kind of to fall down detection method based on human skeleton sequence and convolutional neural networks |
| CN109871804A (en) * | 2019-02-19 | 2019-06-11 | 上海宝尊电子商务有限公司 | A kind of method and system of shop stream of people discriminance analysis |
| US20190294871A1 (en) * | 2018-03-23 | 2019-09-26 | Microsoft Technology Licensing, Llc | Human action data set generation in a machine learning system |
| US20190370537A1 (en) * | 2018-05-29 | 2019-12-05 | Umbo Cv Inc. | Keypoint detection to highlight subjects of interest |
| CN110852305A (en) * | 2019-11-18 | 2020-02-28 | 哈尔滨工程大学 | Human gait feature extraction method |
-
2020
- 2020-04-08 CN CN202010269319.XA patent/CN111401305B/en not_active Expired - Fee Related
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150016A (en) * | 2013-02-20 | 2013-06-12 | 兰州交通大学 | Multi-person motion capture system fusing ultra wide band positioning technology with inertia sensing technology |
| CN103426020A (en) * | 2013-08-14 | 2013-12-04 | 北京凯森世纪科技发展有限公司 | Exclusive infrared passenger flow counter |
| US20190122424A1 (en) * | 2017-10-23 | 2019-04-25 | Fit3D, Inc. | Generation of Body Models and Measurements |
| US20190294871A1 (en) * | 2018-03-23 | 2019-09-26 | Microsoft Technology Licensing, Llc | Human action data set generation in a machine learning system |
| CN207946826U (en) * | 2018-03-30 | 2018-10-09 | 广东华电网维信息科技有限公司 | A kind of system of registering based on dynamic human face identification |
| CN108510491A (en) * | 2018-04-04 | 2018-09-07 | 深圳市未来媒体技术研究院 | Blur the filter method of skeleton critical point detection result under background |
| US20190370537A1 (en) * | 2018-05-29 | 2019-12-05 | Umbo Cv Inc. | Keypoint detection to highlight subjects of interest |
| CN108960211A (en) * | 2018-08-10 | 2018-12-07 | 罗普特（厦门）科技集团有限公司 | A kind of multiple target human body attitude detection method and system |
| CN109272347A (en) * | 2018-08-16 | 2019-01-25 | 苏宁易购集团股份有限公司 | A kind of statistical analysis technique and system of shops's volume of the flow of passengers |
| CN109460702A (en) * | 2018-09-14 | 2019-03-12 | 华南理工大学 | Passenger's abnormal behaviour recognition methods based on human skeleton sequence |
| CN109726672A (en) * | 2018-12-27 | 2019-05-07 | 哈尔滨工业大学 | It is a kind of to fall down detection method based on human skeleton sequence and convolutional neural networks |
| CN109871804A (en) * | 2019-02-19 | 2019-06-11 | 上海宝尊电子商务有限公司 | A kind of method and system of shop stream of people discriminance analysis |
| CN110852305A (en) * | 2019-11-18 | 2020-02-28 | 哈尔滨工程大学 | Human gait feature extraction method |
Non-Patent Citations (3)
| Title |
|---|
| ALE SOLANO: ""Human pose estimation using OpenPose with TensorFlow (Part 1)"", 《AR/VR JOURNEY》 * |
| 刘舒婷: "基于视频监控的室内场所异常检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王祉: "基于视频监控的人流量统计系统设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113592320A (en) * | 2021-06-16 | 2021-11-02 | 成都世纪光合作用科技有限公司 | Dining intention identification method and device and electronic equipment |
| CN113592320B (en) * | 2021-06-16 | 2023-10-03 | 成都世纪光合作用科技有限公司 | Dining intention recognition method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401305B (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9652851B2 (en) | Side window detection in near-infrared images utilizing machine learning | |
| JP6650657B2 (en) | Method and system for tracking moving objects in video using fingerprints | |
| JP6398979B2 (en) | Video processing apparatus, video processing method, and video processing program | |
| WO2021051601A1 (en) | Method and system for selecting detection box using mask r-cnn, and electronic device and storage medium | |
| CN110321761B (en) | Behavior identification method, terminal equipment and computer readable storage medium | |
| CN110399835B (en) | Analysis method, device and system for personnel residence time | |
| JP2014071902A5 (en) | ||
| CN103093198A (en) | Crowd density monitoring method and device | |
| CN111860430A (en) | Identification method and device of fighting behavior, storage medium and electronic device | |
| CN113608663B (en) | Fingertip tracking method based on deep learning and K-curvature method | |
| CN111047622A (en) | Method and device for matching objects in video, storage medium and electronic device | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN111401305B (en) | 4S store customer statistical method and device and electronic equipment | |
| CN111199198A (en) | Image target positioning method, image target positioning device and mobile robot | |
| CN114067406A (en) | Key point detection method, device, equipment and readable storage medium | |
| CN113920158A (en) | Training and traffic object tracking method and device of tracking model | |
| CN111027387B (en) | Method, device and storage medium for acquiring person number evaluation and evaluation model | |
| CN112800923A (en) | Human body image quality detection method and device, electronic equipment and storage medium | |
| CN112884804A (en) | Action object tracking method and related equipment | |
| CN111488887A (en) | Image processing method and device based on artificial intelligence | |
| CN116823884A (en) | Multi-target tracking method, system, computer equipment and storage medium | |
| US20220301279A1 (en) | Systems and methods for using image analysis to automatically determine vehicle information | |
| CN113420667B (en) | Face living body detection method, device, equipment and medium | |
| CN111339226B (en) | Method and device for constructing map based on classification detection network | |
| CN113628148A (en) | Infrared image noise reduction method and device |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210604 |