WO2013182101A1 - Method, device and mobile terminal for determining target person - Google Patents

Abstract

A method, device and mobile terminal for determining a target person. The method for determining a target person comprises: acquiring first feature information of a person in image data; matching the first feature information with second feature information of a target person acquired in advance; and determining whether the person in the image data is the target person according to the matching result. The embodiments of the present invention solve the problems in the existing method for finding a person, and improve the accuracy and effectiveness for finding a person.

Description

 Target person determination method, device and mobile terminal

Technical field

 The present invention relates to the field of communications, and in particular to a method, device, and mobile terminal for determining a target person.

Background technique

 In real life, people often need to find people. For example, look for trafficked people, lost relatives, wanted criminal suspects, etc. The current methods of tracing (for example, posting posters, newspapers, TV tracing, etc.) are difficult to find people because of the small spread of information, the lack of information sources, and the relatively large population mobility.

 In view of the low efficiency, inconvenience, inaccuracy and the like of the tracing method in the related art, no effective solution has been proposed yet.

Summary of the invention

 The invention provides a method, a device and a mobile terminal for determining a target person, so as to overcome the problems of low efficiency, inconvenience and inaccuracy in the prior art tracing method.

 In order to solve the above problem, according to an aspect of the embodiments of the present invention, a method for determining a target person is provided, including: acquiring first feature information of a person in image data; and the first feature information and a target obtained in advance The second feature information of the person is matched; determining whether the person in the image data is the target person according to the matching result.

 Optionally, the first feature information includes: first face information of a person in the image data; and the second feature information includes: second face information of the target person. Optionally, determining whether the person in the image data is the target person according to the matching result includes: determining whether a matching degree of the first face information and the second face information meets a preset condition; A condition is set to determine that the person in the image data is the target person.

Optionally, the method further includes: the first feature information further includes first location information of the person in the image data, and if the person in the image data is determined to be the target person, sending the report to the server First feature information of a person in the image data and first position information of a person in the image data. Optionally, the second feature information further includes: second location information of the target person; matching the first feature information with the second feature information, including: the first location information and the location The second location information is matched; determining whether the first location information has an intersection with the second location information; if there is an intersection, matching the first facial information with the second facial information.

 Optionally, after determining whether the first location information has an intersection with the second location information, the method further includes: determining, according to the determination result, a matching data set, where the matching data set is intersected with the first location information The set of the target person; matching the first face information with the second face information comprises: the first face information and the second face of the target person in the matching data set Information is matched.

 Optionally, acquiring the first feature information of the person in the image data includes: detecting whether there is new image data in the storage device, and if there is a new image, acquiring the first image from the newly added image data The facial information; and/or, the image data is directly acquired by the imaging device, and the first facial information is acquired from the acquired image data.

 Optionally, before the matching the first feature information with the second feature information of the target person obtained in advance, the method further includes: sending a request to the server, requesting to acquire the second feature information; and receiving the server according to the Said second feature information returned by the request; and/or directly receiving the second feature information pushed by the server.

 Optionally, after determining, according to the matching result, whether the person in the image data is the target person, the method further includes: displaying the determination result and/or the matching result to the user.

According to another aspect of the present invention, a determining apparatus for a target person is provided, including: an acquiring module, configured to acquire first feature information of a person in the image data; and a matching module, configured to set the first The feature information is matched with the second feature information of the target person obtained in advance; and the determining module is configured to determine, according to the matching result of the matching module, whether the person in the image data is the target person.

Optionally, the acquiring module is configured to acquire a first facial message of a person in the image data Interest.

 Optionally, the determining module includes: a first determining unit, configured to determine whether a matching degree of the first facial information and the second facial information in the second feature information meets a preset condition; And the unit is configured to determine that the person in the image data is the target person if the determination result of the first determining unit is that the preset condition is met.

 Optionally, the device further includes: a reporting module, configured to send, to the server, the first feature of reporting the person in the image data, if the determination result of the first determining unit is that the preset condition is met Information and first location information of a person in the image data.

 Optionally, the matching module includes: a first matching unit, configured to match the first location information with the second location information of the second feature information; and a second determining unit, configured to determine the Whether the first location information and the second location information intersect; the second matching unit is configured to: when the determination result of the second determining unit is that there is an intersection, the first facial information and the The second face information is matched.

 Optionally, the matching module further includes: a second determining unit, configured to determine, according to a determination result of the second determining unit, a matching data set, where the matching data set is intersected with the first location information The set of the target persons; the second matching unit is configured to match the first face information with the second face information of the target person in the matching data set.

 Optionally, the acquiring module includes: a first acquiring unit, configured to detect whether there is new image data in the storage device, and if there is a new image, obtain the first image from the newly added image data And the second acquisition unit is configured to directly acquire image data by the imaging device, and acquire the first facial information from the acquired image data.

According to still another aspect of the embodiments of the present invention, there is provided a mobile terminal comprising the determining means of any of the above-mentioned target persons provided by the present invention.

According to the embodiment of the present invention, the first feature information of the person in the image data is acquired, the first feature information is matched with the second feature information of the target person obtained in advance, and the person in the image data is determined as the target person according to the matching result. , solved the existing problems of the tracing method and improved the tracing Accuracy and effectiveness.

BRIEF abstract

 1 is a schematic diagram of a target person's determination system in accordance with an embodiment of the present invention;

 2 is a structural block diagram of a determining device of a target person according to an embodiment of the present invention;

 3 is a flow chart of a method of determining a target person according to an embodiment of the present invention;

 4 is a flowchart of a method for determining a target person according to Embodiment 1 of the present invention;

 FIG. 5 is a flowchart of a method for determining a target person according to Embodiment 2 of the present invention. Preferred embodiment of the invention

 Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the features in the embodiments and the embodiments in the present application may be arbitrarily combined with each other.

In view of the existing problems of the tracing method, considering the large-scale use of mobile terminals, a wide range of interconnected mobile networks are formed, and the terminal nodes of the network mostly have imaging and positioning functions. In the embodiment of the present invention, using the network formed by the mobile terminal to perform the tracing is more convenient, more efficient, and more accurate than the traditional tracing method.

 In the embodiment of the present invention, a database of the target person may be established, and information of the target person may be stored, for example, image data of the target person, information of a location where the target person may appear, and the like. The target person information is pushed to the mobile terminal having the camera and the geographic positioning system, and the mobile terminal analyzes the information of the person and the target person in the captured image data, and determines whether the person in the image data captured by the mobile terminal is the target according to the analysis result. people.

1 is a schematic diagram of a target person's determination system according to an embodiment of the present invention. As shown in FIG. 1, the system includes a server and a mobile terminal. Establishing a target person information database on the server side, storing the information of the target person, the mobile terminal acquires the information of the target person from the server, and analyzes the information of the person in the image data in the mobile terminal, and determines the mobile terminal according to the result of the analysis. Whether the person in the image data is the target person. The mobile terminal obtains the tracing database information on the server through the wireless connection. Each data item of the tracing database can include feature information of the person to be sought, as well as location and other related information that may be present, synchronized to the local tracing database. The mobile terminal can be configured to automatically analyze the photographed photos in the background after the photograph is saved, for example, using facial recognition technology, geographic location technology, pattern recognition technology, etc., to compare the information of the person in the photo with the data in the local tracing database. A matching is performed, and it is determined whether the person in the image data in the mobile terminal is the target person according to the matching result.

 In the embodiment of the present invention, the mobile terminal can send the tracing result to the server through a wireless connection. Moreover, the mobile terminal can promptly search for results to the user (for example, sound, vibration, text, graphic display, etc.).

 The embodiments of the present invention are described in detail below.

 According to an embodiment of the present invention, a determining device for a target person is provided.

 2 is a structural block diagram of a determining device of a target person according to an embodiment of the present invention. As shown in FIG. 2, the device mainly includes: an obtaining module 10, a matching module 20, and a determining module 30. The obtaining module 10 is configured to acquire first feature information of a person in the image data. The matching module 20 is connected to the acquiring module 10, and configured to perform the first feature information and the second feature information of the target person obtained in advance. The matching module 30 is connected to the matching module 20 and configured to determine whether the person in the image data is the target person according to the matching result of the matching module.

 In an implementation manner of the embodiment of the present invention, the first feature information acquired by the obtaining module 10 may include first face information of a person in the image data. Matching the first feature information with the second feature information by the matching module 20 may refer to matching the first face information with the second facial feature of the second feature information of the target person. The determining module 30 may determine whether the person in the image data is the target person based on the matching result of the first face information and the second face information. In an embodiment of the present invention, the determining module 30 may include: a first determining unit, configured to determine whether a matching degree of the second facial information in the first facial information and the second feature information meets a preset condition; The first determining unit is configured to determine that the person in the image data is the target person if the determination result of the first determining unit is that the preset condition is satisfied.

In the case of a human target person in the image data, the person search result can also be reported to the server. In an embodiment of the embodiment of the present invention, the first feature information of the person in the image data further includes first location information. For example, the position at which the image data is captured is obtained by the positioning device, from The apparatus of the embodiment of the present invention may further include: a reporting module, configured to send a report to the server if the determination result of the first determining unit is that the preset condition is met The first feature information of the person in the image data and the first location information of the person in the image data. Optionally, the reported information may further include a matching result and the like.

 The second feature information may further include second location information of the target person, and the location information may be location information that may be present by the target person. In the determination process of the target person, only the second feature information of the target person whose first location information and the second location information exist may be matched. In an embodiment of the present invention, the matching module may include: a first matching unit configured to match the first location information with the second location information of the second feature information; and the second determining unit is configured to determine Whether the first location information and the second location information overlap; the second matching unit is configured to match the first facial information with the second facial information if the determination result of the second determining unit is that there is an intersection.

 Optionally, the matching module may further include: a second determining unit, configured to determine, according to a determination result of the second determining unit, a matching data set, where the matching data set is a set of target persons that intersect with the first location information; The matching unit is configured to match the first face information with the second face information of the target person in the matching data set.

 In the embodiment of the present invention, the acquiring module 10 may directly acquire image data by using an image capturing device, and acquire first face information of a person in the image data from the acquired image data. The obtaining module 10 can also detect whether there is new image data in the storage device in real time or at a time, and if so, obtain the first face information from the newly added image data. In an embodiment of the present invention, the obtaining module may include: a first acquiring unit configured to detect whether there is new image data in the storage device, and if there is a newly added image, obtain the newly added image data. The first facial information; and/or the second acquiring unit is configured to directly acquire the image data by the imaging device, and acquire the first facial information from the acquired image data.

Before matching the first feature information with the second feature information of the target person obtained in advance, the second feature information of the target person may be acquired from the server. In an embodiment of the present invention, a request may be sent to the server, requesting to acquire the second feature information, and receiving second feature information returned by the server according to the request, for example, the user may set the target person information of interest, for example, , the user only obtains the information of the target person in his or her area, and the like. In another embodiment of the embodiments of the present invention, The second feature information pushed by the server may be directly received, and the server may periodically push the second feature information of the target person. In the embodiment of the present invention, after determining whether the person in the image data is the target person according to the matching result, the method further includes: displaying the determination result and/or the matching result to the user.

 According to an embodiment of the present invention, there is also provided a mobile terminal, comprising the determining device of any of the above-mentioned target persons according to the embodiment of the present invention.

 According to an embodiment of the present invention, a method for determining a target person is also provided.

 FIG. 3 is a flowchart of a method for determining a target person according to an embodiment of the present invention. As shown in FIG. 3, the method mainly includes steps S302 to S306.

 Step S302: The mobile terminal acquires first feature information of a person in the image data.

 In the embodiment of the present invention, the first feature information may include: first face information of a person in the image data. The image data can be directly acquired by the image capturing device, and the first face information of the person in the image data can be obtained from the acquired image data. The new image data can be detected in the storage device in real time or at a time, and if so, the new image data is updated. The first facial information is acquired in the increased image data.

 Optionally, the first feature information may further include: first location information of the person in the image data. For example, the position at which the image data is captured is acquired by the positioning device, thereby determining the position of the person in the image data.

 Step S304: The mobile terminal matches the first feature information with the second feature information of the target person obtained in advance.

 In the embodiment of the present invention, the second feature information may include: second face information of the target person. Matching the first feature information with the second feature information includes: matching the first face information with the second face information.

Optionally, the second feature information may further include: second location information of the target person; matching the first feature information with the second feature information includes: matching the first location information with the second location information; determining the first Whether the location information intersects with the second location information; if there is an intersection, the first face information is matched with the second face information. With the preferred embodiment, the range of matching can be narrowed to provide matching efficiency. In an embodiment of the embodiment of the present invention, the mobile terminal may be determined according to the foregoing judgment result. And a matching data set, wherein the matching data set is a set of target persons that intersect with the first location information, and matches the first facial information with the second facial information of the target person in the matching data set.

 Step S306, the mobile terminal determines, according to the matching result, whether the person in the image data is the target person. In the embodiment of the present invention, the mobile terminal may determine whether the matching degree of the first facial information and the second facial information meets the preset condition; if the preset condition is met, determine that the person in the image data is the target person. For example, the matching degree threshold is set in advance, and the matching degree threshold may be set in the user segment or in the server. If the matching degree reaches the matching degree threshold, it is determined that the person in the image data is the target person.

 Optionally, the mobile terminal sends the first feature information of the person in the reported image data and the first location information of the person in the image data to the server in the case of determining the person targeted in the image data.

 In an embodiment of the present invention, before the mobile terminal matches the first feature information with the second feature information of the target person that is obtained in advance, the mobile terminal may further send a request to the server to obtain the second feature information. Receiving the second feature information returned by the server according to the request. The mobile terminal can also directly receive the second feature information pushed by the server.

 After the mobile terminal determines whether the person in the image data is the target person according to the matching result, the method further includes: displaying the determination result and/or the matching result to the user.

 According to the embodiment of the present invention, the mobile terminal acquires the first feature information of the person in the image data, matches the first feature information with the second feature information of the target person obtained in advance, and determines, according to the matching result, whether the person in the image data is The target person solves the problems existing in the existing tracing method and improves the accuracy and effectiveness of tracing.

 The above method will be described in detail by way of specific examples.

 In the embodiment of the present invention, according to whether the mobile terminal supports location location, it is divided into two types: "including geographic location matching" and "excluding geographical location matching".

Embodiment 1

In the first embodiment of the present invention, the mobile terminal supports location location as an example for description. In the embodiment of the present invention, the mobile terminal actively (timed or manually) acquires data from the server, or passively receives. The information pushed by the server is added to the local tracing database, and each piece of data can include the photo of the target person and the geographical location that may appear.

 4 is a flowchart of a method for determining a target person according to Embodiment 1 of the present invention. As shown in FIG. 4, the method includes steps S402 to S420.

 Step S402 to step S404, after the mobile terminal takes a photo, the photo is stored.

 Step S406: The mobile terminal automatically analyzes the photo to perform face recognition.

 Step S408: The mobile terminal determines whether there is a face image in the photo. If yes, step S410 is performed, and if no, the process ends.

 Step S410: The mobile terminal determines the current location by using a geographic location positioning function.

 Step S412: The mobile terminal searches for a tracing database by geographic location.

 Step S414: The mobile terminal determines whether a matching data set is obtained, and if yes, performs step S416, and if not, ends.

 Step S416: The mobile terminal identifies the face and the matching data set to perform face matching, and determines the similarity.

 Step S418: The mobile terminal determines whether the similarity meets the preset condition, and if yes, performs the step

S420, if no, end.

 Step S420: The mobile terminal ends the matching result on the end of the month.

 The information of the "^" on the mobile terminal may include: a photo and a geographical location at the time and matching information, such as a mobile terminal mobile number.

Embodiment 2

 In the second embodiment of the present invention, the mobile terminal does not support the location location as an example. In the embodiment of the present invention, the mobile terminal actively (timingly or manually) obtains data from the server, or passively receives the data pushed by the server. , join the local tracing database, each piece of data can include the photo of the target person and the geographical location that may appear.

FIG. 5 is a flowchart of a method for determining a target person according to Embodiment 2 of the present invention. As shown in FIG. 5, the method includes steps S502 to S514. Step S502 to step S504, after the mobile terminal takes a picture, the photo is stored.

 Step S506: The mobile terminal automatically analyzes the photo to perform face recognition.

 Step S508, the mobile terminal determines whether there is a face image in the photo, and if yes, performs step S510, and if not, ends.

 Step S510: The mobile terminal identifies the face and the data set in the database to perform face matching, and determines the similarity.

 Step S512: The mobile terminal determines whether the similarity meets the preset condition, and if yes, performs step S514, and if not, ends.

 Step S514, the mobile terminal ends the matching result on the service end.

 The information on the mobile terminal can include: photo and current geographic location and matching information, mobile terminal mobile number, and the like.

 In the following, a typical application case of the embodiment of the invention will be described by taking a lost elderly person as an example. After discovering that the old man is lost, the relatives pass the basic information of the elderly to the manager of the server, usually by the administrative or social service department such as the public security organ or the neighborhood committee.

 The basic information of the elderly (including the name of the elderly, photos, lost location, time, family contact, etc.) is entered into the tracing database of the server. Since photos usually only need to reflect basic facial features, high-pixel photos are not required, so the amount of data in one piece of data is not too large. Even in the database, other descriptions of facial information can be used instead of pictures or photos, as well as the ability to support pattern matching operations.

 The mobile phone with the target person's confirmation device installed contains a local tracing database. This database can be set by the user to focus on a specific range of tracing information. For example, focus only on the lost information of the city, or focus on the tracing information released in the past week, or focus only on wanted information with high rewards. This can reduce the data footprint of the local tracing database and improve the speed of local matching. Specific users, such as public security personnel, can set up to focus on all tracing information.

The related information of the mobile phone, or by the mobile phone user to manually synchronize with the database, thereby obtaining the missing elderly information. The mobile phone user who installed the target person's confirmation device takes photos at stations, scenic spots, shopping malls, etc. After the user uses the mobile phone to take a photo event, the mobile phone can automatically call the target person's confirmation device in the background, without affecting the user's normal use of the mobile phone. In the case of functions, face recognition, geographic location information acquisition, information matching, and judgment are automatically performed.

 When judging "find suspicious object", the current mobile phone user can be explicitly prompted. Therefore, the mobile phone user can immediately ask the elderly to confirm and report the information to the police or family members, thereby effectively completing the search. Instead of explicitly prompting, the result of judging "find suspicious object" and related information (such as geographic location, original photo of the photo, mobile phone number of the information submission terminal) can be reported to the server. Confirmed by the police or family members.

 Once the missing old man is found, the tracing task is completed. The data is deleted from the server's tracing database and synchronized to the local tracing database in the mobile phone by active or passive means to prevent false positives.

One of ordinary skill in the art will appreciate that all or a portion of the above steps may be accomplished by a program that instructs the associated hardware to be stored in a computer readable storage medium, such as a read only memory, a magnetic disk, or an optical disk. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the above embodiment may be implemented in the form of hardware or in the form of a software function module. Embodiments of the invention are not limited to any particular form of combination of hardware and software.

 The above embodiments are only used to explain the technical solutions of the present application, and are not intended to limit the details of the present application. It should be understood by those skilled in the art that the present invention may be modified or equivalently substituted without departing from the spirit and scope of the present invention.

Industrial Applicability According to the embodiment of the present invention, the first feature information of the person in the image data is acquired, the first feature information is matched with the second feature information of the target person obtained in advance, and the person in the image data is determined according to the matching result. As the target person, it solves the existing problems of the tracing method and improves the accuracy and effectiveness of tracing.

Claims

Claim  1. A method for determining a target person, including:  Acquiring first feature information of a person in the image data;  Matching the first feature information with the second feature information of the target person obtained in advance; determining whether the person in the image data is the target person according to the matching result.  2. The method according to claim 1, wherein the first feature information comprises: first face information of a person in the image data; the second feature information comprises: a second person of the target person Face information.  3. The method according to claim 2, wherein the step of determining whether the person in the image data is the target person based on the matching result comprises:  Determining whether the degree of matching between the first facial information and the second facial information meets a preset condition;  If the preset condition is satisfied, it is determined that the person in the image data is the target person.  4. The method of claim 3, wherein  The first feature information further includes first location information of a person in the image data;  The method further includes:  In the case where it is determined that the person in the image data is the target person, the first feature information of the person in the image data and the first position information of the person in the image data are transmitted to the server.  The method according to claim 4, wherein the second feature information further comprises: second location information of the target person; and step of matching the first feature information with the second feature information Includes:  Matching the first location information with the second location information;  Determining whether the first location information has an intersection with the second location information;  If there is an intersection, the first facial information is matched with the second facial information. 6. The method according to claim 5, determining whether the first location information is related to the second After the step of the intersection of the location information, the method further includes:  Determining, according to the determination result, a matching data set, where the matching data set is a set of the target persons that intersect with the first location information;  The step of matching the first face information with the second face information comprises: matching the first face information with second face information of the target person in the matching data set.  The method according to any one of claims 2 to 4, wherein the step of acquiring the first feature information of the person in the image data comprises:  Detecting whether there is new image data in the storage device, and if there is a new image, acquiring the first facial information from the newly added image data; and/or  The image data is directly acquired by the image pickup device, and the first face information is acquired from the acquired image data.  The method according to any one of claims 1 to 4, wherein the step of matching the first feature information with the second feature information of the target person obtained in advance further comprises:  Sending a request to the server, requesting to acquire the second feature information; receiving the second feature information returned by the server according to the request; and/or  Directly receiving the second feature information pushed by the server.  The method according to any one of claims 1 to 4, after the step of determining whether the person in the image data is the target person based on the matching result, further comprising:  The determination result and/or the matching result are presented to the user.  10. A determining device for a target person, comprising:  An obtaining module, configured to acquire first feature information of a person in the image data;  a matching module, configured to match the first feature information with the second feature information of the target person obtained in advance;  And a determining module, configured to determine, according to a matching result of the matching module, whether the person in the image data is the target person. The device according to claim 10, wherein the first feature information acquired by the acquiring module comprises first face information of a person in the image data. The device according to claim 11, wherein the determining module comprises: a first determining unit, configured to determine a degree of matching between the first facial information and the second facial information in the second feature information Whether the predetermined condition is met; the first determining unit is configured to determine that the person in the image data is the target person if the determination result of the first determining unit is that the preset condition is met.  The device according to claim 12, wherein the first feature information further includes first location information of a person in the image data, the device further comprising: a reporting module, configured to be in the first determining unit If the determination result is that the preset condition is met, the first feature information of the person in the image data and the first location information of the person in the image data are sent to the server.  The device according to claim 13, wherein the matching module comprises: a first matching unit configured to match the first location information with the second location information of the second feature information;  a second determining unit, configured to determine whether the first location information has an intersection with the second location information;  The second matching unit is configured to match the first face information with the second face information in a case where the determination result of the second determining unit is that there is an intersection.  15. The apparatus according to claim 14, wherein  The matching module further includes: a second determining unit, configured to determine a matching data set according to the determination result of the second determining unit, where the matching data set is the target that intersects with the first location information a collection of people;  The matching, by the second matching unit, the first facial information and the second facial information, is: the second matching unit, the first facial information and the matching data set The second facial information of the target person is matched.  The apparatus according to any one of claims 11 to 13, wherein the obtained ear block comprises: a first acquiring unit, configured to detect whether there is new image data in the storage device, and if there is new image data, obtain the first facial information from the newly added image data; and/or The second acquiring unit is configured to directly acquire image data by the imaging device, and acquire the first facial information from the acquired image data.  A mobile terminal comprising the target person determining device according to any one of claims 10 to 16.