CN114926757A - Method and system for retrieving lost article, electronic equipment and computer storage medium - Google Patents
Method and system for retrieving lost article, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN114926757A CN114926757A CN202210418923.3A CN202210418923A CN114926757A CN 114926757 A CN114926757 A CN 114926757A CN 202210418923 A CN202210418923 A CN 202210418923A CN 114926757 A CN114926757 A CN 114926757A
- Authority
- CN
- China
- Prior art keywords
- information
- article
- lost
- image
- image information
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a system for retrieving lost articles, electronic equipment and a computer storage medium. The method for retrieving the lost article comprises the following steps: acquiring owner information and article information of lost articles; acquiring first image information with owner information and article information from a monitoring video stream; acquiring target video information for retrieving lost articles from the monitoring video stream based on the first image information; and acquiring the lost positioning information of the lost article based on the target video information. Through the mode, the lost article can be automatically tracked based on the monitoring video stream, and the efficiency of finding the lost article can be further improved.
Description
Technical Field
The present application relates to the field of video analysis technologies, and in particular, to a method and a system for retrieving a lost article, an electronic device, and a computer storage medium.
Background
In a scenic spot or a garden, people often have the condition of lost articles, and often go through video monitoring and checking by managers in the scenic spot or the garden according to clues of time and position provided by a loser to find the lost articles.
Disclosure of Invention
The technical problem that this application mainly solved is how to follow up the lost article based on the automatic tracking of surveillance video stream, improves the efficiency that the lost article was given for change.
In order to solve the technical problem, the application adopts a technical scheme that: a method for retrieving lost articles is provided. The method for retrieving the lost article comprises the following steps: acquiring owner information and article information of lost articles; acquiring first image information with owner information and article information from a monitoring video stream; acquiring target video information for retrieving lost articles from the monitoring video stream based on the first image information; and acquiring the lost positioning information of the lost article based on the target video information.
The lost article tracking method and device can achieve track tracking of lost articles based on the monitoring video stream, can automatically obtain lost positioning information of the lost articles, and are convenient for an owner to find the lost articles in time, so that the finding efficiency of the lost articles can be improved.
Wherein, the above-mentioned target video information of retrieving lost article based on first image information obtains from the surveillance video stream, includes: and acquiring historical video streams with acquisition time later than that of the first image information from the monitoring video streams as target video information of the lost articles.
By the method, the searching range of the lost articles can be reduced, and the retrieving efficiency of the lost articles can be improved.
Wherein, the above-mentioned target video information of retrieving lost article based on first image information obtains from the surveillance video stream, includes: and acquiring second image information which has article information and is acquired at a time later than the acquisition time of the first image information from the monitoring video stream to serve as target video information of the lost article.
By the method, the searching range of the lost articles can be narrowed, and the retrieving efficiency of the lost articles can be improved.
Wherein, the above-mentioned first image information who has owner's information of the thing and article information of obtaining from the surveillance video stream includes: acquiring target time and/or target position information; acquiring image information with owner information from a monitoring video stream; acquiring image information with article information from the image information with owner information; and acquiring image information with acquisition time within the target time and/or acquisition position information consistent with the target position information from the image information with the owner information and the article information as first image information.
By the mode, the image information with the acquisition time out of the target time and/or the acquisition position information inconsistent with the target position information is filtered from the image information with the owner information and the article information, the searching range of the lost articles can be narrowed, and the retrieving efficiency of the lost articles can be improved.
Wherein, owner's information includes people's face information, before above-mentioned owner's information and the article information of acquireing the lost article, further include: carrying out face recognition and article recognition on image frames of the monitoring video stream to obtain face information and/or article information in each image frame; establishing a mapping relation between the face information and the corresponding image frame, and storing the mapping relation in a first image information base; and establishing a mapping relation between the article information and the corresponding image frame, and storing the mapping relation in a second image information base.
Through the mode, the method and the device realize image recognition of the monitoring video stream, classified storage of the face information and the article information and the like, so that the monitoring video stream is collected, analyzed and the lost articles are simultaneously carried out, and the lost article finding efficiency can be improved.
Wherein, the above-mentioned first image information who has owner's information of the thing and article information of obtaining from the surveillance video stream includes: acquiring target time and/or target position information; acquiring a first image frame with face information from a first image information base; acquiring a second image frame with article information from a second image information base; determining a first image frame or a second image frame with face information and article information as a target image frame; and acquiring an image frame with the acquisition time within the target time and/or the acquisition position information consistent with the target position information from the target image frame as first image information.
By the mode, the image frames with the acquisition time being not within the target time and/or the acquisition position information being inconsistent with the target position information are filtered from the image frames with the owner information and the article information, the searching range of the lost articles can be narrowed, and the finding efficiency of the lost articles can be improved.
Wherein, the above-mentioned second image information who has article information and the acquisition time is later than the acquisition time of first image information of obtaining from the surveillance video stream includes: acquiring the latest acquisition time of a plurality of pieces of first image information; acquiring third image information with article information from the monitoring video stream; and acquiring the image information with the acquisition time later than the latest acquisition time from the third image information as second image information.
By means of the mode, the image information of the lost object and the owner of the lost object which are separated and exist independently can be obtained.
Wherein, the above-mentioned lost locating information based on that the video information of the goal obtains and loses the article, include: recognizing face information of other people except the owner from the target video information; in response to that the distance between the face information of the other people except the owner and the lost article is smaller than the preset distance, acquiring image information which is acquired at a time later than the acquisition time of the first image information and comprises the face information of the other people except the owner as fourth image information; and determining the lost positioning information of the lost article based on the fourth image information.
Through the mode, the lost article tracking device can track other people after the lost article is taken away by other people so as to acquire the lost positioning information of the lost article, and can improve the efficiency and accuracy of finding the lost article.
Wherein, after the first image information with owner information and article information is obtained from the monitoring video stream, before the target video information for retrieving the lost article is obtained from the monitoring video stream based on the first image information, the method further comprises: and identifying the relationship between the owner information and the article information as the attribution relationship based on the first image information.
In this way, it is possible to avoid other people from posing as owners.
In order to solve the technical problem, the application adopts a technical scheme that: a method for retrieving lost articles is provided. The method for retrieving the lost article comprises the following steps: acquiring first image information with owner information and article information from a monitoring video stream; identifying a relationship between the owner information and the item information based on the first image information; in response to the relationship being an attribution relationship, taking the acquisition time of the first image information as a time starting point, and counting the separation duration of the owner and the article; and responding to the separation duration being greater than the preset duration, and generating alarm information.
By the mode, the alarm can automatically give an alarm after the articles are lost.
In order to solve the technical problem, the application adopts a technical scheme that: a system for retrieving lost articles is provided. The system for retrieving the lost article comprises: the video acquisition device is used for acquiring a monitoring video stream; the electronic equipment is communicated with the video acquisition device and is used for acquiring a monitoring video stream from the video acquisition device, acquiring owner information and article information and acquiring first image information with the owner information and the article information from the monitoring video stream; the electronic equipment is used for acquiring target video information for retrieving the lost article from the monitoring video stream based on the first image information and acquiring lost positioning information of the lost article based on the target video information; or the electronic equipment is used for identifying the relation between the owner information and the article information based on the first image information, counting the separation duration of the owner and the article by taking the acquisition time of the first image information as a time starting point in response to the relation as an attribution relation, and generating alarm information in response to the separation duration being greater than a preset duration.
The method and the device can realize the track tracking of the lost articles based on the monitoring video stream, can automatically acquire the lost positioning information of the lost articles, and are convenient for an owner to find the lost articles in time, so that the finding efficiency of the lost articles can be improved; or can automatically alarm after the article is lost.
In order to solve the technical problem, the application adopts a technical scheme that: an electronic device is provided. The electronic device includes: the processor is used for executing the program instructions to realize the method for retrieving the lost article.
In order to solve the technical problem, the application adopts a technical scheme that: a computer storage medium is provided. The computer storage medium stores program instructions, and the program instructions realize the method for retrieving the lost article when being executed.
The beneficial effect of this application is: different from the prior art, the method and the device for detecting the lost article information acquire owner information of the lost article and first image information of the article information from the monitoring video stream, and can determine information such as time, place and the like of the owner and the lost article; then, target video information for retrieving the lost article is obtained from the monitoring video stream based on the first image information, and the target video information obtains the lost positioning information of the lost article. Therefore, the lost article tracking system can realize the track tracking of the lost article based on the monitoring video stream, can automatically acquire the lost positioning information of the lost article, is convenient for an owner to timely retrieve the lost article, and can improve the retrieving efficiency of the lost article.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a method for retrieving a lost article according to the present application;
FIG. 2 is a schematic flow chart diagram illustrating an embodiment of a method for retrieving a lost article according to the present application;
FIG. 3 is a schematic flow chart diagram illustrating an embodiment of the method for retrieving the lost article of the present application;
FIG. 4 is a flowchart illustrating a specific process of step S33 in the embodiment of FIG. 3;
FIG. 5 is a flowchart illustrating a specific process of step S34 in the embodiment of FIG. 3;
FIG. 6 is a schematic flow chart diagram illustrating an embodiment of a method for retrieving a lost article according to the present application;
FIG. 7 is a schematic flow chart diagram illustrating an embodiment of a method for retrieving a lost article according to the present application;
FIG. 8 is a schematic flow chart diagram illustrating an embodiment of a method for retrieving a lost article according to the present application;
FIG. 9 is a schematic view of an embodiment of the system for retrieving lost articles of the present application;
FIG. 10 is a schematic structural diagram of an embodiment of an electronic device of the present application;
FIG. 11 is a schematic structural diagram of an embodiment of a computer storage medium according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first" and "second" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The present application first provides a method for retrieving a lost article, as shown in fig. 1, where fig. 1 is a schematic flow chart of an embodiment of the method for retrieving a lost article. The method for retrieving the lost article in the embodiment specifically comprises the following steps:
step S11: and acquiring owner information and article information of the lost articles.
In an application scenario, the electronic device is provided with an APP corresponding to the retrieving system of the lost article, and the electronic device can obtain owner information and article information of the lost article through the APP, so that the retrieving system of the lost article can obtain the owner information and the article information of the lost article.
When a lost article needs to be searched, a user can input article information, such as the type of the article, and input owner information, such as a face photo of an owner, to a retrieval system of the lost article through the APP.
Step S12: first image information with owner information and item information is obtained from the monitoring video stream.
A plurality of video acquisition devices such as cameras are arranged in the garden, the scenic spot or other management areas and are used for acquiring monitoring video streams in the garden, the scenic spot or other management areas; the lost article retrieving system performs face recognition and article recognition on the image frames of the monitoring video stream, and stores the recognized face information, article information and corresponding image information to obtain an image information base.
When the lost article needs to be searched, the retrieval system of the lost article acquires owner information of the lost article and first image information of the article information from the stored image information library; the first image information includes information such as time, place, and image of the lost article together with the owner.
The video acquisition devices such as the camera and the like are in wired or wireless communication with the electronic equipment, and the camera uploads the acquired monitoring video stream to the finding system of the lost article.
Step S13: and acquiring target video information for retrieving the lost article from the monitoring video stream based on the first image information.
Alternatively, in order to avoid another person impersonating the owner, after step S12 and before step S13, the relationship between the owner information and the item information may also be identified based on the first image information; in response to the relationship being a home relationship, step S13 is performed.
Step S14: and acquiring the lost positioning information of the lost article based on the target video information.
The embodiment first obtains owner information of lost articles and first image information of the article information from a monitoring video stream, and can determine information such as time, place and the like of the owner and the lost articles; then, target video information of the lost article is obtained and retrieved from the monitoring video stream based on the first image information, and the target video information obtains lost positioning information of the lost article. Therefore, the lost article tracking system can realize the track tracking of the lost article based on the monitoring video stream, can automatically acquire the lost positioning information of the lost article, is convenient for an owner to timely retrieve the lost article, and can improve the retrieving efficiency of the lost article.
The present application further provides another embodiment of a method for retrieving a lost article, as shown in fig. 2, the method for retrieving a lost article of the present embodiment specifically includes the following steps:
step S21: and acquiring owner information and article information of the lost articles.
Reference may be made to the above-described embodiments for specific implementations.
Step S22: first image information with owner information and object information is obtained from a monitoring video stream.
Reference may be made to the above-described embodiments for specific implementations.
Step S23: and acquiring the historical video stream with the acquisition time later than that of the first image information from the monitoring video stream as the target video information of the lost article.
The historical video stream contains information such as time and place after the lost article is separated from the owner.
Step S24: and acquiring lost positioning information of the lost article based on the target video information.
The embodiment obtains the lost positioning information of the lost article based on the historical video stream, namely, the lost positioning information of the lost article is determined according to the time, the place and other information after the article is separated from the owner. Therefore, the track tracking of the lost article can be realized based on the historical video stream, and the lost positioning information of the lost article can be automatically acquired.
In another embodiment, as shown in fig. 3, the method for retrieving a lost article of this embodiment specifically includes the following steps:
step S31: and acquiring owner information and article information of the lost articles.
Reference may be made to the above examples for specific embodiments.
Step S32: first image information with owner information and object information is obtained from a monitoring video stream.
Reference may be made to the above-described embodiments for specific implementations.
Step S33: and acquiring second image information which has article information and acquisition time later than that of the first image information from the monitoring video stream as target video information of the lost article.
The second image information includes information such as time and place after the article is separated from the owner.
The lost article retrieving system acquires second image information which has article information and is acquired at a time later than the acquisition time of the first image information from the stored image information base, namely acquires information such as time, place, image picture and the like after the article is separated from the owner.
Alternatively, the present embodiment may implement step S33 by using the method shown in fig. 4, where the method of the present embodiment includes steps S41 to S43.
Step S41: the latest acquisition time of the plurality of first image information is acquired.
And sequencing the plurality of pieces of first image information according to the sequence of the acquisition time, and acquiring the maximum value of the acquisition time as the latest acquisition time.
The lost article retrieving system acquires the latest acquisition time of the acquisition times of the plurality of first image information. The latest collection time is the latest time before the lost article is separated from the owner, and after the latest collection time, the lost article is separated from the owner.
In other embodiments, the maximum value of the frame numbers of the plurality of first image information may be obtained according to the frame number of the image frame, and the acquisition time of the first image information corresponding to the maximum frame number may be the latest acquisition time.
Step S42: and acquiring third image information with the article information from the monitoring video stream.
The lost article retrieval system acquires third image information having article information (target article information) of the lost article from the second image information library.
Step S43: and acquiring the image information with the acquisition time later than the latest acquisition time from the third image information as second image information.
The third image information is the image information containing the lost article, and the image information with the collection time later than the latest collection time is obtained from the third image information, namely the second image information is the image information when the lost article and the owner are separated and exist independently.
Step S34: and acquiring the lost positioning information of the lost article based on the second image information.
The lost article retrieving system determines lost positioning information of lost articles based on information such as time, place, image and the like after the articles are separated from the owner.
Alternatively, the present embodiment may implement step S34 by using the method shown in fig. 5. The method of the present embodiment includes steps S51 to S53.
Step S51: face information of the other person is recognized from the second image information.
The second image information does not contain owner information, namely, if the owner leaves the lost article, the retrieving system of the lost article acquires the face information of other people in the second image information.
Step S52: and acquiring image information which is acquired at a time later than the acquisition time of the first image information and has the face information of the other people as fourth image information in response to the fact that the distance between the face information of the other people and the lost object is smaller than the preset distance.
If the distance between the face information of the other people and the lost article is smaller than the preset distance, the finding and recovering system of the lost article determines that the other people pick up the lost article, and obtains the image information which is acquired at the latest acquisition time later than the first image information and has the face information of the other people so as to track the other people.
Step S53: and determining the lost positioning information of the lost article based on the second image information and the fourth image information.
For example, the position information of the lost article may be obtained from the second image information with the latest acquisition time, that is, the last frame image in which the lost article appears, and if the lost article is not found from the position, the other person may be tracked from the fourth image information, and the lost article may be found from the track of the other person.
On the basis of the above embodiment, the embodiment can track other people after the lost article is taken away by other people, so as to acquire the lost positioning information of the lost article, and can improve the efficiency and accuracy of finding the lost article.
The present application further provides another embodiment of a method for retrieving a lost article, as shown in fig. 6, the retrieving method of the present embodiment specifically includes the following steps:
step S61: and acquiring owner information and article information of the lost articles.
Step S61 is similar to step S31 and is not repeated here.
Step S62: target time and/or target location information is obtained.
Target time and/or target position information set by a user are obtained through an APP of the electronic equipment, and the target time and the target position are used for limiting the searching range of the lost articles.
Step S63: and acquiring image information with owner information from the monitoring video stream.
The image information with the owner information is obtained from the image information of the monitoring video stream, so that the data comparison amount can be reduced, and the efficiency of finding the lost articles can be improved.
Step S64: image information having article information is acquired from image information having owner information.
Step S65: and acquiring image information with acquisition time within the target time and/or acquisition position information consistent with the target position information from the image information with the owner information and the article information as first image information.
The finding system for the lost article filters the image information of which the acquisition time is not within the target time and/or the acquisition position information is inconsistent with the target position information from the image information with the owner information and the article information, can reduce the searching range of the lost article, and further can improve the finding efficiency of the lost article.
Step S66: and acquiring second image information which has article information and acquisition time later than that of the first image information from the monitoring video stream.
Step S66 is similar to step S33 and is not repeated here.
Step S67: and acquiring the lost positioning information of the lost article based on the second image information.
Step S67 is similar to step S34 and is not repeated here.
On the basis of the above embodiment, the present embodiment filters the image information whose acquisition time is not within the target time and/or whose acquisition position information is inconsistent with the target position information from the image information having the owner information and the article information by the limitation of the time information and the position information, so as to reduce the searching range of the lost article and further improve the retrieving efficiency of the lost article.
The present application further provides another embodiment of a method for retrieving a lost article, where owner information of the present embodiment includes face identification information, and article information includes article identification information, as shown in fig. 7, the retrieving method of the present embodiment specifically includes the following steps:
step S71: and carrying out face recognition and article recognition on the image frames of the monitoring video stream to obtain face information and/or article information in each image frame.
The lost article retrieving system performs face recognition on image frames of the monitoring video stream through a face detection model, such as a deep face model, a deep ID model or a faceNet model, and obtains face information, such as face ID, in each image frame; the system for retrieving lost articles identifies the articles in the image frames of the surveillance video stream by an article detection model, such as Proposal (including fast R-CNN and R-FCN), SSD, or Yolo, and obtains article information, such as article object ID, in each image frame.
Step S72: and establishing a mapping relation between the face information and the corresponding image frame, and storing the mapping relation in a first image information base.
The system for retrieving the lost articles can set a first sub-image information base for each face ID, store the face ID and the information of the image frame containing the face ID and the mapping relation between the face ID and the image frame, wherein the information of the image frame at least comprises image picture information, the acquisition time and the position information of the image frame and the like.
The first image information base comprises the first sub-image information base.
Step S73: and establishing a mapping relation between the article information and the corresponding image frame, and storing the mapping relation in a second image information base.
The system for retrieving the lost article sets a second sub-image information base for each article object, stores the ID of the article object, the information of the image frame containing the ID and the mapping relation between the ID and the image frame, and the information of the image frame at least comprises image picture information, the acquisition time and the position information of the image frame and the like.
The second image information repository comprises the second sub-image information repository.
In this embodiment, the image recognition of the surveillance video stream, the classified storage of the face information and the article information, and the like are realized through steps S71 to S73, so that the efficiency of retrieving the lost article can be improved.
Step S74: acquiring owner information and article information of lost articles;
reference may be made to the above examples for specific embodiments.
Step S75: target time and/or target location information is obtained.
Reference may be made to the above-described embodiments for specific implementations.
Step S76: a first image frame having face information is obtained from a first image information base.
The lost article retrieval system matches face information (target face information) input by a user with stored face information to acquire a first image frame with the face information.
Step S77: a second image frame having item information is obtained from a second image information store.
Step S78: and determining the first image frame or the second image frame with the face information and the object information as a target image frame.
The frame number or the image picture information of the first image frame with the face identification information can be matched with the frame number or the image picture information of the second image frame in the second image information base, if the frame numbers are the same or the image picture information is consistent, the first image frame and the second image frame have the face information and the object information at the same time, and the first image frame and the second image frame are determined to be the target image frame.
Step S79: and acquiring an image frame with acquisition time within the target time and/or acquisition position information consistent with the target position information from the target image frame as first image information.
Reference may be made to the above examples for specific embodiments.
Step S791: and acquiring target video information for retrieving the lost article from the monitoring video stream based on the first image information.
Reference may be made to the above examples for specific embodiments.
Step S792: and acquiring lost positioning information of the lost article based on the target video information.
Reference may be made to the above examples for specific embodiments.
On the basis of the above embodiments, the embodiment implements image recognition of the surveillance video stream, and classification storage of the face information and the article information, so that the acquisition and analysis of the surveillance video stream and the loss of the article are performed simultaneously, and the efficiency of retrieving the loss of the article can be improved.
The present application further provides another embodiment of a method for retrieving a lost article, as shown in fig. 8, the retrieving method of the present embodiment specifically includes the following steps:
step S81: first image information with owner information and object information is obtained from a monitoring video stream.
The lost article retrieving system performs face recognition on image frames of the monitoring video stream through a face detection model, such as a deep face model, a deep ID model or a faceNet model, and obtains face information, such as face ID, in each image frame; the system for retrieving lost articles identifies the articles in the image frames of the surveillance video stream by an article detection model, such as Proposal (including fast R-CNN and R-FCN), SSD, or Yolo, and obtains article information, such as article object ID, in each image frame.
There may be multiple face IDs in each image frame, including the owner's corresponding face ID.
Step S82: the relationship between the item owner information and the item information is identified based on the first image information.
As can be seen from the above analysis, the first image information includes both the owner information and the article information, and the distance between the owner information and the article information can be obtained from the first image to determine the relationship therebetween.
Step S83: and in response to the relationship being the attribution relationship, counting the separation duration of the owner and the article by taking the acquisition time of the first image information as a time starting point.
If the distance between the two is less than or equal to the preset distance (different according to the types of the articles), the finding system of the lost article determines that the relationship between the two is the attribution relationship, and if the distance between the two is greater than the preset distance, the finding system of the lost article determines that the two are separated. When the separation occurs, counting time, namely the separation time of the article and the owner, by taking the latest acquisition time of the plurality of first image information as a time starting point.
Step S84: and generating alarm information in response to the separation duration being greater than the preset duration.
If the separation time is longer than the preset time, the owner is considered to be away from the articles, namely the owner loses the articles, and the retrieving system of the lost articles generates alarm information.
The electronic equipment can report the alarm information to a management system of a park, a scenic spot or other management areas so as to broadcast the alarm information, or retrieve the alarm information from a face identity library according to the face information of the owner, and determine the identity and the contact way of the owner, so that the owner of the article can be actively contacted.
The embodiment can actively alarm after the articles are lost.
The present application further provides a system for retrieving a lost article, as shown in fig. 9, the system for retrieving a lost article of this embodiment includes: a video acquisition device 61 and an electronic device 62; the video acquisition device 61 is used for acquiring a monitoring video stream; the electronic device 62 is in communication with the video acquisition device 61 and is configured to acquire a surveillance video stream from the video acquisition device 61, acquire owner information and article information, and acquire first image information with the owner information and the article information from the surveillance video stream; the electronic equipment is used for acquiring target video information of the lost article from the monitoring video stream based on the first image information and acquiring lost positioning information of the lost article based on the target video information; or the electronic equipment is used for identifying the relation between the owner information and the article information based on the first image information, counting the separation duration of the owner and the article by taking the acquisition time of the first image information as a time starting point in response to the relation as an attribution relation, and generating alarm information in response to the separation duration being greater than a preset duration.
In an application scenario, all video capture devices 61 accessing the content of the managed area, such as a camera to an electronic device 62 (intelligent parsing platform), may access in a standard RTSP or national standard manner, the decoding operation is carried out by merging the real-time pictures of the camera, the decoding data is traditionally sent to an article detection model and a human face detection model for carrying out real-time decoding data on the article detection model, real-time detecting and identifying the articles in the picture, outputting data such as article name, time, position and the like, meanwhile, the human face detection model also analyzes the decoded data in real time, detects the human face, outputs information such as a human face snapshot picture, time, position, human face characteristic value and the like, outputs the structures of the object detection model and the human face detection model, respectively takes the object and the human face object as IDs (identity) to perform real-time database storage, and provides lost article searching capability for users.
When the backpack type searching system is used, an owner inputs the type of a lost article, such as a backpack, inputs a face photo of the owner, selects the time and position range to be searched, and starts searching; firstly, searching a picture range in which objects mainly appear by matching face search with time conditions and position conditions, then searching pictures in which objects appear in a corresponding picture range according to the time and position conditions in the content of the camera range, and sequencing picture results according to time sequence to see the positions and time of the objects and the objects together; then, the historical video pictures of the pictures and the time are called, so that the destination of the article can be known, and the owner can know the current position of the article through the video pictures, so that the article can be searched off-line.
In addition, the retrieving system for the lost articles can detect the independently existing articles and give a loss alarm to the articles.
If so, the finding system of the lost article detects the face and the article in the video picture in real time, and judges the person to which the article belongs according to the distance between the face and the article in the picture; when the person belonging to the article leaves the video picture, the article independently exists in the video picture and exceeds a certain time length, the finding system for the lost article generates an article loss alarm, and the face of the person belonging to the associated person of the article is searched in the face identity library according to the face information of the associated person, so that the identity and the contact way of the person can be determined, and the owner of the article can be actively contacted.
The system for retrieving lost articles is also used for implementing the above method for retrieving lost articles, and is not described herein.
As shown in fig. 10, the electronic device 62 of the present embodiment includes a processor 101, a memory 102 coupled to the processor 101, an input/output device 103, and a bus 104.
The processor 101, the memory 102, and the input/output device 103 are respectively connected to the bus 104, the memory 102 stores program instructions, and the processor 101 is configured to execute the program instructions to implement the above method for retrieving lost articles.
In this embodiment, the processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor 101 may be any conventional processor or the like.
The present application further provides a computer storage medium, as shown in fig. 11, fig. 11 is a schematic structural diagram of an embodiment of the computer storage medium of the present application. The computer storage medium 110 has stored thereon program instructions 111, and when executed by a processor (not shown), the program instructions 111 implement a method for retrieving a lost article.
The computer storage medium 110 of the embodiment may be, but is not limited to, a usb disk, an SD card, a PD optical drive, a removable hard disk, a high-capacity floppy drive, a flash memory, a multimedia memory card, a server, etc.
Different from the prior art, the method and the device for detecting the lost article information acquire owner information of the lost article and first image information of the article information from the monitoring video stream, and can determine information such as time, place and the like of the owner and the lost article; then, target video information for retrieving the lost article is obtained from the monitoring video stream based on the first image information, and the target video information obtains the lost positioning information of the lost article. Therefore, the lost article tracking system can realize the track tracking of the lost article based on the monitoring video stream, can automatically acquire the lost positioning information of the lost article, is convenient for an owner to timely retrieve the lost article, and can improve the retrieving efficiency of the lost article.
In addition, if the above functions are implemented in the form of software functions and sold or used as a standalone product, the functions may be stored in a storage medium readable by a mobile terminal, that is, the present application also provides a storage device storing program data, which can be executed to implement the method of the above embodiments, the storage device may be, for example, a usb disk, an optical disk, a server, etc. That is, the present application may be embodied as a software product, which includes several instructions for causing an intelligent terminal to perform all or part of the steps of the methods described in the embodiments.
In the description of the present application, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like is intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be viewed as implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device (e.g., a personal computer, server, network device, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions). For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
The above description is only an embodiment of the present application, and is not intended to limit the scope of the present application, and all equivalent structures or equivalent processes performed by the present application and the contents of the attached drawings, which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (13)
1. A method for retrieving a lost article, comprising:
acquiring owner information and article information of lost articles;
acquiring first image information with the owner information and the article information from a monitoring video stream;
acquiring target video information for retrieving the lost article from the monitoring video stream based on the first image information;
and acquiring the lost positioning information of the lost article based on the target video information.
2. The method as claimed in claim 1, wherein said obtaining target video information for retrieving the lost article from the surveillance video stream based on the first image information comprises:
and acquiring historical video streams with acquisition time later than that of the first image information from the monitoring video streams to serve as target video information of the lost articles.
3. The method for retrieving the lost article according to claim 1, wherein the obtaining the target video information for retrieving the lost article from the surveillance video stream based on the first image information comprises:
and acquiring second image information which has the article information and is acquired at a time later than the acquisition time of the first image information from the monitoring video stream to serve as target video information of the lost article.
4. The method as claimed in claim 1, wherein said obtaining the first image information with the owner information and the article information from the surveillance video stream comprises:
acquiring target time and/or target position information;
acquiring image information with the owner information from a monitoring video stream;
acquiring image information with the article information from the image information with the owner information;
and acquiring image information with acquisition time within the target time and/or acquisition position information consistent with the target position information from the image information with the owner information and the article information as first image information.
5. The method of claim 1, wherein the owner information comprises face information, and further comprising, before the acquiring the owner information and the article information of the lost article:
carrying out face recognition and article recognition on image frames of a monitoring video stream to obtain face information and/or article information in each image frame;
establishing a mapping relation between the face information and the corresponding image frame, and storing the mapping relation in a first image information base;
and establishing a mapping relation between the article information and the corresponding image frame, and storing the mapping relation in a second image information base.
6. The method as claimed in claim 5, wherein said obtaining the first image information with the owner information and the article information from the surveillance video stream comprises:
obtaining target time and/or target location information
Acquiring a first image frame with the face information from the first image information base;
acquiring a second image frame with the article information from the second image information base;
determining the first image frame or the second image frame with the face information and the article information as a target image frame;
and acquiring an image frame with acquisition time within the target time and/or acquisition position information consistent with the target position information from the target image frame as first image information.
7. The method as claimed in claim 3, wherein the step of obtaining the second image information with the article information and the capturing time later than the capturing time of the first image information from the surveillance video stream comprises:
acquiring the latest acquisition time of a plurality of pieces of first image information;
acquiring third image information with the article information from the monitoring video stream;
and acquiring image information with the acquisition time later than the latest acquisition time from the third image information as second image information.
8. The method of claim 1, wherein the obtaining the lost positioning information of the lost article based on the target video information comprises:
recognizing face information of other people except the owner from the target video information;
responding that the distance between the face information of the other people except the owner and the lost article is smaller than a preset distance, and acquiring image information which is acquired at a time later than the acquisition time of the first image information and comprises the face information of the other people except the owner as fourth image information;
and determining the lost positioning information of the lost article based on the fourth image information.
9. The method as claimed in claim 1, wherein after obtaining the first image information with the owner information and the article information from the surveillance video stream, and before obtaining the target video information for retrieving the lost article from the surveillance video stream based on the first image information, the method further comprises:
and identifying the relationship between the owner information and the article information as an attribution relationship based on the first image information.
10. A method for retrieving a lost article, comprising:
acquiring first image information with owner information and article information from a monitoring video stream;
identifying a relationship between the owner information and the item information based on the first image information;
in response to the relationship being an attribution relationship, taking the acquisition time of the first image information as a time starting point, and counting the separation duration of the owner and the article;
and responding to the condition that the separation time length is greater than the preset time length, and generating alarm information.
11. A system for retrieving a lost article, comprising:
the video acquisition device is used for acquiring a monitoring video stream;
the electronic equipment is communicated with the video acquisition device and is used for acquiring the monitoring video stream from the video acquisition device, acquiring owner information and article information and acquiring first image information with the owner information and the article information from the monitoring video stream; the electronic equipment is used for acquiring target video information for retrieving the lost article from the monitoring video stream based on the first image information and acquiring lost positioning information of the lost article based on the target video information; or alternatively
The electronic equipment is used for identifying the relation between the owner information and the article information based on the first image information, responding to the relation as an attribution relation, counting the separation duration of the owner and the article by taking the acquisition time of the first image information as a time starting point, and responding to the separation duration being greater than a preset duration to generate alarm information.
12. An electronic device, comprising: a processor, a memory coupled to the processor, the memory having stored therein program instructions for executing the program instructions to implement the method for retrieving lost articles of any of claims 1 to 10.
13. A computer storage medium having stored thereon program instructions which, when executed, implement the method of retrieving a lost article of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210418923.3A CN114926757A (en) | 2022-04-20 | 2022-04-20 | Method and system for retrieving lost article, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210418923.3A CN114926757A (en) | 2022-04-20 | 2022-04-20 | Method and system for retrieving lost article, electronic equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114926757A true CN114926757A (en) | 2022-08-19 |
Family
ID=82806905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210418923.3A Pending CN114926757A (en) | 2022-04-20 | 2022-04-20 | Method and system for retrieving lost article, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114926757A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497056A (en) * | 2022-11-21 | 2022-12-20 | 南京华苏科技有限公司 | Method for detecting lost articles in region based on deep learning |
| CN116912760A (en) * | 2023-06-25 | 2023-10-20 | 广东百德朗科技有限公司 | Internet of things data processing method and device, electronic equipment and storage medium |
-
2022
- 2022-04-20 CN CN202210418923.3A patent/CN114926757A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497056A (en) * | 2022-11-21 | 2022-12-20 | 南京华苏科技有限公司 | Method for detecting lost articles in region based on deep learning |
| CN116912760A (en) * | 2023-06-25 | 2023-10-20 | 广东百德朗科技有限公司 | Internet of things data processing method and device, electronic equipment and storage medium |
| CN116912760B (en) * | 2023-06-25 | 2024-03-22 | 广东百德朗科技有限公司 | Internet of things data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574506B (en) | Intelligent face pursuit system and method based on deep learning and large-scale clustering | |
| CN110852219B (en) | Multi-pedestrian cross-camera online tracking system | |
| TWI743835B (en) | Information processing method, device and storage medium thereof | |
| CN114926757A (en) | Method and system for retrieving lost article, electronic equipment and computer storage medium | |
| JP5576384B2 (en) | Data processing device | |
| CN105279480A (en) | Method of video analysis | |
| CN108875542B (en) | Face recognition method, device and system and computer storage medium | |
| US8266174B2 (en) | Behavior history retrieval apparatus and behavior history retrieval method | |
| KR20080075091A (en) | Storage of video analysis data for real-time alerting and forensic analysis | |
| JP2017033547A (en) | Information processing apparatus, control method therefor, and program | |
| CN111046235A (en) | Method, system, equipment and medium for searching acoustic image archive based on face recognition | |
| JP2022518459A (en) | Information processing methods and devices, storage media | |
| CN105808542B (en) | Information processing method and information processing apparatus | |
| CN109195011B (en) | Video processing method, device, equipment and storage medium | |
| US11200683B2 (en) | Image processing device and image processing method | |
| CN105279496A (en) | Human face recognition method and apparatus | |
| CN106294577A (en) | Figure chip detection method and device | |
| CN109963113B (en) | Method and device for monitoring interested target | |
| JP5733158B2 (en) | Recognition support device, recognition support method, and program | |
| CN114093014A (en) | Graph code correlation strength calculation method, device, equipment and storage medium | |
| CN110598551B (en) | Method, device, equipment and medium for improving pedestrian identity recognition efficiency | |
| JP2019185205A (en) | Information processor and information processing method and program | |
| Rahman et al. | Deep people detection: A comparative study of SSD and LSTM-decoder | |
| CN110991316B (en) | Method for automatically acquiring shape and identity information applied to open environment | |
| CN115393755A (en) | Visual target tracking method, device, equipment and storage medium |
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 |