CN109993045B - Article searching method, article searching device, article searching system and machine-readable storage medium - Google Patents

Article searching method, article searching device, article searching system and machine-readable storage medium Download PDF

Info

Publication number
CN109993045B
CN109993045B CN201810388308.6A CN201810388308A CN109993045B CN 109993045 B CN109993045 B CN 109993045B CN 201810388308 A CN201810388308 A CN 201810388308A CN 109993045 B CN109993045 B CN 109993045B
Authority
CN
China
Prior art keywords
article
information
target
searching
picture
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.)
Active
Application number
CN201810388308.6A
Other languages
Chinese (zh)
Other versions
CN109993045A (en
Inventor
胡景翔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision System Technology Co Ltd
Original Assignee
Hangzhou Hikvision System Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision System Technology Co Ltd filed Critical Hangzhou Hikvision System Technology Co Ltd
Publication of CN109993045A publication Critical patent/CN109993045A/en
Application granted granted Critical
Publication of CN109993045B publication Critical patent/CN109993045B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Television Signal Processing For Recording (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides an article searching method and device based on video, a searching system and a machine-readable storage medium, wherein the searching method comprises the following steps: identifying one or more items from a video captured by a camera device; storing article information of the identified article; when a search instruction of a target object sent by a client is received, the target object information matched with the search instruction is searched from the stored object information.

Description

Article searching method, article searching device, article searching system and machine-readable storage medium
Technical Field
The present application relates to image processing technologies, and in particular, to a method and an apparatus for searching for an item based on a video, a searching system, and a machine-readable storage medium.
Background
The current article Identification is realized based on Radio Frequency Identification (RFID) technology, and the specific principle is as follows: the radio frequency chip is arranged on the article, the identification code of the article and the information related to the article are recorded in the radio frequency chip, the identification code of the article recorded in the radio frequency chip can be identified by scanning the radio frequency chip through the scanning device, and finally the purpose of identifying the article is achieved.
The articles placed at fixed positions can be identified based on the radio frequency identification technology, but when the articles are lost or placed at the positions are forgotten, the articles can only be manually searched, and the efficiency of manual searching is not high.
Disclosure of Invention
In view of the above, the present application provides a video-based item searching method.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of the embodiments of the present invention, there is provided a video-based item searching method, including:
identifying one or more items from a video captured by a camera device;
storing article information of the identified article;
when a search instruction of a target article sent by a client is received, searching the target article information matched with the search instruction from the stored article information.
Optionally, the storing the item information of the identified item includes:
searching article information matched with the identified article combination description information from the stored article information by taking the identified article combination description information as a searching condition;
if not, storing the article information of the identified article;
if the article position of the identified article is found, judging whether the article position of the identified article is changed, if so, storing the article information of the identified article, and if not, replacing the article appearance time in the found article information with the latest article identification time and storing the latest article identification time.
Optionally, the determining whether the position of the identified article changes includes:
judging whether the identified coordinates of the article or the feature code of the article are the same as the coordinates of the article or the feature code of the article in the searched article information,
if not, determining that the position of the identified article is changed;
if so, it is determined that the location of the identified item has not changed.
Optionally, the searching for the target item information matched with the search instruction from the stored item information includes:
carrying out image recognition on the picture of the target object carried by the search instruction to acquire the description information of the target object;
and searching the target article information matched with the description information of the target article from the stored article information by taking the description information of the target article as a searching condition.
Optionally, the searching for the target item information matched with the search instruction from the stored item information includes:
and searching the target article information matched with the description information of the target article from the stored article information by taking the description information of the target article carried in the search instruction as a search condition.
Optionally, the method further comprises:
and feeding back the position information of the target object to the client according to the information of the target object.
Optionally, the feeding back the location information of the target item to the client according to the information of the target item includes:
acquiring a target picture according to the target article information, wherein the target picture is a picture showing the position of the target article;
and feeding back the target picture to the client.
Optionally, the obtaining a target picture according to the target article information includes:
acquiring picture storage path information from the target article information, wherein the picture storage path information represents the corresponding relation between the description information of the target article and a picture showing the position of the target article;
and acquiring a corresponding target picture from an article picture library according to the picture storage path information, wherein the article picture library stores a plurality of pictures for showing the positions of the articles, which are generated according to the video acquired by the camera equipment.
Optionally, the feeding back the target picture to the client includes:
and when a plurality of target pictures are available, feeding back the target pictures to the client according to a time reverse order.
Optionally, when a search instruction of a target item sent by a client is received, searching for target item information matched with the search instruction from stored item information includes:
when a search instruction which is sent by a client and carries a name of a target object and a name of an associated object is received, with the name of the target object and the name of the associated object as search conditions, searching object information respectively corresponding to the name of the target object and the name of the associated object from the object information;
and screening out the object information which contains the object with the object appearance time within a preset time interval and contains the same identification of the camera equipment from the searched object information, and taking the object information as the target object information matched with the search instruction.
Optionally, the method further includes:
positioning initial playback time according to the object occurrence time in the target object information matched with the search instruction;
and feeding back the video record after the initial playback time called from the stored video records to the client, wherein the stored video records are generated according to the video collected by the camera equipment.
Optionally, when a search instruction of a target item sent by a client is received, searching for target item information matched with the search instruction from stored item information includes:
when a plurality of continuous searching instructions of a target object sent by a client are received, target object information matched with the searching instructions is searched from stored object information for a plurality of times continuously, wherein the description information of the target object carried in each searching instruction is different, the positions of the camera devices corresponding to the camera device identifications in the description information of the target object in each searching instruction are adjacent, and the object occurrence time in the description information of the target object in each searching instruction is determined according to the video record fed back to the client.
Optionally, the searching for the target item information matched with the search instruction from the stored item information includes:
and with the description information of the target object carried in the search instruction as a search condition, searching the stored object information for object information which contains the camera equipment identifier adjacent to the camera equipment identifier corresponding to the acquired target object and contains description information except the camera equipment identifier of the target object, and taking the object information as the target object information.
Optionally, before the obtaining the target picture according to the target article information, the method further includes:
acquiring a regional map indicating the distribution position of each camera and the identification of each camera;
superposing the target picture on the area map, wherein the target picture is positioned near the distribution position of corresponding camera equipment for collecting target articles;
the feeding back the target picture to the client comprises:
and feeding back the regional map superposed with the target picture to the client.
Optionally, the search instruction carries a picture of a person associated with the target object, where the picture of the person is captured from a video record fed back to the client.
According to a second aspect of the embodiments of the present invention, there is provided a video-based item searching apparatus, the apparatus including:
the article identification unit is used for identifying one or more articles from the video acquired by the camera equipment;
an article information holding unit for holding article information of the identified article;
and the searching instruction receiving unit is used for searching the target article information matched with the searching instruction from the stored article information when receiving the searching instruction of the target article sent by the client.
Optionally, the apparatus further comprises:
and the article picture library storage unit is used for storing a plurality of pictures for showing the positions of the articles, which are generated according to the videos collected by the camera equipment.
According to a third aspect of the embodiments of the present invention, there is provided a video-based item searching system, including: the camera shooting device is used for sending the collected video to the article searching device.
According to a fourth aspect of embodiments of the present invention, there is provided a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method described above.
According to the technical scheme, the object in the video is identified according to the collected video, the object information of the object is stored, and further, when the target object is searched, the target object information matched with the search instruction can be information related to the target object, useful information can be provided for object searching, and compared with manual searching, the object searching efficiency can be improved.
Drawings
FIG. 1 is a flow chart of a video-based item finding method shown in an exemplary embodiment of the present application;
FIG. 2 is a flow chart of a video-based item finding method according to yet another exemplary embodiment of the present application;
FIG. 3 is a flow chart of a video-based item finding method according to another exemplary embodiment of the present application;
FIG. 4 is a flow chart of a video-based item finding method shown in yet another exemplary embodiment of the present application;
FIG. 5 is a flow chart of a video-based item finding method according to another exemplary embodiment of the present application;
fig. 6 is a schematic diagram of a region map indicating distribution positions of respective image capturing apparatuses and identifications of the respective image capturing apparatuses according to an exemplary embodiment of the present application;
FIG. 7 is a block diagram of a video-based item search apparatus, according to another exemplary embodiment of the present application;
FIG. 8 is a diagram of a hardware configuration of a server according to another exemplary embodiment of the present application;
fig. 9 is a block diagram of a video-based item search system according to another exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
With the development of the camera technology and the image recognition technology, the camera equipment is widely applied, for example, the camera equipment can be deployed in a studio, a home, a factory, a market, and the like, video acquisition is performed by using the camera equipment, and a video acquisition function of the camera equipment is used.
As shown in fig. 1, the method for searching for an article according to an embodiment of the present invention includes the following steps:
step S10, identifying one or more articles from the video collected by the camera device;
the image pickup apparatus refers to an apparatus having a video capture function, for example, a video camera, or the like.
The camera device can collect images, an individual image can be called as a frame image, the frame image can be regarded as a static picture, a series of continuous frame images form a video, the camera device usually collects the images continuously, the continuously collected frame images form a video code stream after being coded, the video code stream can be transmitted to the server, and the server can decode the video code stream to obtain the frame images.
The camera shooting equipment can be deployed in required sites, for example, various sites such as a family living space, an office site, a public site and the like, specific positions and quantity of the camera shooting equipment can be deployed according to actual needs, one camera shooting equipment can be deployed at a proper position when the site occupied space is small, if the site occupied space is large or complicated, a plurality of camera shooting equipment can be deployed at a plurality of positions, for example, a plurality of camera shooting equipment are deployed at a plurality of positions and in a plurality of directions such as conference rooms, offices and corridors of the office site, and videos collected by the camera shooting equipment can be sent to the server.
The camera device can collect videos in real time, wherein the real time does not mean every moment, the camera device continuously collects the videos according to the self collection frequency, the collected videos comprise frames of images, and the frames of images are images of scene pictures at every moment in the visual angle range collected by the camera device.
The image may include various articles, for example, a person, a mobile phone, a cup, a mouse, a chair, a file bag, a pen, and the like, and each frame of image in the video may be identified by an image identification algorithm to identify one or more articles in the image, where the type of the identifiable article is related to the image identification algorithm used.
Step S11, the item information of the identified item is saved.
The method comprises the steps that article information of each article can be obtained by identifying the article in the video, wherein the article information is information related to the article and comprises the name of the article, the appearance time of the article, personalized information of the article, coordinates of the article (the coordinates of the article in an image), a feature code of the article, an identification of a camera device (such as an ID (identification) of camera identification) and the like, and the personalized information of the article refers to the brand and model of the article or packaging information of the article, ornament information of the article and the like; the article appearance time refers to the appearance time of the current position of the article in the image of the video, and the appearance time can be determined according to the time stamp of each frame of image acquired by the camera device.
The article appearance time may be a time when an article appears in the image for the first time or a time when the article does not appear in the image for the first time, for example, when an article appears in the scene of the camera device for the first time, the article is identified in a frame of image of the video captured by the camera device, the time when the article is identified for the first time is the article appearance time, if the article continuously exists in the scene, the article is identified until the article moves out of the scene, the time when the article is identified for the second time is also the article appearance time, and when the article is identified for a plurality of times, the article appearance time is updated each time, the article appearance time that has been stored when the article was identified before is replaced by the time when the article is identified for the latest time when the article is identified for the plurality of times, therefore, the article appearance time in the article information of the stored article is the latest time of the article in the video, and the article is convenient to search.
And step S12, when a search instruction of the target item sent by the client is received, searching the target item information matched with the search instruction from the stored item information.
The terminal can be provided with a client, and a search instruction of the target object can be input at the client.
The client can be realized in an APP (application) mode or an SDK (Software Development Kit) mode, and the realization mode is not limited. The terminal may include various terminals such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, and the like.
The search instruction may carry related information of the target item, for example, a name, a model, a brand, and the like of the target item, and may be used as a keyword to search the stored item information for item information that matches the information of the target item, where the searched item information is target item information, and the target item information is item information related to the target item.
The target article information matched with the search instruction may be article information including related information in the search instruction in the article information, or may be fuzzy-matched with the related information to search for the article information related to the related information, and a specific matching manner is not limited in this embodiment.
According to the technical scheme, the object is identified according to the collected video, the object information of the object is stored, and further, when the object is searched, the object information matched with the searching instruction can be the information related to the object, useful information can be provided for object searching, and compared with manual searching, the object searching efficiency can be improved.
In an alternative embodiment, as shown in fig. 2, the storing the item information of the identified item in step S11 may include:
step 111, with the combination description information of the identified article as a search condition, searching article information matched with the description information of the identified article from the stored article information;
step 112, if not, storing the article information of the identified article;
and 113, if the article position of the identified article is found, judging whether the article position of the identified article is changed, if so, storing the article information of the identified article, and if not, replacing the article appearance time in the found article information with the latest article identification time and storing the latest article identification time.
In the process of capturing a video by the camera device, a new article may appear in a scene within the view angle range of the camera device, and for the identified new article, because the stored article information does not include information about the new article, the article information of the new article needs to be stored, in this embodiment, according to the combination description information of the identified article as a search condition, the description information may include at least one of the article information, the combination description information may include at least two of the camera device identifier (camera device ID), the article name, and the personalized information of the article, if a single description information is used as the search condition, there may be a similar article that is the same as one description information, which causes inaccurate search, so that an error may exist in the stored article information, and therefore, in this embodiment, the article information matching the combination description information is searched from the stored article information by using the combination description information as the search condition, if the article is not found, the new article is identified, and the article information of the article is stored. And if the position of the identified article is found, further judging whether the article position of the identified article is changed.
In the process of video acquisition, if an article is in a static state within a certain time period, and in the time period when the article is in the static state, because the position of the article does not change, when the article is identified, if the article information of the article identified at each moment is stored, a large amount of repeated data is generated, in order to avoid repeated data, when the position of the identified article changes, the article information of the identified article is stored, and if the position of the identified article does not change, only the article appearance time in the searched article information needs to be replaced by the latest identified article time to store the replaced article information of the article, namely, the article appearance time in the article information of the article which is stored before is updated to the latest article identification time, that is, the time of identifying the article from the current image is taken as the article appearance time to store the updated article information of the article, so that the data volume of the article information can be reduced, the searching speed can be improved, and the data storage space can be reduced.
As to whether the position of the identified article is changed or not in the above step S113, in some alternative embodiments, the position may be determined by:
step S1131, determining whether the identified coordinates of the article or the feature code of the article are the same as the coordinates of the article or the feature code of the article in the stored article information,
step S1132, if the positions of the identified articles are different, determining that the positions of the identified articles are changed;
and step S1133, if the position of the identified article is the same, determining that the position of the identified article is not changed.
The feature code of the article refers to a value obtained through an image recognition algorithm and used for representing the feature of the article, the feature value is, for example, a feature vector obtained by abstracting the detail of the article to a macroscopic feature through a deep learning neural network recognition method, and the feature value can more accurately represent the recognized article and has relative uniqueness.
When a video is collected, in a time period when the article is in a static state, the feature codes of the article identified at each moment are the same, when the position of the article is changed, the calculated feature codes of the article are also changed, and the feature codes are different for different articles, so that when the feature codes of the identified article are judged to be different from the feature codes of the articles in the stored article information, the position of the identified article can be determined to be changed; otherwise, it is determined that the location of the identified item has not changed.
The coordinates of the object refer to the coordinates of the object in the image, one image is usually composed of a plurality of pixel points arranged in a matrix, the pixel point at the upper left corner of the image can be used as an original point, other pixel points and the original point have relative positions, and the relative position of the pixel point is the coordinate of the pixel point. Or using a certain point of the pixel points contained in the article or the pixel point at the center position of the article as the coordinates of the article in the image, or using the coordinates of the pixel points contained in the article as a group of data, and using the group of data as the coordinates of the article in the image.
When the identified coordinates of the article are judged to be different from the coordinates of the article in the stored article information, the position of the identified article can be determined to be changed; otherwise, it is determined that the location of the identified item has not changed.
It should be noted that the above descriptions are not exactly the same, and a certain error range is allowed.
In an alternative embodiment, the target item may be searched in two ways:
in the first mode, searching for a picture of a target article carried in the search instruction, that is, searching in a picture mode, and the above-mentioned searching for target article information matched with the search instruction from stored article information may include:
step S121, carrying out image recognition on the picture of the target object carried by the search instruction, and acquiring the description information of the target object;
and step S122, with the description information of the target object as a searching condition, searching the object information matched with the description information of the target object from the object information.
The picture containing the target object may be input at the client, so that when the picture containing the target object is carried in the search instruction, at this time, the picture containing the target object may be subjected to image recognition by an image recognition algorithm to obtain description information of the target object, where the description information of the target object may include: the name of the target object, the model of the target object, the brand of the target object and the like can be obtained through image recognition.
And after the description information of the target object is obtained, the object information matched with the description information of the target object is searched from the object information by taking the description information as a searching condition.
In a second manner, the searching for at least one kind of description information of the target object carried in the search instruction, that is, the searching is performed in a manner of text information of the target object, and the searching for the target object information matched with the search instruction from the stored object information may include:
and step S123, searching the target article information matched with the description information of the target article from the stored article information by taking the description information of the target article carried in the search instruction as a search condition.
The text of the description information of the target object can be input at the client, for example, the name of the target object, the model of the target object, the brand of the target object and the like are input, so that the description information is carried in the search instruction, and the target object information matched with the description information of the target object is searched from the object information by taking the description information as a search condition.
The difference between the text information searching mode and the picture searching mode is that when the picture searching mode is used, the content of the object which cannot be described by the text information can be obtained by utilizing image recognition, for example, the target object is a cup with a special shape, after the searching instruction carries the picture containing the target object, the feature code of the target object can be recognized by a deep learning neural network recognition method, the feature code of the target object can reflect the shape, the color and the detail information of the object, the feature code of the target object is further used for searching from the stored object information, the similarity calculation is carried out by using the feature code of the target object, so that the corresponding target object information is found, and the accuracy of the object searching can be improved. When the characteristic code of the target object cannot be obtained through character searching, the name, the model, the brand and the like of the target object are usually searched, and because the searching instruction directly carries the description information of the target object and does not need image recognition, the searching speed is relatively high, and if the target object is an uncommon object, the position information of the target object can be accurately searched.
In an alternative embodiment, as shown in fig. 3, after the step S12, the method may further include:
and step S13, feeding back the position information of the target item to the client according to the target item information.
The position information of the target object is obtained based on the target object information, and the position information may be various, for example, the object appearance time in the target object information, the identification of the camera device, and other related information capable of determining the object position may be fed back to the client, for example, the camera device for collecting the target object may be known through the identification of the camera device, and the camera device has an installation position and a visual angle for collecting a video, and accordingly, after being fed back to the client, a user may know that the target object is located within the visual angle range of the camera device, and then determine the position of the target object; or the appearance time of the target object in the visual angle range of the camera equipment can be obtained through the appearance time of the target object and the identification of the camera equipment, so that the position of the target object and the time of the object at the position are judged, and after the position information of the target object is fed back to the client, the user can obtain the position of the target object and further search the target object.
In an alternative embodiment, as shown in fig. 4, the feeding back the location information of the target item to the client according to the target item information in step S13 above may include:
s131, acquiring a target picture according to the target article information, wherein the target picture is a picture showing the position of the target article;
and step S132, feeding back the target picture to the client.
The article information is generated according to an article identified in a video acquired by the camera equipment, the article information can include article description information, and a corresponding relation between the article description information and a picture showing the position where the article is located is established, namely a mapping relation between the article description information and the picture showing the position where the article is located is established, so that a target picture can be obtained according to the target article information.
The picture showing the position of the article is a picture generated according to each frame of image in the video acquired by the image pickup device, the image pickup device can acquire the image of a scene picture in real time, if the article exists in the picture and is identified, the description information of the article can be acquired at this time, the image containing the image of the article is stored as the picture, the picture containing the image of the article can represent the scene where the article exists, that is, the position where the article exists, such as the position of the article in the scene, the condition of the scene where the article exists, the surrounding environment in the scene where the article exists, and the like can be shown.
The generated corresponding relationship between the description information of the object and the corresponding picture showing the position where the object is located can be stored in the object information, and the target object information is a record which is searched from the object information and is matched with the description information of the target object, so that the corresponding picture showing the position where the target object is located can be obtained through the target object information and then fed back to the client.
In this embodiment, the position information of the target object fed back to the client is a picture showing the position of the target object, and the user can visually know the position of the target object by observing the picture, so that the target object can be conveniently found, and the efficiency of finding the object by the user is improved.
In some optional embodiments, the obtaining the target picture according to the target item information in step S131 may include:
step S1311, obtaining picture storage path information from the target article information, wherein the picture storage path information represents a corresponding relation between description information of the target article and a picture showing a position where the target article is located;
step 1312, acquiring a corresponding target picture from an article picture library according to the picture storage path information, wherein the article picture library stores a plurality of pictures of positions where the article is present, the pictures being generated according to the video acquired by the camera equipment.
In this embodiment, the image data representing the position of the article occupies a larger storage space, the article information is text data, and the occupied storage space is smaller, so that the article information and the image representing the position of the article can be respectively stored in different positions, the image data and the text data are stored in a classified manner, which is beneficial to reasonable allocation and utilization of the storage space, and the article information can contain image storage path information, and a corresponding target image can be obtained from an article image library through the storage path information, such as a link address, and the storage path information can be linked to the article image library through the link address to obtain the corresponding target image.
In some examples, when the obtained target picture is multiple, the target picture may be fed back to the client in reverse time order.
As can be seen from the above description, when the target picture is obtained according to the target item information, there may be multiple pieces of target item information that are queried, and therefore, each piece of target item information may be obtained correspondingly to one target picture, or one piece of target item information may be obtained correspondingly to multiple target pictures. The target pictures are generated according to the acquired frame images, the frame images are acquired and generated sequentially according to the time sequence, so the target pictures generated according to the frame images also have the time sequence and are also generated sequentially according to the time sequence, when the target pictures are returned, the target pictures are fed back to the client in a time reverse mode, namely according to the sequence of the target picture generation time (the acquisition time of the target pictures) from late to early, the latest generated target picture is returned first, the earliest generated picture is returned last, so that when the target pictures are displayed on the client, the target picture arranged at the forefront is generated latest, and the target picture arranged at the rearmost is generated earliest, thereby not only being beneficial to acquiring the latest position of the target object, facilitating the search of the target object, but also being beneficial to knowing the position change condition of the target object according to the time, the user is facilitated to search for the item.
In an alternative embodiment, as shown in fig. 5, when receiving a search instruction of a target item sent by a client in step S12, the searching for target item information matching the search instruction from stored item information may include:
step S124, when a search instruction which is sent by a client and carries the name of the target object and the name of the related object is received, the name of the target object and the name of the related object are used as search conditions, and object information corresponding to the name of the target object and the name of the related object respectively is searched from the object information;
and step S125, screening out the object information which contains the object with the object appearance time within the preset time interval and has the same camera equipment identification from the searched object information, and using the object information as a target information record matched with the search instruction.
When identifying an article from a video, one or more articles can be identified, and article information of the article can be obtained, where the article information may include, for example, a name of the article, a model of the article, a brand of the article, and the like, if the identified article is a common article, for example, an image pickup apparatus is installed in an office, and in an office of the office, there are a large number of duplicate articles, for example: if the stored article information of the identified article only comprises the name of the article, when a target article (for example, a mobile phone) is searched according to a search instruction, all the information of the mobile phone which is identified by the camera equipment and appears in the camera equipment can be searched, and finally a large amount of position information of the mobile phone is obtained, and the noise of the position information is high, and after the position information is fed back to a client, a user needs to manually screen and obtain the position information of the required target article, so that the article searching efficiency is low.
For the unique articles or the articles with lower repetition rate, the information of the target articles can be searched quickly by searching the article names, and the position information of the target articles can be determined.
When the similar articles with high repetition rate are searched, the articles can be searched according to the personalized information of the articles, such as the brand of the articles, the model of the articles, the packaging information of the articles, the ornament information of the articles and the like, and the personalized information of the articles is carried in the searching instruction, so that the searching efficiency can be improved.
When searching for similar articles with a high repetition rate, the other method is to search for articles of the same kind with a high repetition rate in a combined searching manner in this embodiment, where the name of the target article and the name of the associated article are carried in the search instruction, and the article associated with the target article refers to an article appearing in the same image as the target article at the same time or within a certain time period, for example, the article to be searched is a mobile phone, and there are other articles around the mobile phone, for example, a water cup, and at this time, the information carried in the search instruction is the mobile phone and the water cup.
And respectively taking the name of the target object and the name of the associated object as keywords to search the object information, searching the object information corresponding to the name of the target object and the name of the associated object, and then screening again according to the object appearance time and the camera equipment identification in the object information to screen out the object information which is contained in the object information and has the same object appearance time in a preset time interval and contains the same camera equipment identification.
Each frame of image in the video collected by the same camera device in the preset time interval is an image containing a target article and a related article, and the screened article information is the article information obtained according to the images, so that the range of the article information to be searched can be reduced through a combined searching mode, the number of matched target article information is reduced, the position information of the target article is obtained more accurately, and the searching efficiency is improved.
In addition to the above-mentioned combined search according to the name of the target item and the name of the associated item, the combined search may also be performed in other manners, for example, as shown in fig. 6, if the user can determine that the target item to be searched is a, and can determine the position where the target item to be searched a appears, for example, a meeting room b, and determine the image capturing device corresponding to the position according to the position where the target item a appears (meeting room b), for example, the image capturing device 2 in the meeting room b, and the item information may include the image capturing device identifier, when searching for the target item, the name of the target item (any description information such as the model or brand of the target item) and the image capturing device identifier may be carried in the search instruction, and the name of the target item a and the identifier of the image capturing device 2 are taken as the search condition, the corresponding target item information is searched from the item information, where the target item information includes both the name of the target item a and the identifier of the camera device 2 in the search instruction, and then the location information of the target item is obtained according to the searched target item information, which may also achieve the purpose of narrowing the range of the searched item information, and certainly, two or more description information of the target item may also be combined and searched as the search condition, which is not limited in this embodiment.
In an alternative embodiment, as shown in fig. 5, the method may further include the steps of:
step S126, positioning the initial playback time according to the object occurrence time in the target object information matched with the search instruction;
and S127, feeding back the video record after the initial playback time called from the stored video record to the client, wherein the stored video record is generated according to the video collected by the camera equipment.
In this embodiment, the object occurrence time in the target object information screened according to the above embodiment is used to locate the initial playback time, where the object occurrence time is also the occurrence time of an image of the target object in the video and is also the time that includes the video of the target object and is acquired by the camera device, and there may be multiple pieces of target object information, so that there may be multiple object occurrence times, and any time in multiple times may be used as the initial playback time, and the video recording after the initial playback time is retrieved from the stored video recording.
It should be noted that the method for feeding back the video to the client may be performed after various searching manners, and is not limited to the method illustrated in fig. 5 after step 125.
In an optional implementation manner, before the obtaining the target picture according to the target item information in step S131, the method further includes:
step S1301, acquiring a regional map indicating the distribution position of each image capture apparatus and the identifier of each image capture apparatus;
step S1302, superposing a target picture on an area map, wherein the target picture is positioned near the distribution position of corresponding camera equipment for collecting a target article;
the step S132 of feeding back the target picture to the client includes: and feeding back the area map superposed with the target picture to the client.
In the present embodiment, as shown in fig. 6, a region map, for example, the region map shown in fig. 6, which shows an office space including an office area and a meeting room a, a meeting room b, and a meeting room c, and in which the distribution positions of the image pickup apparatuses 1 to 15 provided in the office space are shown, and the identification of each image pickup apparatus, for example, the numbers 1 to 15, is marked, may be further acquired, and the acquired target pictures (for example, the picture t1 to the picture t3) may be superimposed on the region map, and each target picture may be located in the vicinity of the distribution position of the image pickup apparatus corresponding to the acquisition target item, for example, the picture t1 is located in the vicinity of the image pickup apparatus 2, the picture t2 is located in the vicinity of the image pickup apparatus 7, and the picture t3 is located in the vicinity of the image pickup apparatus 11, so that the distribution positions of the image pickup apparatus and the image pickup apparatus corresponding to the position where the target item is present may be more intuitively known, helping to know the destination of the target object.
In an optional embodiment, when receiving the search instruction of the target item sent by the client in step S12, searching for the target item information matching the search instruction from the stored item information includes:
when a plurality of continuous searching instructions of the target object sent by the client are received, target object information matched with the searching instructions is searched from the stored object information for a plurality of times continuously, wherein the description information of the target object carried in each searching instruction is different, the positions of the camera devices corresponding to the camera device identifications in the description information of the target object in each searching instruction are adjacent, and the object occurrence time in the description information of the target object in each searching instruction is determined according to the video record fed back to the client.
In an alternative embodiment, the step S12 of searching for the target item information matching the search instruction from the stored item information includes:
and with the description information of the target object carried in the search instruction as a search condition, searching for object information which contains the camera device identifier adjacent to the position corresponding to the camera device identifier of the acquisition target object and contains description information except the camera device identifier of the target object from the stored object information, wherein the object information is used as the target object information, and the description information except the camera device identifier of the target object can be other related information in the description information of the target object, such as the name of the target object, the personalized information of the target object, and the like.
In this embodiment, the search instruction may be continuously input multiple times at the client, the target object information may be searched multiple times through the multiple search instruction, after the object is searched, the user may determine, by observing the video record fed back to the client, the camera device corresponding to the object when the video record disappears and the time when the target object disappears in the video record, in order to further track the destination of the object, the target object may be tracked and searched, and further obtain the position information of the target object, centering on the position where the camera device corresponding to the object when the video record disappears is located, and searching for the target object according to the time when the target object disappears in the video record.
For example, referring to fig. 6, when it is determined that the corresponding image capturing apparatus when the target article disappears is the image capturing apparatus 4 in the figure, and the time of disappearance is 8:00, the above disappearance time, the name of the target article, and the identifier of the above image capturing apparatus 4 are carried in the search instruction, and accordingly, the article information is searched, the article information includes the name of the target article and the identifier of the image capturing apparatus adjacent to the position corresponding to the identifier of the image capturing apparatus 4 (for example, if the image capturing apparatus 1 and the image capturing apparatus 5 in fig. 6 are adjacent to the position corresponding to the image capturing apparatus 4, the identifier of the image capturing apparatus adjacent to the position corresponding to the identifier of the image capturing apparatus 4 is the identifier of the image capturing apparatus 1 and the identifier of the image capturing apparatus 5), and the article information whose article appearance time is after the above disappearance time, the searched article information is used as the matched, the searched target article information includes article information of a target article generated according to a video acquired by the camera device 1 and article information of the target article generated according to a video acquired by the camera device 5, that is, target article information corresponding to each camera device adjacent to a position corresponding to the camera device 4 is searched by taking a position corresponding to the camera device 4 as a center, and then position information of the target article is acquired according to the target article information, a user can judge whether the target article is position information of the target article to be searched according to the position information of the target article fed back to a client, and can judge that the position information of the target article to be searched is generated according to the video acquired by the camera device, for example, the target article is the camera device 5 and then further searched again, and when the target article is searched again, an image pickup device identifier carried by a search instruction is different from an image pickup device identifier carried by a previous search instruction, the image pickup device identifier (for example, the identifier of the image pickup device 5 shown in fig. 6) adjacent to the image pickup device position corresponding to the image pickup device identifier carried in the previous search instruction is searched, the same as the previous search method is used when searching again, the searched article information includes the name of the target article and the image pickup device identifier adjacent to the position corresponding to the identifier of the image pickup device 5 (for example, if the image pickup device 6 in fig. 6 is adjacent to the position corresponding to the image pickup device 5, the image pickup device identifier adjacent to the position corresponding to the identifier of the image pickup device 5 is the identifier of the image pickup device 6), the searched target article information includes the article information of the target article generated according to the video collected by the image pickup device 6, that is, when searching again, the target article information corresponding to the image pickup device 6 adjacent to the position corresponding to the image pickup device 5 is searched with the position corresponding to the image pickup, then the position information of the target object is obtained according to the target object information, the user can judge whether the position information of the target object is the position information of the target object to be searched again according to the position information of the target object fed back to the client, the searching process can be continuously repeated for a plurality of times, the positions of the camera devices corresponding to the camera device identification in the searching instruction are adjacent, and the corresponding position of the camera equipment identification carried in the current searching instruction is used as the center for searching each time, searching the target object step by step according to the position correlation of the camera equipment until the position of the target object appearing last is determined according to the fed back position information of the target object, therefore, in this embodiment, the position change trajectory of the target object can be determined by multiple continuous searches, the direction of the target object is known, and the search efficiency is improved.
In the above embodiment, there may be multiple ways to acquire the camera device identifiers adjacent to the position corresponding to the camera device identifier of the acquisition target article, for example, the article information may include geographic positions of the camera devices, and whether the camera device identifiers are adjacent to each other is determined according to distances between the geographic positions corresponding to the camera devices, or the article information stores the camera device identifiers adjacent to the position corresponding to the camera device identifier in advance, which is not limited in this embodiment.
In an optional implementation manner, the search instruction carries a picture of a person associated with the target object, and the picture of the person is captured from a video record fed back to the client.
In the embodiment, after the video recording is fed back to the client, the user can observe the video recording, when the target object is found to be hidden, for example, a person may be found to be in a pocket or bag, at which point the user may capture a picture of the person from a video recording, the picture of the person may be a picture of a face or may include a picture of the entire body, the picture of the person may be entered into the client, the search instruction may carry the picture of the person, and then the feature code of the person can be obtained from the picture containing the person through an image recognition algorithm, then the characteristic code of the person is taken as a searching condition to obtain the information of the target object matched with the characteristic code of the person so as to obtain the information of the person, or, the tracking search is performed in a manner of multiple continuous searches in the above embodiment, the direction of the target object can be tracked by tracking the person.
Corresponding to the embodiment of the video-based item searching method, the application also provides an embodiment of a video-based item searching device.
Referring to fig. 7, the video-based item searching apparatus 1 includes:
an article identification unit 10 for identifying one or more articles from a video captured by a camera device;
an article information storage unit 11 for storing article information of the identified article;
the search instruction receiving unit 12 is configured to, when a search instruction of a target item sent by a client is received, search target item information matched with the search instruction from stored item information.
The above article searching device further comprises:
and the article picture library storage unit 13 is used for storing a plurality of pictures for showing the positions of the articles, which are generated according to the videos collected by the camera equipment.
The embodiment of the article searching device can be applied to the server.
In an optional embodiment, the article information storage unit may be specifically configured to:
searching article information matched with the identified article combination description information from the stored article information by taking the identified article combination description information as a searching condition;
if not, storing the article information of the identified article;
if the article position of the identified article is found, judging whether the article position of the identified article is changed, if so, storing the article information of the identified article, and if not, replacing the article appearance time in the found article information with the latest article identification time and storing the latest article identification time.
Further, the article information storage unit, wherein the judging whether the position of the identified article has changed, includes:
judging whether the identified coordinates of the article or the feature code of the article are the same as the coordinates of the article or the feature code of the article in the searched article information,
if not, determining that the position of the identified article is changed;
if so, it is determined that the location of the identified item has not changed.
The search instruction receiving unit may be specifically configured to:
carrying out image recognition on the picture of the target object carried by the search instruction to acquire the description information of the target object;
and searching the target article information matched with the description information of the target article from the stored article information by taking the description information of the target article as a searching condition.
Or the search instruction receiving unit may be specifically configured to: and searching the target article information matched with the description information of the target article from the stored article information by taking the description information of the target article carried in the search instruction as a search condition.
The above apparatus may further include:
and the position information feedback unit is used for feeding back the position information of the target object to the client according to the information of the target object.
The position information feedback unit may specifically be configured to:
acquiring a target picture according to the target article information, wherein the target picture is a picture showing the position of the target article;
and feeding back the target picture to the client.
The obtaining of the target picture according to the target article information in the position information feedback unit includes:
acquiring picture storage path information from the target article information, wherein the picture storage path information represents the corresponding relation between the description information of the target article and a picture showing the position of the target article;
and acquiring a corresponding target picture from an article picture library according to the picture storage path information, wherein the article picture library stores a plurality of pictures for showing the positions of the articles, which are generated according to the video acquired by the camera equipment.
The feeding back the target picture to the client in the position information feedback unit includes:
and when a plurality of target pictures are available, feeding back the target pictures to the client according to a time reverse order.
The search instruction receiving unit may be further configured to:
when a search instruction which is sent by a client and carries a name of a target object and a name of an associated object is received, with the name of the target object and the name of the associated object as search conditions, searching object information respectively corresponding to the name of the target object and the name of the associated object from the object information;
and screening out the object information which contains the object with the object appearance time within a preset time interval and contains the same identification of the camera equipment from the searched object information, and taking the object information as the target object information matched with the search instruction.
Further, the search instruction receiving unit may be further configured to:
positioning initial playback time according to the object occurrence time in the target object information matched with the search instruction;
and feeding back the video record after the initial playback time called from the stored video records to the client, wherein the stored video records are generated according to the video collected by the camera equipment.
The search instruction receiving unit may be further configured to:
when a plurality of continuous searching instructions of a target object sent by a client are received, target object information matched with the searching instructions is searched from stored object information for a plurality of times continuously, wherein the description information of the target object carried in each searching instruction is different, the positions of the camera devices corresponding to the camera device identifications in the description information of the target object in each searching instruction are adjacent, and the object occurrence time in the description information of the target object in each searching instruction is determined according to the video record fed back to the client.
The searching for the target article information matched with the search instruction from the stored article information in the search instruction receiving unit includes:
and with the description information of the target object carried in the search instruction as a search condition, searching the stored object information for object information which contains the camera equipment identifier adjacent to the camera equipment identifier corresponding to the acquired target object and contains description information except the camera equipment identifier of the target object, and taking the object information as the target object information.
The position information feedback unit may further be configured to:
before the target picture is obtained according to the target article information:
acquiring a regional map indicating the distribution position of each camera and the identification of each camera;
superposing the target picture on the area map, wherein the target picture is positioned near the distribution position of corresponding camera equipment for collecting target articles;
the feeding back the target picture to the client comprises:
and feeding back the regional map superposed with the target picture to the client.
The search instruction in the search instruction receiving unit carries a picture of a person associated with the target object, wherein the picture of the person is captured from a video record fed back to the client.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a device in a logical sense, the device is formed by reading corresponding computer program instructions in the non-volatile memory into the memory for running through a processor of the server applied to the article searching device. From a hardware aspect, as shown in fig. 8, a hardware structure diagram of a server where the article search device is located is shown, except for the processor, the memory, the external interface, and the nonvolatile memory shown in fig. 8, the server where the device is located in the embodiment may also include other hardware according to an actual function, which is not described again.
An embodiment of the present invention further provides a video-based item searching system, as shown in fig. 9, the system includes: the system comprises a camera device 2 and the article searching device 1 in the embodiment, wherein the camera device 2 is used for sending a collected video to the article searching device 1.
Embodiments of the present invention also provide a machine-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to perform any one of the methods described in the above embodiments.
In one embodiment, a machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and so forth. For example, the machine-readable storage medium may be: a RAM (random Access Memory), a volatile Memory, a non-volatile Memory, a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., an optical disk, a dvd, etc.), or similar storage medium, or a combination thereof.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims (16)

1. A video-based item searching method is characterized by comprising the following steps:
identifying one or more items from a video captured by a camera device;
storing article information of the identified article;
when a search instruction of a target article sent by a client is received, searching the target article information matched with the search instruction from the stored article information;
when a search instruction of a target article sent by a client is received, searching the target article information matched with the search instruction from the stored article information, including:
when a search instruction which is sent by a client and carries a name of a target object and a name of an associated object is received, with the name of the target object and the name of the associated object as search conditions, searching object information respectively corresponding to the name of the target object and the name of the associated object from the object information;
and screening out the object information which contains the object with the object appearance time within a preset time interval and contains the same identification of the camera equipment from the searched object information, and taking the object information as the target object information matched with the search instruction.
2. The method of claim 1, wherein said saving item information for the identified item comprises:
searching article information matched with the identified article combination description information from the stored article information by taking the identified article combination description information as a searching condition;
if not, storing the article information of the identified article;
if the article position of the identified article is found, judging whether the article position of the identified article is changed, if so, storing the article information of the identified article, and if not, replacing the article appearance time in the found article information with the latest article identification time and storing the latest article identification time.
3. The method of claim 2, wherein the determining whether the location of the identified item has changed comprises:
judging whether the identified coordinates of the article or the feature code of the article are the same as the coordinates of the article or the feature code of the article in the searched article information,
if not, determining that the position of the identified article is changed;
if so, it is determined that the location of the identified item has not changed.
4. The method of claim 1, further comprising:
and feeding back the position information of the target object to the client according to the information of the target object.
5. The method according to claim 4, wherein the feeding back the location information of the target item to the client according to the target item information comprises:
acquiring a target picture according to the target article information, wherein the target picture is a picture showing the position of the target article;
and feeding back the target picture to the client.
6. The method according to claim 5, wherein the obtaining a target picture according to the target item information comprises:
acquiring picture storage path information from the target article information, wherein the picture storage path information represents the corresponding relation between the description information of the target article and a picture showing the position of the target article;
and acquiring a corresponding target picture from an article picture library according to the picture storage path information, wherein the article picture library stores a plurality of pictures for showing the positions of the articles, which are generated according to the video acquired by the camera equipment.
7. The method according to claim 5 or 6, wherein the feeding back the target picture to the client comprises:
and when a plurality of target pictures are available, feeding back the target pictures to the client according to a time reverse order.
8. The method of claim 1, further comprising:
positioning initial playback time according to the object occurrence time in the target object information matched with the search instruction;
and feeding back the video record after the initial playback time called from the stored video records to the client, wherein the stored video records are generated according to the video collected by the camera equipment.
9. The method according to claim 8, wherein when receiving a search instruction of a target item sent by a client, searching for target item information matching the search instruction from stored item information, further comprising:
when a plurality of continuous searching instructions of a target object sent by a client are received, target object information matched with the searching instructions is searched from stored object information for a plurality of times continuously, wherein the description information of the target object carried in each searching instruction is different, the positions of the camera devices corresponding to the camera device identifications in the description information of the target object in each searching instruction are adjacent, and the object occurrence time in the description information of the target object in each searching instruction is determined according to the video record fed back to the client.
10. The method according to claim 9, wherein the searching for the target item information matching the search instruction from the stored item information comprises:
and with the description information of the target object carried in the search instruction as a search condition, searching the stored object information for object information which contains the camera equipment identifier adjacent to the camera equipment identifier corresponding to the acquired target object and contains description information except the camera equipment identifier of the target object, and taking the object information as the target object information.
11. The method according to claim 5 or 6,
before the obtaining of the target picture according to the target article information, the method further includes:
acquiring a regional map indicating the distribution position of each camera and the identification of each camera;
superposing the target picture on the area map, wherein the target picture is positioned near the distribution position of corresponding camera equipment for collecting target articles;
the feeding back the target picture to the client comprises:
and feeding back the regional map superposed with the target picture to the client.
12. The method of claim 8, wherein the search instruction carries a picture of a person associated with the target item, wherein the picture of the person is captured from a video recording fed back to the client.
13. A video-based item searching device, comprising:
the article identification unit is used for identifying one or more articles from the video acquired by the camera equipment;
an article information holding unit for holding article information of the identified article;
the searching instruction receiving unit is used for searching the target article information matched with the searching instruction from the stored article information when receiving the searching instruction of the target article sent by the client;
wherein, the search instruction receiving unit is further configured to:
when a search instruction which is sent by a client and carries a name of a target object and a name of an associated object is received, with the name of the target object and the name of the associated object as search conditions, searching object information respectively corresponding to the name of the target object and the name of the associated object from the object information;
and screening out the object information which contains the object with the object appearance time within a preset time interval and contains the same identification of the camera equipment from the searched object information, and taking the object information as the target object information matched with the search instruction.
14. The lookup device as claimed in claim 13 further comprising:
and the article picture library storage unit is used for storing a plurality of pictures for showing the positions of the articles, which are generated according to the videos collected by the camera equipment.
15. A video-based item searching system, comprising: a camera device for sending captured video to an item finding apparatus as claimed in claim 13 or 14.
16. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to perform the method of any of claims 1-15.
CN201810388308.6A 2017-12-29 2018-04-26 Article searching method, article searching device, article searching system and machine-readable storage medium Active CN109993045B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2017114723851 2017-12-29
CN201711472385 2017-12-29

Publications (2)

Publication Number Publication Date
CN109993045A CN109993045A (en) 2019-07-09
CN109993045B true CN109993045B (en) 2021-02-26

Family

ID=67128353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810388308.6A Active CN109993045B (en) 2017-12-29 2018-04-26 Article searching method, article searching device, article searching system and machine-readable storage medium

Country Status (1)

Country Link
CN (1) CN109993045B (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113099162B (en) * 2019-12-20 2022-07-01 杭州海康威视数字技术股份有限公司 Logistics video evidence obtaining method, device and system and storage medium
CN111143596A (en) * 2019-12-31 2020-05-12 维沃移动通信有限公司 Article searching method and electronic equipment
CN111401325A (en) * 2020-04-21 2020-07-10 英华达（上海）科技有限公司 System and method for quickly searching for articles
CN111565301B (en) * 2020-05-25 2021-09-14 珠海格力电器股份有限公司 Indoor monitoring method, device and system, storage medium and camera device
CN111783628A (en) * 2020-06-29 2020-10-16 珠海格力电器股份有限公司 Position tracking method and device, electronic equipment and storage medium
CN112132076A (en) * 2020-09-28 2020-12-25 天津天地伟业智能安全防范科技有限公司 Forgotten object addressing method based on computer vision
CN112652013A (en) * 2021-01-21 2021-04-13 济南浪潮高新科技投资发展有限公司 Camera object finding method based on deep learning
CN113269828B (en) * 2021-04-25 2023-07-18 青岛海尔空调器有限总公司 Method and device for searching articles, air conditioning equipment and storage medium
CN113822133A (en) * 2021-07-16 2021-12-21 青岛海尔科技有限公司 Data processing method, system, device and computer readable storage medium
CN115017365A (en) * 2022-05-23 2022-09-06 北京声智科技有限公司 Article searching method, device, server, terminal and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8410927B2 (en) * 2006-11-14 2013-04-02 TrackThings LLC Apparatus and method for finding a misplaced object using a database and instructions generated by a portable device
CN105516656A (en) * 2015-11-27 2016-04-20 上海博康智能信息技术有限公司 Article real condition viewing method and system
CN105919307A (en) * 2016-06-29 2016-09-07 盒子派（北京）智能科技有限公司 Intelligent storage device and storage system
CN106294558A (en) * 2016-07-26 2017-01-04 北京小米移动软件有限公司 Object positioning method and device
CN106877911A (en) * 2017-01-19 2017-06-20 北京小米移动软件有限公司 Search the method and device of article
CN107477971A (en) * 2017-08-04 2017-12-15 三星电子（中国）研发中心 A kind of management method and equipment to food in refrigerator
CN107480129A (en) * 2017-07-18 2017-12-15 上海斐讯数据通信技术有限公司 A kind of article position recognition methods and the system of view-based access control model identification and speech recognition

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6456234B1 (en) * 2000-06-07 2002-09-24 William J. Johnson System and method for proactive content delivery by situation location

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8410927B2 (en) * 2006-11-14 2013-04-02 TrackThings LLC Apparatus and method for finding a misplaced object using a database and instructions generated by a portable device
CN105516656A (en) * 2015-11-27 2016-04-20 上海博康智能信息技术有限公司 Article real condition viewing method and system
CN105919307A (en) * 2016-06-29 2016-09-07 盒子派（北京）智能科技有限公司 Intelligent storage device and storage system
CN106294558A (en) * 2016-07-26 2017-01-04 北京小米移动软件有限公司 Object positioning method and device
CN106877911A (en) * 2017-01-19 2017-06-20 北京小米移动软件有限公司 Search the method and device of article
CN107480129A (en) * 2017-07-18 2017-12-15 上海斐讯数据通信技术有限公司 A kind of article position recognition methods and the system of view-based access control model identification and speech recognition
CN107477971A (en) * 2017-08-04 2017-12-15 三星电子（中国）研发中心 A kind of management method and equipment to food in refrigerator

Also Published As

Publication number Publication date
CN109993045A (en) 2019-07-09

Similar Documents

Publication Publication Date Title
CN109993045B (en) Article searching method, article searching device, article searching system and machine-readable storage medium
KR101535579B1 (en) Augmented reality interaction implementation method and system
US9805331B2 (en) Smartphone-based asset management system
CN111046235B (en) Method, system, equipment and medium for searching acoustic image archive based on face recognition
GB2554515A (en) Providing relevant video scenes in response to a video search query
CN111638796A (en) Virtual object display method and device, computer equipment and storage medium
US20200202158A1 (en) Methods and systems for detecting and analyzing a region of interest from multiple points of view
KR101841180B1 (en) Place-based image organization
WO2012064532A1 (en) Aligning and summarizing different photo streams
CN101662584A (en) Information processing apparatus and method and computer program
CN105808542B (en) Information processing method and information processing apparatus
KR101738443B1 (en) Method, apparatus, and system for screening augmented reality content
US11120263B1 (en) Method and apparatus for providing education service using satellite imagery based on artificial intelligence
Patel et al. The contextcam: Automated point of capture video annotation
Zhang et al. Multi-video summary and skim generation of sensor-rich videos in geo-space
CN108697934A (en) Guidance information related with target image
CN104486585A (en) Method and system for managing urban mass surveillance video based on GIS
CN105159959A (en) Image file processing method and system
WO2015096427A1 (en) Method and system for locating and searching surveillance video
GB2517944A (en) Locating objects using images from portable devices
CN114416905A (en) Article searching method, label generating method and device
CN110049180A (en) Shoot posture method for pushing and device, intelligent terminal
JP6505242B2 (en) Cluster-based photo navigation
Chen et al. Low-cost asset tracking using location-aware camera phones
WO2023093480A1 (en) Species touring method and system, and readable 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
GR01 Patent grant
GR01 Patent grant