CN113111354A - Target retrieval method and system, terminal device, cloud server, medium and device - Google Patents
Target retrieval method and system, terminal device, cloud server, medium and device Download PDFInfo
- Publication number
- CN113111354A CN113111354A CN202010027267.5A CN202010027267A CN113111354A CN 113111354 A CN113111354 A CN 113111354A CN 202010027267 A CN202010027267 A CN 202010027267A CN 113111354 A CN113111354 A CN 113111354A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- target
- feature
- structured data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000012545 processing Methods 0.000 claims abstract description 64
- 230000008569 process Effects 0.000 claims description 20
- 238000007906 compression Methods 0.000 claims description 13
- 230000006835 compression Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 230000006837 decompression Effects 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 238000005538 encapsulation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013144 data compression Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses a target retrieval method and system, terminal equipment, a cloud server, a medium and equipment, wherein the method comprises the following steps: processing the acquired target image through the first model to obtain structured data; determining model related information corresponding to the first model; generating encrypted data based on the structured data and the model-related information; sending the encrypted data to a cloud server; in the embodiment, because the structured data is reported to the cloud server instead of the original snapshot picture or video stream, the occupation of bandwidth is reduced; the use of cloud server resources is reduced, the cost is saved, and the retrieval efficiency is improved; and, because the structured data does not include specific target information, the safety and the privacy of the target data are ensured.
Description
Technical Field
The present disclosure relates to computer vision technologies, and in particular, to a target retrieval method and system, a terminal device, a cloud server, a medium, and a device.
Background
Object retrieval refers to a process in which a particular object (or one type of object) identifies an object corresponding thereto from among a plurality of objects (or a plurality of types of objects). The main target retrieval method at present is that a front-end acquisition device captures a target picture and uploads the target picture to a server for identification and retrieval, and with the large-scale use of target retrieval, front-end intelligent devices are increasingly popularized, and more pictures are uploaded to the server or a cloud, which puts great requirements on bandwidth and server resources.
Disclosure of Invention
The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a target retrieval method and system, terminal equipment, a cloud server, a medium and equipment.
According to an aspect of the embodiments of the present disclosure, there is provided a target retrieval method applied to a terminal device, including:
processing the acquired target image through the first model to obtain structured data;
determining model related information corresponding to the first model;
generating encrypted data based on the structured data and the model-related information;
and sending the encrypted data to a cloud server.
According to another aspect of the embodiments of the present disclosure, there is provided a target retrieval method applied to a cloud server, including:
receiving encrypted data sent by terminal equipment;
determining structured data and model-related information based on the encrypted data; the structured data is obtained by processing a target image corresponding to a first model, and the model-related information corresponds to the first model;
determining a feature database corresponding to the structured data based on the model-related information;
and retrieving the record data corresponding to the target from the feature database based on the structured data.
According to still another aspect of the embodiments of the present disclosure, there is provided a terminal device including:
the image processing module is used for processing the acquired target image through the first model to obtain structured data;
the information determining module is used for determining model related information corresponding to the first model provided by the image processing module;
the data generation module is used for generating encrypted data based on the structured data obtained by the image processing module and the model related information determined by the information determination module;
and the data sending module is used for sending the encrypted data obtained by the data generating module to a cloud server.
According to still another aspect of the embodiments of the present disclosure, there is provided a cloud server, including:
the data receiving module is used for receiving encrypted data sent by the terminal equipment;
the data analysis module is used for determining the structured data and the relevant information of the model based on the encrypted data received by the data receiving module; the structured data is obtained by processing a target image corresponding to a first model, and the model-related information corresponds to the first model;
the database searching module is used for determining a feature database corresponding to the structured data based on the model related information determined by the data analyzing module;
and the data matching module is used for retrieving the record data corresponding to the target from the characteristic database determined by the database searching module based on the structural data determined by the data analyzing module.
According to still another aspect of the embodiments of the present disclosure, there is provided a target retrieval system including: the cloud server according to the above embodiment and at least one terminal device according to the above embodiment.
According to another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the object retrieval method according to the above-described embodiments.
According to still another aspect of an embodiment of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the target retrieval method described in the foregoing embodiment.
Based on the target retrieval method and system, the terminal device, the cloud server, the medium and the device provided by the embodiment of the disclosure, the acquired target image is processed through the first model to obtain structured data; determining model related information corresponding to the first model; generating encrypted data based on the structured data and the model-related information; sending the encrypted data to a cloud server; in the embodiment, because the structured data is reported to the cloud server instead of the original snapshot picture or video stream, the occupation of bandwidth is reduced; the use of cloud server resources is reduced, the cost is saved, and the retrieval efficiency is improved; and, because the structured data does not include specific target information, the safety and the privacy of the target data are ensured.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 is a block diagram of a target retrieval system according to an exemplary embodiment of the present disclosure.
Fig. 2 is a schematic flow chart of a target retrieval system implementing target retrieval according to another exemplary embodiment of the present disclosure.
Fig. 3 is a flowchart illustrating a target retrieval method according to an exemplary embodiment of the disclosure.
Fig. 4 is a flowchart illustrating a target retrieval method according to another exemplary embodiment of the present disclosure.
Fig. 5 is a schematic flow chart of step 301 in the embodiment shown in fig. 3 of the present disclosure.
Fig. 6 is a flowchart illustrating a target retrieval method according to yet another exemplary embodiment of the present disclosure.
Fig. 7 is a schematic flow chart of step 603 in the embodiment shown in fig. 6 of the present disclosure.
Fig. 8 is a schematic flow chart of step 6033 in the embodiment shown in fig. 7 of the present disclosure.
Fig. 9 is a schematic structural diagram of a terminal device according to an exemplary embodiment of the present disclosure.
Fig. 10 is a schematic structural diagram of a terminal device according to another exemplary embodiment of the present disclosure.
Fig. 11 is a schematic structural diagram of a cloud server according to an exemplary embodiment of the present disclosure.
Fig. 12 is a schematic structural diagram of a cloud server according to another exemplary embodiment of the present disclosure.
Fig. 13 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.
Detailed Description
Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing an associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
The disclosed embodiments may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as terminal devices, computer systems, servers, and the like, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above systems, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Summary of the application
In the process of implementing the present disclosure, the inventors found that, in the prior art, by performing horizontal capacity expansion, increasing server resources, and enhancing processing performance of a cloud in a cluster deployment manner, more terminal devices are supported to access, but this technical scheme has at least the following problems: unlimited capacity expansion can lead to cost increase and lower cost performance.
Exemplary System
The target retrieval system provided by the disclosure comprises a terminal device for performing data acquisition and calculation and a cloud server for retrieval, wherein the data acquisition and calculation of the terminal device is realized by an intelligent device with AI capability, such as an intelligent network camera, a panel machine, a vehicle-mounted device and the like, the target in a target area is detected, tracked and captured, a target picture with good quality (for example, when the target is a human face, the quality of the human face can include whether the target picture is a front face, a shielding area, image definition and the like) is selected preferably, then a deep learning algorithm is used for extracting target attributes, target key points and target characteristic information from the captured picture, optionally, when the target is a human face, the attributes of the human face comprise information such as gender, age, skin color and the like (the attributes such as gender, age and the like can be used for retrieval, and classified storage and display can be performed according to the attributes in the storage process), the face key points comprise position information of a face key region, such as a nose, eyebrows, a mouth, eyes and the like (the function of identifying the face key points is to store information), and the face feature vector is a representation of a face high-dimensional space, which can be 256-dimension or 128-dimension and the like, and is used for comparison and retrieval of the face. Then, packaging the target attribute, the target key point and the target characteristic information according to a structure which can be identified by the cloud server (format packaging enables the cloud server to be identified), packaging the target attribute, the target key point and the target characteristic information into a structured message, and compressing and encrypting the structured message, wherein the structured message also comprises identification model (which can be a neural network) version information used by equipment, and the model version can be associated with a characteristic library of the cloud server; different types of terminal equipment are accessed to the cloud server through the cloud data access layer, and the terminal equipment can report the generated structured data to the cloud server through the access platform for retrieval; the cloud retrieval is used for extracting information such as target characteristics, model versions and identification types (types set in terminal equipment) in the structured data by decompressing and decrypting the structured data, selecting corresponding retrieval services according to the identification types, selecting corresponding characteristic libraries according to the model versions, performing retrieval comparison in the characteristic libraries by using the target characteristic information, and outputting the identification results.
In the embodiment of the disclosure, since the terminal device reports the structured data instead of the original snapshot or video stream, the utilization of bandwidth is reduced, and since the structured data does not contain specific face information, the safety and privacy of the face data are ensured; according to the embodiment of the disclosure, a part of calculation is carried out on the terminal equipment, so that the cost of the cloud server is reduced; the terminal equipment and the cloud server are interacted through the model version, the cloud server can be communicated with the terminal equipment of different identification models, and the same feature library in the cloud server can be retrieved by the terminal equipment of different types only by using the identical identification model; the target retrieval system provided by the embodiment of the disclosure can be applied to the identification of various articles, such as: the face, the human body, the commodity, the license plate and the like can be identified and retrieved by accessing the terminal equipment to the cloud server as long as the terminal equipment integrates the corresponding identification model and the cloud server has a retrieval library of the corresponding model.
FIG. 1 is a block diagram of a target retrieval system according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the target retrieval system may be divided into a device side (including at least one terminal device 11) and a cloud side (including a cloud server 12); in the process of implementing target retrieval by the target retrieval system, the functions of the terminal device 11 and the cloud server 12 include the following:
the terminal device 11 has detection, tracking and snapshot recognition capabilities through an embedded AI chip and an integrated target (e.g., human face, etc.) recognition model, and may include, but is not limited to, the following types: the intelligent snapshot camera, the intelligent panel machine, the intelligent vehicle-mounted equipment and the like.
The terminal device captures the target in the target area, extracts the target attribute, the key point and the characteristic, generates the structured data and uploads the structured data to the cloud.
And the cloud server at the cloud end analyzes the structured data reported by the terminal equipment and selects a corresponding feature library according to the model version used by the terminal equipment.
The cloud server stores feature libraries of different model versions, and the model version used by the feature library needs to be specified when the feature library is registered, and the model version needs to be specified when the feature library is searched.
And comparing the target characteristic information reported by the terminal equipment with the target records in the corresponding characteristic library for calculation, and finding out the most similar target record.
Fig. 2 is a schematic flow chart of a target retrieval system implementing target retrieval according to another exemplary embodiment of the present disclosure. The target retrieval system mainly comprises two parts, namely a device end and a cloud end, and as shown in fig. 2, the target retrieval process comprises the following steps:
201: the terminal equipment detects and tracks the target in the target area through the embedded AI chip and the AI chip to obtain the tracking track of the target.
The AI chip may execute a deep learning algorithm to detect a target (e.g., face detection) appearing in the target area to determine a position of the target, and may obtain a tracking trajectory of the target according to the target position obtained by multiple detections, thereby implementing tracking of the target.
202: the terminal equipment takes a snapshot of the detected and tracked target based on the tracking track of the target, and preferably selects one or a group of snapshot pictures with better quality; among them, the preference may include, but is not limited to: screening a plurality of images to obtain images with better quality, wherein the quality comprises but is not limited to: image definition, a ratio of objects in the image, and the like, for example, when the object is a human face, the image quality may further include: whether it is a face or not.
203: the terminal equipment extracts target attributes, key points and features from the snapshot picture based on a deep learning algorithm integrated on the terminal equipment.
204: when the terminal equipment reports data, the types of the identification models currently integrated by the terminal equipment are reported to the cloud server together, and the cloud server selects different services according to the identification types to process the data reported by the terminal equipment.
The terminal devices (each terminal device can integrate a plurality of recognition models) can recognize different targets by integrating different types of recognition models, for example, the integrated face recognition model can recognize faces, the integrated human body model can recognize human bodies, and the integrated vehicle model can recognize vehicles.
205: marking the integrated model of the current terminal equipment through the model version identification; when the terminal equipment reports data, the model version number information needs to be reported, and the cloud server is associated with the feature library according to the model version number.
Different terminal devices have great difference in performance and computing power, so that models integrated by different terminal devices can be different, a terminal device with strong performance can integrate a model with larger computing power, a terminal device with weak performance can integrate a model with smaller computing power, and the model is continuously updated in an iterative manner (updated according to the updating of the model in the cloud server).
206: and packaging, encrypting and compressing the data such as the structured data, the model version information and the identification type calculated in the step 203, and uploading the data to a cloud server.
207: the terminal equipment establishes connection with the cloud server through a relevant protocol and uploads encrypted data generated on the terminal equipment to the cloud server; the cloud data access layer is a universal data access platform, the device can be accessed into the cloud server as long as the device meets the requirements of relevant protocols and passes relevant authorization authentication, and the cloud server can manage and maintain the state of the terminal device.
208: decompressing and decrypting the data reported by the terminal equipment to obtain structured data, and selecting corresponding retrieval service according to the identification type in the structured data; in the cloud server, each type of retrieval corresponds to one service, and messages reported by each terminal device are balanced into different retrieval services according to the type.
209: and inputting the structure into corresponding services (such as human face retrieval service, human body retrieval service, commodity retrieval service, and the like) according to the identification type.
210: when the terminal device reports data to retrieve, the face library to be retrieved is determined according to the face library name (each terminal device corresponds to at least one face library) associated with the terminal device and the model version number information on the terminal device.
When creating a feature library (for example, in fig. 2, a human face is taken as a retrieval target, the feature library is a human face library, and the human face is taken as a retrieval target in the following description), the cloud server needs to specify a model version corresponding to features in the feature library, and needs to specify a model version during retrieval, where retrieval parameters and thresholds corresponding to different model versions are different.
211: a cloud server face library is uniquely identified by the face library name and the model version number, and the library to be searched needs to be found according to the face library name and the model version number during searching; the face features extracted from different models are very different, so that marking a face library not only needs to designate the name of the face library but also needs to designate the model version number corresponding to the face features in the face library.
212: the features to be retrieved are compared with the features in the face library to be retrieved to find out the record with the minimum distance, and whether the minimum distance is smaller than a threshold value or not can be judged, and the record with the minimum distance is used as a retrieval result.
Exemplary method
Fig. 3 is a flowchart illustrating a target retrieval method according to an exemplary embodiment of the disclosure. The embodiment can be applied to a terminal device, as shown in fig. 3, and includes the following steps:
The target object can be obtained through a camera device arranged on the terminal equipment, and optionally, a target image is processed by utilizing a deep learning algorithm to obtain structured data; for example, the structured data may be obtained by the process shown in steps 201-203 in the embodiment provided in FIG. 2.
In an embodiment, referring to the technical content shown in step 204 in the embodiment provided in fig. 2, a plurality of recognition models are integrated in each terminal device, and the first model may be any one of the plurality of recognition models. In this embodiment, it is necessary to determine the relevant information of the first model for implementing the processing on the target image, for example, the relevant information of the first model is the type information of the first model, and the type information of the model may include, but is not limited to: a face recognition model, a human body recognition model, etc.
Optionally, in the embodiment, as shown in step 206 in the embodiment provided in fig. 2, the manner of obtaining the encrypted data may be implemented by, for example: and packaging, encrypting, compressing and the like to obtain encrypted data.
In the implementation, only partial processing is performed on the acquired target image in the terminal device, the processed encrypted data is sent to the cloud server, and through the processing in the steps, the size of data transmitted between the terminal device and the cloud server is reduced, the transmission efficiency is improved, and the processing pressure of the cloud server is reduced.
According to the target retrieval method provided by the embodiment of the disclosure, the acquired target image is processed through the first model to obtain structured data; determining model related information corresponding to the first model; generating encrypted data based on the structured data and the model-related information; sending the encrypted data to a cloud server; in the embodiment, because the structured data is reported to the cloud server instead of the original snapshot picture or video stream, the occupation of bandwidth is reduced; the use of cloud server resources is reduced, the cost is saved, and the retrieval efficiency is improved; and, because the structured data does not include specific target information, the safety and the privacy of the target data are ensured.
Fig. 4 is a flowchart illustrating a target retrieval method according to another exemplary embodiment of the present disclosure. The embodiment can be applied to a terminal device, as shown in fig. 4, and includes the following steps:
Each terminal device corresponds to one feature library name, and each feature library name corresponds to a plurality of feature libraries, so that the feature library name can be determined under the condition that the terminal device is known; determining the model type (such as a human face recognition model or a human body recognition model) through the recognition of the first model; the determination of the model version identifier may refer to the technical content shown in step 205 in the embodiment provided in fig. 2, the model is continuously updated iteratively in the terminal device, different model version identifiers are obtained after each update, and the model integrated by the current terminal device is marked by the model version identifier.
And step 3022, determining model related information corresponding to the first model based on the feature library name, the model type, and the model version identifier.
3031, carrying out format encapsulation on the structured data, the name of the feature library, the model type and the model version identification according to a set format to obtain encapsulated data with the set format.
The set format corresponds to the identification format of the cloud server.
The purpose of the encapsulation in this embodiment is to make the cloud server recognizable, and therefore, the structured data, the feature library name, the model type, and the model version identifier are encapsulated into a format recognizable by the cloud server by format encapsulation, thereby avoiding the occurrence of a situation in which data content cannot be recognized due to a format problem.
The data compression is a technical method for reducing the data volume to reduce the storage space and improve the transmission, storage and processing efficiency of the data on the premise of not losing useful information, or reorganizing the data according to a certain algorithm to reduce the redundancy and storage space of the data; data compression includes lossy compression and lossless compression. The embodiment can compress the encapsulated data by any compression method in the prior art. The encryption processing proposed in this embodiment may be any encryption manner in the prior art, for example, key encryption (e.g., symmetric encryption, asymmetric encryption, etc.), and the embodiments of this application do not limit the specific compression and encryption techniques.
In the embodiment, the bandwidth occupied by the packaged data and the space occupied by the packaged data in the cloud server are reduced through compression processing, the data transmission efficiency is improved, the processing performance of the cloud server does not need to be enhanced, and the processing cost is reduced; the data security is enhanced by the encryption process. In addition, in this embodiment, because different terminal devices have great differences in performance and computational power, models integrated by different terminal devices may be different, a terminal device with strong performance may integrate a model with larger computational power, and a terminal device with weak performance may integrate a model with smaller computational power; therefore, when the terminal equipment reports the data, the types of the identification models currently integrated by the terminal equipment are reported to the cloud server together, and the cloud server selects different services according to the identification types to process the data reported by the terminal equipment.
As shown in fig. 5, based on the embodiment shown in fig. 3, step 301 may include the following steps:
in step 3011, a first model is determined from at least one model included in the terminal device.
The model of different model types carries out different processing on the target image.
Optionally, each model corresponds to a model type, which may include, but is not limited to: the human face recognition model can realize the recognition of human faces, the human body recognition model can realize the recognition of human bodies, and the vehicle recognition model can realize the recognition of vehicles.
In this embodiment, a deep learning algorithm integrated on the terminal device is used to extract target attributes, key points, and features from the snapshot, and optionally, the structured data may include target attributes, key point information, and the like in addition to the target features.
In some optional embodiments, the method provided in this embodiment further includes:
in response to the detection of the model version updating request, updating the version of the corresponding second model according to the model version updating request;
and storing the updated model version identification, sending the updated model version identification to the cloud server, and updating the feature database in the cloud server.
In this embodiment, the model is continuously updated iteratively, and after the template version in the terminal device is updated according to the version update request, the updated model version identifier may be obtained, and at this time, the feature database in the cloud server still corresponds to the model version identifier before update, so that the updated model version identifier needs to be sent to the cloud server, and a feature database obtained by processing the model corresponding to the updated model version identifier is obtained, and all features in the feature database are obtained based on the updated model.
In some optional embodiments, the method provided in this embodiment further includes:
acquiring an image or video comprising a target; and carrying out target area detection and quality screening on at least one frame of video image in the image or video to obtain a target image.
In this embodiment, in order to implement the retrieval of the target, a target image needs to be obtained first, and optionally, an image or a video including the target may be acquired by an image acquisition device in the terminal device, so as to implement the detection and tracking of the target in the target area; in order to improve the efficiency of subsequent target retrieval, high-quality display of the target in the obtained target image is required, and optionally, one or a group of images with better quality are obtained as the target image through quality screening, wherein the quality evaluation may include but is not limited to: definition, target proportion, etc.
Fig. 6 is a flowchart illustrating a target retrieval method according to yet another exemplary embodiment of the present disclosure. The embodiment can be applied to a cloud server, as shown in fig. 6, and includes the following steps:
step 601, receiving the encrypted data sent by the terminal equipment.
Optionally, in a process of receiving the encrypted data by the cloud server, as shown in step 207 in the embodiment provided with reference to fig. 2, the terminal device establishes a connection with the cloud server through a relevant protocol and uploads the encrypted data generated on the terminal device to the cloud server.
Based on the encrypted data, structured data and model related information are determined, step 602.
The structured data is obtained by processing the target image corresponding to the first model, and the model related information corresponds to the first model.
Optionally, since the encrypted data is generated by compression and encryption in the terminal device, the structured data and the model-related information corresponding to the encrypted data can be obtained by corresponding decompression and decryption; the decompression method adopted in this embodiment corresponds to the compression processing method in the foregoing embodiment, for example, in step 3032, the encrypted data is decompressed by the corresponding decompression method through lossless compression; the decryption method adopted in this embodiment corresponds to the encryption processing method in the above embodiment, for example, the step 3032 encrypts the data by using a symmetric key, and the embodiment decrypts the encrypted data by using a key (the same as the encryption key).
Step 603, determining a feature database corresponding to the structured data based on the model-related information.
The cloud server comprises a plurality of feature databases, the feature data recorded in each feature database can be used for processing the image for the corresponding model to obtain the face features, each feature database corresponds to different models, before the target retrieval is carried out through the structured data, firstly, which feature database needs to be determined for retrieval, the feature database is determined through the relevant information of the model, wherein the relevant information of the model can comprise the type information of the model and the like.
And step 604, retrieving the recorded data corresponding to the obtained target from the feature database based on the structured data.
In the embodiment, after the cloud server determines the feature database corresponding to the structured data according to the model related information, the feature database is searched, so that the search range is reduced, the use of cloud server resources is reduced, the cost is saved, and the search efficiency is improved.
As shown in fig. 7, on the basis of the embodiment shown in fig. 6, step 603 may include the following steps:
In this embodiment, a first feature library name, a first model type, and a first model version identifier obtained from the model-related information correspond to a terminal device that transmits encrypted information, where the first feature library name, the first model type, and the first model version identifier are information related to a first model of a processing target image in the terminal device.
Each service type corresponds to a feature library set, and the feature library set comprises a plurality of feature databases.
The service types can be distinguished by corresponding to different targets, for example, the corresponding service type is face identification when the target is a face, and the corresponding service type is human body identification when the target is a human body; the feature databases obtained by processing different versions of the model are different, and therefore, each service type corresponds to a plurality of feature databases.
In the embodiment, each type of retrieval in the cloud server corresponds to one service, and messages reported by each terminal device are balanced into different retrieval services according to the type; when creating a feature library (for example, the face is taken as a retrieval target in fig. 2, the feature library is a face library at this time, and the face is taken as a retrieval target in the following) by the cloud server, a model version corresponding to the features in the feature library needs to be specified, and a model version needs to be specified during retrieval, and retrieval parameters and threshold values corresponding to different model versions are different; when the terminal device reports data to retrieve, the face library to be retrieved is determined according to the face library name (each terminal device corresponds to at least one face library) associated with the terminal device and the model version number information on the terminal device.
As shown in fig. 8, based on the embodiment shown in fig. 7, step 6033 may include the following steps:
Each feature database corresponds to a feature library name and a model version identifier.
The embodiment realizes that a unique cloud server feature library is determined by the name of the feature library and the version identifier of the model; the face features extracted by different models are very different, so that a face library is marked, the name of the face library is required to be appointed, the model version number corresponding to the face features in the face library is also required to be appointed, the face library of a cloud server is uniquely identified through the face library name and the model version number, and the library required to be retrieved is required to be found according to the face library name and the model version number in retrieval.
Optionally, the method provided in this embodiment further includes:
responding to the second model of the terminal equipment to update the version, and receiving an updated model version identification sent by the terminal equipment; and replacing the model version identification corresponding to the feature database corresponding to the second model based on the updated model version identification.
In the model updating step corresponding to the terminal device in this embodiment, when the terminal device receives the version updating request and performs the version updating, the cloud server corresponds to the model version identifier corresponding to the feature database of the model to be updated, so as to ensure that after the model in the terminal device is updated, the structured data processed by the model can obtain the corresponding feature database in the cloud server.
In some alternative embodiments, the structured data includes a target feature, and the feature database includes a plurality of record data; wherein, each record data comprises characteristic data and characteristic related information.
Optionally, the feature-related information may include, but is not limited to, key points, attributes, and the like.
Step 604 includes: at least one record data matching the target feature is determined based on a distance between the target feature and the feature data in each of the plurality of record data.
In this embodiment, the distance (e.g., euclidean distance, cosine distance, etc.) between the target feature and the feature data in each record data is calculated, and the plurality of record data are sorted according to the distance to determine the record data with the smallest distance, optionally, the distance of the record data with the smallest distance is compared with a preset threshold value in order to improve the accuracy, and when the smallest distance is smaller than the preset threshold value, the record data corresponding to the smallest distance is used as the matched record data; or comparing all the distances obtained by calculation with a preset threshold value, and taking all the record data corresponding to the distances smaller than the preset threshold value as the matched record data.
Optionally, step 602 comprises:
receiving encrypted data which is sent by terminal equipment and is subjected to compression processing and encryption processing; and executing decryption processing and decompression processing on the encrypted data to obtain the structured data and the model related information.
Wherein the decryption process corresponds to an encryption process of the terminal device.
In this embodiment, as shown in step 208 in the embodiment provided in fig. 2, the process of processing the encrypted data in the cloud server may be to decompress and decrypt the data reported by the terminal device to obtain the structured data, where in order to ensure that the correct structured data and the relevant model information can be obtained, the decryption process in the cloud server needs to correspond to the encryption process of the terminal device.
Any of the target retrieval methods provided by the embodiments of the present disclosure may be performed by any suitable device having data processing capabilities, including but not limited to: terminal equipment, a server and the like. Alternatively, any of the target retrieval methods provided by the embodiments of the present disclosure may be executed by a processor, for example, the processor may execute any of the target retrieval methods mentioned by the embodiments of the present disclosure by calling a corresponding instruction stored in a memory. And will not be described in detail below.
Exemplary devices
Fig. 9 is a schematic structural diagram of a terminal device according to an exemplary embodiment of the present disclosure. As shown in fig. 9, the terminal device provided in this embodiment includes:
and the image processing module 91 is configured to process the acquired target image through the first model to obtain structured data.
And an information determining module 92, configured to determine model-related information corresponding to the first model provided by the image processing module 91.
A data generating module 93, configured to generate encrypted data based on the structured data obtained by the image processing module 91 and the model-related information determined by the information determining module 92.
And a data sending module 94, configured to send the encrypted data obtained by the data generating module 93 to the cloud server.
According to the terminal device provided by the embodiment of the disclosure, the acquired target image is processed through the first model to obtain structured data; determining model related information corresponding to the first model; generating encrypted data based on the structured data and the model-related information; sending the encrypted data to a cloud server; in the embodiment, because the structured data is reported to the cloud server instead of the original snapshot picture or video stream, the occupation of bandwidth is reduced; the use of cloud server resources is reduced, the cost is saved, and the retrieval efficiency is improved; and, because the structured data does not include specific target information, the safety and the privacy of the target data are ensured.
Fig. 10 is a schematic structural diagram of a terminal device according to another exemplary embodiment of the present disclosure. As shown in fig. 10, the terminal device of this embodiment includes:
in this embodiment, the image processing module 91 includes: a model determining unit 911 configured to determine a first model from at least one model included in the terminal device; wherein, at least one model corresponds to at least one model type, and the models of different model types carry out different treatments on the target image;
a feature extraction unit 912, configured to perform feature extraction on the target image through the determined first model to obtain a target feature; the target features are taken as structured data.
The information determination module 92 includes: the model information determining unit 921, configured to determine a feature library name, a model type, and a model version identifier of the first model;
the related information determining unit 922 is configured to determine model related information corresponding to the first model based on the feature library name, the model type, and the model version identifier.
The data generation module 93 includes: the encapsulating unit 931 is configured to perform format encapsulation on the structured data, the feature library name, the model type, and the model version identifier according to a set format to obtain encapsulated data with the set format; the set format corresponds to the identification format of the cloud server;
a processing unit 932, configured to perform compression processing and encryption processing on the encapsulated data to obtain processed encrypted data.
Optionally, the terminal device provided in this embodiment further includes:
an image acquisition module 95 for acquiring an image or video including a target; and carrying out target area detection and quality screening on at least one frame of video image in the image or video to obtain a target image.
The version updating module 96 is configured to, in response to detecting the model version updating request, perform version updating on the corresponding second model according to the model version updating request; and storing the updated model version identification, sending the updated model version identification to the cloud server, and updating the feature database in the cloud server.
Fig. 11 is a schematic structural diagram of a cloud server according to an exemplary embodiment of the present disclosure. As shown in fig. 11, the cloud server provided in this embodiment includes:
and the data receiving module 111 is configured to receive the encrypted data sent by the device side.
And a data parsing module 112, configured to determine the structured data and the model-related information based on the encrypted data received by the data receiving module 111.
The structured data is obtained by processing the target image corresponding to the first model, and the model related information corresponds to the first model.
And the database searching module 113 is used for determining a feature database corresponding to the structured data based on the model related information determined by the data analyzing module 112.
And the data matching module 114 is used for retrieving the record data corresponding to the obtained target from the feature database determined by the database searching module 113 based on the structured data determined by the data parsing module 112.
In the embodiment, after the cloud server determines the feature database corresponding to the structured data according to the model related information, the feature database is searched, so that the search range is reduced, the use of cloud server resources is reduced, the cost is saved, and the search efficiency is improved.
Fig. 12 is a schematic structural diagram of a cloud server according to another exemplary embodiment of the present disclosure. As shown in fig. 12, the cloud server provided in this embodiment includes:
in this embodiment, the data parsing module 112 is specifically configured to receive encrypted data that is sent by a terminal device and is subjected to compression processing and encryption processing; carrying out decryption processing and decompression processing on the encrypted data to obtain structured data and model related information; wherein the decryption process corresponds to an encryption process of the terminal device.
The database searching module 113 includes a model identifying unit 1131, configured to determine a first feature library name, a first model type, and a first model version identifier from the model-related information;
a library searching unit 1132, configured to determine a service type implemented by a first model in the terminal device based on the first model type, and determine a feature library set corresponding to the structured data according to the service type; each service type corresponds to a feature library set, and the feature library set comprises a plurality of feature databases;
a library corresponding unit 1133, configured to determine a feature database corresponding to the structured data from the feature library set based on the first feature library name and the first model version identifier.
Optionally, the library corresponding unit 1133 is specifically configured to filter, based on the first feature library name, a plurality of feature databases included in the feature library set, and determine at least one feature database whose feature library name matches the first feature library name; screening at least one characteristic database based on the first model version identification, and determining one characteristic database corresponding to the model version identification and the first model version identification; each feature database corresponds to a feature library name and a model version identifier.
Optionally, the structured data includes a target feature, and the feature database includes a plurality of record data; wherein, each record data comprises characteristic data and characteristic related information; the data matching module 114 is specifically configured to determine at least one record data matching the target feature based on a distance between the target feature and the feature data in each of the plurality of record data.
Optionally, the cloud server provided in this embodiment further includes:
the identifier updating module 115 is configured to perform version updating in response to the second model of the terminal device, and receive an updated model version identifier sent by the terminal device; and replacing the model version identification corresponding to the feature database corresponding to the second model based on the updated model version identification.
According to still another aspect of the embodiments of the present disclosure, there is provided a target retrieval system including: the cloud server provided by any one of the above embodiments and at least one terminal device provided by any one of the above embodiments.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present disclosure is described with reference to fig. 13. The electronic device may be either or both of the first device 100 and the second device 200, or a stand-alone device separate from them that may communicate with the first device and the second device to receive the collected input signals therefrom.
FIG. 13 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.
As shown in fig. 13, the electronic device 130 includes one or more processors 131 and memory 132.
In one example, the electronic device 130 may further include: an input device 133 and an output device 134, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
For example, when the electronic device is the first device 100 or the second device 200, the input device 133 may be a microphone or a microphone array as described above for capturing an input signal of a sound source. When the electronic device is a stand-alone device, the input means 133 may be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.
The input device 133 may also include, for example, a keyboard, a mouse, and the like.
The output device 134 may output various information including the determined distance information, direction information, and the like to the outside. The output devices 134 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device 130 relevant to the present disclosure are shown in fig. 13, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 130 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the object retrieval method according to various embodiments of the present disclosure described in the "exemplary methods" section of this specification above.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in a target retrieval method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (15)
1. A target retrieval method is applied to terminal equipment and comprises the following steps:
processing the acquired target image through the first model to obtain structured data;
determining model related information corresponding to the first model;
generating encrypted data based on the structured data and the model-related information;
and sending the encrypted data to a cloud server.
2. The method of claim 1, wherein the determining model-related information corresponding to the first model comprises:
determining a feature library name, a model type and a model version identifier of the first model;
determining model related information corresponding to the first model based on the feature library name, the model type and the model version identification;
generating, by the computing device, encrypted data based on the structured data and the model-related information, including:
format packaging is carried out on the structured data, the feature library name, the model type and the model version identification according to a set format, and packaged data with the set format are obtained; the set format corresponds to the identification format of the cloud server;
and carrying out compression processing and encryption processing on the packaged data to obtain processed encrypted data.
3. The method of claim 2, wherein the processing of the acquired target image by the first model to obtain structured data comprises:
determining a first model from at least one model included in the terminal device; the model of different model types carries out different processing on the target image;
performing feature extraction on the target image through the determined first model to obtain target features; and taking the target characteristic as the structured data.
4. The method of claim 3, further comprising:
in response to the detection of a model version updating request, updating the version of the corresponding second model according to the model version updating request;
and storing the updated model version identification, sending the updated model version identification to a cloud server, and updating a feature database in the cloud server.
5. The method according to any one of claims 1-4, further comprising, prior to processing the acquired target image through the first model to obtain the structured data:
acquiring an image or video comprising a target;
and carrying out target area detection and quality screening on the image or at least one frame of video image in the video to obtain a target image.
6. A target retrieval method is applied to a cloud server and comprises the following steps:
receiving encrypted data sent by terminal equipment;
determining structured data and model-related information based on the encrypted data; the structured data is obtained by processing a target image corresponding to a first model, and the model-related information corresponds to the first model;
determining a feature database corresponding to the structured data based on the model-related information;
and retrieving the record data corresponding to the target from the feature database based on the structured data.
7. The method of claim 6, wherein the determining a feature database to which the structured data corresponds based on the model-related information comprises:
determining a first feature library name, a first model type and a first model version identification from the model related information;
determining a service type realized by a first model in the terminal equipment based on the first model type, and determining a feature library set corresponding to the structured data according to the service type; each service type corresponds to a feature library set, and the feature library set comprises a plurality of feature databases;
determining a feature database corresponding to the structured data from the feature library set based on the first feature library name and the first model version identification.
8. The method of claim 7, wherein the determining, from the feature library set based on the first feature library name and the first model version identification, a feature database corresponding to the structured data comprises:
screening a plurality of feature databases included in the feature library set based on the first feature library name, and determining at least one feature database with a feature library name matched with the first feature library name;
screening the at least one characteristic database based on the first model version identification, and determining a characteristic database corresponding to the model version identification and the first model version identification; each feature database corresponds to a feature library name and a model version identifier.
9. The method of claim 8, further comprising:
responding to the second model of the terminal equipment to update the version, and receiving an updated model version identifier sent by the terminal equipment;
and replacing the model version identification corresponding to the feature database corresponding to the second model based on the updated model version identification.
10. The method of any of claims 6-9, wherein the structured data includes a target feature, the feature database including a plurality of record data; wherein, each record data comprises characteristic data and characteristic related information;
the retrieving of the record data corresponding to the target from the feature database based on the structured data includes:
determining at least one record data matching the target feature based on a distance between the target feature and a feature data in each of the plurality of record data.
11. The method of claim 6, wherein the receiving the structured data and the model-related information sent by the terminal device comprises:
receiving encrypted data which is sent by the terminal equipment and is subjected to compression processing and encryption processing;
performing decryption processing and decompression processing on the encrypted data to obtain the structured data and the model related information; wherein the decryption process corresponds to an encryption process of the terminal device.
12. A terminal device, comprising:
the image processing module is used for processing the acquired target image through the first model to obtain structured data;
the information determining module is used for determining model related information corresponding to the first model provided by the image processing module;
the data generation module is used for generating encrypted data based on the structured data obtained by the image processing module and the model related information determined by the information determination module;
and the data sending module is used for sending the encrypted data obtained by the data generating module to a cloud server.
13. A cloud server, comprising:
the data receiving module is used for receiving encrypted data sent by the terminal equipment;
the data analysis module is used for determining the structured data and the relevant information of the model based on the encrypted data received by the data receiving module; the structured data is obtained by processing a target image corresponding to a first model, and the model-related information corresponds to the first model;
the database searching module is used for determining a feature database corresponding to the structured data based on the model related information determined by the data analyzing module;
and the data matching module is used for retrieving the record data corresponding to the target from the characteristic database determined by the database searching module based on the structural data determined by the data analyzing module.
14. A computer-readable storage medium storing a computer program for executing the object retrieval method of any one of claims 1 to 11.
15. An electronic device, the electronic device comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the object retrieval method of any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010027267.5A CN113111354A (en) | 2020-01-10 | 2020-01-10 | Target retrieval method and system, terminal device, cloud server, medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010027267.5A CN113111354A (en) | 2020-01-10 | 2020-01-10 | Target retrieval method and system, terminal device, cloud server, medium and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111354A true CN113111354A (en) | 2021-07-13 |
Family
ID=76708805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010027267.5A Pending CN113111354A (en) | 2020-01-10 | 2020-01-10 | Target retrieval method and system, terminal device, cloud server, medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111354A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743451A (en) * | 2021-07-21 | 2021-12-03 | 南方电网深圳数字电网研究院有限公司 | Temperature image recognition method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003058865A (en) * | 2001-08-15 | 2003-02-28 | Nippon Telegr & Teleph Corp <Ntt> | Method and system for distributing video description information, server device for video description information distribution, client device for video description information distribution, program for video description information distribution, and recording medium recording the same program |
| CN101021899A (en) * | 2007-03-16 | 2007-08-22 | 南京搜拍信息技术有限公司 | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information |
| CN108062349A (en) * | 2017-10-31 | 2018-05-22 | 深圳大学 | Video frequency monitoring method and system based on video structural data and deep learning |
| CN108282527A (en) * | 2018-01-22 | 2018-07-13 | 北京百度网讯科技有限公司 | Generate the distributed system and method for Service Instance |
| CN109194926A (en) * | 2018-10-19 | 2019-01-11 | 济南浪潮高新科技投资发展有限公司 | A kind of city security system and its detection method based on edge calculations |
-
2020
- 2020-01-10 CN CN202010027267.5A patent/CN113111354A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003058865A (en) * | 2001-08-15 | 2003-02-28 | Nippon Telegr & Teleph Corp <Ntt> | Method and system for distributing video description information, server device for video description information distribution, client device for video description information distribution, program for video description information distribution, and recording medium recording the same program |
| CN101021899A (en) * | 2007-03-16 | 2007-08-22 | 南京搜拍信息技术有限公司 | Interactive human face identificiating system and method of comprehensive utilizing human face and humanbody auxiliary information |
| CN108062349A (en) * | 2017-10-31 | 2018-05-22 | 深圳大学 | Video frequency monitoring method and system based on video structural data and deep learning |
| CN108282527A (en) * | 2018-01-22 | 2018-07-13 | 北京百度网讯科技有限公司 | Generate the distributed system and method for Service Instance |
| CN109194926A (en) * | 2018-10-19 | 2019-01-11 | 济南浪潮高新科技投资发展有限公司 | A kind of city security system and its detection method based on edge calculations |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743451A (en) * | 2021-07-21 | 2021-12-03 | 南方电网深圳数字电网研究院有限公司 | Temperature image recognition method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017219900A1 (en) | Video detection method, server and storage medium | |
| CA3063126A1 (en) | System and method for biometric identification | |
| CN111897875A (en) | Fusion processing method and device for urban multi-source heterogeneous data and computer equipment | |
| US9639532B2 (en) | Context-based analysis of multimedia content items using signatures of multimedia elements and matching concepts | |
| US10719735B2 (en) | Information processing method, information processing device and video surveillance system | |
| US10621440B2 (en) | Network switching appliance, process and system for performing visual analytics for a streaming video | |
| US20120114177A1 (en) | Image processing system, image capture apparatus, image processing apparatus, control method therefor, and program | |
| US10825310B2 (en) | 3D monitoring of sensors physical location in a reduced bandwidth platform | |
| López et al. | Digital video source identification based on container’s structure analysis | |
| CN111209431A (en) | Video searching method, device, equipment and medium | |
| CN110795703A (en) | Data anti-theft method and related product | |
| US9135566B2 (en) | Apparatus and method for processing sensor data in sensor network using a feature vector identifier of the sensor data | |
| CN111859451A (en) | Processing system of multi-source multi-modal data and method applying same | |
| Khan et al. | Blockchain-enabled deep semantic video-to-video summarization for IoT devices | |
| WO2019051797A1 (en) | Image processing method and apparatus, computer device, and computer-readable storage medium | |
| US9412049B2 (en) | Apparatus and method for recognizing object using correlation between object and content-related information | |
| CN114625918A (en) | Video recommendation method, device, equipment, storage medium and program product | |
| CN115983848A (en) | Security monitoring method and system for encrypted electronic wallet | |
| US10878272B2 (en) | Information processing apparatus, information processing system, control method, and program | |
| US11537636B2 (en) | System and method for using multimedia content as search queries | |
| US20130191368A1 (en) | System and method for using multimedia content as search queries | |
| CN114708578A (en) | Lip action detection method and device, readable storage medium and electronic equipment | |
| Ushapreethi et al. | Action recongnition in video survillance using hipi and map reducing model | |
| CN113111354A (en) | Target retrieval method and system, terminal device, cloud server, medium and device | |
| Mansour et al. | Video querying via compact descriptors of visually salient objects |
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 |