CN112541384A

CN112541384A - Object searching method and device, electronic equipment and storage medium

Info

Publication number: CN112541384A
Application number: CN202010750268.2A
Authority: CN
Inventors: 李蔚琳; 王建军; 张贵明; 黄潇莹
Original assignee: Shenzhen Sensetime Technology Co Ltd
Current assignee: Shenzhen Sensetime Technology Co Ltd
Priority date: 2020-07-30
Filing date: 2020-07-30
Publication date: 2021-03-23
Anticipated expiration: 2040-07-30
Also published as: TW202205150A; CN112541384B; WO2022021711A1

Abstract

The application discloses an object searching method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first image to be confirmed and a face image library containing face images of a search object; executing a human body searching task under the condition that the human face similarity between the human face image library and the first image to be confirmed is determined to exceed a human face similarity threshold value, and the first image to be confirmed is determined to contain the human body of the searched object; the human body searching task comprises the following steps: and comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity exceeding the human similarity threshold value with the first image to be confirmed, and taking the image as at least one target image.

Description

Object searching method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of security protection, in particular to an object searching method and device, electronic equipment and a storage medium.

Background

In the field of security protection, related personnel can search for a searched object through identity information under the condition of determining the identity information of the searched object. With the increase of the monitoring cameras, how to effectively utilize the images acquired by the monitoring cameras to search for the object to be searched has very important significance.

Disclosure of Invention

The application provides an object searching method and device, electronic equipment and a storage medium.

In a first aspect, an object search method is provided, where the method includes:

acquiring a first image to be confirmed and a face image library containing face images of a search object;

executing a human body searching task under the condition that the human face similarity between the human face image library and the first image to be confirmed is determined to exceed a human face similarity threshold value, and the first image to be confirmed is determined to contain the human body of the searched object;

the human body searching task comprises the following steps: and comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity exceeding the human similarity threshold value with the first image to be confirmed, and taking the image as at least one target image.

With reference to any embodiment of the present application, before the performing the human body finding task, the method further includes:

acquiring the human body searching time;

the searching for the first image to be confirmed and comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity between the first image to be confirmed and the first image to be confirmed exceeding a human similarity threshold as at least one target image, and the method comprises the following steps:

in a human body searching time period, comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity between the first image to be confirmed and the first image to be confirmed exceeding the human body similarity threshold value, and using the at least one image as the at least one target image; the starting time of the human body searching time period is the starting time for executing the human body searching task, and the duration of the human body searching time period is the human body searching duration.

With reference to any embodiment of the present application, before the performing the human body finding task, the method further includes: acquiring a human body searching range;

in the human body searching time period, comparing the first image to be confirmed with the images in the database to obtain at least one image, as the at least one target image, of which the similarity with the first image to be confirmed exceeds the human body similarity threshold, including:

and in the human body searching time period, performing human body comparison on the first image to be confirmed and the image of which the acquisition position is located in the human body searching range to obtain at least one image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, and taking the at least one image as the at least one target image.

In combination with any embodiment of the present application, the at least one target image includes a first image and a second image;

before the performing a human finding task, the method further comprises: acquiring a human body comparison time interval;

in the human body searching time period, performing human body comparison on the first image to be confirmed and the image of which the acquisition position is located in the human body searching range to obtain at least one image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, and taking the at least one image as the at least one target image, wherein the method comprises the following steps:

comparing the first image to be confirmed with the image of which the acquisition position is located in the human body searching range to obtain an image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, and taking the image as the first image;

acquiring at least one third image with the acquisition position located in the human body search range after the starting time of the search time period;

when the sum of the human body comparison time interval and the human body comparison duration is smaller than the human body searching duration and the first image is successfully sent to the first terminal within the human body interval time period, performing human body comparison on the first image to be confirmed and the at least one third image to obtain an image, of the at least one third image, of which the similarity with the first image to be confirmed exceeds the human body similarity threshold, and taking the image as the second image; the human body comparison duration is the duration from the starting time of the human body searching time period to the obtaining of the first image.

In combination with any embodiment of the present application, the human body search task further includes:

sending a first alarm instruction containing the at least one target image to a second terminal; the first warning instruction is used for indicating the second terminal to display the at least one target image.

With reference to any embodiment of the present application, after obtaining, by using the first to-be-confirmed image search database, a first to-be-confirmed image having feature data matching the first to-be-confirmed image, before performing a human body finding task, the method further includes:

acquiring a second image to be confirmed; the acquisition position of the second image to be confirmed is different from the acquisition position of the first image to be confirmed;

under the condition that the face similarity between a fourth image and the second image to be confirmed exceeds the face similarity threshold and the second image to be confirmed contains a human body, stopping executing the human body searching task, and performing human body comparison on the second image to be confirmed and the images in the database to obtain an image with the similarity between the second image to be confirmed and the human body similarity threshold, wherein the similarity between the second image to be confirmed and the images to be confirmed exceeds the human body similarity threshold, and the image is used as a new target image; the fourth image is an image in the face image library, wherein the face similarity between the fourth image and the first image to be confirmed exceeds the face similarity threshold.

With reference to any one of the embodiments of the present application, the acquiring a first image to be confirmed includes:

acquiring a first video stream to be processed; the first video stream to be processed is acquired through a face camera;

and intercepting a frame of image from the first video stream to be processed as the first image to be confirmed.

acquiring a second video stream to be processed; the second video stream to be processed comprises the first video stream to be processed and a video stream acquired by a human body camera;

and storing the images in the second video stream to be processed to the database.

In combination with any embodiment of the present application, the at least one target image includes a fifth image, and the method further includes:

under the condition of receiving a video viewing request aiming at the fifth image sent by the second terminal, intercepting a video stream to be shown containing the fifth image from the video stream to be processed;

and sending the video stream to be displayed to the second terminal.

In a second aspect, an object search apparatus is provided, the apparatus including:

the device comprises an acquisition unit, a search unit and a display unit, wherein the acquisition unit is used for acquiring a first image to be confirmed and a face image library containing a face image of a search object;

the processing unit is used for executing a human body searching task under the condition that an image with the human face similarity exceeding a human face similarity threshold value exists in the human face image library and the first image to be confirmed is determined to contain the human body of the searched object;

In combination with any embodiment of the present application, the obtaining unit is further configured to obtain a human body search duration before the human body search task is executed;

With reference to any embodiment of the present application, the obtaining unit is further configured to obtain a human body search range before the human body search task is executed;

the acquisition unit is further configured to acquire a human body comparison time interval before the human body search task is executed;

With reference to any embodiment of the present application, the obtaining unit is further configured to, after obtaining a first image to be confirmed having feature data matching the first image to be confirmed by using the first image to be confirmed to search the database, obtain a second image to be confirmed before performing the human body search task; the acquisition position of the second image to be confirmed is different from the acquisition position of the first image to be confirmed;

the processing unit is further configured to, when it is determined that the face similarity between a fourth image and the second image to be confirmed exceeds the face similarity threshold and it is determined that the second image to be confirmed contains a human body, stop executing the human body search task, perform human body comparison between the second image to be confirmed and the images in the database, and obtain an image, as a new target image, of which the similarity between the second image to be confirmed and the second image to be confirmed exceeds the human body similarity threshold; the fourth image is an image in the face image library, wherein the face similarity between the fourth image and the first image to be confirmed exceeds the face similarity threshold.

With reference to any embodiment of the present application, the obtaining unit is configured to:

With reference to any embodiment of the present application, the obtaining unit is further configured to obtain a second video stream to be processed before the human body search task is executed; the second video stream to be processed comprises the first video stream to be processed and a video stream acquired by a human body camera;

the object searching device further comprises: and the storage unit is used for storing the images in the second video stream to be processed into the database.

In combination with any embodiment of the present application, the at least one target image includes a fifth image, and the apparatus further includes:

the intercepting unit is used for intercepting a video stream to be displayed containing the fifth image from the video stream to be processed under the condition of receiving a video viewing request aiming at the fifth image sent by the second terminal;

and the sending unit is used for sending the video stream to be displayed to the second terminal.

In a third aspect, a processor is provided, which is configured to perform the method according to the first aspect and any one of the possible implementations thereof.

In a fourth aspect, an electronic device is provided, comprising: a processor, transmitting means, input means, output means, and a memory for storing computer program code comprising computer instructions, which, when executed by the processor, cause the electronic device to perform the method of the first aspect and any one of its possible implementations.

In a fifth aspect, there is provided a computer-readable storage medium having stored therein a computer program comprising program instructions which, if executed by a processor, cause the processor to perform the method of the first aspect and any one of its possible implementations.

A sixth aspect provides a computer program product comprising a computer program or instructions which, when run on a computer, causes the computer to perform the method of the first aspect and any of its possible implementations.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments or the background art of the present application, the drawings required to be used in the embodiments or the background art of the present application will be described below.

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

Fig. 1 is a schematic flowchart of an object searching method according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of an object search apparatus according to an embodiment of the present application;

fig. 3 is a schematic diagram of a hardware structure of an object search apparatus according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

In the security field, related personnel can search for a searched object through identity information under the condition of determining the identity information (such as a photo of the searched object) of the searched object. With the increase of more monitoring cameras, related personnel can search for the searched object based on the identity information of the searched object and the monitoring cameras.

In the current object searching method, the face image of the searched object is compared with the face image collected by the monitoring camera to search the searched object (i.e. the face image of the searched object is used as a searching basis to search the searched object). Because the accuracy of face comparison is in positive correlation with the image quality of the face image, the accuracy of face comparison is low under the condition that the quality of the face image collected by the monitoring camera is low, and further the searching effect is poor. The low quality of the face image includes at least one of the following situations: the human face area in the human face image is not clear, the human face area in the human face image is incomplete, and the human face area in the human face image is shielded.

In order to improve the accuracy of face comparison, the quality of the face image used for face comparison needs to exceed a quality threshold. Because the quality of the face image mainly depends on the monitoring camera for acquiring the face image, and the monitoring cameras which are installed in the public places at present and have the quality of the face image exceeding the quality threshold are fewer. This results in poor searching effect of the current object searching method. The value of the quality threshold can be determined according to actual requirements, specifically, the larger the value of the quality threshold is, the higher the accuracy of face comparison is, but the higher the requirement on hardware configuration of a monitoring camera for acquiring a face image is.

For example, the area a can be divided into three areas a, b and c, wherein the quality of the face image acquired by the monitoring camera in the area a exceeds a quality threshold, the quality of the face image acquired by the monitoring camera in the area b does not exceed the quality threshold, and the quality of the face image acquired by the monitoring camera in the area c exceeds the quality threshold. In the process that the relevant person in the place A searches the search object by taking the face image of the search object as a search basis, if the search object is in the area b, the relevant person in the place A cannot know the track of the search object.

Based on this, the embodiment of the application provides a technical scheme to improve the search effect. The embodiments of the present application will be described below with reference to the drawings.

For convenience of description, a camera with the quality of the acquired face image exceeding the quality threshold is referred to as a face camera, and a camera with the quality of the acquired face image not exceeding the quality threshold is referred to as a human body camera.

The execution subject of the embodiment of the application is an object searching device. The optional object finding means may be one of the following: server, computer. Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an object searching method according to an embodiment of the present disclosure.

101. And acquiring a first image to be confirmed and a face image library.

In the embodiment of the present application, the first image to be confirmed is an image containing arbitrary content. Optionally, the first image to be confirmed is an image collected by a human face camera.

In one implementation of obtaining the first image to be confirmed, the object searching device receives the first image to be confirmed input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of acquiring the first image to be confirmed, the object searching device receives the first image to be confirmed sent by the first control terminal. Optionally, the first control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment.

In the embodiment of the application, the face image library comprises the face image of the searched object. For example, the face image library includes three face images, and at this time, the search object is three. For another example, if the relevant person wants to search for the search object in the B site, the face image of the search object in the B site may be stored in the face image library.

It should be understood that the facial image library may contain facial images of at least one search object. For example, the face image includes an image a and an image b, where the image a is a face image of a third person, and the image b is a face image of a fourth person, and at this time, the face image library includes face images of two search objects.

In one implementation of obtaining the facial image library, the object searching device receives the facial image library input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of acquiring the face image library, the object searching device receives the face image library sent by the second control terminal. Optionally, the second control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment. The second control terminal may be the same as or different from the first control terminal.

102. And executing a human body searching task under the condition that the human face similarity between the human face image library and the first image to be confirmed is determined to exceed a human face similarity threshold value, and the first image to be confirmed is determined to contain a human body.

In the embodiment of the present application, the face similarity refers to the similarity between faces in two images. For example, image a contains a human face a and image B contains a human face B. The face similarity between the image a and the image B refers to the similarity between the face a and the face B. For another example, image a contains a face a and a face B, and image B contains a face c. The human face similarity between the image a and the image B includes: the similarity between the face a and the face c, and the similarity between the face b and the face c.

And the face similarity exceeds a face similarity threshold value, and the characters corresponding to the two faces are represented as the same person. For example, the similarity of a face between the image a and the image B is the similarity between the face a and the face B. And if the face similarity between the image A and the image B exceeds the face similarity threshold, the person corresponding to the face a and the person corresponding to the face B are the same person. As another example, the degree of similarity between the human face of the image a and the image B includes: the similarity between the face a and the face c, and the similarity between the face b and the face c. And if the similarity between the face a and the face c exceeds the face similarity threshold, the person corresponding to the face a and the person corresponding to the face c are the same person. And if the similarity between the face b and the face c exceeds the face similarity threshold, the person corresponding to the face b and the person corresponding to the face c are the same person.

The object searching device can determine whether an image with the human face similarity exceeding the human face similarity threshold exists in the human face image library by comparing the first image to be confirmed with the image in the human face image library, and further determine that the first image to be confirmed contains the searched object. For example, the face image library contains a face image of the search object, and if an image whose face similarity with the first image to be confirmed exceeds a face similarity threshold exists in the face image library, the first image to be confirmed is characterized to contain the search object.

The human face similarity of the two images is obtained by comparing human faces of the two images, the number of the human face cameras is less than that of the human body cameras, and the monitoring range of the human face cameras is less than that of the human body cameras. Because the images in the face image library may not contain a human body (in the embodiment of the present application, the human body includes a body other than a human head), when it is determined that the first image to be confirmed contains a human body, the first image to be confirmed and the image acquired by the human body camera can be subjected to human body comparison, and the image acquired by the human body camera can be used to expand the search range.

In a possible implementation manner, the object search apparatus obtains feature data carrying semantic information of the first image to be confirmed by performing feature extraction processing on the first image to be confirmed. The object searching device can determine whether the first image to be confirmed contains a human body according to the information carried by the characteristic data.

It should be understood that, in the case that the first image to be confirmed includes at least two faces, if a face whose similarity between the first image to be confirmed and the face images in the face image library exceeds the face similarity threshold is referred to as a target face, the object search apparatus performs a body comparison between the first image to be confirmed and an image acquired by the body camera in the case that the first image to be confirmed includes a body corresponding to the target face (i.e., a body including a search object).

For example, it is assumed that the first image to be confirmed includes a face a and a face b, and the face image library includes an image a, where the image a and the face b only include one face. And if the face similarity between the face a and the image A exceeds the face similarity threshold value, and the face similarity between the face b and the image A does not exceed the face similarity threshold value, the face a is the target face. If the person corresponding to the face a is called Zhang III. And under the condition that the object searching device determines that the first image to be confirmed contains Zhang III human body, carrying out human body comparison on the first image to be confirmed and the image collected by the human body camera.

Although the images collected by the human body camera cannot meet the requirement of human face comparison (namely, the image quality does not exceed the quality threshold), the images can be used for human body comparison, wherein the human body comparison means that the similarity between human body characteristic data of the two images is determined. Therefore, when it is determined that an image with a human face similarity exceeding a human face similarity threshold exists in the human face image library and it is determined that the first image to be confirmed contains a human body corresponding to the target human face, the object searching device can perform further searching based on the image acquired by the human body camera and the first image to be confirmed to expand a searching range, thereby improving a searching effect.

Based on this, the object searching device searches based on the image to be confirmed as the object, namely executes the human body searching task, when determining that the image with the human face similarity between the image to be confirmed and the first image to be confirmed exceeds the human face similarity threshold exists in the human face image library and determining that the first image to be confirmed contains the human body corresponding to the target human face. In the embodiment of the application, the object searching device executes the following steps in the process of executing the human body searching task: 1. and comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity exceeding the human similarity threshold value with the first image to be confirmed as at least one target image.

In the embodiment of the application, the database comprises images collected by the human body camera. It should be understood that the database containing the images collected by the human body camera may be, for example, the database containing the images collected by the human body camera and the images collected by the human face camera. The human body comparison means that whether the characters in the two images are the same person or not is determined by calculating the similarity between the human body feature vectors of the two images. The human body characteristic vectors carry the identity information of the persons in the images, and the similarity between the human body characteristic vectors of the two images exceeds a human body similarity threshold value, so that the persons in the two images are represented as the same person.

For example, the human feature vector extracted from the image 1 is a, the human feature vector extracted from the image 2 is b, and in the case that the similarity between the human feature vector a and the human feature vector b exceeds a human similarity threshold, it is determined that the person in the image 1 and the person in the image 2 are the same person.

The identity information of the person carried by the human body feature vector comprises: apparel attributes, appearance features, and variation features of the character. The apparel attribute includes at least one of the characteristics of all items that decorate the human body (e.g., jacket color, pants length, hat style, shoe color, not to umbrella, bag type, presence or absence of a mask, mask color). The appearance characteristics comprise body type, gender, hair style, hair color, age, whether wearing glasses or not and whether holding things in the chest or not. The variation characteristics include: posture and stride.

For example, categories of jacket color or pants color or shoe color or hair color include: black, white, red, orange, yellow, green, blue, violet, brown. Categories of pant length include: trousers, shorts, skirt. The categories of hat styles include: no hat, baseball cap, peaked cap, flat hat, fisherman cap, beret, hat. The categories of not opening the umbrella include: and opening or not opening the umbrella. The categories of hair style include: long hair, short hair, bald head and bald head. The gesture categories include: riding posture, standing posture, walking posture, running posture, sleeping posture, and lying posture. The stride refers to the stride size of a person walking, and the stride size can be represented by distance, such as: 0.3 meter, 0.4 meter, 0.5 meter, 0.6 meter.

The object searching device compares the first image to be confirmed with the images in the database by human body, determines at least one image with similarity exceeding the human body similarity threshold between the first image to be confirmed and the first image to be confirmed, and obtains at least one target image containing the searched object. Because the database comprises the images collected by the human body camera, the monitoring range of the human body camera is larger than that of the human face camera, and the object searching device can expand the searching range by executing a human body searching task, so that the searching effect is improved.

When the first to-be-confirmed image of the object is searched, by implementing the technical scheme provided by the embodiment of the application, the image collected by the human face camera can be used for searching, and the image collected by the human body camera can also be used for searching. Because the precision of the face comparison is higher than that of the human body, the object searching device determines that the first image to be confirmed comprises the face in the face image library by comparing the face of the first image to be confirmed with the image in the face image library, and the first image to be confirmed comprises the human body corresponding to the face in the face image library, and the image collected by the human body camera can be used for searching on the premise of not reducing the searching accuracy, so that the searching range is expanded, and the searching effect is improved.

As an optional implementation manner, before performing the human body finding task, the object finding apparatus further performs the following steps:

2. and acquiring the human body searching time length.

Because the identity information of the person carried by the human body feature vector has timeliness, in order to further improve the searching accuracy, an effective time length, namely the human body searching time length, can be set for the human body searching task. For example, in the first image to be confirmed, the search object is a white jacket, but the search object may change the jacket to black after leaving the place in the first image to be confirmed. At this time, if the first image to be confirmed is used to search for the object to be searched, the search accuracy and the search efficiency are reduced.

In one implementation of obtaining the human body search duration, the object search device receives the human body search duration input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of obtaining the human body search time, the object search device receives the human body search time sent by the second control terminal. Optionally, the second control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment. Optionally, the second control terminal may be the same as or different from the first control terminal.

After the human body searching duration is obtained, the object searching device executes the following steps in the process of executing the step 1:

3. and in a human body searching time period, comparing the first image to be confirmed with the images in the database to obtain at least one image with the similarity exceeding the human body similarity threshold value with the first image to be confirmed, and taking the at least one image as the at least one target image.

In the embodiment of the application, the starting time of the human body searching time period is the starting time of the object searching device for executing the human body searching task, and the duration of the human body searching time period is the human body searching duration.

For example, the object search apparatus starts to perform the human body search task at 10 o 'clock 45 min 30 sec on 8 th 7/2020 by performing step 102, and at this time, the start time of the human body search time period is 10 o' clock 45 min 30 sec on 8 th 2020. Assuming that the human body searching time duration is 1 hour, and at this time, the human body searching time duration is from 10 o 'clock 45 min 30 sec at 7 month and 8 day of 2020 year to 11 o' clock 45 min 30 sec at 7 month and 8 day of 2020 year.

In the embodiment of the application, the object searching device executes the human body searching task in the human body searching time period, so that the accuracy of human body searching can be improved.

4. and acquiring the human body searching range.

Because the moving distance of the search object in the human body search time length is not too far, a search range, namely a human body search range, can be set for the human body search task for improving the search efficiency and the search accuracy. For example, the human body search range may be a circular area with the position of the camera acquiring the first image to be confirmed as the center of a circle and 1 km as the radius.

In one implementation of obtaining the human body search range, the object search apparatus receives the human body search range input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of obtaining the human body search range, the object search device receives the human body search range sent by the third control terminal. Optionally, the third control terminal may be any one of the following: cell-phone, computer, panel computer, server, wearable equipment. Optionally, the third control terminal may be the same as or different from the first control terminal.

After acquiring the human body search range, the object search device executes the following steps in the process of executing step 3:

5. and in the human body searching time period, performing human body comparison on the first image to be confirmed and the image of which the acquisition position is located in the human body searching range to obtain at least one image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, and taking the at least one image as the at least one target image.

Since the position of the monitoring camera is determined, the acquisition position information carried by the images in the database is also determined. For example, the image a is acquired by the monitoring camera a, the positions of the monitoring camera a are 116.25 degrees of east longitude and 39.55 degrees of north latitude, and at this time, the acquired position information carried by the image a is 116.25 degrees of east longitude and 39.55 degrees of north latitude. For another example, the acquisition position information carried by the image a is a monitoring camera No. 1.

In a possible implementation manner, in the process of executing the human body searching task, the object searching device performs human body comparison on the first image to be confirmed and the image with the carried acquisition position information within the human body searching range, and obtains at least one image with the similarity exceeding the human body similarity threshold value with the first image to be confirmed as at least one target image.

In another possible implementation manner, in the process of executing the human body searching task, the object searching device performs human body comparison on the image acquired by the monitoring camera located in the human body searching range and the first image to be confirmed to obtain at least one image, of which the similarity with the first image to be confirmed exceeds the human body similarity threshold, as the at least one target image.

In the embodiment of the application, the object searching device executes the human body searching task in the human body searching range, so that the accuracy of human body searching can be further improved, and the searching efficiency is improved.

Before proceeding with the following explanation, the human body comparison processing and the face comparison processing are first defined. In the embodiment of the present application, the one-time human body comparison processing means that the object search apparatus completes human body comparison between the search image (including the first image to be confirmed and a second image to be confirmed, which will be mentioned later) and the image whose collection position is within the search range in the database. For example, the object search device performs the human body matching process at 14: 36/30 seconds on 7/9/2020. Assuming 36 minutes and 30 seconds by 14 points at 7, 9, 2020 and 9, the images in the database whose acquisition positions are within the search range include: and the object searching device executes human body comparison processing once under the condition that the object searching device respectively performs human body comparison on the first image to be confirmed with the image a, the image b and the image c and obtains human body similarity between the first image to be confirmed and the image a, human body similarity between the first image to be confirmed and the image b and human body similarity between the first image to be confirmed and the image c.

In the embodiment of the application, the primary face comparison processing means that the object searching device completes the face comparison between the reference face image and the image in the database. For example, the object finding apparatus performs the face matching process at 14: 40/30 seconds on 7/9/2020. Assuming that by 14 points 40 minutes 30 seconds by 7/9/2020, the images in the database include: and the object searching device executes face comparison processing once under the condition that the object searching device respectively compares the reference face image with the image a, the image b and the image c and obtains the face similarity between the reference face image and the image a, the face similarity between the reference face image and the image b and the face similarity between the reference face image and the image c.

As an optional implementation manner, before performing the human body finding task, the object finding apparatus further performs the following steps: 6. and acquiring the human body comparison time interval.

The camera acquires images by acquiring the video stream, and the video stream acquired by the camera is in a continuous state, so that the images in the database are continuously increased. Considering that the movement distance of the searched object is short in a short time, if the object searching device continuously performs the step of comparing the first image to be confirmed with the image of which the acquisition position is located in the human body searching range within the human body searching time period, the searching efficiency will be reduced.

Therefore, in the embodiment of the application, the object searching device performs at least one human body comparison processing within the human body searching time period to complete the human body searching task, and a time interval exists between any two human body comparison processing, so that the data processing amount of the object searching device is reduced, and the searching efficiency of the object searching device is improved.

For example, the human search time period is 10 o 'clock 45 min 30 sec at 8 d 7/8 of 2020 to 45 o' clock 45 min 30 sec at 8 d 7/8 of 2020. The time of the first human body comparison processing executed by the object searching device in the human body searching time period is as follows: the time of the second human body comparison processing executed by the object search device in the human body search time period is as follows, from 10: 45: 30 seconds at 8/7/2020 to 10: 45: 50 seconds at 8/7/2020: 10 o' clock 45 min 55 sec at 8/7/2020 to 46 min 05 sec at 8/7/2020. The time interval between the first human body comparison and the second human body comparison is 5 seconds.

In the embodiment of the application, the human body comparison time interval can be determined according to actual requirements. Optionally, the human body comparison time interval is 3 seconds.

In one implementation of obtaining the human body comparison time interval, the object searching device receives the human body comparison time interval input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of obtaining the human body comparison time interval, the object searching device receives the human body comparison time interval sent by the fourth control terminal. Optionally, the fourth control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment. Optionally, the fourth control terminal may be the same as or different from the first control terminal.

In order to facilitate the relevant personnel to timely master the track information of the searched object, the object searching device can send the target image to the first terminal after obtaining the target image by executing human body comparison processing. Therefore, the related personnel can grasp the track information of the searched object through the target image displayed by the first terminal.

Under the condition that the number of the target images obtained by the object searching device through executing the human body comparison processing once is large, the object searching device needs long time for successfully sending all the target images to the first terminal, and the human body comparison time interval is short. This may occur that, in a case where the target image obtained by performing the current human body comparison processing is not successfully transmitted to the first terminal, the target image obtained by performing the next human body comparison processing is successfully transmitted to the first terminal. Therefore, in the process of displaying the target images, the sequence of displaying the target images by the first terminal is not matched with the acquisition time of the target images.

For example, the execution time of the current human body comparison processing is from 10 o 'clock 45 min 30 sec at 8 d at 7/8/2020 to 45 o' clock 50 sec at 10 d at 8 d at 7/8/2020, and the time of the next human body comparison processing is: 10 o' clock 45 min 52 sec at 8/7/2020 to 45 min 57 sec at 8/7/2020. The target image obtained by the object searching device through executing the current human body comparison processing comprises: image a, image b, image c, image d, image e, and image f. The target image obtained by the object searching device through executing the next human body comparison processing comprises: image g. The object finding apparatus transmits the target image obtained by performing the current time of the body matching process to the first terminal from 10 o 'clock 45 min 50 sec on 8 o' clock 7/8 n 2020, and has successfully transmitted the image a, the image b, the image c, and the image d to the first terminal at 10 o 'clock 45 min 57 sec on 8 o' clock 7/8 n 2020. The object finding apparatus transmits the target image obtained by performing the current time of the human body matching process to the first terminal from 10 o 'clock 45 min 57 sec at 7/8/2020, and successfully transmits the image e and the image g to the first terminal at 10 o' clock 45 min 57 sec at 7/8/2020, while the image f is not transmitted to the first terminal. This will result in the first terminal presenting image g before image f, which is acquired earlier than image g.

In order to avoid the above situation, in a case where the human body matching process performed by the object search device in the human body matching time period exceeds 1, after the human body matching time interval is obtained, the object search device performs the following steps in the process of performing step 5:

7. and comparing the first image to be confirmed with the image of which the acquisition position is located in the human body searching range to obtain an image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, and taking the image as a first image.

In this embodiment of the application, step 7 is a first human body comparison process performed by the object finding device in a human body comparison time period, that is, step 7 is performed by the object finding device from the start time of the human body comparison time period, and a first image obtained by performing step 7 is a target image, that is, the first image belongs to at least one target image.

8. And acquiring at least one third image with the acquisition position positioned in the human body search range after the starting time of the search time period.

If the time is up to the starting time of the search time period, the image in the database located in the human body search range is called a first image to be compared. And after the initial time of the search time period, the newly added image in the database and positioned in the human body search range is called a second image to be compared. The object searching apparatus performs step 7 to compare the first image to be confirmed with the first image to be compared, and the second image to be compared is an image that is not compared with the first image to be confirmed. That is, when the object search apparatus completes step 7, the at least one third image is an image that has not been compared with the first image to be confirmed.

In one implementation of obtaining the at least one third image, the object searching device receives the at least one third image input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of acquiring at least one third image, the object searching device receives at least one third image sent by the fifth control terminal. Optionally, the fifth control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment. Optionally, the fifth control terminal may be the same as or different from the first control terminal.

9. And comparing the first image to be confirmed with the at least one third image to obtain an image, as the second image, of which the similarity with the first image to be confirmed exceeds the human body similarity threshold value, when the sum of the human body comparison time interval and the human body comparison time length is smaller than the human body searching time length and the first image is successfully sent to the first terminal within the human body interval time length.

In the embodiment of the present application, the human body comparison duration refers to a duration consumed by the object search device to perform the first human body comparison processing, that is, the human body comparison duration is a duration from the start time of the human body search time period to the time of obtaining the first image.

The sum of the human body comparison time interval and the human body comparison time duration is less than the human body search time duration representation, and after the object search device performs step 7, the human body comparison processing (hereinafter, referred to as the second human body comparison processing) may be performed again. In the process of executing the second human body comparison processing, the object searching device performs human body comparison on the first image to be confirmed and at least one third image so as to determine an image of which the similarity with the first image to be confirmed exceeds the human body similarity threshold from the at least one third image.

And executing second human body comparison processing under the condition that the object searching device is determined to successfully send the target image obtained by the first human body comparison to the first terminal, so that the condition that the sequence of displaying the target image by the first terminal is not matched with the acquisition time of the target image can be avoided.

Therefore, in the case that the object search apparatus successfully sends the first image to the first terminal within the human body interval time period, the object search apparatus performs human body comparison on the first image to be confirmed and the at least one third image to obtain a target image (i.e., the second image) of the at least one third image, in which the similarity between the target image and the first image to be confirmed exceeds the human body similarity threshold, that is, in steps 7 to 9, the at least one target image includes the first image and the second image.

It should be understood that only the first human body matching process and the second human body matching process are described in steps 7 and 9, and in practical applications, the number of human body matching processes performed by the object search apparatus in the search time period may exceed 2.

As an optional implementation manner, in order to enable the relevant person to know the track of the searched object in time, in the case that the at least one target image is obtained by performing the above steps, the object searching device may send a first warning instruction including the at least one target image to the second terminal, where the first warning instruction is used to instruct the second terminal to display the at least one target image. Therefore, the related personnel can know the track of the searched object through the second terminal and further find the searched object. The first terminal and the second terminal may be the same or different, and this is not limited in this application.

As an alternative embodiment, after the database is searched using the first image to be confirmed, and the first image to be confirmed having the feature data matching the first image to be confirmed is obtained, and before the human body finding task is performed, the object finding apparatus further performs the following steps:

10. and acquiring a second image to be confirmed.

In this embodiment of the application, the acquisition position of the second image to be confirmed may be within the search range, and the acquisition position of the second image to be confirmed may also be outside the search range, which is not limited in this application. Optionally, the second image to be confirmed is an image acquired by a human face camera.

In one implementation of obtaining the second image to be confirmed, the object searching device receives the second image to be confirmed input by the user through the input component. The above-mentioned input assembly includes: keyboard, mouse, touch screen, touch pad, audio input device, etc.

In another implementation manner of acquiring the second image to be confirmed, the object searching device receives the second image to be confirmed sent by the sixth control terminal. Optionally, the sixth control terminal may be any one of: cell-phone, computer, panel computer, server, wearable equipment. Optionally, the sixth control terminal may be the same as or different from the first control terminal.

11. And stopping executing the human body searching task and comparing the second image to be confirmed with the images in the database to obtain an image with the similarity exceeding the human body similarity threshold value with the second image to be confirmed as a new target image under the condition that the human face similarity between the fourth image and the second image to be confirmed exceeds the human face similarity threshold value and the second image to be confirmed contains a human body.

In the embodiment of the present application, the fourth image is an image in the face image library, in which the face similarity with the first image to be confirmed exceeds a face similarity threshold. For example, the face image library contains images a and images b. The human face similarity between the first image to be confirmed and the image a exceeds the human face similarity threshold, and the human face similarity threshold between the first image to be confirmed and the image b does not exceed the human face similarity threshold. Image a is the fourth image.

If the object searching device determines that the face similarity between the second image to be confirmed and the fourth image exceeds the face similarity threshold, the second image to be confirmed and the fourth image are characterized to contain the same person, namely the first image to be confirmed and the second image to be confirmed both contain the searched object. Since the acquisition position of the second image to be confirmed is different from the acquisition position of the first image to be confirmed, the position of the search object has changed.

In order to improve the searching efficiency and the searching accuracy, under the condition that the face similarity between the fourth image and the second image to be confirmed exceeds the face similarity threshold value and the second image to be confirmed contains a human body of a searched object, the human body searching task is stopped to be executed, the second image to be confirmed is compared with the image in the database for the human body, and the image of which the similarity with the second image to be confirmed exceeds the human body similarity threshold value is obtained and serves as a new target image.

Optionally, the human body search task in the embodiment of the present application refers to a search task established based on the first image to be confirmed (hereinafter, referred to as a first search task). After the second image to be confirmed is obtained, the object search device stops executing the search task established based on the first image to be confirmed, and executes the search task established based on the second image to be confirmed (which will be referred to as a second search task hereinafter), so as to obtain a new target image.

Optionally, the search range of the second search task is the same as the search range of the first search task, the search duration of the second search task is the same as the search duration of the first search task, and the human body comparison time interval of the second search task is the same as the human body comparison time interval of the first search task.

In order to enable the relevant personnel to know the track of the searched object in time, under the condition that the face similarity between the fourth image and the second image to be confirmed exceeds the face similarity threshold value and the second image to be confirmed contains a human body, the object searching device can send a second alarm instruction containing the first image to be confirmed to the second terminal, wherein the second alarm instruction is used for indicating the second terminal to display the first image to be confirmed. Therefore, the related personnel can know the track of the searched object through the second terminal and further find the searched object.

As an alternative embodiment, the object search apparatus performs the following steps in the process of performing step 101:

12. and acquiring a first video stream to be processed.

In this step, the object searching device is in communication connection with the face camera. The object finding device can acquire a first video stream to be processed from the face camera through the communication connection. For example, if the object search device is in communication connection with the face camera in the area a, the object search device may obtain the video stream acquired by the face camera in the area a.

13. And intercepting a frame image from the first video stream to be processed as the first image to be confirmed.

The object searching device can determine whether the searched object appears in the range monitored by the face camera by comparing the image in the first video stream to be processed with the image in the face image library. For example, the first video stream to be processed is acquired by a face camera in area a. The object searching device can determine whether the searching object is present in the area a by comparing the image in the first video stream to be processed with the face image of the searching object (i.e. the image in the face image library).

Optionally, the object searching apparatus intercepts any frame of image from the first to-be-processed video stream as a first to-be-confirmed image.

14. and acquiring a second video stream to be processed.

In this step, the object searching device is also in communication connection with the human body camera. The object searching device can acquire the video stream collected by the human body camera from the human body camera through the communication connection. For example, if the object search device is in communication connection with the human body camera in the area a, the object search device may obtain the video stream acquired by the human body camera in the area a.

In the embodiment of the application, the second video stream to be processed includes the first video stream to be processed and a video stream acquired by a human body camera.

15. And storing the images in the second video stream to be processed into the database.

The object searching device stores the images in the second video stream to be processed into the database, so that human body searching can be carried out in the range monitored by the human body camera and the range monitored by the human body camera. For example, the second video stream to be processed includes a video stream acquired by a face camera in the area a and a video stream acquired by a human body camera in the area a. And in the process of executing the human body searching task by the object searching device, comparing the first image to be confirmed with the image in the second video stream to be processed by a human body so as to determine whether the searched object appears in the area A.

It should be understood that, since the requirement of the face comparison on the image quality is higher than that of the human body comparison, in step 13, the object searching apparatus performs the face comparison on the face image of the searched object and the image in the first to-be-processed video stream, and some images containing the searched object may be missed.

For example (example 1), the first to-be-processed video stream contains image a, image b, and image c. The object finding means determines that the face similarity between the face image of the finding object and the image a exceeds a face similarity threshold. However, since the image quality of the image b is lower than the quality threshold, the object finding device determines that the face similarity between the face image of the finding object and the image b does not exceed the face similarity threshold.

Under the condition that the missed images containing the search objects contain the human bodies of the search objects, the object search device can find the missed images containing the search objects by executing the step 15, so that the search effect is improved. For example, in example 1, if the image b contains a human body of the search target, the target search apparatus determines that the search target is contained in the image b when it is determined that the human body similarity between the image a and the image b exceeds the human body similarity threshold by taking the image a as the first image to be confirmed in the process of step 15.

As an optional implementation manner, the at least one target image includes a fifth image, and after obtaining the at least one target image, the object search apparatus further performs the following steps:

16. and when a video viewing request for the fifth image sent by the second terminal is received, intercepting a video stream to be shown containing the fifth image from the video stream to be processed.

In order to further confirm the track of the searched object, the related personnel can send a request for viewing the video containing the searched object to the object searching device through the second terminal.

And the object searching device intercepts the video stream to be displayed containing the fifth image from the video stream to be processed under the condition of receiving a video viewing request aiming at the fifth image sent by the second terminal. It should be understood that the playing time of the video stream to be displayed may be determined according to actual requirements, which is not limited in the present application.

17. And sending the video stream to be displayed to the second terminal.

The object searching device sends the video stream to be displayed to the second terminal, so that the second terminal can display the video stream to be displayed to related personnel, and the related personnel can acquire more track information of the searched object.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

The method of the embodiments of the present application is set forth above in detail and the apparatus of the embodiments of the present application is provided below.

Referring to fig. 2, fig. 2 is a schematic structural diagram of an object searching apparatus according to an embodiment of the present application, where the apparatus 1 includes: an acquisition unit 11, a processing unit 12, a storage unit 13, an interception unit 14, and a transmission unit 15, wherein:

an acquiring unit 11, configured to acquire a first image to be confirmed and a face image library including a face image of a search object;

the processing unit 12 is configured to execute a human body search task when it is determined that an image with a human face similarity exceeding a human face similarity threshold exists in the human face image library and it is determined that the first image to be determined contains a human body of the search object;

With reference to any embodiment of the present application, the obtaining unit 11 is further configured to obtain a human body search duration before the human body search task is executed;

With reference to any embodiment of the present application, the obtaining unit 11 is further configured to obtain a human body search range before the human body search task is executed;

the obtaining unit 11 is further configured to obtain a human body comparison time interval before the human body search task is executed;

With reference to any embodiment of the present application, the obtaining unit 11 is further configured to, after obtaining a first image to be confirmed having feature data matching the first image to be confirmed by using the first image to be confirmed to search a database, obtain a second image to be confirmed before performing a human body search task; the acquisition position of the second image to be confirmed is different from the acquisition position of the first image to be confirmed;

the processing unit 12 is further configured to, when it is determined that the face similarity between the fourth image and the second image to be confirmed exceeds the face similarity threshold and it is determined that the second image to be confirmed includes a human body, stop executing the human body search task, perform human body comparison between the second image to be confirmed and the images in the database, and obtain an image whose similarity with the second image to be confirmed exceeds the human body similarity threshold, as a new target image; the fourth image is an image in the face image library, wherein the face similarity between the fourth image and the first image to be confirmed exceeds the face similarity threshold.

With reference to any embodiment of the present application, the obtaining unit 11 is configured to:

With reference to any embodiment of the present application, the obtaining unit 11 is further configured to obtain a second video stream to be processed before the human body search task is executed; the second video stream to be processed comprises the first video stream to be processed and a video stream acquired by a human body camera;

the object searching device further comprises: a storage unit 13, configured to store the image in the second to-be-processed video stream in the database.

an intercepting unit 14, configured to intercept, when a video viewing request for the fifth image sent by the second terminal is received, a to-be-displayed video stream including the fifth image from the to-be-processed video stream;

a sending unit 15, configured to send the video stream to be displayed to the second terminal.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present application may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Fig. 3 is a schematic diagram of a hardware structure of an object search apparatus according to an embodiment of the present application. The object finding device 2 comprises a processor 21, a memory 22, an input device 23, an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are coupled by a connector, which includes various interfaces, transmission lines or buses, etc., and the embodiment of the present application is not limited thereto. It should be appreciated that in various embodiments of the present application, coupled refers to being interconnected in a particular manner, including being directly connected or indirectly connected through other devices, such as through various interfaces, transmission lines, buses, and the like.

The processor 21 may be one or more Graphics Processing Units (GPUs), and in the case that the processor 21 is one GPU, the GPU may be a single-core GPU or a multi-core GPU. Alternatively, the processor 21 may be a processor group composed of a plurality of GPUs, and the plurality of processors are coupled to each other through one or more buses. Alternatively, the processor may be other types of processors, and the like, and the embodiments of the present application are not limited.

Memory 22 may be used to store computer program instructions, as well as various types of computer program code for executing the program code of aspects of the present application. Alternatively, the memory includes, but is not limited to, Random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for associated instructions and data.

The input means 23 are for inputting data and/or signals and the output means 24 are for outputting data and/or signals. The input device 23 and the output device 24 may be separate devices or may be an integral device.

It is understood that, in the embodiment of the present application, the memory 22 may be used to store not only the relevant instructions, but also relevant data, for example, the memory 22 may be used to store the first image to be confirmed acquired through the input device 23, or the memory 22 may also be used to store at least one target image obtained through the processor 21, and the like, and the embodiment of the present application is not limited to the data specifically stored in the memory.

It will be appreciated that fig. 3 only shows a simplified design of the object finding apparatus. In practical applications, the object search apparatus may also include other necessary components, including but not limited to any number of input/output devices, processors, memories, etc., and all object search apparatuses that can implement the embodiments of the present application are within the scope of the present application.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It is also clear to those skilled in the art that the descriptions of the various embodiments of the present application have different emphasis, and for convenience and brevity of description, the same or similar parts may not be repeated in different embodiments, so that the parts that are not described or not described in detail in a certain embodiment may refer to the descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in or transmitted over a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)), or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., Digital Versatile Disk (DVD)), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the above method embodiments. And the aforementioned storage medium includes: various media that can store program codes, such as a read-only memory (ROM) or a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Claims

1. An object finding method, characterized in that the method comprises:

2. The method of claim 1, wherein prior to said performing a human finding task, the method further comprises:

acquiring the human body searching time;

3. The method of claim 2, wherein prior to said performing a human finding task, the method further comprises: acquiring a human body searching range;

4. The method of claim 3, wherein the at least one target image comprises a first image and a second image;

5. The method of any one of claims 1 to 4, wherein the human search task further comprises:

6. The method of claim 1, wherein after the retrieving a database using the first to-be-confirmed image to obtain the first to-be-confirmed image having feature data matching the first to-be-confirmed image, before the performing a human body finding task, the method further comprises:

7. The method according to any one of claims 1 to 6, wherein the acquiring of the first image to be confirmed comprises:

8. The method of claim 7, wherein prior to said performing a human finding task, the method further comprises:

9. The method of claim 8, wherein the at least one target image comprises a fifth image, the method further comprising:

and sending the video stream to be displayed to the second terminal.

10. An object finding apparatus, characterized in that the apparatus comprises:

11. An electronic device, comprising: a processor and a memory for storing computer program code comprising computer instructions which, if executed by the processor, the electronic device performs the method of any of claims 1 to 9.

12. A computer-readable storage medium, in which a computer program is stored, which computer program comprises program instructions which, if executed by a processor, cause the processor to carry out the method of any one of claims 1 to 9.