WO2023005662A1 - 图像处理方法及装置、电子设备、程序产品及计算机可读存储介质 - Google Patents

图像处理方法及装置、电子设备、程序产品及计算机可读存储介质 Download PDF

Info

Publication number
WO2023005662A1
WO2023005662A1 PCT/CN2022/105242 CN2022105242W WO2023005662A1 WO 2023005662 A1 WO2023005662 A1 WO 2023005662A1 CN 2022105242 W CN2022105242 W CN 2022105242W WO 2023005662 A1 WO2023005662 A1 WO 2023005662A1
Authority
WO
WIPO (PCT)
Prior art keywords
face image
image
target
escort
task
Prior art date
Application number
PCT/CN2022/105242
Other languages
English (en)
French (fr)
Inventor
周俊竹
张泽
方琪
周冉曌
洪蔓漫
Original Assignee
上海商汤智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海商汤智能科技有限公司 filed Critical 上海商汤智能科技有限公司
Publication of WO2023005662A1 publication Critical patent/WO2023005662A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G06Q10/063114—Status monitoring or status determination for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras

Definitions

  • the present disclosure relates to the field of security technologies, and in particular to an image processing method and device, electronic equipment, program products, and computer-readable storage media.
  • Escort task means that the escort accompanies the escorted person to the destination. In order to determine whether the escorted person has reached the destination, it is necessary to monitor the escort mission.
  • the traditional method determines whether the escort has reached the destination by manual point-to-point, so as to complete the monitoring of the escort task.
  • the monitoring efficiency of this method is low, and the labor cost is high.
  • Embodiments of the present disclosure provide an image processing method and device, electronic equipment, program products, and a computer-readable storage medium.
  • An embodiment of the present disclosure provides an image processing method, the method comprising: acquiring a target accompanying task and a first human face image, the target accompanying task includes at least one escort, and the acquisition location of the first human face image is The termination position of the target accompanying task; acquiring at least one second face image, the time stamp of the at least one second face image is different from the time stamp of the first face image, and the at least one face image The acquisition position of the second human face image is the termination position; in the case of determining that the characters in the first human face image include one of the at least one escort, determine whether the target accompanying task meets the task requirements , the detection result is obtained, the task requirement includes: the at least one second face image contains at least one escort of the target accompanying task; the detection result includes that the target accompanying task meets the task requirement In the case of , it is determined that the accompanying result of the target accompanying task is normal.
  • the method before the determination of whether the target accompanying task meets the task requirements, the method further includes: obtaining the time spent performing the target accompanying task; the task requirements also include : The time spent on executing the target accompanying task is less than the execution duration of the target accompanying task.
  • the acquiring the time spent on executing the target accompanying task includes: acquiring the start time stamp of performing the target accompanying task; according to the start time stamp and the first person The time stamp of the face image is used to obtain the time spent performing the target accompanying task.
  • the escort route of the target escort task is located in the target area, and the at least one escort includes the target escort; the method further includes: acquiring a first image of the target area and A first trajectory of the target escort in the first image, the first trajectory being displayed in the first image.
  • the acquiring the trajectory of the target escort in the first image includes: acquiring at least one second image and a third face image of the target escort, The at least one second image is collected by at least one target camera in the target area; at least one third image is determined from the at least one second image, and the at least one third image is Matching with the third face image; obtaining the first track of the target escort in the first image according to the position of the camera capturing the at least one third image in the first image .
  • the method before acquiring at least one second image, further includes: acquiring a valid time period; sending a trajectory detection instruction to the at least one target camera, and the trajectory detection instruction is used to indicate The at least one target camera collects images within the effective time period; the acquiring at least one second image includes: using at least one image captured by the at least one target camera as the at least one second image image.
  • the displaying the first trajectory in the first image includes: when an instruction to display the trajectory of the target escort is detected, displaying the first trajectory in the first image The first trace is shown in .
  • the method before displaying the first trajectory in the first image, further includes: acquiring a fourth face image of the object to be searched, and using the fourth face image Retrieving the database to obtain a fifth face image matching the fourth face image; displaying the first track in the first image includes: determining that the object to be searched meets the track display condition In this case, the first track is displayed in the first image; the track display condition includes one of the following: the object to be found is one of the at least one escort, and the object to be found is one of said at least one escort.
  • the acquisition of the fourth face image of the object to be searched for, using the fourth face image to retrieve a database, and obtaining a fifth face image matching the fourth face image include : When it is determined that the person in the first human face image does not include any one of the at least one escort or when it is determined that the at least one second human face image does not include the at least one escort In this case, the fourth face image of the object to be searched is obtained, and the database is searched using the fourth face image to obtain a fifth face image matching the fourth face image.
  • the method also includes: acquiring at least one sixth human face image, the collection position of the at least one sixth human face image is the termination position; after determining that the at least one sixth human face image does not contain the In the case of the at least one accompanying person, output supplementary recording prompt information; according to at least one seventh human face image and the at least one sixth human face image input for the supplementary recording prompt information, the at least A second face image, the collection position of the at least one seventh face image is the termination position.
  • the method further includes: outputting warning information when the detection result includes that the target accompanying task does not satisfy the task requirement.
  • the acquisition of the target accompanying task includes: acquiring the eighth human face image, at least one ninth human face image and the termination position in the case of executing the creating accompanying task program, the The acquisition position of at least one ninth human face image is the same as the acquisition position of the eighth human face image; when it is determined that the person in the eighth human face image includes a registered escort, according to the at least one The registered accompanying person and the person in the eighth person's face image contained in the ninth person's face image are obtained to obtain the at least one person accompanying; after determining that the person in the eighth person's face image is registered In the case of an accompanying person, the at least one accompanying person is obtained according to the registered accompanying person included in the at least one ninth facial image; according to the termination position, the at least one accompanying person and the At least one escort creates the target escort task.
  • the registered accompanied person contained in the at least one ninth human face image includes the first person, and the registered escort included in the at least one ninth human face image Registering the escorted person and obtaining the at least one accompanied person includes: when a deletion instruction for the first person is detected, deleting the first person from the at least one ninth face image Deleting the included registered escorts to obtain the at least one accompanied person; or, in the case of detecting an addition instruction for a second person, according to the second person and the at least one first sheet The registered accompanying persons included in the nine face images are obtained to obtain the at least one accompanied person.
  • the acquiring the end position includes: when an instruction to input an end position is detected, displaying at least one position to be selected; after detecting a selection instruction for the at least one position to be selected In some cases, the end position is obtained according to the selection instruction and the at least one candidate position.
  • the method further includes: obtaining an accompanying reason for the target accompanying task.
  • the method before creating the target escort task according to the termination location, the at least one escort and the at least one escort, the method further includes: according to the eighth The starting position is obtained from the collection position of the face image; the creation of the target accompanying task based on the termination position, the at least one escort and the at least one accompanied person includes: based on the starting position, The termination location, the at least one escort and the at least one escort create the target escort task.
  • An embodiment of the present disclosure provides an image processing device, which includes: an acquisition unit configured to acquire a target accompanying task and a first human face map, the target accompanying task includes at least one escort, and the first human face
  • the image collection location is the termination location of the target accompanying task;
  • the acquisition unit is further configured to acquire at least one second face image, and the time stamp of the at least one second face image is the same as the first The time stamps of the face images are different, and the collection position of the at least one second face image is the termination position;
  • the determining unit is configured to determine that the person in the first face image includes the at least one accompanying person In the case of one of the personnel, it is determined whether the target escort task meets the task requirements, and the detection result is obtained.
  • the task requirements include: the at least one second face image contains at least one of the target escort tasks.
  • the determination unit is further configured to determine that the accompanying result of the target accompanying task is normal when the detection result includes that the target accompanying task meets
  • An embodiment of the present disclosure provides an electronic device, including: a processor and a memory, the memory is configured to store computer program codes, the computer program codes include computer instructions, and when the processor executes the computer instructions , the electronic device executes a method such as the above image processing method and any possible implementation thereof.
  • An embodiment of the present disclosure provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a processor, the The processor executes the method according to the first aspect and any possible implementation manner thereof.
  • An embodiment of the present disclosure also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the some or all of the steps.
  • FIG. 1 is a schematic diagram of an accompanying monitoring system architecture provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of another accompanying monitoring system architecture provided by an embodiment of the present disclosure.
  • FIG. 4 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure.
  • FIG. 5 is a schematic diagram of a hardware structure of an image processing device provided by an embodiment of the present disclosure.
  • At least one (item) means one or more
  • “multiple” means two or more
  • at least two (items) means two or three And three or more
  • "and/or” is used to describe the association relationship of associated objects, indicating that there can be three types of relationships, for example, "A and/or B” can mean: only A exists, only B exists, and A exists at the same time and B, where A and B can be singular or plural.
  • the character "/" can indicate that the contextual objects are an "or” relationship, which refers to any combination of these items, including any combination of single items (items) or plural items (items).
  • At least one item (piece) of a, b or c can mean: a, b, c, "a and b", “a and c", “b and c", or "a and b and c ", where a, b, c can be single or multiple.
  • 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 present disclosure.
  • the occurrences of this 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 understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.
  • Escort task means that the escort accompanies the escorted person to the destination.
  • the escort mission needs to be monitored.
  • the traditional method determines whether the escort has reached the destination by manual point-to-point, so as to complete the monitoring of the escort task.
  • the monitoring efficiency of this method is low, and the labor cost is high. Based on this, embodiments of the present disclosure provide a technical solution to improve monitoring efficiency and reduce labor costs.
  • the execution subject of the embodiments of the present disclosure is an image processing apparatus, where the image processing apparatus may be any electronic device capable of executing the technical solutions disclosed in the method embodiments of the present disclosure.
  • the image processing device may be one of the following: a mobile phone, a computer, a tablet computer, and a wearable smart device.
  • FIG. 1 is a schematic structural diagram of an accompanying monitoring system 11 provided by an embodiment of the present disclosure.
  • image processing device 112 may be a server.
  • the image processing device 112 can be deployed in the control center of the supervision area.
  • At least one camera 111 is a camera within the supervision area.
  • At least one camera 111 is configured to collect one or more of images and videos in the supervision area.
  • the image processing device 112 processes one or more of the images and videos collected by the at least one camera 111 based on the technical solutions provided below, and can monitor the target accompanying tasks in the supervision area.
  • the image processing device 112 can acquire the first human face image and at least one second human face image through at least one camera 111, and then based on the technical solution provided below, the first human face image and at least one second human face image imagery, monitoring target escort missions within the regulatory area.
  • FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present disclosure.
  • the target accompanying task includes at least one escort, and the collection location of the first human face image is the termination position of the target accompanying task.
  • the target escort task includes the following information: the end position of the target escort task, the list of escorts, and the list of escorts, wherein the list of escorts includes at least one escort, and the list of escorts includes at least one escort .
  • the list of escorts may be at least one face image, and the list of escorts may also be at least one face image.
  • the escort list of the target escort task includes Zhang San's face image
  • the escort list of the target escort task includes the face images of Li Si and Wang Wu.
  • the escorts for the target escort task include Zhang San.
  • the escorts for the task of escorting the target include Li Si and Wang Wu.
  • the image collection location may be the location of the imaging device that collects the image.
  • the first human face image is collected by camera a
  • the position of camera a is the collection position of the first human face image.
  • the image collection location may also be the location of the scene corresponding to the image.
  • the first human face image is obtained by collecting images of scene b by camera a
  • the position of scene b is the collection position of the first human face image.
  • the first face image is collected by an access control device, and the location where the first face image is collected is the location of the access control device.
  • the collection position of the first face image is the end position, that is, the position of the access control device that collects the first face image is the end position.
  • the image processing device receives the target accompanying task input by the user through the input component.
  • the input component includes at least one of the following: a keyboard, a mouse, a touch screen, a touch pad, and an audio input device.
  • the image processing device receives the target accompanying task sent by the terminal.
  • the terminal may be at least one of the following: an access control device, a mobile phone, a computer, a tablet computer, a server, and a wearable device.
  • the image processing device receives the first face image input by the user through the input component.
  • the image processing device receives the first face image sent by the terminal.
  • the image processing apparatus includes an imaging device. The image processing device uses an imaging device to collect a face image as a first face image.
  • the step of acquiring the target accompanying task and the step of acquiring the first human face image may be performed separately or simultaneously.
  • the image processing device may first acquire the task of accompanying the target, and then acquire the first face image.
  • the image processing device may acquire the first face image first, and then acquire the target accompanying task.
  • the image processing device acquires the first human face image during the process of acquiring the target accompanying task, or acquires the target accompanying task during the process of acquiring the first human face image.
  • At least one second face image may include one second face image, or may include two or more second face images.
  • the time stamp of the first face image is different from the time stamp of at least one second face image, that is, the collection time of the first face image is the same as the collection time of any second face image. different.
  • the time stamp of the first face image is different from the time stamp of image a.
  • the time stamp of the first face image is different from the time stamp of image a, and the time stamp of the first face image is different from the time stamp of image b Poke different.
  • the collection positions of at least one second human face image are all end positions, that is, the positions of any second human face images are all end positions.
  • the time interval between the collection time of any one of the at least one second face image and the collection time of the first face image is smaller than the first time threshold.
  • the first time threshold is 2 minutes
  • the acquisition time of the first face image is t1
  • at least one second face image includes image a and image b. Then, the time interval between the acquisition time of image a and t1 is less than 2 minutes, and the time interval between the acquisition time of image b and t1 is less than 2 minutes.
  • the at least one second face image is collected by the access control device, and the collection location of the at least one second face image is the location of the access control device.
  • the collection position of the at least one second face image is the end position, that is, the position of the access control device that collects the at least one second face image is the end position.
  • the image processing device receives at least one second face image input by a user through an input component.
  • the image processing device receives at least one second face image sent by the terminal.
  • the above-mentioned task requirements include: the above-mentioned at least one of the first
  • the two-person face image contains at least one escort of the above-mentioned target accompanying task.
  • the characters in the first face image include at least one of the escorts, indicating that the characters in the first face image are escorts, that is, the escort of the target accompanying task has reached the end position of the target accompanying task, that is, the target accompanying task has been completed. Finish. Therefore, the image processing device determines whether the target accompanying task satisfies the task requirement and obtains the detection result when it is determined that the person in the first human face image includes at least one of the escorts. Wherein, the detection result includes that the target accompanying task satisfies the task requirement or the target accompanying task does not meet the task requirement.
  • the task requirement includes at least one second human face image including at least one escorted person of the target escort task, that is, the at least one second human face image includes the human face images of all the accompanied people.
  • the image processing device determines whether the target accompanying task meets the task requirement by determining whether at least one second human face image contains at least one accompanying person.
  • the image processing apparatus acquires at least one second face image before determining that the person in the first face image includes one of the at least one escort.
  • the escort inputs an instruction to the image processing device to end the task of escorting the target, and the image processing device turns on the camera to collect images after detecting the instruction.
  • the image processing device outputs the first prompt message of "Please escort for face recognition”, and uses the face image collected by the camera after outputting the first prompt message as the first face image.
  • After collecting the first face image output the second prompt message of "please escort for face recognition", and use at least one face image collected by the camera after outputting the second prompt message as at least one The second face image.
  • the escort inputs an instruction to the access control device to end the task of escorting the target, and the access control device turns on the camera to collect images after detecting the instruction.
  • the access control device outputs a third prompt message of "Please escort for face recognition", and uses the face image collected by the camera after outputting the third prompt message as the first face image.
  • After collecting the first face image output the fourth prompt message of "Please perform face recognition for the escort", and use at least one face image collected by the camera after outputting the fourth prompt message as at least one The second face image.
  • the access control device sends the first face image and at least one second face image to the image processing device.
  • the image processing apparatus acquires at least one second face image when it is determined that the person in the first face image includes one of the at least one escort.
  • the escort inputs an instruction to the image processing device to end the task of escorting the target, and the image processing device turns on the camera to collect images after detecting the instruction.
  • the image processing device outputs the fifth prompt message of "Please escort for face recognition", and uses the face image collected by the camera after outputting the fifth prompt message as the first face image.
  • the escort After collecting the first human face image, face recognition is performed on the first human face image, and when it is determined that the person in the first human face image includes at least one of the escorts, output "please be accompanied” Perform face recognition" as the sixth prompt information, and use at least one face image collected by the camera after outputting the sixth prompt information as at least one second face image.
  • the escort inputs an instruction to the access control device to end the task of escorting the target, and the image processing device turns on the camera to collect images after detecting the instruction.
  • the image processing device outputs a seventh prompt message of "Please escort for face recognition", and uses at least one face image collected by the camera after outputting the seventh prompt message as at least one second face image.
  • the eighth prompt message After collecting at least one second face image, output the eighth prompt message of "Please escort for face recognition", and use the face image collected by the camera after outputting the eighth prompt message as the first face image.
  • the access control device After collecting the first face image and at least one second face image, the access control device sends the sum of the first face image to the image processing device. After the image processing device receives the first face image sent by the access control device, it performs face recognition on the first face image, and when it is determined that the person in the first face image includes at least one of the escorts , and send the first verification passing instruction to the access control device. The access control device sends at least one second face image to the image processing device after detecting the first verification pass instruction.
  • the target accompanying task meets the task requirements, that is, at least one second face image contains at least one accompanying person of the target accompanying task. At this time, it means that all the accompanying persons have reached the end position of the target accompanying task, and then the target is determined. Accompanying tasks are normal.
  • the image processing device determines that at least one second face image does not contain at least one escort of the target escort task, that is, at least one second face image does not contain all the escorts, it is determined that the target escort task does not meet the task requirements, That is, it is determined that the target accompanying task is abnormal.
  • the image processing device determines whether the person in the first face image is an escort by performing face recognition on the first face image. In the case of determining that the person in the first face image is the escort, it is determined that the escort has arrived at the end position of the target escort task, and then by performing face recognition on at least one second face image, it is determined that at least one person to be accompanied Whether the member reaches the termination position. In this way, the monitoring of the target accompanying task is completed, the labor cost is reduced, and the monitoring efficiency is improved.
  • the image processing device further performs the following steps before determining whether the target accompanying task meets the task requirements and obtaining the detection result:
  • the time spent on executing the target accompanying task may be the time spent on executing the target accompanying task. For example, if the task of accompanying the target has been executed, the time taken to complete the task of accompanying the target is the time taken to complete the task of accompanying the target.
  • the image processing apparatus receives the time spent on executing the target accompanying task input by the user through the input component. In another implementation manner of acquiring the time spent on executing the target accompanying task, the image processing apparatus receives the time spent on executing the target accompanying task sent by the terminal.
  • the task requirement further includes: the time spent executing the target accompanying task is less than the execution time of the target accompanying task.
  • the execution duration of the target accompanying task is the basis for judging whether the execution of the target accompanying task is timed out.
  • the time spent executing the target accompanying task is less than the execution duration of the target accompanying task, indicating that the execution of the target accompanying task has not timed out; Task has timed out.
  • step 1 the image processing device determines that the target escort task satisfies Task requirements, that is, to determine that the target accompanying task is normal. Otherwise, the image processing device determines that the task requirement is not met, that is, determines that the target accompanying task is abnormal.
  • the image processing device performs the following steps during step 1:
  • the start time stamp represents the time when the target escort task starts to be executed. For example, if the start time stamp of the target escort task is 16:2:3 on July 27, 2021, then the time to start executing the target escort task is 16:2:3 on July 27, 2021.
  • the image processing apparatus receives the start time stamp input by the user through the input component. In another implementation manner of acquiring the execution start time stamp, the image processing apparatus receives the start time stamp sent by the terminal.
  • the time stamp of the image represents the acquisition time of the image. For example, if the time stamp of the first face image is 16:3:3 on July 27, 2021, then the acquisition time of the first face image is 16:3:3 on July 27, 2021.
  • the acquisition time of the first face image is the time when the escort reaches the termination position.
  • the time when the escort reaches the end position can be regarded as the end time of the target accompanying task, so the timestamp of the first face image is the end time of the target accompanying task.
  • the image processing device can then obtain the time taken to finish executing the target accompanying task according to the start time stamp and the time stamp of the first face image, as the above-mentioned time spent performing the target accompanying task.
  • the image processing device uses the time period between the start time stamp and the time stamp of the first face image as the time spent on executing the target accompanying task. In another possible implementation manner, the image processing device determines the duration between the start timestamp and the timestamp of the first face image, and uses the sum of the duration and the first value as the time spent performing the target accompanying task . For example, if the time period between the start time stamp and the time stamp of the first face image is 80 minutes, and the first value is 2 minutes, then it takes 82 minutes to perform the task of escorting the target.
  • the image processing device determines the duration between the start timestamp and the timestamp of the first face image, and uses the difference between the duration and the second value as the time spent performing the target accompanying task . For example, if the time period between the start time stamp and the time stamp of the first face image is 80 minutes, and the second value is 3 minutes, then it takes 77 minutes to perform the task of escorting the target.
  • the escort route of the target escort mission is located within the target area.
  • the target area may be any area, for example, the target area is a campus.
  • the target area is a regulatory area.
  • the target area is a hospital.
  • the escort route of the target escort task is located in the target area, which means that during the execution of the target escort task, the trajectories of all escorts and all escorted persons should be located in the target area.
  • at least one escorted person includes a target escorted person, wherein the target escorted person is any one of the at least one accompanied person.
  • the image processing device further performs the following steps: 4. Acquire the first image of the target area and the first trajectory of the target escort in the first image, and display the above-mentioned first track.
  • the first image is an image obtained by collecting images of the target area.
  • the target area is a campus.
  • the image obtained by collecting images of the campus is the first image.
  • the target area is a supervision area.
  • An image obtained by collecting images of the supervision area is the first image.
  • the track of the accompanied person in the image is determined according to the track of the accompanied person in the target area.
  • the trajectory of the target escort within the target area is starting from point A, passing through point B, and arriving at point C. If in the first image, the pixel corresponding to point A is pixel a, the pixel corresponding to point B is pixel b, and the pixel corresponding to point C is pixel c. Then, the first trajectory is the trajectory passing through pixel a, pixel b and pixel c.
  • the image processing apparatus receives the first image input by the user through the input component. In another implementation manner of acquiring the first image, the image processing apparatus receives the first image sent by the terminal. In an implementation manner of acquiring the first trajectory, the image processing apparatus receives the first trajectory input by the user through the input component. In another implementation manner of acquiring the first track, the image processing apparatus receives the first track sent by the terminal.
  • the step of acquiring the first image and the step of acquiring the first trajectory may be performed separately, or may be performed simultaneously.
  • the image processing device may acquire the first image first, and then acquire the first trajectory.
  • the image processing device may acquire the first trajectory first, and then acquire the first image.
  • the image processing apparatus acquires the first track during the process of acquiring the first image, or acquires the first image during the process of acquiring the first track.
  • the detailed information of the target area displayed in the first image is richer than the detailed information of the target area displayed in the map data.
  • the detailed information of the target area includes one or more than one of the following: outline of the target area, building information in the target area, and road information in the target area.
  • this embodiment displays the track of the target escort in the first image, which can be compared with displaying the track of the target escort in the map.
  • the trajectory of the escort brings better display effect. For example, buildings and roads within regulatory areas cannot be displayed on the map. Obviously, displaying the position where the target is escorted by the target on the map does not have a good display effect. Since the image of the supervision area includes buildings and roads, displaying the trajectory of the target escort on the image of the supervision area can improve the display effect.
  • the target escort in the embodiment of the present disclosure is only an example, and it should not be understood that only the track of one escort can be displayed in the first image.
  • the image processing device may display the trajectories of all escorts in the target escort task in the first image.
  • the image processing device when the image processing device acquires the first image, at least one escort includes a target escort, wherein the target escort is any one of the at least one escort.
  • the image processing device further executes the following steps: 5. Obtain a second trajectory of the target escort in the first image, and display the second trajectory in the first image.
  • the realization process of step 5 can refer to the realization process of step 4, wherein the target escort in step 4 corresponds to the target escort in step 5, and the first trajectory in step 4 corresponds to the second trajectory in step 5.
  • the target escort in the embodiment of the present disclosure is only an example, and it should not be understood that the track of only one escort can be displayed in the first image.
  • the image processing device may display the trajectories of all escorts in the target escort task in the first image.
  • the image processing device displays the first trajectory and the second trajectory in the first image when the first image, the first trajectory and the second trajectory are acquired. That is, in practical applications, the image processing device may display the trajectories of all escorts and all escorted persons in the target escort task in the first image.
  • the image processing device acquires the first trajectory of the target escort in the first image by performing the following steps:
  • the pictures captured by at least one target camera are all located in the target area.
  • the at least one target camera may include one target camera, and the at least one target camera may also include two target cameras or more than two target cameras.
  • At least one second image may include one second image, and at least one second image may also include two or more second images.
  • At least one target camera can also include two target cameras or more than two target cameras, and at least one second image includes two or more second images
  • different second images can be composed of different target cameras.
  • captured by the camera For example, at least one target camera includes camera a and camera b, and at least one second image includes second image A and second image B.
  • the second image A is collected by the camera a
  • the second image B is collected by the camera b.
  • the image processing device receives at least one second image input by a user through an input component.
  • the image processing apparatus receives at least one second image sent by the terminal.
  • the image processing device receives a third face image input by a user through an input component. In another implementation manner of acquiring the third face image, the image processing device receives the third face image sent by the terminal. It should be understood that, in the embodiments of the present disclosure, the step of acquiring at least one second image and the step of acquiring the third face image may be performed separately or simultaneously. For example, the image processing device may acquire at least one second image first, and then acquire a third face image. For another example, the image processing device may acquire a third face image first, and then acquire at least one second image. For another example, the image processing device acquires a third human face image during the process of acquiring at least one second image, or acquires at least one second image during the process of acquiring the third human face image.
  • the images matched with the third face image all include the target escort. At least one third image matches the third face, that is, at least one third image contains the target escort.
  • the third image includes the target escort, indicating that the target escort appears within the shooting range of the target camera that collects the third image. Therefore, the position of the target escort can be determined according to the position of the target camera that captures the third image.
  • the position of the target camera in the first image is determined according to the position of the target camera in the target area. For example, if the target camera is at point A of the target area, in the first image, the pixel corresponding to point A is pixel a, then the position of the target camera in the first image is the position of pixel a in the first image.
  • the image processing device uses the position of the target camera that captures the third image in the first image as the position of the target escort in the first image.
  • at least one third image includes a third image a, the third image a is captured by the target camera A, and the position of the target camera A in the first image is p1. Then, the first trajectory of the target escort in the first image is p1.
  • the at least one third image includes a third image a and a third image b, the third image a is captured by the target camera A, and the third image b is captured by the target camera B.
  • the position of target camera A in the first image is p1, and the position of target camera B in the first image is p2.
  • the first trajectory of the target escort in the first image is the trajectory between p1 and p2.
  • the image processing device may acquire the second trajectory of the target escort in the first image through the following steps: acquiring at least one second image and the face image of the target escort of the target escort, the realization of this step
  • the process refer to the implementation process of step 6, wherein the target escort corresponds to the target escort, and the face image of the target escort corresponds to the third face image.
  • the implementation process of this step can refer to the implementation process of step 7, wherein at least One third image corresponds to at least one image of the target escort, and the face image of the target escort corresponds to the third face image.
  • the second track of the target escort in the above-mentioned first image is obtained.
  • At least one third image corresponds to at least one target escort image
  • the first trajectory corresponds to the second trajectory.
  • the image processing device before acquiring at least one second image, the image processing device further performs the following steps:
  • the at least one target camera can collect images within a specified time period.
  • the working time period is the time period during which at least one target camera collects images according to regulations.
  • the image processing apparatus receives the working time period input by the user through the input component.
  • the image processing apparatus receives the working time period sent by the terminal.
  • the image processing device needs to use the images collected by at least one target camera to determine the trajectory of the target escort, and the accompanying task may be performed within a certain period of time, so that at least one target camera collects images during the execution time period of the accompanying task , the work efficiency of at least one target camera can be improved, and the energy consumption of at least one target camera can be reduced.
  • the trajectory detection instruction is used to instruct at least one target camera to collect images during the execution time period of the target accompanying task.
  • the trajectory detection instruction is determined by the image processing device according to the execution time period of the target accompanying task.
  • the trajectory detection instruction is configured by the user through the image processing device. For example, the manager of the target area wishes to make the cameras in the target area collect images from 8:00 to 20:00 every day, and then configure trajectory detection instructions through the image processing device to indicate that at least one target camera is in the target escort task. Acquire images during the execution time period.
  • the image processing device can enable the at least one target camera to collect images during the working time period, thereby improving the working efficiency of the at least one target camera and reducing the energy consumption of the at least one target camera.
  • the image processing device acquires at least one second image by performing the following steps:
  • the image processing device displays the first trajectory in the first image in case an instruction to display the trajectory of the target escort is detected.
  • the user inputs an instruction to display the track of the target escort to the image processing device through the input component. For example, the user inputs an instruction to display the track of the target escort to the image processing device by clicking the touch screen of the image processing device.
  • the image processing device further performs the following steps before displaying the first trajectory in the first image:
  • the object to be found may be the person the user wishes to find. For example, if the user wants to check the trajectory of Zhang San in the target area, Zhang San can be used as the object to be found.
  • the database includes registered face images and identity information of people included in the registered face images.
  • the image processing device receives a fourth face image input by a user through an input component.
  • the image processing device receives the fourth face image sent by the terminal.
  • the images matched with the fourth face image all contain the object to be searched.
  • the fifth face image matches the third face, that is, the fifth face image contains the object to be searched.
  • the image processing device displays the first trajectory in the first image when it is determined that the object to be searched satisfies the trajectory display condition, wherein the trajectory display condition includes one of the following: the object to be searched It is one of at least one escort, and the object to be found is one of at least one escort.
  • the image processing device when the image processing device determines that the object to be searched is the escort, or the object to be searched is the escorted person, it displays the first trajectory of the target escorted person in the first image.
  • the object to be searched has a common track with at least one escort and at least one accompanied person, that is, the object to be searched, at least one escort , At least one of the accompanying persons is a companion. Therefore, the image processing device displays the track of the person traveling with the object to be searched in the target area, which is beneficial to find the object to be found.
  • the image processing device performs the following steps during step 12:
  • the first face image is an image used to verify the identity information of the escort, and if the first face image does not include any of the at least one escort, it means that the task of escorting the target is abnormal. At least one second face image does not include at least one escorted person, indicating that the escorted target has not reached the termination position, that is, the target escorted task is abnormal.
  • the image processing device executes step 12 when it is determined that the person in the first face image does not include any of the at least one escort, and then displays the first trajectory based on the execution result of step 12 .
  • the object to be searched is an escort in the task of escorting the target, and the object to be searched is an escort in the task of accompanying the target.
  • the object to be searched is an escort who does not appear in the first face image, or the object to be searched is an escort who does not appear in at least one second face image.
  • at least one escort includes Zhang San and Li Si, and at least one escort includes Wang Wu and Saturday.
  • the first face image includes Zhang San, and at least one second face image includes Wang Wu.
  • the object to be searched can be Li Si, and the object to be searched can also be Saturday.
  • the image processing device acquires at least one second face image when it is determined that the person in the first face image is one of the at least one escort. In some embodiments, after the image processing device determines that the person in the first face image is one of the at least one escort, before acquiring at least one second face image, the following steps are further performed:
  • At least one sixth facial image may include one sixth facial image, or may include two or more sixth facial images.
  • the collection positions of at least one sixth human face image are all end positions, that is, the positions of any sixth human face image are all end positions.
  • the at least one sixth face image is collected by the access control device, and the collection location of the at least one sixth face image is the location of the access control device.
  • the collection position of at least one sixth human face image is the end position, that is, the position of the access control device that collects at least one sixth human face image is the end position.
  • the image processing device receives at least one sixth face image input by a user through an input component. In another implementation manner of acquiring at least one sixth face image, the image processing device receives at least one sixth face image sent by the terminal.
  • At least one sixth face image does not contain at least one accompanying person, indicating that the accompanying person may not have returned to the termination position, or the image processing device did not recognize some The escorted person, or an escorted person has returned to the termination location, but does not appear in at least one of the sixth face images.
  • the user may be prompted to confirm the list of escorts who have returned to the termination position, so as to improve the monitoring accuracy of the target escort task.
  • the post-recording prompt information is used to prompt the user to confirm the list of escorts who have returned to the termination position.
  • the post-entry prompt information includes the unrecorded accompanied persons, wherein the unrecorded accompanied persons include the accompanied persons not included in at least one sixth face image.
  • at least one escort of the target escort task includes Zhang San, Li Si, and Wang Wu.
  • the image processing device performs face recognition on the at least one sixth face image, and determines that the at least one sixth face image includes Zhang San. At this time, both Li Si and Wang Wu were not recorded as escorts.
  • the post-recording prompt information may include "the accompanying persons who have not returned include Li Si and Wang Wu".
  • the at least one seventh face image input for the supplementary recording prompt information is the face image of at least one supplementary recording escort, wherein the supplementary recording of the escort includes the user confirming that he has returned to the termination position but not included in the list of escorts who have returned to the terminated position.
  • the image processing device acquires the face image to be verified before acquiring at least one seventh face image input for the post-recording prompt information. In a case where it is determined that the person in the face image to be verified includes at least one of the escorts, at least one seventh face image input for the post-recording prompt information is acquired.
  • the image processing device after the image processing device receives at least one seventh human face image input for the post-recording prompt information, it outputs reconfirmation prompt information. For example, reconfirm that the prompt message is "The task of escorting the target cannot be changed after submission".
  • the image processing device uses at least one seventh face image and at least one sixth face image as the at least one second face image.
  • at least one seventh face image includes image a
  • at least one sixth face image includes image b and image c
  • at least one second face image includes image a, image b and image c.
  • the image processing device prompts the user to confirm the list of escorts who have returned to the termination position by outputting supplementary recording prompt information, thereby improving the monitoring accuracy of the target escort task.
  • the image processing device also performs the following steps:
  • the detection results include that the target accompanying task does not meet the task requirements, indicating that the target accompanying task is abnormal. Therefore, an alarm message is output to prompt relevant personnel that the target accompanying task is abnormal.
  • the warning information carries information indicating that the target escort mission is abnormal.
  • the warning information may be voice prompt information, such as: "The target escort mission has an escort who has not returned to the termination position”.
  • the warning information may be text prompt information, such as: a prompt window pops up on the display interface of the image processing device, and the prompt window contains prompt text, such as: "The task of escorting the target exceeds 20 minutes".
  • the image processing device obtains the target accompanying task by performing the following steps:
  • the eighth face image, at least one ninth face image and the above-mentioned termination position obtain the eighth face image, at least one ninth face image and the above-mentioned termination position, the collection position of the above-mentioned at least one ninth face image is the same as the above-mentioned eighth face image
  • the images are collected at the same location, and the time stamp of the at least one ninth face image is different from the time stamp of the eighth face image.
  • creating the accompanying task program may be a program executed by the image processing device when the creating instruction is detected. For example, if an escort needs to create a target escort task, he can input creation instructions to the image processing device through the touch screen of the image processing device, so that the image processing device executes the program for creating an escort task and displays an interface for creating an escort task. The escort can then create a target escort task by inputting the target escort task information on the create escort task interface.
  • At least one ninth facial image may include one ninth facial image, or may include two or more ninth facial images.
  • the timestamp of the eighth facial image is different from the timestamp of at least one ninth facial image, that is, the acquisition time of the eighth facial image is the same as the acquisition time of any ninth facial image. different.
  • the time stamp of the eighth face image is different from the time stamp of image a.
  • the time stamp of the eighth face image is different from the time stamp of image a, and the time stamp of the eighth face image is different from the time stamp of image b Poke different.
  • the time interval between the acquisition time of any one of the at least one ninth facial image and the acquisition time of the eighth facial image is less than the second time threshold, wherein the second The time threshold may also be the same as the first time threshold, and the second time threshold may also be different from the first time threshold.
  • the second time threshold is 3 minutes
  • the acquisition time of the eighth face image is t1
  • at least one ninth face image includes image a and image b.
  • the time interval between the acquisition time of image a and t1 is less than 3 minutes
  • the time interval between the acquisition time of image b and t1 is less than 3 minutes.
  • the termination location is the termination location of the newly created accompanying task, that is, the termination location of the target accompanying mission.
  • the image processing device receives the eighth face image input by the user through the input component. In another implementation manner of acquiring the eighth face image, the image processing device receives the eighth face image sent by the terminal. In yet another implementation manner of acquiring an eighth human face image, the image processing apparatus includes an imaging device. The image processing device uses the imaging device to collect a face image as the eighth face image.
  • the image processing device receives at least one ninth face image input by a user through an input component.
  • the image processing device receives at least one ninth face image sent by the terminal.
  • the image processing apparatus includes an imaging device. The image processing device uses an imaging device to collect a face image as at least one ninth face image.
  • the image processing apparatus receives the termination position input by the user through the input component. In another implementation manner of acquiring the termination location, the image processing apparatus receives the termination location sent by the terminal. It should be understood that in the embodiment of the present disclosure, the step of acquiring the eighth human face image, the step of acquiring at least one ninth human face image, and the step of acquiring the termination position may be performed separately or simultaneously.
  • the image processing apparatus acquires at least one ninth human face image and the termination position before determining that the person in the eighth human face image includes at least one of the escorts.
  • the escort inputs an instruction to the image processing device to end the task of escorting the target, and the image processing device turns on the camera to collect images after detecting the instruction.
  • the image processing device outputs the ninth prompt message of "Please escort for face recognition", and uses the face image collected by the camera after outputting the ninth prompt message as the eighth face image.
  • After collecting the eighth human face image output the tenth prompt message of "Please perform face recognition for the accompanying person", and use at least one face image collected by the camera after outputting the tenth prompt message as at least one Ninth face image.
  • the image processing device collects the eighth face image the position input by the user through the input component is used as the termination position.
  • the escort inputs an instruction to the access control device to end the task of escorting the target.
  • the access control device detects the instruction, it turns on the camera to collect images, and takes the position input by the user through the input component as end position.
  • the access control device outputs the eleventh prompt message of "Please escort for face recognition", and uses the face image collected by the camera after outputting the eleventh prompt message as the eighth face image.
  • After collecting the eighth human face image output the twelfth prompt message of "Please perform face recognition for the escort", and use at least one face image collected by the camera after outputting the twelfth prompt information as at least A ninth face image.
  • the access control device sends the eighth face image, at least one ninth face image and the termination position to the image processing device.
  • the image processing device acquires at least one ninth human face image and the termination position when it is determined that the person in the eighth human face image includes at least one of the escorts.
  • the escort inputs an instruction to the image processing device to end the task of escorting the target, and the image processing device turns on the camera to collect images after detecting the instruction.
  • the image processing device outputs the thirteenth prompt message of "please escort for face recognition", and uses the face image collected by the camera after outputting the thirteenth prompt message as the eighth face image.
  • After collecting the eighth face image perform face recognition on the eighth face image, and when it is determined that the person in the eighth face image includes at least one of the escorts, output "please be accompanied" Perform face recognition" fourteenth prompt information, and use at least one face image collected by the camera after outputting the fourteenth prompt information as at least one ninth face image.
  • the image processing device further uses the position input by the user as the end position when it is determined that the person in the eighth human face image includes at least one of the escorts.
  • the escort inputs an instruction to the access control device to end the task of escorting the target. After detecting the instruction, the image processing device turns on the camera to collect images, and the location input by the user through the input component as the end position.
  • the image processing device outputs a fifteenth prompt message of "Please escort for face recognition", and uses at least one face image collected by the camera after outputting the fifteenth prompt message as at least one ninth face image.
  • the access control device After collecting at least one ninth face image, output the sixteenth prompt message of "please escort for face recognition", and use the face image collected by the camera after outputting the sixteenth prompt message as the eighth face image.
  • the access control device After obtaining the eighth face image, at least one ninth face image and the termination position, the access control device sends the eighth face image to the image processing device.
  • the image processing device receives the eighth face image sent by the access control device, it performs face recognition on the eighth face image, and when it is determined that the person in the eighth face image includes at least one of the escorts , and send the second verification passing instruction to the access control device.
  • the access control device detects the second verification pass instruction, it sends at least one ninth face image and the termination position to the image processing device.
  • registered escorts include escorts with identity information.
  • Zhang San is an escort of area A
  • the manager of area A registers Zhang San through the image processing device.
  • the registration process includes inputting Zhang San's face image a, Zhang San's identity information, and Zhang San's identity to be registered as an escort to the image processing device.
  • the image processing device determines that the person in face image a is Zhang San by registering Zhang San, and that Zhang San is a registered escort.
  • the characters in the eighth face image include registered escorts, indicating that there are escorts creating escort tasks, so it can be based on the registered escorts contained in at least one ninth face image and the characters in the eighth face image , get at least one escort.
  • the image processing device uses the registered escort included in the at least one ninth facial image and the person in the eighth facial image as at least one escort.
  • the registered escorts contained in at least one ninth human face image are Zhang San and Li Si
  • the character in the eighth human face image is Wang Wu.
  • at least one accompanying person includes Zhang San, Li Si and Li Si. Wang Wu.
  • the registered accompanied persons include accompanied persons with identity information.
  • Zhang San is an escort of area A, and the manager of area A registers Zhang San through the image processing device. Including, inputting Zhang San's face image a, Zhang San's identity information, and Zhang San's required registration identity as the accompanying person to the image processing device.
  • the image processing device determines that the person in face image a is Zhang San by registering Zhang San, and that Zhang San is a registered escort.
  • the characters in the eighth face image include registered escorts, indicating that there are escorts creating escort tasks, so at least one escort can be obtained based on the registered escorts contained in at least one ninth face image.
  • the image processing device uses the registered escort contained in at least one ninth human face image as at least one escort.
  • the registered escorts contained in at least one ninth face image are Zhang San and Li Si, and at this time, at least one accompanied person includes Zhang San and Li Si.
  • the image processing device uses the termination position obtained by performing step 18 as the termination position of the target escort task, and uses the at least one escort obtained by performing step 19 as at least one escort of the target escort task, Using the at least one escort obtained by performing step 20 as the at least one escort of the target escort task to create the target escort task.
  • the user can create a target accompanying task through the image processing device, and then can monitor the target accompanying task through face recognition in subsequent processing.
  • the image processing device performs one of the following steps during the step of "obtaining the at least one escorted person according to the registered escorted person included in the at least one ninth human face image":
  • the first person is any registered escort contained in at least one ninth face image.
  • the image processing device determines that the registered escorts contained in the at least one ninth face image include Zhang San and Li Si by performing face recognition on at least one ninth image, then the first person may be Zhang San, The first person can also be Li Si.
  • the user can delete any one or more of the registered escorts contained in at least one ninth face image by inputting a deletion command to the image processing device, and obtain at least one escort.
  • the registered accompanying persons contained in at least one ninth face image include Zhang San, Li Si and Wang Wu, and the user can input a deletion instruction for Zhang San to the image processing device to remove Zhang San from at least one
  • the registered escorts contained in the ninth face image are deleted, and at least one of the escorts is determined to be Li Si and Wang Wu.
  • the user can input a deletion command for Li Si to the image processing device, so as to delete Li Si from the registered escorts contained in at least one ninth face image, and determine that at least one escort is Zhang San and Wang Wu .
  • the user can also input a deletion instruction for Li Si and a deletion instruction for Wang Wu to the image processing device, so as to delete Li Si and Wang Wu from the registered escorts contained in at least one ninth face image, and determine At least one of the escorts was Zhang San.
  • the second person is any registered escort.
  • the image processing device uses the second person and the registered escort contained in at least one ninth face image as at least one escort.
  • the image processing device may perform step 23 on the basis of performing step 22 to obtain at least one escort. For example, the image processing device determines that the registered escorts contained in the at least one ninth face image include Zhang San and Li Si by performing face recognition on the at least one ninth face image. In a case where the deletion instruction for Zhang San and the addition instruction for Wang Wu are detected, it is determined that at least one escort includes Li Si and Wang Wu.
  • the image processing device When the image processing device performs face recognition on at least one ninth face image to determine at least one person to be accompanied, and an error occurs, the image processing device executes step 22, or executes step 23, or executes step 22 and step 23, improving the accuracy of at least one escort, thereby improving the monitoring accuracy of the target escort task.
  • the image processing device acquires the termination position by performing the following steps:
  • the image processing apparatus displays at least one candidate position in a list form. In another possible implementation manner, the image processing apparatus displays at least one position to be selected in the form of a drop-down box.
  • the selection instruction includes a position selected from at least one candidate position.
  • the image processing device can determine the end position according to the selection instruction and at least one candidate position. In some embodiments, the image processing device also performs the following steps:
  • the accompanying reason includes a reason for performing the task of accompanying the target.
  • the reason for accompanying is that the accompanying person is sick and needs to go to the hospital.
  • the reason for the escort is that the escort needs to go shopping.
  • the image processing device before performing step 21, the image processing device further performs the following steps:
  • the image processing device uses the collection position of the eighth human face image as a starting position. After performing step 27, the image processing device performs the following steps in the process of performing step 21:
  • the image processing device uses the starting position obtained by executing step 27 as the starting position of the target accompanying task, and the image processing device uses the ending position obtained by performing step 18 as the ending position of the target accompanying task , at least one escort obtained by performing step 19 is used as at least one escort of the target accompanying task, and at least one escort obtained by performing step 20 is used as at least one accompanied person of the target accompanying task, and the target accompanying task is created.
  • the user after the user has created the task of accompanying the target through the image processing device, the user can check the execution time of the task of accompanying the target through the image processing device.
  • the embodiments of the present disclosure also provide a possible application scenario.
  • the supervisor In the supervision area, when the supervised personnel need to move, they usually need to be accompanied by the supervisor. For example, the supervised person is not feeling well and needs to go to a hospital within the supervision area for medical treatment. At this time, the supervisor needs to accompany the supervised person to the hospital. Therefore, based on the technical solutions provided by the embodiments of the present disclosure, it is possible to monitor the accompanying tasks in the supervision area.
  • FIG. 3 is a schematic structural diagram of another accompanying monitoring system 31 provided by an embodiment of the present disclosure.
  • image processing device 312 may be a server.
  • the image processing device 312 can be deployed in the control center of the supervision area.
  • the camera 311 is a camera in the supervision area
  • the access control device 313 is the access control device in the supervision area.
  • the access control device 313 can collect images, and the access control device has an input component.
  • Supervisor a and supervisor b need to accompany supervised person c and supervised person d from A in the supervision area to B in the supervision area.
  • Supervisor a or supervisor b creates a target escort task on access control device C at A.
  • the process of creating an accompanying task for a target includes that supervisor a or supervisor b inputs an instruction for creating an accompanying task to the access control device, so that the access control device C executes the procedure for creating the accompanying task.
  • Supervisor a or supervisor b inputs the reason for escorting the target to the access control device C.
  • the supervisor a or supervisor b can input to the access control device C that the end position of the target accompanying task is the access control device D at B, and the access control device C receives the input from the supervisor a After the termination position, the termination position is stored.
  • the supervisor a, the supervisor b, the supervised person c and the supervised person d go to the image collection area of the access control device C in turn to collect face images.
  • the access control device C uses the collected face image of the supervisor a, the face image of the supervisor b, the face image of the supervised person c, and the face image of the supervisor d as at least one ninth face image, and At least one ninth face image is stored.
  • the supervisor a or supervisor b goes to the image collection area of the access control device C to collect face images.
  • the access control device C uses the collected face image of the supervisor a or the face image of the supervisor b as the eighth face image, and sends the eighth face image to the image processing device, so that the image processing device 312 determines the eighth face image. Whether the person in the eight-face image contains registered escorts. When the image processing device 312 determines that the person in the eighth face image includes the registered escort, it sends the second verification pass instruction to the access control device C. The access control device C sends at least one ninth human face image and the termination position to the image processing device 312 when detecting the second verification pass instruction. The image processing device 312 further creates a target accompanying task according to the eighth human face image, at least one ninth human facial image, the termination location and the accompanying reason.
  • the supervisor a or supervisor b inputs an instruction to end the target accompanying task to the access control device D, so that the access control device D enters the end target Information on accompanying missions.
  • the access control device D when the access control device D detects an instruction to end the task of escorting the target, it prompts the escort to perform face recognition. At this time, the supervised person c and the supervised person d go to the image collection area of the access control device D to collect face images. The access control device D uses the collected face images of the supervised person c and the supervised person d as at least one second face image, and stores at least one second face image. When the access control device D prompts for verification, the supervisor a or supervisor b goes to the image collection area of the access control device D to collect face images.
  • the access control device D uses the collected face image of the supervisor a or the face image of the supervisor b as the first face image, and sends the first face image to the image processing device, so that the image processing device 312 determines the first face image. Whether the person in a face image includes the escort of the target accompanying task. When the image processing device 312 determines that the person in the first human face image includes the escort of the target accompanying task, and the collection position of the first human face image is the end position of the target accompanying task, it sends the first correction to the access control device D. Pass the instruction. The access control device D sends at least one second face image to the image processing device 312 when the first verification instruction is detected.
  • the image processing device 312 further determines whether the collection position of the at least one second human face image is the termination position of the target escort task, and whether the at least one second human face image includes all the escorts of the target escort task. When the image processing device 312 determines that at least one second face image contains all escorts of the target escort task, and the acquisition position of the at least one second face image is the termination position of the target escort task, determine the target escort task normal. Otherwise, the image processing device 312 determines that the target accompanying task is abnormal.
  • FIG. 4 is a schematic structural diagram of an image processing device provided by an embodiment of the present disclosure.
  • the image processing device 40 includes: an acquiring unit 41 and a determining unit 42 .
  • the image processing device 40 further includes a sending unit 43 and an output unit 44 .
  • the acquiring unit 41 is configured to acquire a target accompanying task and a first face map, the target accompanying task includes at least one escort, and the acquisition position of the first human face image is the termination position of the target accompanying task;
  • the acquisition unit 41 is further configured to acquire at least one second face image, the time stamp of the at least one second face image is different from the time stamp of the first face image, and the at least one The acquisition position of the second face image is the termination position;
  • the determining unit 42 is configured to determine the target when it is determined that the person in the first face image includes one of the at least one escort Whether the escort task satisfies the task requirements, and obtain the detection result, the task requirements include: the at least one second face image contains at least one escort of the target escort task; the determination unit 42 is also configured to When the detection result includes that the target accompanying task meets the task requirement, it is determined that the accompanying result of the target accompanying task is normal.
  • the acquiring unit 41 is further configured to acquire the time spent on executing the target accompanying task before determining whether the target accompanying task satisfies the task requirement and obtaining the detection result; the task requirement It also includes: the time spent on executing the target accompanying task is shorter than the execution duration of the target accompanying task.
  • the acquisition unit 41 is further configured to: acquire the start time stamp of executing the target accompanying task; according to the start time stamp and the time stamp of the first face image, obtain The time spent performing accompanying tasks for said target.
  • the escort route of the target escort task is located in the target area, and the at least one escort includes the target escort; the acquisition unit 41 is further configured to acquire the first An image and a first trajectory of the target escort in the first image, the first trajectory being displayed in the first image.
  • the acquisition unit 41 is configured to: acquire at least one second image and a third face image of the target escort, and the at least one second image is obtained by the Acquired by at least one target camera in the target area; at least one third image is determined from the at least one second image, and the at least one third image matches the third face image; according to the acquisition The position of the camera in the first image of the at least one third image obtains the first trajectory of the target escort in the first image.
  • the acquisition unit 41 is further configured to acquire a valid time period during the acquisition of at least one second image;
  • the image processing device 40 further includes: a sending unit 43 configured to send to the At least one target camera sends a trajectory detection instruction, and the trajectory detection instruction is used to instruct the at least one target camera to collect images within the effective time period;
  • the acquisition unit 41 is configured to capture the at least one target camera to At least one image of is used as the at least one second image.
  • the acquisition unit 41 is configured to: display the first trajectory in the first image when an instruction to display the trajectory of the target escort is detected.
  • the acquiring unit 41 is further configured to acquire a fourth human face image of the object to be searched before displaying the first trajectory in the first image, and use the fourth human face image retrieval database, to obtain a fifth face image matching the fourth face image; when it is determined that the object to be searched satisfies the track display condition, display the first track in the first image;
  • the track display condition includes one of the following: the object to be searched is one of the at least one escort, and the object to be searched is one of the at least one escorted person.
  • the acquiring unit 41 is configured to: when it is determined that the person in the first face image does not include any of the at least one escort or when it is determined that the at least one When the second face image does not include the at least one accompanying person, obtain the fourth face image of the object to be searched, use the fourth face image to search the database, and obtain the same as the fourth face image Matching fifth face image.
  • the acquisition unit 41 is further configured to determine that the person in the first face image includes one of the at least one escort in the at least one second image After that, before the acquisition of at least one second human face image, at least one sixth human face image is obtained, and the acquisition position of the at least one sixth human face image is the termination position; the image processing The device 40 also includes: an output unit 44, configured to output supplementary recording prompt information when it is determined that the at least one sixth face image does not contain the at least one accompanied person; the determination unit 42 is also configured to In order to obtain the at least one second face image based on the at least one seventh face image and the at least one sixth face image input for the post-recording prompt information, the at least one seventh face image The collection position of the face image is the termination position.
  • the output unit 44 is further configured to: output warning information when the detection result includes that the target accompanying task does not meet the task requirement.
  • the acquiring unit 41 is configured to: acquire the eighth human face image, at least one ninth human facial image and the termination position in the case of executing the accompanying task creation program, the The acquisition position of at least one ninth human face image is the same as the acquisition position of the eighth human face image; when it is determined that the person in the eighth human face image includes a registered escort, according to the at least one The registered accompanying person and the person in the eighth person's face image contained in the ninth person's face image are obtained to obtain the at least one person accompanying; after determining that the person in the eighth person's face image is registered In the case of an accompanying person, the at least one accompanying person is obtained according to the registered accompanying person included in the at least one ninth facial image; according to the termination position, the at least one accompanying person and the At least one escort creates the target escort task.
  • the acquisition unit 41 is configured to: when a deletion instruction for the first person is detected, remove the first person from the at least one ninth face image The included registered escorts are deleted to obtain the at least one accompanied person; or, in the case of detecting an addition instruction for a second person, according to the second person and the at least one The registered accompanying person contained in the ninth face image is obtained from the at least one accompanying person.
  • the acquisition unit 41 is configured to: display at least one position to be selected when an instruction to input a termination position is detected; In the case of , the end position is obtained according to the selection instruction and the at least one candidate position.
  • the acquiring unit 41 is further configured to: acquire a reason for accompanying the target accompanying task.
  • the acquisition unit 41 is further configured to: obtain a start position according to the collection position of the eighth face image;
  • the at least one escort, and creating the target escort task includes: creating the target escort task according to the start location, the end location, the at least one escort, and the at least one escort.
  • the image processing device determines whether the person in the first face image is an escort by performing face recognition on the first face image. In the case of determining that the person in the first face image is the escort, it is determined that the escort has arrived at the end position of the target escort task, and then by performing face recognition on at least one second face image, it is determined that at least one person to be accompanied Whether the member reaches the termination position. In this way, the monitoring of the target accompanying task is completed, the labor cost is reduced, and the monitoring efficiency is improved.
  • the apparatus provided by the embodiments of the present disclosure has functions or includes modules that can be used to execute the methods described in the above method embodiments, and the implementation can refer to the descriptions of the above method embodiments.
  • FIG. 5 is a schematic diagram of a hardware structure of an image processing device provided by an embodiment of the present disclosure.
  • the image processing device 50 includes a processor 51 , a memory 52 , an input device 53 and an output device 54 .
  • the processor 51 , the memory 52 , the input device 53 and the output device 54 are coupled through connectors, and the connectors include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment of the present disclosure.
  • coupling refers to interconnection in a specific manner, including direct connection or indirect connection through other devices, for example, connection through various interfaces, transmission lines, and buses.
  • the processor 51 may be one or more graphics processing units (graphics processing unit, GPU).
  • the GPU may be a single-core GPU or a multi-core GPU.
  • the processor 51 may be a processor group composed of multiple GPUs, and the multiple processors are coupled to each other through one or more buses.
  • the processor may also be other types of processors, etc., which are not limited in this embodiment of the present disclosure.
  • the memory 52 may be configured to store computer program instructions and various computer program codes including program codes configured to execute the solutions of the present disclosure.
  • the memory includes, but is not limited to, random access memory (random access memory, RAM), read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable read only memory, EPROM), or portable read-only memory (compact disc read-only memory, CD-ROM), which is configured to store related instructions and data.
  • the input device 53 is configured to input one or more of data and signals
  • the output device 54 is configured to output one or more of data and signals.
  • the input device 53 and the output device 54 can be independent devices, or an integrated device.
  • the memory 52 can be configured not only to store relevant instructions, but also to store relevant data.
  • the memory 52 can be configured to store the target accompanying task and the first person's The face image, or the memory 52 can also be configured to store the detection results obtained by the processor 51, etc., and the embodiment of the present disclosure does not limit the data stored in the memory.
  • Fig. 5 only shows a simplified design of an image processing device.
  • the image processing device may also include other necessary components, including but not limited to any number of input/output devices, processors, memories, etc., and all image processing devices that can implement the embodiments of the present disclosure are included in this within the scope of public protection.
  • the disclosed systems, devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • all or part of them may be implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it 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 the computer program instructions are loaded and executed on the computer, all or part of the processes or functions according to the embodiments of the present disclosure will be generated.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in or transmitted via a computer-readable storage medium.
  • the computer instructions can be sent from a website site, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) Another website site, computer, server or data center for transmission.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (digital versatile disc, DVD), or a semiconductor medium (for example, a solid state disk (solid state disk, SSD)) wait.
  • a magnetic medium for example, a floppy disk, a hard disk, a magnetic tape
  • an optical medium for example, a digital versatile disc (digital versatile disc, DVD)
  • a semiconductor medium for example, a solid state disk (solid state disk, SSD)
  • the processes can be completed by computer programs to instruct related hardware.
  • the programs can be stored in computer-readable storage media.
  • When the programs are executed may include the processes of the foregoing method embodiments.
  • the aforementioned storage medium includes: various media capable of storing program codes such as read-only memory (ROM) or random access memory (RAM), magnetic disk or optical disk.
  • the person in the first face image is an escort. In the case of determining that the person in the first face image is the escort, it is determined that the escort has arrived at the end position of the target escort task, and then by performing face recognition on at least one second face image, it is determined that at least one person to be accompanied Whether the member reaches the termination position. In this way, the monitoring of the target accompanying task is completed, the labor cost is reduced, and the monitoring efficiency is improved.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

一种图像处理方法及装置、电子设备、程序产品及计算机可读存储介质。该方法包括：获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果；在所述检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。

Description

图像处理方法及装置、电子设备、程序产品及计算机可读存储介质
相关申请的交叉引用
本公开基于申请号为202110874726.8、申请日为2021年07月30日、申请名称为“图像处理方法及装置、电子设备及计算机可读存储介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此以引入方式并入本公开。
技术领域
本公开涉及安防技术领域，尤其涉及一种图像处理方法及装置、电子设备、程序产品及计算机可读存储介质。
背景技术
陪同任务指，陪同员陪同被陪同员到达目的地。为确定被陪同员是否达到目的地，需要对陪同任务进行监测。传统方法通过人工点到的方式，确定被陪同员是否达到目的地，以完成对陪同任务的监测。但该种方法的监测效率低，且人力成本高。
发明内容
本公开实施例提供一种图像处理方法及装置、电子设备、程序产品及计算机可读存储介质。
本公开实施例提供了一种图像处理方法，所述方法包括：获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果，所述任务要求包括：所述至少一张第二人脸图像包含所述目标陪同任务的至少一个被陪同员；在所述检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。
结合本公开任一实施方式，所述确定所述目标陪同任务是否满足任务要求，得到检测结果之前，所述方法还包括：获取执行所述目标陪同任务所花的时间；所述任务要求还包括：所述执行所述目标陪同任务所花的时间小于所述目标陪同任务的执行时长。
结合本公开任一实施方式，所述获取执行所述目标陪同任务所花的时间，包括：获取执行所述目标陪同任务的起始时间戳；依据所述起始时间戳和所述第一人脸图像的时间戳，得到执行所述目标陪同任务所花的时间。
结合本公开任一实施方式，所述目标陪同任务的陪同路线位于目标区域内，所述至少一个被陪同员包括目标被陪同员；所述方法还包括：获取所述目标区域的第一图像和所述目标陪同员在所述第一图像中的第一轨迹，在所述第一图像中显示所述第一轨迹。
结合本公开任一实施方式，所述获取所述目标被陪同员在所述第一图像中的轨迹，包括：获取至少一张第二图像和所述目标被陪同员的第三人脸图像，所述至少一张第二图像均由所述目标区域内的至少一个目标摄像头采集得到；从所述至少一张第二图像中确定至少一张第三图像，所述至少一张第三图像均与所述第三人脸图像匹配；依据采集所述至少一张第三图像的摄像头在所述第一图像中的位置，得到所述目标被陪同员在所述第一图像中的第一轨迹。
结合本公开任一实施方式，所述获取至少一张第二图像之前，所述方法还包括：获取有效时间段；向所述至少一个目标摄像头发送轨迹检测指令，所述轨迹检测指令用于指示所述至少一个目标摄像头在所述有效时间段内采集图像；所述获取至少一张第二图像，包括：将所述至少一个目标摄像头采集到的至少一张图像作为所述至少一张第二图像。
结合本公开任一实施方式，所述在所述第一图像中显示所述第一轨迹，包括：在检测到显示所述目标被陪同员的轨迹的指令的情况下，在所述第一图像中显示所述第一轨迹。
结合本公开任一实施方式，所述在所述第一图像中显示所述第一轨迹之前，所述方法还包括：获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹 配的第五人脸图像；所述在所述第一图像中显示所述第一轨迹，包括：在确定所述待查找对象满足轨迹显示条件的情况下，在所述第一图像中显示所述第一轨迹；所述轨迹显示条件包括以下中的一个：所述待查找对象为所述至少一个陪同员中的一个、所述待查找对象为所述至少一个被陪同员中的一个。
结合本公开任一实施方式，所述获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像，包括：在确定所述第一人脸图像中的人物不包括所述至少一个陪同员中任一个的情况下或在确定所述至少一张第二人脸图像不包括所述至少一个被陪同员的情况下，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像。
结合本公开任一实施方式，所述在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下之后，所述获取至少一张第二人脸图像之前，所述方法还包括：获取至少一张第六人脸图像，所述至少一张第六人脸图像的采集位置为所述终止位置；在确定所述至少一张第六人脸图像未包含所述至少一个被陪同员的情况下，输出补录提示信息；依据针对所述补录提示信息输入的至少一张第七人脸图像和所述至少一张第六人脸图像，得到所述至少一张第二人脸图像，所述至少一张第七人脸图像的采集位置为所述终止位置。
结合本公开任一实施方式，所述方法还包括：在所述检测结果包括所述目标陪同任务不满足所述任务要求的情况下，输出告警信息。
结合本公开任一实施方式，所述获取目标陪同任务，包括：在执行创建陪同任务程序的情况下，获取第八人脸图像、至少一张第九人脸图像和所述终止位置，所述至少一张第九人脸图像的采集位置与所述第八人脸图像的采集位置相同；在确定所述第八人脸图像中的人物包括已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的所述已注册陪同员和所述第八人脸图像中的人物，得到所述至少一个陪同员；在确定所述第八人脸图像中的人物为已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员；依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
结合本公开任一实施方式，所述至少一张第九人脸图像所包含的所述已注册被陪同员包括第一人物，所述依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员，包括：在检测到针对所述第一人物的删除指令的情况下，将所述第一人物从所述至少一张第九人脸图像所包含的所述已注册被陪同员中删除，得到所述至少一个被陪同员；或，在检测到针对第二人物的添加指令的情况下，依据所述第二人物和所述至少一张第九人脸图像所包含的所述已注册被陪同员，得到所述至少一个被陪同员。
结合本公开任一实施方式，所述获取终止位置，包括：在检测到输入终止位置的指令的情况下，显示至少一个待选位置；在检测到针对所述至少一个待选位置的选择指令的情况下，依据所述选择指令和所述至少一个待选位置，得到所述终止位置。
结合本公开任一实施方式，所述方法还包括：获取所述目标陪同任务的陪同原因。
结合本公开任一实施方式，所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务之前，所述方法还包括：依据所述第八人脸图像的采集位置得到起始位置；所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务，包括：依据所述起始位置、所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
本公开实施例提供了一种图像处理装置，所述装置包括：获取单元，配置为获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；所述获取单元，还配置为获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；确定单元，配置为在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果，所述任务要求包括：所述至少一张第二人脸图像包含所述目标陪同任务的至少一个被陪同员；所述确定单元，还配置为在所述 检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。
本公开实施例提供了一种电子设备，包括：处理器和存储器，所述存储器配置为存储计算机程序代码，所述计算机程序代码包括计算机指令，在所述处理器执行所述计算机指令的情况下，所述电子设备执行如上述图像处理方法及其任意一种可能实现的方式的方法。
本公开实施例提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序包括程序指令，在所述程序指令被处理器执行的情况下，使所述处理器执行如上述第一方面及其任意一种可能实现的方式的方法。
本公开实施例还提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如本公开实施例中所描述的部分或全部步骤。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
附图说明
为了更清楚地说明本公开实施例或背景技术中的技术方案，下面将对本公开实施例或背景技术中所需要使用的附图进行说明。
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。
图1为本公开实施例提供的一种陪同监测系统架构示意图；
图2为本公开实施例提供的一种图像处理方法的流程示意图；
图3为本公开实施例提供的另一种陪同监测系统架构示意图；
图4为本公开实施例提供的一种图像处理装置的结构示意图；
图5为本公开实施例提供的一种图像处理装置的硬件结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本公开方案，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。
本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是还包括没有列出的步骤或单元，或还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
应当理解，在本公开中，“至少一个(项)”是指一个或者多个，“多个”是指两个或两个以上，“至少两个(项)”是指两个或三个及三个以上，“和/或”，用于描述关联对象的关联关系，表示可以存在三种关系，例如，“A和/或B”可以表示：只存在A，只存在B以及同时存在A和B三种情况，其中A，B可以是单数或者复数。字符“/”可表示前后关联对象是一种“或”的关系，是指这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b或c中的至少一项(个)，可以表示：a，b，c，“a和b”，“a和c”，“b和c”，或“a和b和c”，其中a，b，c可以是单个，也可以是多个。字符“/”还可表示数学运算中的除号，例如，a/b＝a除以b；6/3＝2。“以下至少一项(个)”或其类似表达。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本公开的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
陪同任务指，陪同员陪同被陪同员到达目的地。为确定被陪同员是否达到目的地，需要对陪同 任务进行监测。传统方法通过人工点到的方式，确定被陪同员是否达到目的地，以完成对陪同任务的监测。但该种方法的监测效率低，且人力成本高。基于此，本公开实施例提供了一种技术方案，以提高监测效率，并降低人力成本。
本公开实施例的执行主体为图像处理装置，其中，图像处理装置可以是任意一种可执行本公开方法实施例所公开的技术方案的电子设备。在一些实施例中，图像处理装置可以是以下中的一种：手机、计算机、平板电脑、可穿戴智能设备。
应理解，本公开方法实施例还可以通过处理器执行计算机程序代码的方式实现。下面结合本公开实施例中的附图对本公开实施例进行描述。
请参阅图1，图1所示为本公开实施例提供的一种陪同监测系统11架构示意图。在图1中，图像处理装置112与至少一个摄像头111之间具有通信连接。在一些实施例中，图像处理装置112可以是服务器。图像处理装置112可部署在监管区域的控制中心。至少一个摄像头111均为监管区域内的摄像头。至少一个摄像头111均配置为采集监管区域内的图像和视频中的一种或多种。图像处理装置112基于下文提供的技术方案对至少一个摄像头111所采集到的图像和视频中的一种或多种进行处理，可监测监管区域内的目标陪同任务。如，图像处理装置112可通过至少一个摄像头111采集得到第一人脸图像和至少一张第二人脸图像，进而基于下文提供的技术方案、第一人脸图像和至少一张第二人脸图像，监测监管区域内的目标陪同任务。
请参阅图2，图2是本公开实施例提供的一种图像处理方法的流程示意图。
201、获取目标陪同任务和第一人脸图像，上述目标陪同任务包括至少一个陪同员，上述第一人脸图像的采集位置为上述目标陪同任务的终止位置。
本公开实施例中，目标陪同任务包括以下信息：目标陪同任务的终止位置、陪同员名单、被陪同员名单，其中，陪同员名单包括至少一个陪同员，被陪同员名单包括至少一个被陪同员。在一些实施例中，陪同员名单可以是至少一张人脸图像，被陪同员名单也可以是至少一张人脸图像。例如，目标陪同任务的陪同员名单包括张三的人脸图像，目标陪同任务的被陪同员名单包括李四的人脸图像和王五的人脸图像。此时，目标陪同任务的陪同员包括张三。目标陪同任务的被陪同员包括李四和王五。
本公开实施例中，图像的采集位置可以是，采集图像的成像设备的位置。例如，第一人脸图像由摄像头a采集得到，摄像头a的位置即为第一人脸图像的采集位置。图像的采集位置还可以是，图像所对应的场景的位置。例如，第一人脸图像由摄像头a对场景b采集图像得到，场景b的位置即为第一人脸图像的采集位置。在一种可能实现的方式中，第一人脸图像由门禁设备采集得到，第一人脸图像的采集位置为该门禁设备的位置。第一人脸图像的采集位置为终止位置，即采集第一人脸图像的门禁设备的位置为终止位置。在一种获取目标陪同任务的实现方式中，图像处理装置接收用户通过输入组件输入的目标陪同任务。在一些实施例中，输入组件包括以下至少一种：键盘、鼠标、触控屏、触控板和音频输入器。在另一种获取目标陪同任务的实现方式中，图像处理装置接收终端发送的目标陪同任务。在一些实施例中，终端可以是以下至少一种：门禁设备、手机、计算机、平板电脑、服务器、可穿戴设备。在一种获取第一人脸图的实现方式中，图像处理装置接收用户通过输入组件输入的第一人脸图。在另一种获取第一人脸图的实现方式中，图像处理装置接收终端发送的第一人脸图。在又一种获取第一人脸图像的实现方式中，图像处理装置包括成像设备。图像处理装置使用成像设备采集一张人脸图像作为第一人脸图像。
应理解，在本公开实施例中，获取目标陪同任务的步骤和获取第一人脸图像的步骤可以分开执行，也可以同时执行。例如，图像处理装置可先获取目标陪同任务，再获取第一人脸图像。又例如，图像处理装置可先获取第一人脸图像，再获取目标陪同任务。再例如，图像处理装置在获取目标陪同任务的过程中获取第一人脸图像，或在获取第一人脸图像的过程中获取目标陪同任务。
202、获取至少一张第二人脸图像，上述至少一张第二人脸图像的采集位置为上述终止位置，上述至少一张第二人脸图像的时间戳与上述第一人脸图像的时间戳不同。
本公开实施例中，至少一张第二人脸图像可以包括一张第二人脸图像，也可以包括两张或两张以上第二人脸图像。
本公开实施例中，第一人脸图像的时间戳与至少一张第二人脸图像的时间戳不同，即第一人脸图像的采集时间与任意一张第二人脸图像的采集时间均不同。例如，若至少一张第二人脸图像包括图像a，那么第一人脸图像的时间戳与图像a的时间戳不同。又例如，若至少一张第二人脸图像包括图像a和图像b，那么第一人脸图像的时间戳与图像a的时间戳不同，且第一人脸图像的时间戳与图像b的时间戳不同。
本公开实施例中，至少一张第二人脸图像的采集位置均为终止位置，即任意一张第二人脸图像的位置均为终止位置。
在一些实施例中，至少一张第二人脸图像中任意一张人脸图像的采集时间，与第一人脸图像的采集时间之间的时间间隔均小于第一时间阈值。例如，第一时间阈值为2分钟，第一人脸图像的采集时间为t1，至少一张第二人脸图像包括图像a和图像b。那么，图像a的采集时间与t1之间的时间间隔小于2分钟，且图像b的采集时间与t1之间的时间间隔小于2分钟。
在一种可能实现的方式中，至少一张第二人脸图像由门禁设备采集得到，至少一张第二人脸图像的采集位置为该门禁设备的位置。至少一张第二人脸图像的采集位置为终止位置，即采集至少一张第二人脸图像的门禁设备的位置为终止位置。在一种获取至少一张第二人脸图像的实现方式中，图像处理装置接收用户通过输入组件输入的至少一张第二人脸图像。在另一种获取至少一张第二人脸图像的实现方式中，图像处理装置接收终端发送的至少一张第二人脸图像。
203、在确定上述第一人脸图像中的人物包括上述至少一个陪同员中的一个的情况下，确定上述目标陪同任务是否满足任务要求，得到检测结果，上述任务要求包括：上述至少一张第二人脸图像包含上述目标陪同任务的至少一个被陪同员。
第一人脸图像中的人物包括至少一个陪同员的一个，说明第一人脸图像中的人物为陪同员，即目标陪同任务的陪同员已到达目标陪同任务的终止位置，即目标陪同任务已结束。因此，图像处理装置在确定第一人脸图像中的人物包括至少一个陪同员中的一个的情况下，确定目标陪同任务是否满足任务要求，得到检测结果。其中，检测结果包括目标陪同任务满足任务要求或目标陪同任务不满足任务要求。
在一种可能实现的方式中，任务要求包括至少一张第二人脸图像包括目标陪同任务的至少一个被陪同员，即至少一张第二人脸图像包括所有被陪同员的人脸图像。在该种实现方式中，图像处理装置通过确定至少一张第二人脸图像中是否包含至少一个陪同员，确定目标陪同任务是否满足任务要求。
在一种可能实现的方式中，图像处理装置在确定第一人脸图像中的人物包括至少一个陪同员中的一个之前，获取至少一张第二人脸图像。在一个基于该种实现方式的应用场景中，陪同员向图像处理装置输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像。图像处理装置输出“请陪同员进行人脸识别”的第一提示信息，并将摄像头在输出第一提示信息后采集到的人脸图像作为第一人脸图像。在采集完第一人脸图像后，输出“请被陪同员进行人脸识别”的第二提示信息，并将摄像头在输出第二提示信息后采集到的至少一张人脸图像作为至少一张第二人脸图像。在另一个基于该种实现方式的应用场景中，陪同员向门禁设备输入结束目标陪同任务的指令，门禁设备在检测到该指令后，开启摄像头采集图像。门禁设备输出“请陪同员进行人脸识别”的第三提示信息，并将摄像头在输出第三提示信息后采集到的人脸图像作为第一人脸图像。在采集完第一人脸图像后，输出“请被陪同员进行人脸识别”的第四提示信息，并将摄像头在输出第四提示信息后采集到的至少一张人脸图像作为至少一张第二人脸图像。门禁设备将第一人脸图像和至少一张第二人脸图像发送至图像处理装置。
在另一种可能实现的方式中，图像处理装置在确定第一人脸图像中的人物包括至少一个陪同员中的一个的情况下，获取至少一张第二人脸图像。在一个基于该种实现方式的应用场景中，陪同员向图像处理装置输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像。图像处理装置输出“请陪同员进行人脸识别”的第五提示信息，并将摄像头在输出第五提示信息后采集到的人脸图像作为第一人脸图像。在采集完第一人脸图像后，对第一人脸图像进行人脸识别，并在确定第一人脸图像中的人物包括至少一个陪同员中的一个的情况下，输出“请被陪同员 进行人脸识别”的第六提示信息，并将摄像头在输出第六提示信息后采集到的至少一张人脸图像作为至少一张第二人脸图像。在另一个基于该种实现方式的应用场景中，陪同员向门禁设备输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像。图像处理装置输出“请陪同员进行人脸识别”的第七提示信息，并将摄像头在输出第七提示信息后采集到的至少一张人脸图像作为至少一张第二人脸图像。在采集完至少一张第二人脸图像后，输出“请陪同员进行人脸识别”的第八提示信息，并将摄像头在输出第八提示信息后采集到的人脸图像作为第一人脸图像。
门禁设备在采集完第一人脸图像和至少一张第二人脸图像后，将第一人脸图像和发送至图像处理装置。图像处理装置在接收到门禁设备发送的第一人脸图像后，对第一人脸图像进行人脸识别，并在确定第一人脸图像中的人物包括至少一个陪同员中的一个的情况下，向门禁设备发送第一校验通过指令。门禁设备在检测第一校验通过指令后，将至少一张第二人脸图像发送至图像处理装置。
204、在上述检测结果包括上述目标陪同任务满足上述任务要求的情况下，确定上述目标陪同任务正常。
本步骤中，目标陪同任务满足任务要求，即至少一张第二人脸图像包含目标陪同任务的至少一个被陪同员，此时说明被陪同员已全部达到目标陪同任务的终止位置，进而确定目标陪同任务正常。
若图像处理装置确定至少一张第二人脸图像未包含目标陪同任务的至少一个被陪同员，即至少一张第二人脸图像未包含所有被陪同员，确定目标陪同任务不满足任务要求，即确定目标陪同任务异常。
本公开实施例中，图像处理装置通过对第一人脸图像进行人脸识别，确定第一人脸图像中的人物是否为陪同员。在确定第一人脸图像中的人物为陪同员的情况下，确定陪同员已到目标陪同任务的终止位置，进而通过对至少一张第二人脸图像进行人脸识别，确定至少一个被陪同员是否达到终止位置。由此完成对目标陪同任务的监测，降低人力成本，并提高监测效率。
在一些实施例中，图像处理装置在确定目标陪同任务是否满足任务要求，得到检测结果之前，还执行以下步骤：
1、获取执行上述目标陪同任务所花的时间。
在实施过程中，执行目标陪同任务所花的时间可以是，执行目标陪同任务已花的时间。例如，目标陪同任务已执行完，那么执行完目标陪同任务所花的时间为，执行完目标陪同任务所花的时间。
在一种获取执行目标陪同任务所花的时间的实现方式中，图像处理装置接收用户通过输入组件输入的执行目标陪同任务所花的时间。在另一种获取执行目标陪同任务所花的时间的实现方式中，图像处理装置接收终端发送的执行目标陪同任务所花的时间。
在图像处理装置执行步骤1的情况下，任务要求还包括：执行目标陪同任务所花的时间小于目标陪同任务的执行时长。
本公开实施例中，目标陪同任务的执行时长，为判断执行目标陪同任务是否超时的依据。示例性地，执行目标陪同任务所花的时间小于目标陪同任务的执行时长，说明执行目标陪同任务未超时；执行目标陪同任务所花的时间大于或等于目标陪同任务的执行时长，说明执行目标陪同任务已超时。
执行目标陪同任务未超时，说明目标陪同任务正常。在步骤1中，图像处理装置在确定至少一张第二人脸图像包括至少一个被陪同员，且执行目标陪同任务所花的时间小于目标陪同任务的执行时长的情况下，确定目标陪同任务满足任务要求，即确定目标陪同任务正常。否则，图像处理装置确定不满足任务要求，即确定目标陪同任务异常。
在一些实施例中，图像处理装置在执行步骤1的过程中执行以下步骤：
2、获取执行上述目标陪同任务的起始时间戳。
本公开实施例中，起始时间戳表征开始执行目标陪同任务的时间。例如，目标陪同任务的起始时间戳为2021年7月27日16点2分3秒，那么开始执行目标陪同任务的时间为2021年7月27日16点2分3秒。
在一种获取起始时间戳的实现方式中，图像处理装置接收用户通过输入组件输入的起始时间戳。在另一种获取执行起始时间戳的实现方式中，图像处理装置接收终端发送的起始时间戳。
3、依据上述起始时间戳和上述第一人脸图像的时间戳，得到执行上述目标陪同任务所花的时间。
本公开实施例中，图像的时间戳表征图像的采集时间。例如，第一人脸图像的时间戳为2021年7月27日16点3分3秒，那么第一人脸图像的采集时间为2021年7月27日16点3分3秒。
在第一人脸图像中的人物为陪同员的情况下，第一人脸图像的采集时间即为陪同员达到终止位置的时间。而陪同员达到终止位置的时间可视为目标陪同任务的结束时间，因此第一人脸图像的时间戳即为目标陪同任务的结束时间。图像处理装置进而可依据起始时间戳和第一人脸图像的时间戳，得到执行完目标陪同任务所花的时间，作为上述执行目标陪同任务所花的时间。
在一种可能实现的方式中，图像处理装置将起始时间戳至第一人脸图像的时间戳之间时长，作为执行目标陪同任务所花的时间。在另一种可能实现的方式中，图像处理装置确定起始时间戳至第一人脸图像的时间戳之间时长，并将该时长与第一值的和作为执行目标陪同任务所花的时间。例如，起始时间戳至第一人脸图像的时间戳之间时长为80分钟，第一值为2分钟，那么执行目标陪同任务所花的时间为82分钟。在又一种可能实现的方式中，图像处理装置确定起始时间戳至第一人脸图像的时间戳之间时长，并将该时长与第二值的差作为执行目标陪同任务所花的时间。例如，起始时间戳至第一人脸图像的时间戳之间时长为80分钟，第二值为3分钟，那么执行目标陪同任务所花的时间为77分钟。
在一些实施例中，目标陪同任务的陪同路线位于目标区域内。本公开实施例中，目标区域可以是任意区域，例如，目标区域是校园。又例如，目标区域是监管区域。再例如，目标区域是医院。目标陪同任务的陪同路线位于目标区域内，说明在执行目标陪同任务的过程中，所有陪同员的轨迹和所有被陪同员的轨迹均应位于目标区域内。在该种实施方式中，至少一个被陪同员包括目标被陪同员，其中，目标被陪同员为至少一个被陪同员中的任意一个。在该种实施方式中，图像处理装置还执行以下步骤：4、获取上述目标区域的第一图像和上述目标被陪同员在上述第一图像中的第一轨迹，在上述第一图像中显示上述第一轨迹。
本公开实施例中，第一图像为对目标区域采集图像得到的图像。例如，假设目标区域为校园。通过对校园采集图像得到的图像为第一图像。又例如，目标区域为监管区域。通过对监管区域采集图像得到的图像为第一图像。
本公开实施例中，被陪同员在图像中的轨迹，依据被陪同员在目标区域内的轨迹确定。例如，目标被陪同员在目标区域内的轨迹为从A点出发经过B点到达C点。若在第一图像中，与A点对应的像素为像素a，与B点对应的像素为像素b，与C点对应的像素为像素c。那么，第一轨迹为经过像素a、像素b和像素c的轨迹。
在一种获取第一图像的实现方式中，图像处理装置接收用户通过输入组件输入的第一图像。在另一种获取第一图像的实现方式中，图像处理装置接收终端发送的第一图像。在一种获取第一轨迹的实现方式中，图像处理装置接收用户通过输入组件输入的第一轨迹。在另一种获取第一轨迹的实现方式中，图像处理装置接收终端发送的第一轨迹。应理解，在本公开实施例中，获取第一图像的步骤和获取第一轨迹的步骤可以分开执行，也可以同时执行。例如，图像处理装置可先获取第一图像，再获取第一轨迹。又例如，图像处理装置可先获取第一轨迹，再获取第一图像。再例如，图像处理装置在获取第一图像的过程中获取第一轨迹，或在获取第一轨迹的过程中获取第一图像。
在一个基于步骤4实现的应用场景中，第一图像所显示的目标区域的细节信息，比地图数据所显示的目标区域的细节信息丰富。其中，目标区域的细节信息包括以下中的一个或大于一个：目标区域的轮廓、目标区域内的建筑物信息、目标区域内的道路信息。
在该种应用场景中，由于第一图像相较于地图，包含的目标区域内的细节信息更丰富，本实施例在第一图像中显示目标被陪同员的轨迹，可比在地图中显示目标被陪同员的轨迹，带来更好的显示效果。例如，地图上无法显示监管区域内的建筑物和道路。显然在地图上显示目标被陪同员出现的位置，所带来的显示效果不佳。由于监管区域的图像包括建筑物和道路，在监管区域的图像上显示目标被陪同员的轨迹，可提升显示效果。
应理解，本公开实施例中的目标被陪同员仅为示例，不应理解为仅能在第一图像中显示一个被陪同员的轨迹。在实际应用中，图像处理装置可在第一图像中显示目标陪同任务中所有被陪同员的轨迹。
在一些实施例中，在图像处理装置获取第一图像的情况下，至少一个陪同员包括目标陪同员，其中，目标陪同员为至少一个陪同员中的任意一个。在该种实施方式中，图像处理装置还执行以下步骤：5、获取目标陪同员在上述第一图像中的第二轨迹，在上述第一图像中显示上述第二轨迹。步骤5的实现过程可参见步骤4的实现过程，其中，步骤4中的目标被陪同员与步骤5中的目标陪同员对应，步骤4中的第一轨迹与步骤5中的第二轨迹对应。应理解，本公开实施例中的目标陪同员仅为示例，不应理解为仅能在第一图像中显示一个陪同员的轨迹。在实际应用中，图像处理装置可在第一图像中显示目标陪同任务中所有陪同员的轨迹。
在一些实施例中，图像处理装置在获取第一图像、第一轨迹和第二轨迹的情况下，在第一图像中显示第一轨迹和第二轨迹。即在实际应用中，图像处理装置可在第一图像中显示目标陪同任务中所有陪同员的轨迹以及所有被陪同员的轨迹。
在一些实施例中，图像处理装置通过执行以下步骤，获取目标被陪同员在第一图像中的第一轨迹：
6、获取至少一张第二图像和上述目标被陪同员的第三人脸图像，上述至少一张第二图像均由上述目标区域内的至少一个目标摄像头采集得到。
本公开实施例中，至少一个目标摄像头所采集的画面均位于目标区域内。至少一个目标摄像头可以包括一个目标摄像头，至少一个目标摄像头也可以包括两个目标摄像头或两个以上目标摄像头。至少一张第二图像可以包括一张第二图像，至少一张第二图像也可以包括两张或两张以上第二图像。
在至少一个目标摄像头也可以包括两个目标摄像头或两个以上目标摄像头，且至少一张第二图像包括两张或两张以上第二图像的情况下，不同的第二图像可以由不同的目标摄像头采集得到。例如，至少一个目标摄像头包括摄像头a和摄像头b，至少一张第二图像包括第二图像A和第二图像B。第二图像A由摄像头a采集得到，第二图像B由摄像头b采集得到。在一种获取至少一张第二图像的实现方式中，图像处理装置接收用户通过输入组件输入的至少一张第二图像。在另一种获取至少一张第二图像的实现方式中，图像处理装置接收终端发送的至少一张第二图像。在又一种获取至少一张第二图像的实现方式中，图像处理装置与至少一个目标摄像头之间具有通信连接。图像处理装置通过该通信连接，获取至少一个目标摄像头采集到的至少一张第二图像。
在一种获取第三人脸图像的实现方式中，图像处理装置接收用户通过输入组件输入的第三人脸图像。在另一种获取第三人脸图像的实现方式中，图像处理装置接收终端发送的第三人脸图像。应理解，在本公开实施例中，获取至少一张第二图像的步骤和获取第三人脸图像的步骤可以分开执行，也可以同时执行。例如，图像处理装置可先获取至少一张第二图像，再获取第三人脸图像。又例如，图像处理装置可先获取第三人脸图像，再获取至少一张第二图像。再例如，图像处理装置在获取至少一张第二图像的过程中获取第三人脸图像，或在获取第三人脸图像的过程中获取至少一张第二图像。
7、从上述至少一张第二图像中确定至少一张第三图像，上述至少一张第三图像均与上述第三人脸图像匹配。
本公开实施例中，与第三人脸图像匹配的图像均包含目标被陪同员。至少一张第三图像均与第三人脸匹配，即至少一张第三图像均包含目标被陪同员。
8、依据采集上述至少一张第三图像的目标摄像头在上述第一图像中的位置，得到上述目标被陪同员在上述第一图像中的第一轨迹。
第三图像包含目标被陪同员，说明目标被陪同员出现在采集第三图像的目标摄像头的拍摄范围内。因此，可依据采集第三图像的目标摄像头的位置确定目标被陪同员的位置。
本公开实施例中，目标摄像头在第一图像中的位置依据目标摄像头在目标区域中的位置确定。例如，目标摄像头在目标区域的A点，在第一图像中，与A点对应的像素为像素a，那么目标摄像头在第一图像中的位置，即为像素a在第一图像中的位置。
在一种可能实现的方式中，图像处理装置将采集第三图像的目标摄像头在第一图像中的位置，作为目标被陪同员在第一图像中的位置。例如，至少一张第三图像包括第三图像a，第三图像a由目标摄像头A采集得到，目标摄像头A在第一图像中的位置为p1。那么，目标被陪同员在第一图像中 的第一轨迹为p1。又例如，至少一张第三图像包括第三图像a和第三图像b，第三图像a由目标摄像头A采集得到，第三图像b由目标摄像头B采集得到。目标摄像头A在第一图像中的位置为p1，目标摄像头B在第一图像中的位置为p2。那么，目标被陪同员在第一图像中的第一轨迹为p1与p2之间的轨迹。
在一些实施例中，图像处理装置可通过以下步骤获取目标陪同员在第一图像中的第二轨迹：获取至少一张第二图像和目标陪同员的目标陪同员人脸图像，该步骤的实现过程可参见步骤6的实现过程，其中，目标陪同员与目标被陪同员对应，目标陪同员人脸图像与第三人脸图像对应。从至少一张第二图像中确定至少一张目标陪同员图像，至少一张目标陪同员图像均与目标陪同员人脸图像匹配，该步骤的实现过程可参见步骤7的实现过程，其中，至少一张第三图像与至少一张目标陪同员图像对应，目标陪同员人脸图像与第三人脸图像对应。依据采集至少一张目标陪同员图像的目标摄像头在第一图像中的位置，得到目标陪同员在上述第一图像中的第二轨迹，该步骤的实现过程可参见步骤8的实现过程，其中，至少一张第三图像与至少一张目标陪同员图像对应，第一轨迹与第二轨迹对应。
在一些实施例中，图像处理装置在获取至少一张第二图像之前，还执行以下步骤：
9、获取所述至少一个目标摄像头的工作时间段。
为提高至少一个目标摄像头的工作效率，减少至少一个目标摄像头的能耗，可使至少一个目标摄像头在规定时间段内采集图像。本公开实施例中，工作时间段即为至少一个目标摄像头按规定采集图像的时间段。在一种获取工作时间段的实现方式中，图像处理装置接收用户通过输入组件输入的工作时间段。在另一种获取工作时间段的实现方式中，图像处理装置接收终端发送的工作时间段。
10、向上述至少一个目标摄像头发送轨迹检测指令，上述轨迹检测指令用于指示上述至少一个目标摄像头在上述工作时间段内采集图像。
由于图像处理装置确定目标被陪同员的轨迹需要利用至少一个目标摄像头采集到的图像，而陪同任务可能是在某段时间内执行的，使至少一个目标摄像头在陪同任务的执行时间段内采集图像，可提高至少一个目标摄像头的工作效率，并减少至少一个目标摄像头的能耗。
本公开实施例中，轨迹检测指令用于指示至少一个目标摄像头在目标陪同任务的执行时间段内采集图像。
在一种可能实现的方式中，轨迹检测指令是图像处理装置依据目标陪同任务的执行时间段确定的。在另一种可能实现的方式中，轨迹检测指令是用户通过图像处理装置配置的。例如，目标区域的管理人员，希望使目标区域内的摄像头在每天的8:00～20:00采集图像，进而可通过图像处理装置配置轨迹检测指令，以指示至少一个目标摄像头在目标陪同任务的执行时间段内采集图像。图像处理装置通过执行步骤10，可使至少一个目标摄像头在工作时间段内采集图像，进而提高至少一个目标摄像头的工作效率，并减少至少一个目标摄像头的能耗。在执行完步骤10后，图像处理装置通过执行以下步骤获取至少一张第二图像：
11、将上述至少一个目标摄像头采集到的至少一张图像作为上述至少一张第二图像。
在一些实施例中，图像处理装置在检测到显示目标被陪同员的轨迹的指令的情况下，在第一图像中显示第一轨迹。在一种可能实现的方式中，用户通过输入组件向图像处理装置输入显示目标被陪同员的轨迹的指令。例如，用户通过点击图像处理装置的触摸显示屏，向图像处理装置输入显示目标被陪同员的轨迹的指令。
在一些实施例中，图像处理装置在第一图像中显示第一轨迹之前，还执行以下步骤：
12、获取待查找对象的第四人脸图像，使用上述第四人脸图像检索数据库，得到与上述第四人脸图像匹配的第五人脸图像。
本公开实施例中，待查找对象可以是用户希望找寻的人。例如，用户希望查看张三在目标区域内的轨迹，可将张三作为待查找对象。数据库包括已注册人脸图像，以及已注册人脸图像中所包含的人物的身份信息。在一种获取第四人脸图像的实现方式中，图像处理装置接收用户通过输入组件输入的第四人脸图像。在另一种获取第四人脸图像的实现方式中，图像处理装置接收终端发送的第四人脸图像。在实施过程中，与第四人脸图像匹配的图像均包含待查找对象。第五人脸图像与第三 人脸匹配，即第五人脸图像包含待查找对象。
在执行完步骤12后，图像处理装置在确定上述待查找对象满足轨迹显示条件的情况下，在上述第一图像中显示上述第一轨迹，其中，轨迹显示条件包括以下中的一个：待查找对象为至少一个陪同员中的一个、待查找对象为至少一个被陪同员中的一个。
在该种实施方式中，图像处理装置在确定待查找对象为陪同员，或待查找对象为被陪同员的情况下，在第一图像中显示目标被陪同员的第一轨迹。在确定待查找对象为陪同员，或待查找对象为被陪同员的情况下，待查找对象与至少一个陪同员和至少一个被陪同员均有过共同轨迹，即待查找对象、至少一个陪同员、至少一个被陪同员均为同行人。因此，图像处理装置显示与待查找对象同行人在目标区域内的轨迹，有利于找寻待查找对象。在一些实施例中，图像处理装置在执行步骤12的过程中执行以下步骤：
13、在确定上述第一人脸图像中的人物不包括上述至少一个陪同员中任一个的情况下或在确定上述至少一张第二人脸图像不包括上述至少一个被陪同员的情况下，获取待查找对象的第四人脸图像，使用上述第四人脸图像检索数据库，得到与上述第四人脸图像匹配的第五人脸图像。
在该种实施方式中，第一人脸图像为用于校验陪同员身份信息的图像，若第一人脸图像不包括至少一个陪同员中的任一个，说明目标陪同任务出现异常。至少一张第二人脸图像不包括至少一个被陪同员，说明目标陪同任务有被陪同员未到达终止位置，即目标陪同任务出现异常。
在目标陪同任务出现异常的情况下，用户可通过查看目标陪同任务中任意一人的轨迹，确定目标陪同任务的情况。因此，图像处理装置在确定第一人脸图像中的人物不包括至少一个陪同员中任一个的情况下执行步骤12，进而基于步骤12的执行结果显示第一轨迹。
在一些实施例中，在步骤13中，待查找对象为目标陪同任务中的陪同员，待查找对象或为目标陪同任务中的被陪同员。在一些实施例中，在步骤13中，待查找对象为未出现在第一人脸图像中的陪同员，待查找对象或为未出现在至少一张第二人脸图像中的被陪同员。例如，至少一个陪同员包括张三和李四，至少一个被陪同员包括王五和周六。第一人脸图像包括张三，至少一张第二人脸图像包括王五。那么待查找对象可以是李四，待查找对象也可以是周六。
若在步骤201～步骤204中，图像处理装置在确定第一人脸图像中的人物为至少一个陪同员中的一个的情况下，获取至少一张第二人脸图像。在一些实施例中，图像处理装置在确定第一人脸图像中的人物为至少一个陪同员中的一个的情况下之后，在获取至少一张第二人脸图像之前，还执行以下步骤：
14、获取至少一张第六人脸图像，上述至少一张第六人脸图像的采集位置为上述终止位置。
本公开实施例中，至少一张第六人脸图像可以包括一张第六人脸图像，也可以包括两张或两张以上第六人脸图像。
本公开实施例中，至少一张第六人脸图像的采集位置均为终止位置，即任意一张第六人脸图像的位置均为终止位置。
在一种可能实现的方式中，至少一张第六人脸图像由门禁设备采集得到，至少一张第六人脸图像的采集位置为该门禁设备的位置。至少一张第六人脸图像的采集位置为终止位置，即采集至少一张第六人脸图像的门禁设备的位置为终止位置。
在一种获取至少一张第六人脸图像的实现方式中，图像处理装置接收用户通过输入组件输入的至少一张第六人脸图像。在另一种获取至少一张第六人脸图像的实现方式中，图像处理装置接收终端发送的至少一张第六人脸图像。
15、在确定上述至少一张第六人脸图像未包含上述至少一个被陪同员的情况下，输出补录提示信息。
至少一张第六人脸图像未包含至少一个被陪同员，说明有被陪同员可能未回到终止位置，或图像处理装置对至少一张第六人脸图像进行人脸识别未识别到某些被陪同员，或有被陪同员已回到终止位置，但未出现在至少一张第六人脸图像中。此时，可提示用户确认已回到终止位置的被陪同员名单，以提高目标陪同任务的监测准确度。
本公开实施例中，补录提示信息用于提示用户确认已回到终止位置的被陪同员名单。在一些实 施例中，补录提示信息包括未录入被陪同员，其中，未录入被陪同员包括至少一张第六人脸图像中未包含的被陪同员。例如，目标陪同任务的至少一个被陪同员包括张三、李四、王五。图像处理装置对至少一张第六人脸图像进行人脸识别，确定至少一张第六人脸图像包括张三。此时，李四和王五均为未录入被陪同员。此时，补录提示信息可包括“未返回被陪同员包括李四和王五”。
16、依据针对上述补录提示信息输入的至少一张第七人脸图像和上述至少一张第六人脸图像，得到上述至少一张第二人脸图像，上述至少一张第七人脸图像的采集位置为上述终止位置。
本公开实施例中，针对补录提示信息输入的至少一张第七人脸图像，为至少一个补录被陪同员的人脸图像，其中，补录被陪同员包括用户确定已回到终止位置但未在已回到终止位置的被陪同员名单中的被陪同员。
在一些实施例中，图像处理装置在获取针对补录提示信息输入的至少一张第七人脸图像之前，获取待校验人脸图像。在确定待校验人脸图像中的人物包括至少一个陪同员中的一个的情况下，获取针对补录提示信息输入的至少一张第七人脸图像。
在一些实施例中，图像处理装置在接收到针对补录提示信息输入的至少一张第七人脸图像之后，输出再次确认提示信息。例如，再次确认提示信息是“目标陪同任务提交后将不可更改”。
在一种得到至少一张第二人脸图像的实现方式中，图像处理装置将至少一张第七人脸图像和至少一张第六人脸图像，作为至少一张第二人脸图像。例如，至少一张第七人脸图像包括图像a，至少一张第六人脸图像包括图像b和图像c，至少一张第二人脸图像包括图像a、图像b和图像c。在步骤14～步骤16中，图像处理装置通过输出补录提示信息，提示用户确认已回到终止位置的被陪同员名单，从而提高目标陪同任务的监测准确度。在一些实施例中，图像处理装置还执行以下步骤：
17、在上述检测结果包括上述目标陪同任务不满足上述任务要求的情况下，输出告警信息。
检测结果包括目标陪同任务不满足任务要求，说明目标陪同任务异常。因此，输出告警信息，以提示相关人员目标陪同任务异常。
本公开实施例中，告警信息携带提示目标陪同任务异常的信息，例如，告警信息可以是语音提示信息，如：“目标陪同任务有被陪同员未回到终止位置”。又例如，告警信息可以是文字提示信息，如：在图像处理装置的显示界面上弹出提示窗口，提示窗口内包含提示文字，如：“目标陪同任务超时20分钟”。在一些实施例中，图像处理装置通过执行以下步骤获取目标陪同任务：
18、在执行创建陪同任务程序的情况下，获取第八人脸图像、至少一张第九人脸图像和上述终止位置，上述至少一张第九人脸图像的采集位置与上述第八人脸图像的采集位置相同，且上述至少一张第九人脸图像的时间戳与上述第八人脸图像的时间戳不同。
本公开实施例中，创建陪同任务程序可以是，图像处理装置在检测到创建指令的情况下执行的程序。例如，陪同员需要创建目标陪同任务，可通过图像处理装置的触摸显示屏向图像处理装置输入创建指令，从而使图像处理装置执行创建陪同任务程序，并显示创建陪同任务界面。陪同员进而可通过在创建陪同任务界面输入目标陪同任务的信息，创建目标陪同任务。
本公开实施例中，至少一张第九人脸图像可以包括一张第九人脸图像，也可以包括两张或两张以上第九人脸图像。
本公开实施例中，第八人脸图像的时间戳与至少一张第九人脸图像的时间戳不同，即第八人脸图像的采集时间与任意一张第九人脸图像的采集时间均不同。例如，若至少一张第九人脸图像包括图像a，那么第八人脸图像的时间戳与图像a的时间戳不同。又例如，若至少一张第九人脸图像包括图像a和图像b，那么第八人脸图像的时间戳与图像a的时间戳不同，且第八人脸图像的时间戳与图像b的时间戳不同。在一些实施例中，至少一张第九人脸图像中任意一张人脸图像的采集时间，与第八人脸图像的采集时间之间的时间间隔均小于第二时间阈值，其中，第二时间阈值与第一时间阈值也可以相同，第二时间阈值与第一时间阈值也可以不同。例如，第二时间阈值为3分钟，第八人脸图像的采集时间为t1，至少一张第九人脸图像包括图像a和图像b。那么，图像a的采集时间与t1之间的时间间隔小于3分钟，且图像b的采集时间与t1之间的时间间隔小于3分钟。
本公开实施例中，终止位置为新创建的陪同任务的终止位置，即为目标陪同任务的终止位置。
在一种获取第八人脸图的实现方式中，图像处理装置接收用户通过输入组件输入的第八人脸图。 在另一种获取第八人脸图的实现方式中，图像处理装置接收终端发送的第八人脸图。在又一种获取第八人脸图像的实现方式中，图像处理装置包括成像设备。图像处理装置使用成像设备采集一张人脸图像作为第八人脸图像。
在一种获取至少一张第九人脸图的实现方式中，图像处理装置接收用户通过输入组件输入的至少一张第九人脸图。在另一种获取至少一张第九人脸图的实现方式中，图像处理装置接收终端发送的至少一张第九人脸图。在又一种获取至少一张第九人脸图像的实现方式中，图像处理装置包括成像设备。图像处理装置使用成像设备采集一张人脸图像作为至少一张第九人脸图像。
在一种获取终止位置的实现方式中，图像处理装置接收用户通过输入组件输入的终止位置。在另一种获取终止位置的实现方式中，图像处理装置接收终端发送的终止位置。应理解，在本公开实施例中，获取第八人脸图像的步骤、获取至少一张第九人脸图像的步骤以及获取终止位置的步骤可以分开执行，也可以同时执行。
在一种可能实现的方式中，图像处理装置在确定第八人脸图像中的人物包括至少一个陪同员中的一个之前，获取至少一张第九人脸图像和终止位置。
在一个基于该种实现方式的应用场景中，陪同员向图像处理装置输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像。图像处理装置输出“请陪同员进行人脸识别”的第九提示信息，并将摄像头在输出第九提示信息后采集到的人脸图像作为第八人脸图像。在采集完第八人脸图像后，输出“请被陪同员进行人脸识别”的第十提示信息，并将摄像头在输出第十提示信息后采集到的至少一张人脸图像作为至少一张第九人脸图像。图像处理装置在采集第八人脸图像后，还将用户通过输入组件输入的位置作为终止位置。在另一个基于该种实现方式的应用场景中，陪同员向门禁设备输入结束目标陪同任务的指令，门禁设备在检测到该指令后，开启摄像头采集图像，并将用户通过输入组件输入的位置作为终止位置。门禁设备输出“请陪同员进行人脸识别”的第十一提示信息，并将摄像头在输出第十一提示信息后采集到的人脸图像作为第八人脸图像。在采集完第八人脸图像后，输出“请被陪同员进行人脸识别”的第十二提示信息，并将摄像头在输出第十二提示信息后采集到的至少一张人脸图像作为至少一张第九人脸图像。门禁设备将第八人脸图像、至少一张第九人脸图像和终止位置发送至图像处理装置。在另一种可能实现的方式中，图像处理装置在确定第八人脸图像中的人物包括至少一个陪同员中的一个的情况下，获取至少一张第九人脸图像和终止位置。
在一个基于该种实现方式的应用场景中，陪同员向图像处理装置输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像。图像处理装置输出“请陪同员进行人脸识别”的第十三提示信息，并将摄像头在输出第十三提示信息后采集到的人脸图像作为第八人脸图像。在采集完第八人脸图像后，对第八人脸图像进行人脸识别，并在确定第八人脸图像中的人物包括至少一个陪同员中的一个的情况下，输出“请被陪同员进行人脸识别”的第十四提示信息，并将摄像头在输出第十四提示信息后采集到的至少一张人脸图像作为至少一张第九人脸图像。图像处理装置还在确定第八人脸图像中的人物包括至少一个陪同员中的一个的情况下，将用户输入的位置作为终止位置。在另一个基于该种实现方式的应用场景中，陪同员向门禁设备输入结束目标陪同任务的指令，图像处理装置在检测到该指令后，开启摄像头采集图像，并将用户通过输入组件输入的位置作为终止位置。图像处理装置输出“请陪同员进行人脸识别”的第十五提示信息，并将摄像头在输出第十五提示信息后采集到的至少一张人脸图像作为至少一张第九人脸图像。在采集完至少一张第九人脸图像后，输出“请陪同员进行人脸识别”的第十六提示信息，并将摄像头在输出第十六提示信息后采集到的人脸图像作为第八人脸图像。门禁设备在获取第八人脸图像、至少一张第九人脸图像和终止位置后，将第八人脸图像和发送至图像处理装置。图像处理装置在接收到门禁设备发送的第八人脸图像后，对第八人脸图像进行人脸识别，并在确定第八人脸图像中的人物包括至少一个陪同员中的一个的情况下，向门禁设备发送第二校验通过指令。门禁设备在检测第二校验通过指令后，将至少一张第九人脸图像和终止位置发送至图像处理装置。
19、在确定上述第八人脸图像中的人物包括已注册陪同员的情况下，依据上述至少一张第九人脸图像所包含的上述已注册陪同员和上述第八人脸图像中的人物，得到上述至少一个陪同员。
本公开实施例中，已注册陪同员包括具有身份信息的陪同员。例如，张三为A区域的陪同员，A区域的管理人员通过图像处理装置对张三进行注册。注册过程包括，向图像处理装置输入张三的人脸图像a、张三的身份信息以及张三所需注册的身份为陪同员。图像处理装置通过对张三进行注册，确定人脸图像a中的人物为张三，且张三为已注册陪同员。
第八人脸图像中的人物包括已注册陪同员，说明有陪同员在创建陪同任务，因此可依据至少一张第九人脸图像所包含的已注册陪同员和第八人脸图像中的人物，得到至少一个陪同员。在一种可能实现的方式中，图像处理装置将至少一张第九人脸图像所包含的已注册陪同员和第八人脸图像中的人物，作为至少一个陪同员。例如，至少一张第九人脸图像所包含的已注册陪同员为张三和李四，第八人脸图像中的人物为王五，此时，至少一个陪同员包括张三、李四和王五。
20、在确定上述第八人脸图像中的人物为已注册陪同员的情况下，依据上述至少一张第九人脸图像所包含的已注册被陪同员，得到上述至少一个被陪同员。
本公开实施例中，已注册被陪同员包括具有身份信息的被陪同员。例如，张三为A区域的被陪同员，A区域的管理人员通过图像处理装置对张三进行注册。包括，向图像处理装置输入张三的人脸图像a、张三的身份信息以及张三所需注册的身份为被陪同员。图像处理装置通过对张三进行注册，确定人脸图像a中的人物为张三，且张三为已注册被陪同员。
第八人脸图像中的人物包括已注册陪同员，说明有陪同员在创建陪同任务，因此可依据至少一张第九人脸图像所包含的已注册被陪同员，得到至少一个被陪同员。在一种可能实现的方式中，图像处理装置将至少一张第九人脸图像所包含的已注册被陪同员，作为至少一个被陪同员。例如，至少一张第九人脸图像所包含的已注册被陪同员为张三和李四，此时，至少一个被陪同员包括张三和李四。
21、依据上述终止位置、上述至少一个陪同员和上述至少一个被陪同员，创建上述目标陪同任务。
在一种可能实现的方式中，图像处理装置将通过执行步骤18获取的终止位置作为目标陪同任务的终止位置，将通过执行步骤19得到的至少一个陪同员作为目标陪同任务的至少一个陪同员，将通过执行步骤20得到的至少一个被陪同员作为目标陪同任务的至少一个被陪同员，创建目标陪同任务。在步骤18～步骤21中，用户可通过图像处理装置创建目标陪同任务，进而可在后续处理中，通过人脸识别实现对目标陪同任务的监测。
在一些实施例中，图像处理装置在执行“依据上述至少一张第九人脸图像所包含的已注册被陪同员，得到上述至少一个被陪同员”的步骤中，执行以下中一个步骤：
22、在检测到针对第一人物的删除指令的情况下，将上述第一人物从上述至少一张第九人脸图像所包含的上述已注册被陪同员中删除，得到上述至少一个被陪同员。
本步骤中，第一人物为至少一张第九人脸图像所包含的任意一个已注册被陪同员。例如，图像处理装置通过对至少一张第九图像进行人脸识别，确定至少一张第九人脸图像包含的已注册被陪同员包括张三和李四，那么第一人物可以是张三，第一人物也可以是李四。在步骤22中，用户可通过向图像处理装置输入删除指令，删除至少一张第九人脸图像所包含的已注册被陪同员中的任意一个或一个以上，得到至少一个被陪同员。例如，至少一张第九人脸图像所包含的已注册被陪同员包括张三、李四和王五，用户可向图像处理装置输入针对张三的删除指令，以将张三从至少一张第九人脸图像所包含的已注册被陪同员中删除，确定至少一个被陪同员为李四和王五。
用户可向图像处理装置输入针对李四的删除指令，以将李四从至少一张第九人脸图像所包含的已注册被陪同员中删除，确定至少一个被陪同员为张三和王五。用户还可向图像处理装置输入针对李四的删除指令以及针对王五的删除指令，以将李四和王五从至少一张第九人脸图像所包含的已注册被陪同员中删除，确定至少一个被陪同员为张三。
23、在检测到针对第二人物的添加指令的情况下，依据上述第二人物和上述至少一张第九人脸图像所包含的上述已注册被陪同员，得到上述至少一个被陪同员。
在一些实施例中，第二人物为任意已注册被陪同员。在一种可能实现的方式中，图像处理装置将第二人物和至少一张第九人脸图像所包含的已注册被陪同员，作为至少一个被陪同员。
在一些实施例中，图像处理装置可在执行步骤22的基础上，执行步骤23，得到至少一个被陪同员。例如，图像处理装置通过对至少一张第九人脸图像进行人脸识别，确定至少一张第九人脸图像所包含的已注册被陪同员包括张三和李四。在检测到针对张三的删除指令以及针对王五的添加指令的情况下，确定至少一个被陪同员包括李四和王五。在图像处理装置通过对至少一张第九人脸图像进行人脸识别，确定至少一个被陪同员，出现误差的情况下，图像处理装置通过执行步骤22，或通过执行步骤23，或通过执行步骤22以及步骤23，提高至少一个被陪同员的准确度，从而提高目标陪同任务的监测准确度。在一些实施例中，图像处理装置通过执行以下步骤获取终止位置：
24、在检测到输入终止位置的指令的情况下，显示至少一个待选位置。
在一种可能实现的方式中，图像处理装置以列表的形式显示至少一个待选位置。在另一种可能实现的方式中，图像处理装置以下拉框的形式显示至少一个待选位置。
25、在检测到针对上述至少一个待选位置的选择指令的情况下，依据上述选择指令和上述至少一个待选位置，得到上述终止位置。
本公开实施例中，选择指令包括从至少一个待选位置中选择的位置。图像处理装置依据选择指令和至少一个待选位置，可确定终止位置。在一些实施例中，图像处理装置还执行以下步骤：
26、获取上述目标陪同任务的陪同原因。
本公开实施例中，陪同原因包括执行目标陪同任务的原因。例如，陪同原因是被陪同员生病需要去医院。又例如，陪同原因是被陪同员需要购物。在一些实施例中，图像处理装置在执行步骤21之前，还执行以下步骤：
27、依据所述第八人脸图像的采集位置得到起始位置。
在一种可能实现的方式中，图像处理装置将第八人脸图像的采集位置作为起始位置。在执行完步骤27后，图像处理装置在执行步骤21的过程中执行以下步骤：
28、依据所述起始位置、所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
在一种可能实现的方式中，图像处理装置将通过执行步骤27获取的起始位置作为目标陪同任务的起始位置，图像处理装置将通过执行步骤18获取的终止位置作为目标陪同任务的终止位置，将通过执行步骤19得到的至少一个陪同员作为目标陪同任务的至少一个陪同员，将通过执行步骤20得到的至少一个被陪同员作为目标陪同任务的至少一个被陪同员，创建目标陪同任务。在一些实施例中，用户在通过图像处理装置创建完目标陪同任务后，可通过图像处理装置查看目标陪同任务的执行时长。
基于本公开实施例提供的技术方案，本公开实施例还提供了一种可能的应用场景。
在监管区域内，被监管员需要流动时，通常需要监管员陪同。例如，被监管员身体不舒服，需要去监管区域内的医院看病，此时，需要监管员陪同被监管员去医院。因此，可基于本公开实施例提供的技术方案，实现对监管区域内的陪同任务进行监测。
请参阅图3，图3所示为本公开实施例提供的另一种陪同监测系统31架构示意图。在图3中，图像处理装置312与摄像头311之间具有通信连接，图像处理装置212与门禁设备313之间也具有通信连接。在一些实施例中，图像处理装置312可以是服务器。图像处理装置312可部署在监管区域的控制中心。摄像头311为监管区域内的摄像头，门禁设备313为监管区域内的门禁设备。其中，门禁设备313可采集图像，且门禁设备具有输入组件。
监管员a和监管员b需要陪同被监管员c和被监管员d，从监管区域内的A处到监管区域内的B处。监管员a或监管员b在A处的门禁设备C上创建目标陪同任务。创建目标陪同任务的过程包括，监管员a或监管员b向门禁设备输入创建陪同任务的创建指令，以使门禁设备C执行创建陪同任务的程序。监管员a或监管员b向门禁设备C输入目标陪同任务的陪同原因。在门禁设备C提示输入终止位置的情况下，监管员a或监管员b可向门禁设备C输入目标陪同任务的终止位置为B处的门禁设备D，门禁设备C在接收到监管员a输入的终止位置后，对终止位置进行存储。
在门禁设备C提示请进行人脸识别的情况下，监管员a、监管员b、被监管员c和被监管员d，依次到门禁设备C的图像采集区域进行人脸图像采集。门禁设备C将采集到的监管员a的人脸图像、 监管员b的人脸图像、被监管员c的人脸图像、监管员d的人脸图像作为至少一张第九人脸图像，并储存至少一张第九人脸图像。在门禁设备C提示请进行校验的情况下，监管员a或监管员b到门禁设备C的图像采集区域进行人脸图像采集。门禁设备C将采集到的监管员a的人脸图像或监管员b的人脸图像作为第八人脸图像，并将第八人脸图像发送至图像处理装置，以使图像处理装置312确定第八人脸图像中的人物是否包含已注册陪同员。图像处理装置312在确定第八人脸图像中的人物包含已注册陪同员的情况下，向门禁设备C发送第二校验通过指令。门禁设备C在检测到第二校验通过指令的情况下，将至少一张第九人脸图像和终止位置发送至图像处理装置312。图像处理装置312进而依据第八人脸图像、至少一张第九人脸图像、终止位置和陪同原因，创建目标陪同任务。监管员a、监管员b、被监管员c和被监管员d达到门禁设备D后，监管员a或监管员b向门禁设备D输入结束目标陪同任务的指令，以使门禁设备D录入结束目标陪同任务的信息。
示例性地，门禁设备D在检测到结束目标陪同任务的指令的情况下，提示被陪同员进行人脸识别。此时，被监管员c和被监管员d到门禁设备D的图像采集区域进行人脸图像采集。门禁设备D将采集到的被监管员c的人脸图像和被监管员d的人脸图像作为至少一张第二人脸图像，并储存至少一张第二人脸图像。在门禁设备D提示请进行校验的情况下，监管员a或监管员b到门禁设备D的图像采集区域进行人脸图像采集。门禁设备D将采集到的监管员a的人脸图像或监管员b的人脸图像作为第一人脸图像，并将第一人脸图像发送至图像处理装置，以使图像处理装置312确定第一人脸图像中的人物是否包含目标陪同任务的陪同员。图像处理装置312在确定第一人脸图像中的人物包含目标陪同任务的陪同员，且第一人脸图像的采集位置为目标陪同任务的终止位置的情况下，向门禁设备D发送第一校验通过指令。门禁设备D在检测到第一校验通过指令的情况下，将至少一张第二人脸图像发送至图像处理装置312。图像处理装置312进而确定至少一张第二人脸图像的采集位置是否为目标陪同任务的终止位置，以及至少一张第二人脸图像是否包含目标陪同任务的所有被陪同员。图像处理装置312在确定至少一张第二人脸图像包含目标陪同任务的所有陪同员，且至少一张第二人脸图像的采集位置为目标陪同任务的终止位置的情况下，确定目标陪同任务正常。否则图像处理装置312确定目标陪同任务异常。
本领域技术人员可以理解，在实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的执行顺序应当以其功能和可能的内在逻辑确定。
上述详细阐述了本公开实施例的方法，下面提供了本公开实施例的装置。
请参阅图4，图4为本公开实施例提供的一种图像处理装置的结构示意图，该图像处理装置40包括：获取单元41、确定单元42。在一些实施例中，图像处理装置40还包括发送单元43和输出单元44。其中：获取单元41，配置为获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；所述获取单元41，还配置为获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；确定单元42，配置为在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果，所述任务要求包括：所述至少一张第二人脸图像包含所述目标陪同任务的至少一个被陪同员；所述确定单元42，还配置为在所述检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。
结合本公开任一实施方式，所述获取单元41，还配置为在确定所述目标陪同任务是否满足任务要求，得到检测结果之前，获取执行所述目标陪同任务所花的时间；所述任务要求还包括：所述执行所述目标陪同任务所花的时间小于所述目标陪同任务的执行时长。
结合本公开任一实施方式，所述获取单元41还配置为：获取执行所述目标陪同任务的起始时间戳；依据所述起始时间戳和所述第一人脸图像的时间戳，得到执行所述目标陪同任务所花的时间。
结合本公开任一实施方式，所述目标陪同任务的陪同路线位于目标区域内，所述至少一个被陪同员包括目标被陪同员；所述获取单元41，还配置为获取所述目标区域的第一图像和所述目标陪同员在所述第一图像中的第一轨迹，在所述第一图像中显示所述第一轨迹。
结合本公开任一实施方式，所述获取单元41，配置为：获取至少一张第二图像和所述目标被陪 同员的第三人脸图像，所述至少一张第二图像均由所述目标区域内的至少一个目标摄像头采集得到；从所述至少一张第二图像中确定至少一张第三图像，所述至少一张第三图像均与所述第三人脸图像匹配；依据采集所述至少一张第三图像的摄像头在所述第一图像中的位置，得到所述目标被陪同员在所述第一图像中的第一轨迹。
结合本公开任一实施方式，所述获取单元41，还配置为在所述获取至少一张第二图像获取有效时间段；所述图像处理装置40还包括：发送单元43，配置为向所述至少一个目标摄像头发送轨迹检测指令，所述轨迹检测指令用于指示所述至少一个目标摄像头在所述有效时间段内采集图像；所述获取单元41，配置为将所述至少一个目标摄像头采集到的至少一张图像作为所述至少一张第二图像。
结合本公开任一实施方式，所述获取单元41，配置为：在检测到显示所述目标被陪同员的轨迹的指令的情况下，在所述第一图像中显示所述第一轨迹。
结合本公开任一实施方式，所述获取单元41，还配置为在所述第一图像中显示所述第一轨迹之前，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像；在确定所述待查找对象满足轨迹显示条件的情况下，在所述第一图像中显示所述第一轨迹；所述轨迹显示条件包括以下中的一个：所述待查找对象为所述至少一个陪同员中的一个、所述待查找对象为所述至少一个被陪同员中的一个。
结合本公开任一实施方式，所述获取单元41，配置为：在确定所述第一人脸图像中的人物不包括所述至少一个陪同员中任一个的情况下或在确定所述至少一张第二人脸图像不包括所述至少一个被陪同员的情况下，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像。
结合本公开任一实施方式，所述获取单元41，还配置为在所述至少一张第二图像在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下之后，在所述获取至少一张第二人脸图像之前，获取至少一张第六人脸图像，所述至少一张第六人脸图像的采集位置为所述终止位置；所述图像处理装置40还包括：输出单元44，配置为在确定所述至少一张第六人脸图像未包含所述至少一个被陪同员的情况下，输出补录提示信息；所述确定单元42，还配置为依据针对所述补录提示信息输入的至少一张第七人脸图像和所述至少一张第六人脸图像，得到所述至少一张第二人脸图像，所述至少一张第七人脸图像的采集位置为所述终止位置。
结合本公开任一实施方式，所述输出单元44，还配置为：在所述检测结果包括所述目标陪同任务不满足所述任务要求的情况下，输出告警信息。
结合本公开任一实施方式，所述获取单元41，配置为：在执行创建陪同任务程序的情况下，获取第八人脸图像、至少一张第九人脸图像和所述终止位置，所述至少一张第九人脸图像的采集位置与所述第八人脸图像的采集位置相同；在确定所述第八人脸图像中的人物包括已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的所述已注册陪同员和所述第八人脸图像中的人物，得到所述至少一个陪同员；在确定所述第八人脸图像中的人物为已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员；依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
结合本公开任一实施方式，所述获取单元41，配置为：在检测到针对所述第一人物的删除指令的情况下，将所述第一人物从所述至少一张第九人脸图像所包含的所述已注册被陪同员中删除，得到所述至少一个被陪同员；或，在检测到针对第二人物的添加指令的情况下，依据所述第二人物和所述至少一张第九人脸图像所包含的所述已注册被陪同员，得到所述至少一个被陪同员。
结合本公开任一实施方式，所述获取单元41，配置为：在检测到输入终止位置的指令的情况下，显示至少一个待选位置；在检测到针对所述至少一个待选位置的选择指令的情况下，依据所述选择指令和所述至少一个待选位置，得到所述终止位置。
结合本公开任一实施方式，所述获取单元41，还配置为：获取所述目标陪同任务的陪同原因。
结合本公开任一实施方式，所述获取单元41，还配置为：依据所述第八人脸图像的采集位置得到起始位置；所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目 标陪同任务，包括：依据所述起始位置、所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
本公开实施例中，图像处理装置通过对第一人脸图像进行人脸识别，确定第一人脸图像中的人物是否为陪同员。在确定第一人脸图像中的人物为陪同员的情况下，确定陪同员已到目标陪同任务的终止位置，进而通过对至少一张第二人脸图像进行人脸识别，确定至少一个被陪同员是否达到终止位置。由此完成对目标陪同任务的监测，降低人力成本，并提高监测效率。在一些实施例中，本公开实施例提供的装置具有功能或包含模块可以用于执行上文方法实施例描述的方法，其实现可以参照上文方法实施例的描述。
图5为本公开实施例提供的一种图像处理装置的硬件结构示意图。该图像处理装置50包括处理器51，存储器52，输入装置53，输出装置54。该处理器51、存储器52、输入装置53和输出装置54通过连接器相耦合，该连接器包括各类接口、传输线或总线等等，本公开实施例对此不作限定。应当理解，本公开的各个实施例中，耦合是指通过特定方式的相互联系，包括直接相连或者通过其他设备间接相连，例如可以通过各类接口、传输线、总线等相连。
处理器51可以是一个或多个图形处理器(graphics processing unit，GPU)，在处理器51是一个GPU的情况下，该GPU可以是单核GPU，也可以是多核GPU。在一些实施例中，处理器51可以是多个GPU构成的处理器组，多个处理器之间通过一个或多个总线彼此耦合。在一些实施例中，该处理器还可以为其他类型的处理器等等，本公开实施例不作限定。
存储器52可配置为存储计算机程序指令，以及配置为执行本公开方案的程序代码在内的各类计算机程序代码。在本公开的一些实施例中，存储器包括但不限于是随机存储记忆体(random access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmable read only memory，EPROM)、或便携式只读存储器(compact disc read-only memory，CD-ROM)，该存储器配置为存储相关指令及数据。
输入装置53配置为输入数据和信号中的一种或多种，以及输出装置54配置为输出数据和信号中的一种或多种。输入装置53和输出装置54可以是独立的器件，也可以是一个整体的器件。
可以理解的是，本公开实施例中，存储器52不仅可配置为存储相关指令，还可配置为存储相关数据，如该存储器52可配置为存储通过输入装置53获取的目标陪同任务和第一人脸图，又或者该存储器52还可配置为存储通过处理器51得到的检测结果等等，本公开实施例对于该存储器中所存储的数据不作限定。
可以理解的是，图5仅仅示出了一种图像处理装置的简化设计。在实际应用中，图像处理装置还可以分别包含必要的其他元件，包含但不限于任意数量的输入/输出装置、处理器、存储器等，而所有可以实现本公开实施例的图像处理装置都在本公开的保护范围之内。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本公开的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的工作过程，可以参考前述方法实施例中的对应过程。所属领域的技术人员还可以清楚地了解到，本公开各个实施例描述各有侧重，因此，在某一实施例未描述或未详细描述的部分可以参见其他实施例的记载。
在本公开所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以 是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本公开实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者通过所述计算机可读存储介质进行传输。所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，数字通用光盘(digital versatile disc，DVD)、或者半导体介质(例如固态硬盘(solid state disk，SSD))等。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，该流程可以由计算机程序来指令相关的硬件完成，该程序可存储于计算机可读取存储介质中，该程序在执行时，可包括如上述各方法实施例的流程。而前述的存储介质包括：只读存储器(read-only memory，ROM)或随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可存储程序代码的介质。
工业实用性
本公开实施例中，通过对第一人脸图像进行人脸识别，确定第一人脸图像中的人物是否为陪同员。在确定第一人脸图像中的人物为陪同员的情况下，确定陪同员已到目标陪同任务的终止位置，进而通过对至少一张第二人脸图像进行人脸识别，确定至少一个被陪同员是否达到终止位置。由此完成对目标陪同任务的监测，降低人力成本，并提高监测效率。

Claims (35)

  1. 一种图像处理方法，所述方法包括：
    获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；
    获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；
    在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果，所述任务要求包括：所述至少一张第二人脸图像包含所述目标陪同任务的至少一个被陪同员；
    在所述检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。
  2. 根据权利要求1所述的方法，其中，所述确定所述目标陪同任务是否满足任务要求，得到检测结果之前，所述方法还包括：
    获取执行所述目标陪同任务所花的时间；
    所述任务要求还包括：所述执行所述目标陪同任务所花的时间小于所述目标陪同任务的执行时长。
  3. 根据权利要求2所述的方法，其中，所述获取执行所述目标陪同任务所花的时间，包括：
    获取执行所述目标陪同任务的起始时间戳；
    依据所述起始时间戳和所述第一人脸图像的时间戳，得到执行所述目标陪同任务所花的时间。
  4. 根据权利要求1至3中任意一项所述的方法，其中，所述目标陪同任务的陪同路线位于目标区域内，所述至少一个被陪同员包括目标被陪同员；
    所述方法还包括：
    获取所述目标区域的第一图像和所述目标陪同员在所述第一图像中的第一轨迹，在所述第一图像中显示所述第一轨迹。
  5. 根据权利要求4所述的方法，其中，所述获取所述目标被陪同员在所述第一图像中的轨迹，包括：
    获取至少一张第二图像和所述目标被陪同员的第三人脸图像，所述至少一张第二图像均由所述目标区域内的至少一个目标摄像头采集得到；
    从所述至少一张第二图像中确定至少一张第三图像，所述至少一张第三图像均与所述第三人脸图像匹配；
    依据采集所述至少一张第三图像的摄像头在所述第一图像中的位置，得到所述目标被陪同员在所述第一图像中的第一轨迹。
  6. 根据权利要求5所述的方法，其中，所述获取至少一张第二图像之前，所述方法还包括：
    获取有效时间段；
    向所述至少一个目标摄像头发送轨迹检测指令，所述轨迹检测指令用于指示所述至少一个目标摄像头在所述有效时间段内采集图像；
    所述获取至少一张第二图像，包括：
    将所述至少一个目标摄像头采集到的至少一张图像作为所述至少一张第二图像。
  7. 根据权利要求4至6中任意一项所述的方法，其中，所述在所述第一图像中显示所述第一轨迹，包括：
    在检测到显示所述目标被陪同员的轨迹的指令的情况下，在所述第一图像中显示所述第一轨迹。
  8. 根据权利要求4至6中任意一项所述的方法，其中，所述在所述第一图像中显示所述第一轨迹之前，所述方法还包括：
    获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像；
    所述在所述第一图像中显示所述第一轨迹，包括：
    在确定所述待查找对象满足轨迹显示条件的情况下，在所述第一图像中显示所述第一轨迹；
    所述轨迹显示条件包括以下中的一个：所述待查找对象为所述至少一个陪同员中的一个、所述待查找对象为所述至少一个被陪同员中的一个。
  9. 根据权利要求8所述的方法，其中，所述获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像，包括：
    在确定所述第一人脸图像中的人物不包括所述至少一个陪同员中任一个的情况下或在确定所述至少一张第二人脸图像不包括所述至少一个被陪同员的情况下，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像。
  10. 根据权利要求1至9中任意一项所述的方法，其中，所述在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下之后，所述获取至少一张第二人脸图像之前，所述方法还包括：
    获取至少一张第六人脸图像，所述至少一张第六人脸图像的采集位置为所述终止位置；
    在确定所述至少一张第六人脸图像未包含所述至少一个被陪同员的情况下，输出补录提示信息；
    依据针对所述补录提示信息输入的至少一张第七人脸图像和所述至少一张第六人脸图像，得到所述至少一张第二人脸图像，所述至少一张第七人脸图像的采集位置为所述终止位置。
  11. 根据权利要求1至10中任意一项所述的方法，其中，所述方法还包括：
    在所述检测结果包括所述目标陪同任务不满足所述任务要求的情况下，输出告警信息。
  12. 根据权利要求1至10中任意一项所述的方法，其中，所述获取目标陪同任务，包括：
    在执行创建陪同任务程序的情况下，获取第八人脸图像、至少一张第九人脸图像和所述终止位置，所述至少一张第九人脸图像的采集位置与所述第八人脸图像的采集位置相同；
    在确定所述第八人脸图像中的人物包括已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的所述已注册陪同员和所述第八人脸图像中的人物，得到所述至少一个陪同员；
    在确定所述第八人脸图像中的人物为已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员；
    依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
  13. 根据权利要求12所述的方法，其中，所述至少一张第九人脸图像所包含的所述已注册被陪同员包括第一人物，所述依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员，包括：
    在检测到针对所述第一人物的删除指令的情况下，将所述第一人物从所述至少一张第九人脸图像所包含的所述已注册被陪同员中删除，得到所述至少一个被陪同员；或，
    在检测到针对第二人物的添加指令的情况下，依据所述第二人物和所述至少一张第九人脸图像所包含的所述已注册被陪同员，得到所述至少一个被陪同员。
  14. 根据权利要求12或13所述的方法，其中，所述获取终止位置，包括：
    在检测到输入终止位置的指令的情况下，显示至少一个待选位置；
    在检测到针对所述至少一个待选位置的选择指令的情况下，依据所述选择指令和所述至少一个待选位置，得到所述终止位置。
  15. 根据权利要求12至14中任意一项所述的方法，其中，所述方法还包括：
    获取所述目标陪同任务的陪同原因。
  16. 根据权利要求12至15中任意一项所述的方法，其中，所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务之前，所述方法还包括：
    依据所述第八人脸图像的采集位置得到起始位置；
    所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务，包括：
    依据所述起始位置、所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
  17. 一种图像处理装置，所述装置包括：
    获取单元，配置为获取目标陪同任务和第一人脸图，所述目标陪同任务包括至少一个陪同员，所述第一人脸图像的采集位置为所述目标陪同任务的终止位置；
    所述获取单元，还配置为获取至少一张第二人脸图像，所述至少一张第二人脸图像的时间戳与所述第一人脸图像的时间戳不同，所述至少一张第二人脸图像的采集位置为所述终止位置；
    确定单元，配置为在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下，确定所述目标陪同任务是否满足任务要求，得到检测结果，所述任务要求包括：所述至少一张第二人脸图像包含所述目标陪同任务的至少一个被陪同员；
    所述确定单元，还配置为在所述检测结果包括所述目标陪同任务满足所述任务要求的情况下，确定所述目标陪同任务的陪同结果为正常。
  18. 根据权利要求17所述的装置，其中，所述获取单元，还配置为在确定所述目标陪同任务是否满足任务要求，得到检测结果之前，获取执行所述目标陪同任务所花的时间；所述任务要求还包括：所述执行所述目标陪同任务所花的时间小于所述目标陪同任务的执行时长。
  19. 根据权利要求18所述的装置，其中，所述获取单元还配置为：获取执行所述目标陪同任务的起始时间戳；依据所述起始时间戳和所述第一人脸图像的时间戳，得到执行所述目标陪同任务所花的时间。
  20. 根据权利要求17至19中任意一项所述的装置，其中，所述目标陪同任务的陪同路线位于目标区域内，所述至少一个被陪同员包括目标被陪同员；所述获取单元，还配置为获取所述目标区域的第一图像和所述目标陪同员在所述第一图像中的第一轨迹，在所述第一图像中显示所述第一轨迹。
  21. 根据权利要求20所述的装置，其中，所述获取单元，配置为：获取至少一张第二图像和所述目标被陪同员的第三人脸图像，所述至少一张第二图像均由所述目标区域内的至少一个目标摄像头采集得到；从所述至少一张第二图像中确定至少一张第三图像，所述至少一张第三图像均与所述第三人脸图像匹配；依据采集所述至少一张第三图像的摄像头在所述第一图像中的位置，得到所述目标被陪同员在所述第一图像中的第一轨迹。
  22. 根据权利要求21所述的装置，其中，所述获取单元，还配置为在所述获取至少一张第二图像获取有效时间段；所述图像处理装置还包括：发送单元，配置为向所述至少一个目标摄像头发送轨迹检测指令，所述轨迹检测指令用于指示所述至少一个目标摄像头在所述有效时间段内采集图像；所述获取单元，配置为将所述至少一个目标摄像头采集到的至少一张图像作为所述至少一张第二图像。
  23. 根据权利要求20至22中任意一项所述的装置，其中，所述获取单元，配置为：在检测到显示所述目标被陪同员的轨迹的指令的情况下，在所述第一图像中显示所述第一轨迹。
  24. 根据权利要求20至22中任意一项所述的装置，其中，所述获取单元，还配置为在所述第一图像中显示所述第一轨迹之前，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像；在确定所述待查找对象满足轨迹显示条件的情况下，在所述第一图像中显示所述第一轨迹；所述轨迹显示条件包括以下中的一个：所述待查找对象为所述至少一个陪同员中的一个、所述待查找对象为所述至少一个被陪同员中的一个。
  25. 根据权利要求24所述的装置，其中，所述获取单元，配置为：在确定所述第一人脸图像中的人物不包括所述至少一个陪同员中任一个的情况下或在确定所述至少一张第二人脸图像不包括所述至少一个被陪同员的情况下，获取待查找对象的第四人脸图像，使用所述第四人脸图像检索数据库，得到与所述第四人脸图像匹配的第五人脸图像。
  26. 根据权利要求17至25中任意一项所述的装置，其中，所述获取单元，还配置为在所述至少一张第二图像在确定所述第一人脸图像中的人物包括所述至少一个陪同员中的一个的情况下之后，在所述获取至少一张第二人脸图像之前，获取至少一张第六人脸图像，所述至少一张第六人脸图像的采集位置为所述终止位置；所述图像处理装置还包括：输出单元，配置为在确定所述至少一张第六人脸图像未包含所述至少一个被陪同员的情况下，输出补录提示信息；所述确定单元，还配置为依据针对所述补录提示信息输入的至少一张第七人脸图像和所述至少一张第六人脸图像，得到 所述至少一张第二人脸图像，所述至少一张第七人脸图像的采集位置为所述终止位置。
  27. 根据权利要求17至26中任意一项所述的装置，其中，所述输出单元，还配置为：在所述检测结果包括所述目标陪同任务不满足所述任务要求的情况下，输出告警信息。
  28. 根据权利要求17至26中任意一项所述的装置，其中，所述获取单元，配置为：在执行创建陪同任务程序的情况下，获取第八人脸图像、至少一张第九人脸图像和所述终止位置，所述至少一张第九人脸图像的采集位置与所述第八人脸图像的采集位置相同；在确定所述第八人脸图像中的人物包括已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的所述已注册陪同员和所述第八人脸图像中的人物，得到所述至少一个陪同员；在确定所述第八人脸图像中的人物为已注册陪同员的情况下，依据所述至少一张第九人脸图像所包含的已注册被陪同员，得到所述至少一个被陪同员；依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
  29. 根据权利要求28所述的装置，其中，所述获取单元，配置为：在检测到针对所述第一人物的删除指令的情况下，将所述第一人物从所述至少一张第九人脸图像所包含的所述已注册被陪同员中删除，得到所述至少一个被陪同员；或，在检测到针对第二人物的添加指令的情况下，依据所述第二人物和所述至少一张第九人脸图像所包含的所述已注册被陪同员，得到所述至少一个被陪同员。
  30. 根据权利要求28或29所述的装置，其中，所述获取单元，配置为：在检测到输入终止位置的指令的情况下，显示至少一个待选位置；在检测到针对所述至少一个待选位置的选择指令的情况下，依据所述选择指令和所述至少一个待选位置，得到所述终止位置。
  31. 根据权利要求18至30中任意一项所述的装置，其中，所述获取单元，还配置为：获取所述目标陪同任务的陪同原因。
  32. 根据权利要求18至31中任意一项所述的装置，其中，所述获取单元，还配置为：依据所述第八人脸图像的采集位置得到起始位置；所述依据所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务，包括：依据所述起始位置、所述终止位置、所述至少一个陪同员和所述至少一个被陪同员，创建所述目标陪同任务。
  33. 一种电子设备，包括：处理器和存储器，所述存储器配置为存储计算机程序代码，所述计算机程序代码包括计算机指令，在所述处理器执行所述计算机指令的情况下，所述电子设备执行如权利要求1至16中任意一项所述的方法。
  34. 一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序包括程序指令，在所述程序指令被处理器执行的情况下，使所述处理器执行权利要求1至16中任意一项所述的方法。
  35. 一种计算机程序产品，包括计算机可读代码，在所述计算机可读代码在电子设备中运行的情况下，所述电子设备中的处理器执行如权利要求1至16中任意一项所述的方法。
PCT/CN2022/105242 2021-07-30 2022-07-12 图像处理方法及装置、电子设备、程序产品及计算机可读存储介质 WO2023005662A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110874726.8A CN113591713A (zh) 2021-07-30 2021-07-30 图像处理方法及装置、电子设备及计算机可读存储介质
CN202110874726.8 2021-07-30

Publications (1)

Publication Number Publication Date
WO2023005662A1 true WO2023005662A1 (zh) 2023-02-02

Family

ID=78252956

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/105242 WO2023005662A1 (zh) 2021-07-30 2022-07-12 图像处理方法及装置、电子设备、程序产品及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN113591713A (zh)
WO (1) WO2023005662A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113591713A (zh) * 2021-07-30 2021-11-02 深圳市商汤科技有限公司 图像处理方法及装置、电子设备及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009194711A (ja) * 2008-02-15 2009-08-27 Oki Electric Ind Co Ltd 領域利用者管理システムおよびその管理方法
CN110837512A (zh) * 2019-11-15 2020-02-25 北京市商汤科技开发有限公司 访客信息管理方法及装置、电子设备和存储介质
CN111739181A (zh) * 2020-05-19 2020-10-02 深圳市商汤科技有限公司 考勤方法及装置、电子设备及存储介质
CN113033392A (zh) * 2021-03-24 2021-06-25 中国工商银行股份有限公司 基于数据机房场景下的人员距离确定方法及装置
CN113591713A (zh) * 2021-07-30 2021-11-02 深圳市商汤科技有限公司 图像处理方法及装置、电子设备及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009194711A (ja) * 2008-02-15 2009-08-27 Oki Electric Ind Co Ltd 領域利用者管理システムおよびその管理方法
CN110837512A (zh) * 2019-11-15 2020-02-25 北京市商汤科技开发有限公司 访客信息管理方法及装置、电子设备和存储介质
CN111739181A (zh) * 2020-05-19 2020-10-02 深圳市商汤科技有限公司 考勤方法及装置、电子设备及存储介质
CN113033392A (zh) * 2021-03-24 2021-06-25 中国工商银行股份有限公司 基于数据机房场景下的人员距离确定方法及装置
CN113591713A (zh) * 2021-07-30 2021-11-02 深圳市商汤科技有限公司 图像处理方法及装置、电子设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN113591713A (zh) 2021-11-02

Similar Documents

Publication Publication Date Title
JP5500303B1 (ja) 監視システム、監視方法、監視プログラム、ならびに該プログラムを記録した記録媒体
JP6885682B2 (ja) 監視システム、管理装置、及び監視方法
US20130329059A1 (en) Person detection system
JP5568153B1 (ja) 乗客探知システム
CN109887234B (zh) 一种防儿童走失方法、装置、电子设备及存储介质
CN112767586A (zh) 通行检测方法及装置、电子设备及计算机可读存储介质
CN110199316A (zh) 相机和相机的图像处理方法
CN112767585A (zh) 通行检测方法及装置、电子设备及计算机可读存储介质
WO2023005662A1 (zh) 图像处理方法及装置、电子设备、程序产品及计算机可读存储介质
CN108090982A (zh) 一种签到方法、系统及终端设备
US20180197000A1 (en) Image processing device and image processing system
JP6499750B2 (ja) 顔照合システムおよび顔照合方法
US12094250B2 (en) Image processing apparatus, control method, and non-transitory storage medium
WO2023273151A1 (zh) 巡更监测方法及装置、电子设备及计算机可读存储介质
CN114882576B (zh) 人脸识别方法、电子设备、计算机可读介质和程序产品
WO2023273066A1 (zh) 人脸考勤方法及装置、电子设备、存储介质和计算机程序产品
US11676439B2 (en) Face authentication system and face authentication method
CN115810228A (zh) 人脸识别门禁管理方法、装置、电子设备和存储介质
CN112950438A (zh) 数据处理方法、装置、计算机设备及存储介质
CN112784627A (zh) 一种身份识别的方法、装置、电子设备及介质
CN110705447A (zh) 手部图像的检测方法、装置及电子设备
US11810168B2 (en) Auditing mobile transactions based on symbol cues and transaction data
CN109345748B (zh) 用户设备关联方法、装置、服务端、检测设备及介质
CN113420677B (zh) 确定合理图像的方法、装置、电子设备及存储介质
WO2022068024A1 (zh) 图像检索方法及装置、电子设备及存储介质

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE