Target detection method, system and related equipment based on control platform

By using cameras on the deployment platform for video data preprocessing and multi-camera identification, the problem of inability to actively report suspicious targets and real-time area deployment in the prior art is solved, and more efficient monitoring and flexible deployment are achieved.

CN114640764BActive Publication Date: 2024-11-05SHENZHEN ANRUAN HUISHI TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210196297.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-01
Publication Date
2024-11-05
Estimated Expiration
2042-03-01

AI Technical Summary

Technical Problem

The existing control platform cannot actively report suspicious targets in real time, and cannot achieve real-time regional control, resulting in inefficient monitoring.

Method used

A target detection method based on the layout control platform is designed, using a camera to obtain target information through the communication unit, perform video data preprocessing and comparison, and alarm information is issued if matched, and real-time performance is improved through identification and tracking of multiple cameras.

Benefits of technology

It improves the flexibility and real-time nature of regional layout control, realizes active real-time detection and tracking of suspicious targets, and improves monitoring efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114640764B_ABST
    Figure CN114640764B_ABST
Patent Text Reader

Abstract

The present invention is applicable to the application field of artificial intelligence technology, and provides a target detection method, system and related equipment based on a control platform, wherein the control platform includes a control server and at least two cameras, and the target detection method includes: the camera obtains target information through a communication unit, wherein the target information is sent by the control server; obtains real-time video data through a media unit; converts and encodes through an encoding unit; pre-processes the video data through an algorithm processing unit to obtain information to be detected; compares the target information with the information to be detected through a business unit, wherein if the information to be detected obtains the same target image attribute as the target information through comparison, the camera sends the alarm information corresponding to the target image attribute through the communication unit. The present invention improves the flexibility of regional control, and further improves the real-time performance of control through the recognition and tracking of multiple cameras.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology application, and in particular relates to a target detection method, system and related equipment based on a control platform. Background Art

[0002] The main functions of traditional cameras and intelligent AI (Artificial Intelligence) cameras are still recording and capturing targets and then transmitting them to the background server platform. On the server platform, it is possible to search for targets and even the trajectory of the target. This is a technology that is currently available in the application market, but this technology belongs to a large-scale hardware and software system, involving a wide range of equipment, personnel and application technologies, and the cost is also very high. In addition, the current server platform cannot actively discover suspicious persons, and technicians manually search for targets on the platform. The function of searching for suspicious targets can easily assist managers in monitoring the monitoring area, but the current platform system including cameras and servers still has its shortcomings. First, it cannot actively discover suspicious targets, and technicians have to wait for the main search for suspicious targets. When the target is found, it is often a large difference from the time when the target appears. This brings certain difficulties to tracking after obtaining the target; second, relying solely on the platform system cannot achieve real-time regional control. This is because the monitoring equipment deployed between regions does not have the function of being interrelated, but only has the function of sending data to the server, and the server itself can perform global control, which makes the existing platform system inefficient. Summary of the invention

[0003] The embodiments of the present invention provide a target detection method, system and related equipment based on a control platform, aiming to solve the problem that the current control method cannot actively report suspicious targets in real time and cannot achieve real-time regional control.

[0004] In a first aspect, an embodiment of the present invention provides a target detection method based on a control platform, wherein the control platform includes a control server and at least two cameras, wherein the target detection method is applied to each of the cameras, wherein each of the cameras includes a media unit, an encoding unit, an algorithm processing unit, a business unit, and a communication unit, and wherein the target detection method includes the following steps:

[0005] The camera acquires target information through the communication unit, wherein the target information is sent by the deployment control server;

[0006] The camera obtains the video data shot in real time through the media unit;

[0007] The camera converts and encodes the video data through the encoding unit to obtain a static image that can be transmitted through the communication unit;

[0008] The camera pre-processes the video data through the algorithm processing unit to obtain information to be detected;

[0009] The camera compares the target information with the information to be detected through the business unit, wherein if the information to be detected obtains the same target image attribute as the target information through comparison, the camera sends out alarm information corresponding to the target image attribute through the communication unit.

[0010] Furthermore, if the information to be detected obtains the same target image attribute as the target information through comparison, the step of the camera sending the alarm information corresponding to the target image attribute through the communication unit includes the following sub-steps:

[0011] Define that one of the cameras that detects and obtains the target image attribute is a first camera, and the other cameras except the first camera are second cameras, the first camera initiates a target tracking request for the target image attribute to the second camera, and obtains at least two sets of target tracking images through the second camera;

[0012] The first camera selects the best image from all the target tracking images according to a preset best selection rule;

[0013] The first camera encodes the best image using the encoding unit and obtains current time position information;

[0014] The first camera uses the best image and the current time position information as the alarm information, and sends it through the communication unit to release storage space.

[0015] Furthermore, after the step of sending the alarm information by the communication unit using the best image and the current time position information by the first camera, the step further includes:

[0016] The first camera deletes the video data shot in real time by itself and the detected target image attributes to release storage space.

[0017] Furthermore, in the step of the camera comparing the target information with the information to be detected through the business unit, if the information to be detected does not obtain the same target image attribute as the target information through comparison, the target detection method further includes the following steps:

[0018] The camera deletes the video data shot by itself in real time.

[0019] Furthermore, the camera pre-processes the video data through the algorithm processing unit to obtain the information to be detected, including the following sub-steps:

[0020] The algorithm processing unit performs frame decomposition processing on the video data to obtain a frame decomposition image;

[0021] The algorithm processing unit uses a preset target detection algorithm to perform target detection on the deframed image, and the target detection objects include faces, human figures, and vehicles; wherein:

[0022] If the deframed image contains at least one of a face, a human figure, and a vehicle, outputting the deframed image as the information to be detected;

[0023] If the deframed image does not contain at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle, the algorithm processing unit deletes the deframed image and does not perform subsequent steps.

[0024] Furthermore, the step of the first camera initiating a target tracking request for the target image to the second camera, and obtaining at least two sets of target tracking images through the second camera includes the following sub-steps:

[0025] The first camera initiates target tracking of the target image attribute to the second camera, so that the second camera detects the respective deframed images;

[0026] The first camera acquires the deframed images with the same target information attribute from the second camera, obtains at least two groups of deframed images containing the target image, and uses them as the target tracking images.

[0027] In a second aspect, an embodiment of the present invention further provides a camera, including a media module, an encoding module, an algorithm processing module, a service module, and a communication module, wherein:

[0028] The communication module is used to obtain target information, wherein the target information is sent by the deployment control server;

[0029] The media module is used to obtain video data captured in real time;

[0030] The encoding module is used to convert and encode the video data to obtain a static image that can be transmitted through the communication unit;

[0031] The algorithm processing module is used to pre-process the video data to obtain the information to be detected;

[0032] The business module is used to compare the target information with the information to be detected;

[0033] The communication module is also used to send out alarm information corresponding to the target image.

[0034] In the third aspect, an embodiment of the present invention also provides a target detection system based on a control platform, including a control server and at least two cameras as described in the above embodiments. When the target detection system is running, it implements the steps of the target detection method based on a control platform as described in any one of the above embodiments. The control server is also used to receive the alarm information issued by the camera.

[0035] In a fourth aspect, an embodiment of the present invention further provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the target detection method based on the control platform as described in any one of the above embodiments are implemented.

[0036] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the target detection method based on the control platform as described in any one of the above embodiments are implemented.

[0037] The beneficial effects achieved by the present invention are due to the adoption of a control method based mainly on edge devices such as cameras, and the issuance of target information through a user-oriented control server platform according to actual needs, thereby improving the flexibility of regional control and further improving the real-time performance of control through the recognition and tracking of multiple cameras. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of the steps of the target detection method based on the control platform provided by an embodiment of the present invention;

[0039] Figure 2 It is a sub-flow chart of step S103 in the target detection method based on the control platform provided in an embodiment of the present invention;

[0040] Figure 3 It is a sub-flow chart of step S104 in the target detection method based on the control platform provided in an embodiment of the present invention;

[0041] Figure 4 is a schematic diagram of the structure of a target detection system 210 provided in an embodiment of the present invention;

[0042] Figure 5 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0044] Please refer to Figure 1 , Figure 1 The present invention is a flowchart of a target detection method based on a control platform provided by an embodiment of the present invention. The control platform described in the embodiment of the present invention includes a control server and at least two cameras. The target detection method is applied to each of the cameras. The cameras include an encoding unit, an algorithm processing unit, a business unit, and a communication unit. The target detection method specifically includes the following steps:

[0045] S101. The camera obtains target information through the communication unit, wherein the target information is sent by the control server.

[0046] Specifically, the control server is a user-oriented system platform for integrating control information and controlling the camera. The communication unit of the camera is used to communicate with the control server and other cameras. In an embodiment of the present invention, the user actively inputs data through the control server to send the target information. The target information is used to determine a detected object, which may be a human figure, a face, a vehicle, etc. The camera obtains the target information sent by the control server through the communication unit and determines the task of detecting the target information.

[0047] S102: The camera obtains video data shot in real time through the media unit.

[0048] Specifically, the media unit has a function of acquiring image data. Generally, the camera collects video data within its viewing angle through a camera or other device. For equipment used for monitoring, detection, etc., the video data is obtained by real-time shooting.

[0049] S103: The camera converts and encodes the video data through the encoding unit to obtain a static image that can be transmitted through the communication unit.

[0050] Specifically, in an embodiment of the present invention, the encoding unit is used to encode and convert the video data, for example, to encode the image information processed in YUV format into a jpeg picture. When the communication unit transmits data with the control server, the jpeg format picture obtained by the encoding unit will be used as the transmission data.

[0051] S104: The camera pre-processes the video data through the algorithm processing unit to obtain information to be detected.

[0052] Please refer to Figure 2 , Figure 2 It is a sub-flow chart of step S104 in the target detection method based on the control platform provided in an embodiment of the present invention, which specifically includes the following sub-steps:

[0053] S1041. The algorithm processing unit performs frame de-framing processing on the video data to obtain a frame de-framing image.

[0054] In an embodiment of the present invention, the video data is a plurality of frames of image data captured by the camera within a period of time. In order to facilitate subsequent image processing and recognition, the algorithm processing unit first performs frame decomposition processing on the video data to obtain the frame decomposition images. Exemplarily, the duration of the video data is 30 seconds, and the frame decomposition processing is performed according to the rule of performing frame decomposition once every second. Therefore, the algorithm processing unit obtains a set of 30 frame decomposition images based on the video data, and regards the set of 30 frame decomposition images as an object for recognition processing by the algorithm processing unit.

[0055] S1042: The algorithm processing unit uses a preset target detection algorithm to perform target detection on the deframed image, and the objects of target detection include faces, human figures, and vehicles.

[0056] Specifically, in an embodiment of the present invention, the algorithm processing unit can run a trained target detection algorithm with target detection function on the computing resources of the camera without the need to link with the computing resources of other platforms. The target detection algorithm can detect and mark all faces, human figures, vehicles and other objects in the image. For the collection object containing multiple deframed images in the above step S1031, the algorithm processing unit processes them in the order of the generation time of the deframed images.

[0057] Among them, the target detection result of each of the deframed images according to the target detection algorithm is further divided into:

[0058] S1043a: If the deframed image contains at least one of a face, a human figure, and a vehicle, output the deframed image as the information to be detected.

[0059] If the target detection algorithm detects at least one object including a face, a human figure, and a vehicle in the deframed image, the deframed image is regarded as a valid image in which the target information may exist. The embodiment of the present invention does not specifically limit the target information to only one of the information including a face, a human figure, a vehicle, etc. In actual use, the object of the target information may be one or more, and its type is not limited to one type. Therefore, when the target detection algorithm detects at least one object, it can be considered that the deframed image may have a valid image. At this time, the algorithm processing unit outputs it as the information to be detected.

[0060] S1043b: If the deframed image does not contain at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle, the algorithm processing unit deletes the deframed image and does not perform subsequent steps.

[0061] If the target detection algorithm does not detect at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle in the deframed image, the current deframed image is deemed to contain no valid information. Here, the algorithm processing unit deletes the deframed image, terminates the current recognition task, and performs recognition of the next frame of the deframed image. When the deframed image obtained from the video data is recognized, the process returns to step S102 to continue acquiring the video data through the encoding unit. It should be noted that the situation in which at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle is not detected in the embodiment of the present invention means that the deframed image does not contain any content that can be regarded as a detection object. According to the accuracy and rules of the target detection algorithm, a target occlusion rate that is too high and a target that is in a back-facing state can be considered to contain no valid content. This can be set according to actual needs.

[0062] S105, the camera compares the target information with the information to be detected through the business unit, wherein if the information to be detected obtains the same target image attribute as the target information through the comparison, the camera sends out alarm information corresponding to the target image attribute through the communication unit.

[0063] In an embodiment of the present invention, the business unit is able to run a trained target comparison algorithm with a target comparison function on the computing resources of the camera. Specifically, in this step, the business unit compares the face, human shape, vehicle and other information in the information to be detected with the target information sent by the control server, and obtains a comparison result based on the degree of similarity, that is, whether the face, human shape and vehicle in the information to be detected matches the target information. If the information to be detected obtains the same target image attributes as the target information through comparison, the camera sends the alarm information corresponding to the target image to the control server through the communication unit.

[0064] For details, please refer to Figure 3 , Figure 3 It is a sub-flow chart of step S105 in the target detection method based on the control platform provided by an embodiment of the present invention. The step in step S105 where the camera sends the target image attributes to the control server through the communication unit includes the following sub-steps:

[0065] S1051. Define a camera that detects and obtains the target image attribute as a first camera, and cameras other than the first camera as second cameras. The first camera initiates a target tracking request for the target image attribute to the second camera, and obtains at least two groups of target tracking images through the second camera.

[0066] The above step S1051 specifically includes the following sub-steps:

[0067] S10511. The first camera initiates a target tracking request for the target image attribute to the second camera, so that the second camera detects the respective deframed images.

[0068] In an embodiment of the present invention, the control platform includes at least two cameras. For the sake of convenience, the camera that detects and obtains the information to be detected is defined as the first camera, and the rest are defined as the second cameras according to the arrangement order, that is, the number of the first camera is one, and the number of the second cameras can be multiple. The first camera first initiates target tracking to other cameras, that is, the first camera takes the time when it first detects the target image attribute corresponding to the target information as the tracking starting point, and initiates tracking of the target image attribute to other cameras, so that the other cameras detect their respective deframed images.

[0069] S10512: The first camera obtains the deframed images having the same target information from the second camera, obtains at least two groups of deframed images including the target image, and uses them as the target tracking images.

[0070] In an embodiment of the present invention, taking the case where all cameras except the first camera have captured and identified the target image attributes as an example, each of the cameras will obtain at least one set of the deframed images containing the target image attributes, and the first camera receives these deframed images, and adds the deframed images captured by itself to obtain at least two sets of the deframed images containing the target image, which are used as the target tracking images.

[0071] S1052: The first camera selects the best image from all the target tracking images according to a preset best selection rule.

[0072] The first camera selects the best image from all the target tracking images according to a preset best selection rule. The preset best selection rule can be adjusted according to actual needs. Exemplarily, the preset best selection rule is to select the image with the highest resolution and the lowest occlusion rate from the target tracking images.

[0073] S1053: The first camera uses the encoding unit to encode the best image and obtain current time position information.

[0074] S1054: The first camera sends out an alarm message through the communication unit using the best image and the current time position information.

[0075] Specifically, the alarm information includes the best image and the current time position information corresponding to the best image. Before the camera sends out the alarm, it also includes a process of using the encoding unit to encode the best image accordingly. After the control server receives the alarm information sent by any of the cameras, it will regard the current target information as being detected by the control platform, and display the alarm information to the user through a user interface or notification.

[0076] Furthermore, in the above step S105, if the information to be detected does not obtain a target image identical to the target information through comparison, the target detection method further includes the following steps:

[0077] The first camera deletes the video data shot in real time by itself to release storage space.

[0078] Furthermore, after the above step S1054, in order to facilitate the control platform to perform the next target detection, the following steps are also included:

[0079] The camera deletes the video data shot in real time by itself and the detected target image attributes to release storage space.

[0080] The beneficial effects achieved by the present invention are due to the adoption of a control method based mainly on edge devices such as cameras, and the issuance of target information through a user-oriented control server platform according to actual needs, thereby improving the flexibility of regional control and further improving the real-time performance of control through the recognition and tracking of multiple cameras.

[0081] The embodiment of the present invention further provides a camera 200, including a media module 201, an encoding module 202, an algorithm processing module 203, a service module 204, and a communication module 205, wherein:

[0082] The communication module 205 is used to obtain target information, wherein the target information is sent by the control server;

[0083] The media module 201 is used to obtain the video data shot in real time;

[0084] The encoding module 202 is used to convert and encode the video data to obtain a static image that can be transmitted through the communication unit;

[0085] The algorithm processing module 203 is used to pre-process the video data to obtain information to be detected;

[0086] The business module 204 is used to compare the target information with the information to be detected;

[0087] The communication module 205 is also used to send out the alarm information corresponding to the target image.

[0088] The embodiment of the present invention also provides a target detection system 210 based on a control platform, please refer to Figure 4 , Figure 4 It is a structural diagram of a target detection system 210 provided in an embodiment of the present invention. The target detection system 210 includes a control server 211 and at least two cameras 200 as described in the above embodiments. The target detection system 210 based on the control platform can implement the steps in the target detection method based on the control platform in the above embodiments, and can achieve the same technical effect. Please refer to the description in the above embodiments and will not be repeated here.

[0089] The embodiment of the present invention also provides a computer device, please refer to Figure 5 , Figure 5300 is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. The computer device 300 includes: a memory 302, a processor 301, and a computer program stored in the memory 302 and executable on the processor 301.

[0090] The processor 301 calls the computer program stored in the memory 302 to execute the steps of the target detection method provided in the embodiment of the present invention. Figure 1 , including:

[0091] S101. The camera obtains target information through the communication unit, wherein the target information is sent by the control server.

[0092] S102: The camera obtains video data shot in real time through the media unit.

[0093] S103: The camera converts and encodes the video data through the encoding unit to obtain a static image that can be transmitted through the communication unit.

[0094] S104: The camera pre-processes the video data through the algorithm processing unit to obtain information to be detected.

[0095] S105, the camera compares the target information with the information to be detected through the business unit, wherein if the information to be detected obtains a target image identical to the target information through the comparison, the camera sends out alarm information corresponding to the target image through the communication unit.

[0096] Furthermore, if the information to be detected obtains the same target image attribute as the target information through comparison, the step of the camera sending the alarm information corresponding to the target image attribute through the communication unit includes the following sub-steps:

[0097] Define that one of the cameras that detects and obtains the target image attribute is a first camera, and the other cameras except the first camera are second cameras, the first camera initiates a target tracking request for the target image attribute to the second camera, and obtains at least two sets of target tracking images through the second camera;

[0098] The first camera selects the best image from all the target tracking images according to a preset best selection rule;

[0099] The first camera encodes the best image using the encoding unit and obtains current time position information;

[0100] The first camera uses the best image and the current time position information as the alarm information, and sends it through the communication unit to release storage space.

[0101] Furthermore, after the step of sending the alarm information by the communication unit using the best image and the current time position information by the first camera, the step further includes:

[0102] The first camera deletes the video data shot in real time by itself and the detected target image attributes to release storage space.

[0103] Furthermore, in the step of the camera comparing the target information with the information to be detected through the business unit, if the information to be detected does not obtain the same target image attribute as the target information through comparison, the target detection method further includes the following steps:

[0104] The camera deletes the video data shot by itself in real time.

[0105] Furthermore, the camera pre-processes the video data through the algorithm processing unit to obtain the information to be detected, including the following sub-steps:

[0106] The algorithm processing unit performs frame decomposition processing on the video data to obtain a frame decomposition image;

[0107] The algorithm processing unit uses a preset target detection algorithm to perform target detection on the deframed image, and the target detection objects include faces, human figures, and vehicles; wherein:

[0108] If the deframed image contains at least one of a face, a human figure, and a vehicle, outputting the deframed image as the information to be detected;

[0109] If the deframed image does not contain at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle, the algorithm processing unit deletes the deframed image and does not perform subsequent steps.

[0110] Furthermore, the step of the first camera initiating a target tracking request for the target image to the second camera, and obtaining at least two sets of target tracking images through the second camera includes the following sub-steps:

[0111] The first camera initiates target tracking of the target image attribute to the second camera, so that the second camera detects the respective deframed images;

[0112] The first camera acquires the deframed images with the same target information attribute from the second camera, obtains at least two groups of deframed images containing the target image, and uses them as the target tracking images.

[0113] The computer device 300 provided in the embodiment of the present invention can implement the steps in the target detection method based on the control platform in the above embodiment, and can achieve the same technical effect. Please refer to the description in the above embodiment and will not be repeated here.

[0114] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes and steps in the target detection method based on the control platform provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0115] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0116] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0118] The embodiments of the present invention are described above in conjunction with the accompanying drawings. What is disclosed is only the preferred embodiment of the present invention. However, the present invention is not limited to the above-mentioned specific implementation manner. The above-mentioned specific implementation manner is only illustrative rather than restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms and equivalent changes without departing from the scope of protection of the purpose of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A target detection method based on a control platform, wherein the control platform includes a control server and at least two cameras, wherein the target detection method is applied to each of the cameras. It is characterized in that Each of the cameras includes a media unit, an encoding unit, an algorithm processing unit, a service unit, and a communication unit. The target detection method includes the following steps: The camera acquires target information through the communication unit, wherein the target information is sent by the deployment control server; The camera obtains the video data shot in real time through the media unit; The camera converts and encodes the video data through the encoding unit to obtain a static image that can be transmitted through the communication unit; The camera pre-processes the video data through the algorithm processing unit to obtain information to be detected; The camera compares the target information with the information to be detected through the business unit, wherein if the information to be detected obtains the same target image attribute as the target information through the comparison, the camera sends out alarm information corresponding to the target image attribute through the communication unit; If the information to be detected obtains the same target image attribute as the target information through comparison, the step of the camera sending the alarm information corresponding to the target image attribute through the communication unit includes the following sub-steps: A camera that detects and obtains the target image attribute is defined as a first camera, and other cameras except the first camera are defined as second cameras. The first camera initiates a target tracking request for the target image attribute to the second camera, and obtains at least two sets of target tracking images through the second camera. The first camera selects the best image from all the target tracking images according to a preset best selection rule; The first camera encodes the best image using the encoding unit and obtains current time position information; The first camera uses the best image and the current time position information as the alarm information and sends it through the communication unit.

2. The target detection method based on the control platform according to claim 1, It is characterized in that After the step of sending the alarm information by the communication unit using the best image and the current time position information by the first camera, the method further includes: The first camera deletes the video data shot in real time by itself and the detected target image attributes to release storage space.

3. The target detection method based on the control platform according to claim 1, It is characterized in that In the step of comparing the target information with the information to be detected by the camera through the business unit, if the information to be detected does not obtain the same target image attribute as the target information through comparison, the target detection method further includes the following steps: The camera deletes the video data shot in real time by itself to release storage space.

4. The target detection method based on the control platform according to claim 1, It is characterized in that The camera pre-processes the video data through the algorithm processing unit to obtain the information to be detected, including the following sub-steps: The algorithm processing unit performs frame decomposition processing on the video data to obtain a frame decomposition image; The algorithm processing unit uses a preset target detection algorithm to perform target detection on the deframed image, and the target detection objects include faces, human figures, and vehicles; wherein: If the deframed image contains at least one of a face, a human figure, and a vehicle, outputting the deframed image as the information to be detected; If the deframed image does not contain at least one of the objects selected from the group consisting of a human face, a human figure, and a vehicle, the algorithm processing unit deletes the deframed image and does not perform subsequent steps.

5. The target detection method based on the control platform as claimed in claim 4, It is characterized in that The step of initiating a target tracking request for the target image attribute to the second camera and obtaining at least two sets of target tracking images through the second camera includes the following sub-steps: The first camera initiates a target tracking request for the target image attribute to the second camera, so that the second camera detects the respective deframed images; The first camera acquires the deframed images with the same target information from the second camera, obtains at least two groups of deframed images containing the target image, and uses them as the target tracking images.

6. A target detection system based on a control platform, It is characterized in that It includes a control server and at least two cameras, wherein the cameras include a media module, an encoding module, an algorithm processing module, a business module, and a communication module, wherein: The communication module is used to obtain target information, wherein the target information is sent by the deployment control server; The media module is used to obtain the video data shot in real time; The encoding module is used to convert and encode the video data to obtain a static image that can be transmitted through the communication unit; The algorithm processing module is used to pre-process the video data to obtain the information to be detected; The business module is used to compare the target information with the information to be detected; The communication module is also used to send out the alarm information corresponding to the target image attribute; When the target detection system is running, the steps of the target detection method based on the control platform as described in any one of claims 1 to 5 are implemented, and the control server is also used to receive the alarm information issued by the camera.

7. A computer device, It is characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the target detection method based on the control platform as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the target detection method based on the control platform as described in any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Face recognition-based monitor method and system and storage medium

    CN108875466A

  • Target tracking method, device, system, equipment and storage medium

    CN111754551A

  • Three-dimensional modeling method and device

    WO2020057355A1