Object detection method, electronic device, storage medium and computer program product

Abstract

The embodiment of the present invention provides an object detection method, an electronic device, a storage medium and a computer program product to improve the real-time performance of object detection. In the embodiment of the present invention, the business server does not need to manually acquire and enter the features of the object to be detected, nor does it need to perform feature comparison. It only needs to use the simulated feature library created by the object detection server to timely create and execute the task to be executed, and send the features acquired by the task execution device on the business server side to the object detection server when executing the task to be executed. The object detection server receives the features of the object to be detected sent by the feature management server and performs feature comparison. This avoids the manual acquisition and entry of the features of the object to be detected, and can quickly create the task to be executed after the feature management server sends the features of the object to be detected, thereby quickly completing the object detection and improving the real-time performance of the object detection.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of information processing technology, and in particular, to an object detection method, an electronic device, a storage medium, and a computer program product. Background Art

[0002] In the current object monitoring system, the features of the object to be detected are uniformly managed by the feature management server, and the business server cannot directly obtain the features of the object to be detected. Therefore, when the business server needs to detect the object to be detected, the staff needs to obtain the features of the object to be detected from the feature management server and manually enter them into the business server, thereby creating a task to be executed. Subsequently, when the business server detects the object to be detected, the features obtained by the task execution device on the business server side when executing the task to be executed are compared with the features manually entered by the staff, thereby completing the object detection.

[0003] It can be seen that in the current object detection system, since the features of the object to be detected need to be acquired and input manually, object detection cannot be performed in real time.

[0004] Therefore, a real-time object detection method is urgently needed. Summary of the invention

[0005] The embodiments of the present invention provide an object detection method, an electronic device, a storage medium and a computer program product to improve the real-time performance of object detection.

[0006] A first aspect of an embodiment of the present invention provides an object detection method, which is applied to a service server. The method includes:

[0007] According to the position range of the object to be detected, the image acquisition device located in the position range is configured as the task execution device;

[0008] Creating a task to be executed according to the task execution device and the simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server;

[0009] The object features obtained by the task execution device executing the task to be executed are sent to the object detection server, and the object features and the features of the object to be detected are used by the object detection server to detect whether the object to be detected appears within the position range.

[0010] Optionally, the method further comprises:

[0011] determining whether a notification message for a pre-created simulation feature library sent by the object detection server is received;

[0012] upon receiving the notification message, sending a location range request to the feature management server;

[0013] Receive the location range of the object to be detected sent by the feature management server in response to the location range request.

[0014] Optionally, the method further comprises:

[0015] Obtaining images collected by the task execution device when executing the task to be executed;

[0016] Obtaining object features extracted from the image;

[0017] Adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information;

[0018] The image processing information is added to a message queue, and the message queue is used by the object detection server to pull the image processing information including the feature library identifier of the simulation feature library, and extract the object feature from the image processing information.

[0019] Optionally, adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information includes:

[0020] Adding a feature library identifier of the simulation feature library, a task identifier of the task to be executed, and a device identifier of the task execution device to the object feature to obtain image processing information;

[0021] The method further comprises:

[0022] Receiving and saving the alarm information sent by the object detection server and carrying the task identifier and the device identifier, wherein the alarm information is generated when the object detection server detects that the object to be detected appears within the location range, indicating that the object to be detected appears within the detection range of the task execution device corresponding to the device identifier;

[0023] Obtaining the alarm push switch configuration information of the simulation feature library;

[0024] When the alarm push configuration switch is configured to be turned on, the alarm information is pushed to the alarm terminal corresponding to the business server.

[0025] Optionally, the method further comprises:

[0026] Obtaining a new position range of the object to be detected;

[0027] According to the new position range, configuring the image acquisition device located in the new position range as a new task execution device;

[0028] Acquire an identity database of the object to be detected pre-created by the object detection server, wherein the identity database includes: features of the object to be detected sent by the feature management server, and object features corresponding to the alarm information;

[0029] Creating a new task to be executed according to the new task execution device and the identity library;

[0030] The object features obtained by the new task execution device executing the new task to be executed are compared with the features in the identity database to determine whether the object to be detected appears within the new location range.

[0031] A second aspect of an embodiment of the present invention provides an object detection method, which is applied to an object detection server. The method includes:

[0032] Upon receiving the features of the object to be detected sent by the feature management server, creating a simulation feature library;

[0033] Acquire object features from a business server, wherein the object features are obtained after the business server creates a task to be executed based on the simulation feature library, and the object features are extracted from an image captured by a task execution device that executes the task to be executed;

[0034] Comparing the features of the object to be detected with the features of the object, and generating an alarm message if the comparison is successful;

[0035] The alarm information is sent to the service server.

[0036] Optionally, the method further comprises:

[0037] Upon receiving the features of the object to be detected sent by the feature management server, creating an identity library of the object to be detected;

[0038] Saving the characteristics of the object to be detected in the identity database;

[0039] The object features corresponding to the alarm information are added to the identity database.

[0040] Optionally, after generating the warning information, the method further includes:

[0041] Querying whether the archive library stores the archive of the object to be detected;

[0042] When the archive of the object to be detected is stored in the archive library, the alarm information is added to the archive of the object to be detected, and a label is added to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server;

[0043] When the archive of the object to be detected is not stored in the archive library, a file is created for the object to be detected, and the alarm information is added to the file of the object to be detected, and a label is added to the file of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

[0044] Optionally, obtaining object features from the business server includes:

[0045] A connection message queue is provided, wherein the message queue stores image processing information obtained by the business server processing an image collected by a task execution device executing the task to be executed, and information of other tasks, wherein the image processing information at least includes: object features and a feature library identifier of the simulation feature library;

[0046] The image processing information including the feature library identifier of the simulation feature library is pulled from the message queue, and the object feature is extracted from the image processing information.

[0047] Optionally, the image processing information further includes: a task identifier of the task to be executed and a device identifier of the task execution device; generating alarm information includes:

[0048] An alarm message carrying the task identifier and the device identifier is generated, wherein the alarm message indicates that the object to be detected appears within a detection range of a task execution device corresponding to the device identifier.

[0049] A third aspect of an embodiment of the present invention provides an object detection device, which is applied to a service server, and the device includes:

[0050] A first configuration module, configured to configure an image acquisition device located in the position range as a task execution device according to the position range of the object to be detected;

[0051] A first creation module, used to create a task to be executed according to the task execution device and a simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server;

[0052] The object feature sending module is used to send the object features obtained by the task execution device executing the task to be executed to the object detection server, and the object features and the features of the object to be detected are used for the object detection server to detect whether the object to be detected appears within the position range.

[0053] Optionally, the device further comprises:

[0054] A notification message determination module, used to determine whether a notification message for a pre-created simulation feature library sent by the object detection server is received;

[0055] A location range request sending module, configured to send a location range request to the feature management server upon receiving the notification message;

[0056] The first location range receiving module is used to receive the location range of the object to be detected sent by the feature management server in response to the location range request.

[0057] Optionally, the device further comprises:

[0058] An image acquisition module, used to obtain images collected by the task execution device when executing the task to be executed;

[0059] An object feature acquisition module, used to obtain object features extracted from the image;

[0060] An image processing information determination module, used for adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information;

[0061] The information adding module is used to add the image processing information to a message queue, and the message queue is used by the object detection server to pull the image processing information including the feature library identifier of the simulation feature library, and extract object features from the image processing information.

[0062] Optionally, the image processing information determination module is specifically used to:

[0063] Adding a feature library identifier of the simulation feature library, a task identifier of the task to be executed, and a device identifier of the task execution device to the object feature to obtain image processing information;

[0064] The device also includes:

[0065] an alarm information receiving module, used to receive and save the alarm information sent by the object detection server and carrying the task identifier and the device identifier, wherein the alarm information is generated when the object detection server detects that the object to be detected appears within the position range, indicating that the object to be detected appears within the detection range of the task execution device corresponding to the device identifier;

[0066] A configuration information acquisition module, used to acquire the alarm push switch configuration information of the simulation feature library;

[0067] The push module is used to push the alarm information to the alarm terminal corresponding to the business server when the alarm push configuration switch is configured to be turned on.

[0068] Optionally, the device further comprises:

[0069] A second position range receiving module, used to obtain a new position range of the object to be detected;

[0070] A second configuration module is used to configure the image acquisition device located in the new position range as a new task execution device according to the new position range;

[0071] An identity library acquisition module, used to acquire an identity library of the object to be detected pre-created by the object detection server, wherein the identity library includes: features of the object to be detected sent by the feature management server, and object features corresponding to the alarm information;

[0072] A second creation module, used to create a new task to be executed according to the new task execution device and the identity library;

[0073] The comparison module is used to compare the object features obtained by the new task execution device executing the new task to be executed with the features in the identity database to determine whether the object to be detected appears within the new location range.

[0074] According to a fourth aspect of an embodiment of the present invention, an object detection device is applied to an object detection server, and the device includes:

[0075] A simulation feature library creation module is used to create a simulation feature library when receiving the features of the object to be detected sent by the feature management server;

[0076] An object feature acquisition module, used to acquire object features from a business server, wherein the object features are obtained after the business server creates a task to be executed based on the simulation feature library, and the object features are extracted from an image collected by a task execution device that executes the task to be executed;

[0077] An alarm information generating module, used for comparing the characteristics of the object to be detected with the characteristics of the object, and generating alarm information when the comparison is successful;

[0078] The alarm information sending module is used to send the alarm information to the service server.

[0079] Optionally, the device further comprises:

[0080] An identity library creation module, configured to create an identity library of an object to be detected upon receiving the features of the object to be detected sent by the feature management server;

[0081] A saving module, used for saving the features of the object to be detected into the identity database;

[0082] The identity database information adding module is used to add the object features corresponding to the alarm information to the identity database.

[0083] Optionally, the device further comprises:

[0084] A query module, used to query whether the archive store stores the archive of the object to be detected;

[0085] A file information adding module, used for adding the alarm information to the file of the object to be detected when the file of the object to be detected is stored in the file library, and adding a label to the file of the object to be detected according to the attribute information of the object to be detected sent by the feature management server;

[0086] The archive creation module is used to create an archive for the object to be detected when the archive does not store the archive of the object to be detected, add the alarm information to the archive of the object to be detected, and add a label to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

[0087] Optionally, the object feature acquisition module includes:

[0088] A message queue connection submodule, used to connect to a message queue, wherein the message queue stores image processing information obtained by the business server processing an image collected by a task execution device that executes the task to be executed, as well as information of other tasks, wherein the image processing information at least includes: object features and a feature library identifier of the simulation feature library;

[0089] The pulling submodule is used to pull the image processing information including the feature library identifier of the simulation feature library from the message queue, and extract the object feature from the image processing information.

[0090] Optionally, the image processing information further includes: a task identifier of the task to be executed and a device identifier of the task execution device; and the alarm information generating module is specifically used to:

[0091] An alarm message carrying the task identifier and the device identifier is generated, wherein the alarm message indicates that the object to be detected appears within a detection range of a task execution device corresponding to the device identifier.

[0092] A fifth aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the object detection method as described in the first aspect or the second aspect of the present invention.

[0093] A sixth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the object detection method as described in the first aspect or the second aspect of the present invention is implemented.

[0094] A seventh aspect of an embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the object detection method described in the first aspect or the second aspect of the present invention.

[0095] The object detection method provided by the embodiment of the present invention receives the features of the object to be detected sent by the feature management server through the object detection server, and creates a simulation feature library, so that the business server can use the simulation feature library and the location range of the object to be detected to timely create and execute the task to be executed. Subsequently, the object features obtained by executing the task are sent to the object detection server that has obtained the features of the object to be detected to complete feature comparison and realize object detection.

[0096] In the embodiment of the present invention, the business server does not need to manually acquire and enter the features of the object to be detected, nor does it need to perform feature comparison. It only needs to use the simulated feature library created by the object detection server to timely create and execute the task to be executed, and send the features acquired by the task execution device on the business server side when executing the task to be executed to the object detection server. The object detection server receives the features of the object to be detected sent by the feature management server and performs feature comparison. This avoids the manual acquisition and entry of the features of the object to be detected, and can quickly create the task to be executed after the feature management server sends the features of the object to be detected, thereby quickly completing object detection and improving the real-time performance of object detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0098] Figure 1 is a schematic diagram of a communication process of an object detection system according to an embodiment of the present invention;

[0099] Figure 2 is a flow chart of an object detection method according to an embodiment of the present invention;

[0100] Figure 3 is a flow chart of another object detection method according to an embodiment of the present invention;

[0101] Figure 4is a flow chart of another object detection method according to an embodiment of the present invention;

[0102] Figure 5 is a flow chart of another object detection method according to an embodiment of the present invention;

[0103] Figure 6 is a flow chart of another object detection method according to an embodiment of the present invention;

[0104] Figure 7 is a structural block diagram of an object detection device according to an embodiment of the present invention;

[0105] Figure 8 It is a structural block diagram of another object detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0106] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0107] Reference Figure 1 , shows the communication process of the object detection system, the object detection system includes: a feature management server, an object detection server, and a business server.

[0108] In the embodiment of the present invention, the feature management server, the object detection server, and the business server are interconnected through a network, and the interaction between them is achieved through API interface calls and message queues.

[0109] In practical applications, when an object needs to be detected, the object detection system needs to perform the following interactive steps:

[0110] 1. The feature management server sends the features of the object to be detected to the object detection server;

[0111] 2. The object detection server creates a simulated feature library;

[0112] 3. The business server creates tasks to be executed based on the model feature library and the location range of the object to be detected;

[0113] 4. The business server obtains the object features corresponding to the task to be executed according to the execution result of the task to be executed, and sends the object features to the object detection server;

[0114] 5. The object detection server compares the object features with the features of the object to be detected, generates corresponding alarm information, and sends it to the business server.

[0115] The object detection method provided by the embodiment of the present invention is explained in detail below. The method is applied to the object detection system. Figure 2, shows a flow chart of an object detection method according to an embodiment of the present invention, which may specifically include the following steps:

[0116] S201, when receiving the features of the object to be detected sent by the feature management server, the object detection server creates a simulation feature library and sends a notification message for the pre-created simulation feature library to the business server.

[0117] In an embodiment of the present invention, after receiving the features, the object detection server creates a simulated feature library, which is actually an empty feature library. Its purpose is to simulate the feature library required by the business system to create tasks to be executed, so that the business server can create tasks to be executed according to the normal process without changing the business logic of the business server to create tasks to be executed.

[0118] In the embodiment of the present invention, after creating the simulation feature library, the object detection server will also send a corresponding notification message to the business server so that the business service can create the corresponding tasks to be executed in a timely manner.

[0119] In the embodiment of the present invention, the object detection server completes the final feature comparison, so the business system does not need to obtain the features of the object to be detected, and even if the simulation feature library is empty, it does not affect the execution of subsequent services. The business server only needs to use the simulation feature library to create the corresponding task to be executed.

[0120] S202: The service server configures the image acquisition device located in the position range as the task execution device according to the position range of the object to be detected.

[0121] In the embodiment of the present invention, the location range of the object to be detected can be directly sent from the feature management server to the business object server, or can be manually obtained and entered by the staff, or can be received from other devices. Even in the case where the staff manually enters the location range of the object to be detected, since the embodiment of the present invention does not need to manually enter the features of the object to be detected, the overall efficiency of the object detection system can still be improved.

[0122] In the embodiment of the present invention, the location range of the object to be detected is determined according to the location or department where the object to be detected may appear, and accordingly, the image acquisition device corresponding to the location or department can be configured as the task execution device.

[0123] S203: The business server creates a task to be executed according to the task execution device and the simulation feature library.

[0124] In an embodiment of the present invention, the business server can configure all image acquisition devices within the location range of the object to be detected as task execution devices, thereby creating corresponding tasks to be executed based on these task execution devices and the simulation feature library to obtain images captured by the corresponding task execution devices and obtain object features.

[0125] S204: The business server sends the object features obtained by the task execution device executing the task to be executed to the object detection server.

[0126] S205: The object detection server obtains object features from the business server.

[0127] S206: The object detection server compares the features of the object to be detected with the features of the object, and generates warning information if the comparison is successful.

[0128] S207: The object detection server sends the alarm information to the service server.

[0129] In an embodiment of the present invention, the business server sends the object features obtained by executing the task to be executed to the object detection server. The object detection server compares the features of the object to be detected with the object features from the business server, and generates alarm information and sends it to the business server to realize the detection of the object to be detected.

[0130] The object detection method provided by the embodiment of the present invention is explained in detail below from the service server side. The method is applied to the service server. Figure 3 , shows a flow chart of an object detection method according to an embodiment of the present invention, which may specifically include the following steps:

[0131] S301, according to the position range of the object to be detected, configuring an image acquisition device located in the position range as a task execution device.

[0132] S302, creating a task to be executed according to the task execution device and a simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server.

[0133] The steps S301-S302 are similar to the aforementioned steps S202-203 and will not be repeated here.

[0134] S303: sending object features obtained by the task execution device executing the task to be executed to the object detection server, wherein the object features and features of the object to be detected are used by the object detection server to detect whether the object to be detected appears within the location range.

[0135] In the embodiment of the present invention, the business server sends the object features obtained by executing the task to be executed to the object detection server, so that the object detection server compares the features of the object to be detected with the object features from the business server to detect the object to be detected.

[0136] In an optional embodiment, another object detection method is disclosed, such as Figure 4 As shown, the method comprises the following steps:

[0137] S401, according to the position range of the object to be detected, configuring an image acquisition device located in the position range as a task execution device.

[0138] S402, creating a task to be executed according to the task execution device and the simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server.

[0139] The above steps S401-S402 are similar to the above steps S301-S302, and the present invention will not be repeated here.

[0140] S403: Obtain images collected by the task execution device when executing the task to be executed.

[0141] In the embodiment of the present invention, the object to be detected may be a person or an object. Explanation is given by assuming that the object to be detected is a person:

[0142] For example, the task execution device executes the task to be executed, captures images within the detection range, and regards all images containing any person as images to be detected, and then further processes the images to be detected.

[0143] S404: Obtain object features extracted from the image.

[0144] In the embodiment of the present invention, the service server may extract features from the image to obtain object features, or the task execution device may directly extract features after obtaining the image and send the obtained object features to the service server.

[0145] S405, adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information.

[0146] In the embodiment of the present invention, the business server may add a corresponding feature library identifier of a simulation feature library based on which the task to be executed is created to each acquired object feature, so as to obtain image processing information.

[0147] In the embodiment of the present invention, the image processing information obtained by the service server carries the corresponding feature library identifier, so that the object detection system can determine the corresponding features of the object to be detected after acquiring the image processing information.

[0148] S406, adding the image processing information to a message queue, the message queue being used by the object detection server to pull the image processing information including the feature library identifier of the simulation feature library, and extracting object features from the image processing information.

[0149] In the embodiment of the present invention, there are multiple messages in the message queue, and the object detection server can filter out object features related to the object to be detected according to the feature library identifier of the simulation feature library carried by each message to perform object detection.

[0150] In the embodiment of the present invention, kafka can be used to implement the message queue, and other feasible methods can also be used to implement the message queue, such as rabbitMq or rocketMq and other message queues.

[0151] In an optional implementation, the step S405 specifically includes: adding the feature library identifier of the simulation feature library, the task identifier of the task to be executed, and the device identifier of the task execution device to the object feature to obtain image processing information. In this case, the method further includes the following steps:

[0152] S407, receiving and saving the alarm information sent by the object detection server and carrying the task identifier and the device identifier, wherein the alarm information is generated when the object detection server detects that the object to be detected appears within the location range, indicating that the object to be detected appears within the detection range of the task execution device corresponding to the device identifier.

[0153] In the embodiment of the present invention, the image processing information obtained by the service server also includes the task identifier of the task to be executed associated with the object features contained in the image processing information, and the device identifier of the task execution device that captured the image. Therefore, the object detection server can determine whether the object to be detected appears within the detection range of the task execution device based on the task identifier and device identifier carried by the image processing information.

[0154] S408, obtaining the alarm push switch configuration information of the simulation feature library;

[0155] S409: When the alarm push configuration switch is configured to be turned on, the alarm information is pushed to the alarm terminal corresponding to the business server.

[0156] In the embodiment of the present invention, the simulation feature library is configured with an alarm push switch, which is closed by default. The staff can manually change the alarm push switch configuration information to turn on the switch. For example, for some important objects to be detected, the alarm push switch can be turned on so that the alarm information related to the object to be detected can be pushed to the corresponding alarm terminal in real time to play the role of real-time alarm.

[0157] In the embodiment of the present invention, when the service server obtains the alarm information from the object detection server, the alarm information can be saved in a corresponding database for subsequent query and analysis.

[0158] In an embodiment of the present invention, after the business server obtains the alarm information from the object detection server, it is also necessary to query the alarm push switch configuration information of the corresponding simulation feature library. If the alarm push configuration switch is configured to be turned on, the business server needs to push the alarm message to the alarm terminal in real time.

[0159] In an optional implementation manner, the location range of the object to be detected may be sent by the feature management server to the service server. In this case, the method further includes:

[0160] Step S1, determining whether a notification message for a pre-created simulation feature library sent by the object detection server is received.

[0161] Step S2: upon receiving the notification message, sending a location range request to the feature management server.

[0162] Step S3: receiving the location range of the object to be detected sent by the feature management server in response to the location range request.

[0163] In an embodiment of the present invention, after the object detection server completes the creation of the simulation feature library, the business server can obtain the location range of the object to be detected in a timely manner through the notification message sent by the object detection service, thereby quickly creating a corresponding task to be executed to quickly perform real-time detection of the object to be detected.

[0164] In an optional implementation, the notification message and the location range of the object to be detected may also be directly sent by a superior department to a corresponding technician, and the technician completes the setting of the location range of the object to be detected through a business server.

[0165] In an optional implementation, after the object detection server receives the features of the object to be detected, it will also create an identity library for the object to be detected, and in the process of detecting the object to be detected, the object features corresponding to each alarm information generated are added to the identity library. When the object to be detected needs to be monitored next time, the business server can directly use the identity library to create a task to be executed and complete the detection process. In this case, the embodiment of the present invention discloses another object detection method, such as Figure 5 As shown, the method comprises the following steps:

[0166] S501: Acquire a new position range of the object to be detected.

[0167] In the embodiment of the present invention, after the object detection server receives the relevant information of the object to be detected for the first time and executes the corresponding detection task, it can obtain the identity library of the object to be detected. Therefore, when the object to be detected is detected next time, the service server can directly obtain the corresponding task to be executed based on the identity library and the new location range of the object to be detected.

[0168] In the embodiment of the present invention, the new location range of the object to be detected may be directly sent from the feature management server to the business object server, may be manually obtained and entered by a staff member, or may be received from other devices.

[0169] S502: According to the new position range, configure the image acquisition device located in the new position range as a new task execution device.

[0170] S503, obtaining an identity database of the object to be detected pre-created by the object detection server, wherein the identity database includes: features of the object to be detected sent by the feature management server, and object features corresponding to the alarm information.

[0171] S504: Create a new task to be executed according to the new task execution device and the identity library.

[0172] S505: Compare the object features obtained by the new task execution device executing the new task to be executed with the features in the identity database to determine whether the object to be detected appears within the new location range.

[0173] In the embodiment of the present invention, since the identity library has stored the relevant information (features and identity information) of the object to be detected, the business server no longer needs to rely on the simulated feature library created by the object detection server, and can directly complete the creation of the task to be executed and the comparison of the object features based on the identity library, thereby further improving the efficiency of object detection.

[0174] The object detection method provided by the embodiment of the present invention is explained in detail below from the object detection server side. The method is applied to the object detection server. Figure 6 , shows a flow chart of an object detection method according to an embodiment of the present invention, which may specifically include the following steps:

[0175] S601, when receiving the features of the object to be detected sent by the feature management server, create a simulation feature library.

[0176] S602, obtaining object features from a business server, wherein the object features are obtained after the business server creates a task to be executed based on the simulation feature library, and the object features are extracted from an image captured by a task execution device that executes the task to be executed.

[0177] In an optional implementation manner, the step S602 may specifically include the following sub-steps:

[0178] S6021, connect to a message queue, wherein the message queue stores image processing information obtained by the business server from processing images captured by a task execution device that executes the task to be executed, as well as information of other tasks, wherein the image processing information includes at least object features and a feature library identifier of the simulation feature library.

[0179] S6022: Pull out image processing information including the feature library identifier of the simulation feature library from the message queue, and extract object features from the image processing information.

[0180] In the embodiment of the present invention, the business server can create a part of the tasks to be executed according to the simulation feature library created by the object detection server, or directly use the identity library to create other tasks to be executed. The tasks to be executed created using the simulation feature library need to be compared with the features by the object detection server, while the tasks to be executed created directly using the identity library can be compared with the features by the business server. The image processing information obtained by the business server after processing the image from the task execution device is added to the message queue.

[0181] Therefore, after connecting to the message queue and pulling multiple messages, the object detection server needs to filter according to the feature library identifier of the simulated feature library carried by the image processing information to filter out the object features that need to be matched by the object detection server, and then complete the corresponding object detection task.

[0182] S603, comparing the features of the object to be detected with the features of the object, and generating alarm information if the comparison is successful.

[0183] In the embodiment of the present invention, the business server adds the image processing information obtained by real-time processing to the message queue, and the object detection server can obtain the real-time image processing information by connecting to the message queue, thereby enhancing the real-time nature of the alarm information.

[0184] In an optional implementation manner, the image processing information obtained by the business server further includes: a task identifier of the task to be executed and a device identifier of the task execution device.

[0185] In this case, the step S603 specifically includes:

[0186] An alarm message carrying the task identifier and the device identifier is generated, wherein the alarm message indicates that the object to be detected appears within a detection range of a task execution device corresponding to the device identifier.

[0187] S604: Send the alarm information to the service server.

[0188] In an optional embodiment, the method further comprises the following steps:

[0189] S605: When the feature of the object to be detected sent by the feature management server is received, an identity database of the object to be detected is created.

[0190] The above step S605 can be executed synchronously with step S601.

[0191] S606: Save the features of the object to be detected in the identity database.

[0192] In an embodiment of the present invention, after receiving the features of the object to be detected sent by the feature management server, the object detection server can create an identity library associated with the object to be detected, in which the initial information of the object to be detected is stored (for example, it may be: portrait photos and identity information, including ID number, name, gender, etc.).

[0193] S607: Add the object features corresponding to the alarm information to the identity database.

[0194] In an embodiment of the present invention, when the object detection server generates an alarm message, it means that the object to be detected has been detected, and the object feature corresponding to the alarm message can be considered to be the latest object feature related to the object to be detected. Therefore, the object feature can be added to the identity library associated with the object to be detected to maintain the timeliness of the features stored in the identity library and improve the accuracy of subsequent detections.

[0195] In an optional embodiment, the method further comprises the following steps:

[0196] S608: Query whether the archive library stores the archive of the object to be detected.

[0197] S609, when the archive of the object to be detected is stored in the archive library, the alarm information is added to the archive of the object to be detected, and a label is added to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

[0198] S610, when the archive of the object to be detected is not stored in the archive library, create an archive for the object to be detected, add the alarm information to the archive of the object to be detected, and add a label to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

[0199] In an embodiment of the present invention, after the object detection server generates an alarm by comparing the features of the object to be detected with the object features, it can query the file information based on the identity information in the features of the object to be detected. If the file information is found, the file information is updated. If the file information is not found, a new associated file of the object to be detected is created. At the same time, the attribute information of the object to be detected sent by the feature management server adds a custom tag to the associated file.

[0200] In the embodiment of the present invention, the archive information may be stored in a third-party database that is in communication with the service server, or may be stored in a database of the service server, so that the archive information of each object to be detected may be quickly queried through the service server later.

[0201] In the embodiment of the present invention, the object detection server can manage the archive information of each object to be detected, including operations such as creation and update.

[0202] In the embodiment of the present invention, since the archive information of each object to be detected includes the alarm information updated in real time by the object detection server, the area where the object to be detected has appeared can be quickly learned by querying the archive information, and the action route of the object to be detected can also be obtained based on the analysis of the archive information. In the embodiment of the present invention, the associated archive of the object to be detected is one-to-one with the identity library of the object to be detected, and can be used in association to obtain the real-time identity information and real-time activity area of ​​the object to be detected.

[0203] Based on the same inventive concept, an embodiment of the present invention provides an object detection device, which is applied to a service server. Figure 7 , Figure 7 Schematic diagram of an object detection device provided by an embodiment of the present invention. Figure 7 As shown, the device comprises:

[0204] A first configuration module 701 is used to configure an image acquisition device located in a position range as a task execution device according to a position range of an object to be detected;

[0205] A first creation module 702 is used to create a task to be executed according to the task execution device and the simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server;

[0206] The object feature sending module 703 is used to send the object features obtained by the task execution device executing the task to be executed to the object detection server, and the object features and the features of the object to be detected are used for the object detection server to detect whether the object to be detected appears within the location range.

[0207] Optionally, the device further comprises:

[0208] A notification message determination module, used to determine whether a notification message for a pre-created simulation feature library sent by the object detection server is received;

[0209] A location range request sending module, configured to send a location range request to the feature management server upon receiving the notification message;

[0210] The first location range receiving module is used to receive the location range of the object to be detected sent by the feature management server in response to the location range request.

[0211] Optionally, the device further comprises:

[0212] An image acquisition module, used to obtain images collected by the task execution device when executing the task to be executed;

[0213] An object feature acquisition module, used to obtain object features extracted from the image;

[0214] An image processing information determination module, used for adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information;

[0215] The information adding module is used to add the image processing information to a message queue, and the message queue is used by the object detection server to pull the image processing information including the feature library identifier of the simulation feature library, and extract object features from the image processing information.

[0216] Optionally, the image processing information determination module is specifically used to:

[0217] Adding a feature library identifier of the simulation feature library, a task identifier of the task to be executed, and a device identifier of the task execution device to the object feature to obtain image processing information;

[0218] The device also includes:

[0219] an alarm information receiving module, used to receive and save the alarm information sent by the object detection server and carrying the task identifier and the device identifier, wherein the alarm information is generated when the object detection server detects that the object to be detected appears within the position range, indicating that the object to be detected appears within the detection range of the task execution device corresponding to the device identifier;

[0220] A configuration information acquisition module, used to acquire the alarm push switch configuration information of the simulation feature library;

[0221] The push module is used to push the alarm information to the alarm terminal corresponding to the business server when the alarm push configuration switch is configured to be turned on.

[0222] Optionally, the device further comprises:

[0223] A second position range receiving module, used to obtain a new position range of the object to be detected;

[0224] A second configuration module is used to configure the image acquisition device located in the new position range as a new task execution device according to the new position range;

[0225] An identity library acquisition module, used to acquire an identity library of the object to be detected pre-created by the object detection server, wherein the identity library includes: features of the object to be detected sent by the feature management server, and object features corresponding to the alarm information;

[0226] A second creation module, used to create a new task to be executed according to the new task execution device and the identity library;

[0227] The comparison module is used to compare the object features obtained by the new task execution device executing the new task to be executed with the features in the identity database to determine whether the object to be detected appears within the new location range.

[0228] Based on the same inventive concept, an embodiment of the present invention provides an object detection device, which is applied to an object detection server. Figure 8 , Figure 8 is a schematic diagram of an object detection device provided by an embodiment of the present invention.

[0229] like Figure 8 As shown, the device comprises:

[0230] The simulation feature library creation module 801 is used to create a simulation feature library when receiving the features of the object to be detected sent by the feature management server;

[0231] An object feature acquisition module 802 is used to acquire object features from a business server, wherein the object features are obtained after the business server creates a task to be executed based on the simulation feature library, and the object features are extracted from an image collected by a task execution device that executes the task to be executed;

[0232] The warning information generating module 803 is used to compare the characteristics of the object to be detected with the characteristics of the object, and generate warning information when the comparison is successful;

[0233] The alarm information sending module 804 is used to send the alarm information to the service server.

[0234] Optionally, the device further comprises:

[0235] An identity library creation module, configured to create an identity library of an object to be detected upon receiving the features of the object to be detected sent by the feature management server;

[0236] A saving module, used for saving the features of the object to be detected into the identity database;

[0237] The identity database information adding module is used to add the object features corresponding to the alarm information to the identity database.

[0238] Optionally, the device further comprises:

[0239] A query module, used to query whether the archive store stores the archive of the object to be detected;

[0240] A file information adding module, used for adding the alarm information to the file of the object to be detected when the file of the object to be detected is stored in the file library, and adding a label to the file of the object to be detected according to the attribute information of the object to be detected sent by the feature management server;

[0241] The archive creation module is used to create an archive for the object to be detected when the archive does not store the archive of the object to be detected, add the alarm information to the archive of the object to be detected, and add a label to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

[0242] Optionally, the object feature acquisition module 802 includes:

[0243] A message queue connection submodule, used to connect to a message queue, wherein the message queue stores image processing information obtained by the business server parsing an image collected by a task execution device that executes the task to be executed, as well as information of other tasks, wherein the image processing information at least includes: object features and a feature library identifier of the simulation feature library;

[0244] The pulling submodule is used to pull the image processing information including the feature library identifier of the simulation feature library from the message queue, and extract the object feature from the image processing information.

[0245] Optionally, the image processing information further includes: a task identifier of the task to be executed and a device identifier of the task execution device; the alarm information generating module 803 is specifically used to:

[0246] An alarm message carrying the task identifier and the device identifier is generated, wherein the alarm message indicates that the object to be detected appears within a detection range of a task execution device corresponding to the device identifier.

[0247] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0248] An embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor, when executed, implements the steps in the object detection method described in any of the above embodiments.

[0249] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the object detection method described in any of the above embodiments are implemented.

[0250] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the object detection method described in any of the above embodiments when executed by a processor.

[0251] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0252] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0253] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0254] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0255] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0256] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0257] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0258] The object detection method, electronic device, storage medium and computer program product provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An object detection method, It is characterized in that Applied to a business server, the method comprises: According to the position range of the object to be detected, the image acquisition device located in the position range is configured as the task execution device; Creating a task to be executed according to the task execution device and the simulated feature library pre-created by the object detection server, wherein the simulated feature library is created after the object detection server receives the features of the object to be detected sent by the feature management server; The object features obtained by the task execution device executing the task to be executed are sent to the object detection server, and the object features and the features of the object to be detected are used by the object detection server to detect whether the object to be detected appears within the position range.

2. The method according to claim 1, It is characterized in that The method further comprises: determining whether a notification message for a pre-created simulation feature library sent by the object detection server is received; upon receiving the notification message, sending a location range request to the feature management server; Receive the location range of the object to be detected sent by the feature management server in response to the location range request.

3. The method according to claim 1 or 2, It is characterized in that The method further comprises: Obtaining images collected by the task execution device when executing the task to be executed; Obtaining object features extracted from the image; Adding a feature library identifier of the simulation feature library to the object feature to obtain image processing information; The image processing information is added to a message queue, and the message queue is used by the object detection server to pull the image processing information including the feature library identifier of the simulation feature library, and extract the object feature from the image processing information.

4. The method according to claim 3, It is characterized in that Adding the feature library identifier of the simulation feature library to the object feature to obtain image processing information includes: Adding a feature library identifier of the simulation feature library, a task identifier of the task to be executed, and a device identifier of the task execution device to the object feature to obtain image processing information; The method further comprises: Receiving and saving the alarm information sent by the object detection server and carrying the task identifier and the device identifier, wherein the alarm information is generated when the object detection server detects that the object to be detected appears within the location range, indicating that the object to be detected appears within the detection range of the task execution device corresponding to the device identifier; Obtaining the alarm push switch configuration information of the simulation feature library; When the alarm push configuration switch is configured to be turned on, the alarm information is pushed to the alarm terminal corresponding to the business server.

5. The method according to claim 4, It is characterized in that The method further comprises: Obtaining a new position range of the object to be detected; According to the new position range, configuring the image acquisition device located in the new position range as a new task execution device; Acquire an identity database of the object to be detected pre-created by the object detection server, wherein the identity database includes: features of the object to be detected sent by the feature management server, and object features corresponding to the alarm information; Creating a new task to be executed according to the new task execution device and the identity library; The object features obtained by the new task execution device executing the new task to be executed are compared with the features in the identity database to determine whether the object to be detected appears within the new location range.

6. An object detection method, It is characterized in that Applied to an object detection server, the method comprises: Upon receiving the features of the object to be detected sent by the feature management server, creating a simulation feature library; Acquire object features from a business server, wherein the object features are obtained after the business server creates a task to be executed based on the simulation feature library, and the object features are extracted from an image captured by a task execution device that executes the task to be executed; Comparing the features of the object to be detected with the features of the object, and generating an alarm message if the comparison is successful; The alarm information is sent to the service server.

7. The method according to claim 6, It is characterized in that The method further comprises: Upon receiving the features of the object to be detected sent by the feature management server, creating an identity library of the object to be detected; Saving the characteristics of the object to be detected in the identity database; The object features corresponding to the alarm information are added to the identity database.

8. The method according to claim 6 or 7, It is characterized in that After generating the warning information, the method further includes: Querying whether the archive library stores the archive of the object to be detected; When the archive of the object to be detected is stored in the archive library, the alarm information is added to the archive of the object to be detected, and a label is added to the archive of the object to be detected according to the attribute information of the object to be detected sent by the feature management server; When the archive of the object to be detected is not stored in the archive library, a file is created for the object to be detected, and the alarm information is added to the file of the object to be detected, and a label is added to the file of the object to be detected according to the attribute information of the object to be detected sent by the feature management server.

9. The method according to claim 6 or 7, It is characterized in that Get object characteristics from the business server, including: A connection message queue is provided, wherein the message queue stores image processing information obtained by the business server processing an image collected by a task execution device executing the task to be executed, and information of other tasks, wherein the image processing information at least includes: object features and a feature library identifier of the simulation feature library; The image processing information including the feature library identifier of the simulation feature library is pulled from the message queue, and the object feature is extracted from the image processing information.

10. The method according to claim 9, It is characterized in that The image processing information also includes: the task identifier of the task to be executed and the device identifier of the task execution device; generating alarm information includes: An alarm message carrying the task identifier and the device identifier is generated, wherein the alarm message indicates that the object to be detected appears within a detection range of a task execution device corresponding to the device identifier.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory, It is characterized in that The processor executes the computer program to implement the object detection method according to any one of claims 1-5 or 6-10.

12. A computer-readable storage medium having a computer program / instructions stored thereon, It is characterized in that When the computer program / instruction is executed by a processor, the object detection method according to any one of claims 1 to 5 or 6 to 10 is implemented.

13. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instruction is executed by a processor, the object detection method according to any one of claims 1 to 5 or 6 to 10 is implemented.

Images