CN114267019A - Identification method, device, equipment and storage medium - Google Patents
Identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114267019A CN114267019A CN202111637753.XA CN202111637753A CN114267019A CN 114267019 A CN114267019 A CN 114267019A CN 202111637753 A CN202111637753 A CN 202111637753A CN 114267019 A CN114267019 A CN 114267019A
- Authority
- CN
- China
- Prior art keywords
- monitored
- position information
- information
- area
- target image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The present disclosure provides an identification method, apparatus, device and storage medium, and relates to the field of artificial intelligence technology such as deep learning, computer vision, smart city and the like. The method comprises the following steps: acquiring a target image; determining position information of an object to be monitored in a target image, and recording the position information as first position information; determining position information of an object to be monitored in a world coordinate system based on the first position information and a conversion matrix corresponding to the target image, and recording the position information as second position information, wherein the conversion matrix is used for converting the position of the object to be monitored in the pixel coordinate system into the position of the object in the world coordinate system; and in response to the fact that the object to be monitored is determined to be in the stopping state and the stopping time exceeds a preset threshold value, judging the stopping area of the object to be monitored based on the second position information, and executing operation corresponding to the judgment result. The identification method provided by the disclosure can be used for rapidly identifying and managing the object to be monitored in the image, and the management efficiency is improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies such as deep learning, computer vision, smart cities, and the like, and in particular, to an identification method, apparatus, device, and storage medium.
Background
For city management, due to the particularity of the operation mode of the stall dealer, it is difficult to perform standard management on the stall. Especially at some traffic intersections, irregular dealers may cause disorder of traffic order and may affect the appearance of the city.
Disclosure of Invention
The disclosure provides an identification method, apparatus, device and storage medium.
According to a first aspect of the present disclosure, there is provided an identification method comprising: acquiring a target image; determining position information of an object to be monitored in a target image, and recording the position information as first position information; determining position information of an object to be monitored in a world coordinate system based on the first position information and a conversion matrix corresponding to the target image, and recording the position information as second position information, wherein the conversion matrix is used for converting the position of the object to be monitored in the pixel coordinate system into the position of the object in the world coordinate system; and in response to the fact that the object to be monitored is in the stopping state and the stopping time exceeds a preset threshold value, judging the stopping area of the object to be monitored based on the second position information, and executing operation corresponding to the judgment result.
According to a second aspect of the present disclosure, there is provided an identification apparatus comprising: a first acquisition module configured to acquire a target image; the monitoring device comprises a first determining module, a second determining module and a monitoring module, wherein the first determining module is configured to determine position information of an object to be monitored in a target image, and the position information is recorded as first position information; the second determining module is configured to determine position information of the object to be monitored in a world coordinate system based on the first position information and a conversion matrix corresponding to the target image, and the position information is recorded as second position information, wherein the conversion matrix is used for converting positions in a pixel coordinate system into positions in the world coordinate system; and the execution module is configured to respond to the fact that the object to be monitored is determined to be in the staying state and the staying time exceeds a preset threshold value, judge the staying area of the object to be monitored based on the second position information, and execute the operation corresponding to the judgment result.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in any one of the implementations of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described in any one of the implementation manners of the first aspect.
According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method as described in any of the implementation ways of the first aspect.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is an exemplary system architecture diagram in which the present disclosure may be applied;
FIG. 2 is a flow diagram for one embodiment of an identification method according to the present disclosure;
FIG. 3 is a flow diagram of another embodiment of an identification method according to the present disclosure;
FIG. 4 is a schematic diagram of an application scenario of an identification method according to the present disclosure;
FIG. 5 is a schematic structural diagram of one embodiment of an identification appliance according to the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing the identification method of an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that, in the present disclosure, the embodiments and the features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the identification method or identification apparatus of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or transmit information or the like. Various client applications may be installed on the terminal devices 101, 102, 103.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the electronic devices described above. It may be implemented as multiple pieces of software or software modules, or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may provide various services. For example, the server 105 may analyze and process the target image acquired from the terminal apparatuses 101, 102, 103, and generate a processing result (e.g., perform an operation corresponding to the determination result).
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces or modules of software (e.g., to provide distributed services), or as a single piece or module of software. And is not particularly limited herein.
It should be noted that the identification method provided by the embodiment of the present disclosure is generally executed by the server 105, and accordingly, the identification device is generally disposed in the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of an identification method according to the present disclosure is shown. The identification method comprises the following steps:
In the present embodiment, the subject of execution of the recognition method (e.g., the server 105 shown in fig. 1) may acquire the target image. The target image may be acquired by an image sensor, the image sensor is a sensor capable of acquiring an image, and generally refers to a camera sensor (hereinafter referred to as a camera), and other image sensors may also be used according to actual situations, which is not limited in this embodiment.
In practical applications, the recognition method provided by this embodiment can be applied to a smart city, the target image can be collected by a fixed camera, and the fixed camera is a camera which is located anywhere in the smart city, such as on a road, in a cell, and the like. After the fixed cameras collect images in real time, the collected images can be uploaded to an image database, and the images collected by all the fixed cameras are stored in the image database.
It should be noted that the camera is generally installed at a higher position, and the viewing angle is not blocked, so as to ensure that more information can be collected.
In this embodiment, the execution subject may determine the position information of the object to be monitored in the target image, and record the position information as the first position information. Since the object to be monitored is identified, tracked and managed in this embodiment, the executing body may first determine the position of the object to be monitored in the acquired target image. That is, the executing entity may first identify and detect the target image to determine whether the target image includes the object to be monitored, and determine the position information of the object to be monitored in the target image when it is determined that the object to be monitored appears in the target image. As an example, the executing body detects the target image by using a depth learning model trained in advance, so as to obtain position information of the object to be monitored in the target image, which is denoted as first position information.
It should be noted that the object to be monitored in this embodiment may be any object that needs to be monitored and identified.
As an example, the object to be monitored may be a vendor, and when the object to be monitored is a vendor, the execution main body may identify the vendor, determine location information of the vendor in the target image, and determine whether the vendor is in a predetermined area and/or a predetermined time, thereby implementing management of the vendor. Among them, the stall refers to a stall person, a free-flow seller, and a non-certified stall in real life.
As another example, the object to be monitored may also be a vehicle, and when the object to be monitored is a vehicle, the identification method may be applied to monitoring and identifying a parking state of the vehicle, determining position information of the vehicle in the target image, and determining whether the vehicle is parked in a specified area and/or within a specified time, thereby implementing management of the parking state of the vehicle and whether parking violation is performed.
As another example, the object to be monitored may also be an obstacle, and when the object to be monitored is an obstacle, the identification method may identify the obstacle that appears, determine the position information of the obstacle in the target image, and determine whether the obstacle is in a prescribed area, thereby implementing intelligent management of the obstacle.
Of course, the object to be detected in this embodiment may also be other objects, which are not limited to the above, and this is not specifically limited in this embodiment.
In this embodiment, the object to be detected is described as a vendor.
In this embodiment, the executing body may determine, as the second position information, the position information of the object to be monitored in the world coordinate system based on the first position information and a conversion matrix corresponding to the target image, where the conversion matrix is used to convert the position in the pixel coordinate system into the position in the world coordinate system. The transformation matrix may be configured to transform a coordinate of any point in the image from a pixel coordinate system to a coordinate in a world coordinate system, that is, for any point in the image, if the coordinate of the point in the image is known, a coordinate position of the point in the world coordinate system may be obtained through the transformation matrix corresponding to the image. Because the target image is collected by the cameras, and the configuration information such as the view angle and the precision of each camera is not necessarily the same, the conversion matrix corresponding to each camera is different, that is, the conversion matrix corresponding to the image collected by the same camera is the same, and the conversion matrix corresponding to the image collected by different cameras is different. In this embodiment, the executing body determines the position information of the object to be monitored in the world coordinate system based on the first position information obtained in step 202 and the conversion matrix corresponding to the target image, and records the position information as the second position information.
As a first example, the executing body may calibrate the target image in a three-point calibration manner, so as to obtain a conversion matrix corresponding to the target image. In the three-point calibration mode, when the actual coordinates of any three non-collinear points in the image are known, the conversion from the image pixels to the actual physical coordinates can be performed in a three-point conversion mode, so that a corresponding conversion matrix is obtained.
As a second example, the execution subject may calibrate the target image by a four-point calibration method, so as to obtain a conversion matrix corresponding to the target image. The four-point calibration method is that when the actual coordinates of each point of any quadrangle in the image are known, the conversion from the image pixel to the actual physical coordinates can be performed by the perspective transformation method, so as to obtain the corresponding conversion matrix.
As a third example, the executing entity may calibrate the target image in a multi-point calibration manner, so as to obtain a conversion matrix corresponding to the target image. In the multi-point calibration mode, when the actual coordinates of more than four points in the image are known, the conversion from the image pixels to the actual physical coordinates can be performed by an iterative method, so that a corresponding conversion matrix is obtained. The iterative method may be RANSAC (RANdom SAmple Consensus), or may also be an iterative method such as least square combination, for example. The method can improve the conversion precision of the coordinate conversion matrix in the image global.
And 204, in response to the fact that the object to be monitored is determined to be in the staying state and the staying time exceeds the preset threshold, judging the staying area of the object to be monitored based on the second position information, and executing operation corresponding to the judgment result.
In this embodiment, the executing entity may determine, based on the second position information, a staying area of the object to be monitored when it is determined that the object to be monitored is in a staying state and the staying time exceeds a preset threshold, and execute an operation corresponding to the determination result. That is, in this embodiment, after acquiring the actual position information of the object to be monitored, the executing body may determine the state of the object to be monitored based on the position information, and if the object to be monitored is currently in the stay state, that is, the coordinates of the object to be monitored are not changed (the object to be monitored does not move in one place for a long time), and the stay time exceeds the preset threshold, the executing body may determine the stay area of the object to be monitored based on the second position information, and execute the operation corresponding to the determination result.
In this embodiment, the executing entity configures the system in advance according to an actual scene, and mainly includes: and configuring information such as a staying area of the object to be monitored, a non-stopping area of the object to be monitored, a staying time threshold of the object to be monitored, the operable time information of the object to be monitored, camera calibration parameters and the like.
For example, when the object to be monitored is a vendor, the executing entity configures the system in advance according to an actual scene, and mainly includes: configuring information such as a stall available area, a stall forbidden area, a stall staying time threshold, a stall placing area threshold, stall available time information, camera calibration parameters and the like. The execution main body judges whether the second position information is a preset area or not under the condition that the stall is determined to be in the stall state and the stall time exceeds a preset threshold value. For example, if the vendor stays in a preset vendor stop area, the information of the vendor is sent to the warning module, so that the warning module gives an alarm to the vendor.
The identification method provided by the embodiment of the disclosure comprises the steps of firstly obtaining a target image; then determining the position information of the object to be monitored in the target image, and recording the position information as first position information; then determining the position information of the object to be monitored under the world coordinate system based on the first position information and the conversion matrix corresponding to the target image, and recording the position information as second position information; and finally, in response to the fact that the object to be monitored is in the stopping state and the stopping time exceeds a preset threshold value, judging the stopping area of the object to be monitored based on the second position information, and executing operation corresponding to the judgment result. In the identification method in this embodiment, the method may determine, based on the target image, first position information of the object to be monitored in a pixel coordinate system of the image and second position information of the object to be monitored in a world coordinate system, determine, based on the second position information, a staying area of the object to be monitored when it is determined that the object to be monitored is in a staying state and the staying time exceeds a preset threshold, and then perform an operation corresponding to a determination result, so that the position of the object to be monitored can be determined, the staying area of the object to be monitored can be determined, the object to be monitored in the image can be identified and managed quickly, and the identification efficiency and the management efficiency of the object to be monitored are improved.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
With continued reference to fig. 3, fig. 3 illustrates a flow 300 of another embodiment of an identification method according to the present disclosure. The identification method comprises the following steps:
Step 301 is substantially the same as step 201 in the foregoing embodiment, and the specific implementation manner may refer to the foregoing description of step 201, which is not described herein again.
In this embodiment, an executing subject of the recognition method (for example, the server 105 shown in fig. 1) may detect the target image by using a depth learning model trained in advance, so as to determine the position information of the object to be monitored in the target image, and record the position information as the first position information. Specifically, the execution main body can input the target image into a pre-trained deep learning model, the deep learning model detects the target image, and the first position information of the object to be monitored in the target image is output, so that the accuracy of detecting and identifying the object to be monitored is improved.
In this embodiment, the executing body may determine, based on the first position information and a transformation matrix corresponding to the target image, position information of the object to be monitored in a world coordinate system, and record the position information as second position information, where the transformation matrix is used to transform a position in a pixel coordinate system into a position in the world coordinate system. Step 303 is substantially the same as step 203 of the previous embodiment, and specific implementation manners may refer to the foregoing description of step 203, which is not described herein again.
In some optional embodiments of this embodiment, the target image is calibrated in a self-learning calibration manner, so as to obtain a conversion matrix corresponding to the target image.
In this implementation manner, the execution main body may calibrate the target image in a self-learning calibration manner, so as to obtain a conversion matrix corresponding to the target image. The self-learning calibration mode does not need to manually give out calibration information, and the system automatically learns and obtains the conversion matrix. In the self-learning process, the vehicle projection coordinates are obtained by detecting key points of the appeared common targets, mainly vehicles; then, a conversion matrix is calculated based on the approximate length and width of the vehicle. In the process of system self-learning, the acquired vehicle projection is used for multiple times, and an optimal conversion matrix (namely the mean square error is minimum) is learned in an iterative mode. Thereby improving the conversion accuracy of the conversion matrix.
And step 304, judging the staying area of the object to be monitored based on the second position information.
In this embodiment, the execution subject may determine the stay area of the object to be monitored based on the second position information. The execution main body can configure information such as a staying area of an object to be monitored or a no-stopping area of the object to be monitored in advance according to an actual scene. Therefore, the execution main body judges whether the second position information of the object to be monitored is a preset staying area of the object to be monitored or a forbidden area of the object to be monitored.
If the staying area of the object to be monitored is a preset no-stop area, executing step 305; if the staying area of the object to be monitored is the preset staying area, step 306 and step 309 are executed.
In this embodiment, the execution main body may send the information of the object to be monitored to the alarm module when determining that the staying area of the object to be monitored is the preset no-stop area based on the second position information.
For example, if the current staying area of the stall is a no-parking area, the execution main body sends the information of the stall to the alarm module, so that the alarm module alarms the stall, and the stall leaves as soon as possible, thereby realizing the management of the stall. The information of the vendors can include specific location information of the vendors, description information of the vendors, and the like.
In this embodiment, the executing body may calculate the area of the object to be monitored in a case where it is determined that the staying area of the object to be monitored is the preset staying available area based on the second position information. If the area where the object to be monitored stays is the staying area, the area of the object to be monitored is further calculated, and therefore the object to be monitored is comprehensively managed.
In some optional implementations of this embodiment, the calculating the area of the object to be monitored includes: determining the region information of an object to be monitored in a target image by using a pre-trained deep learning model, and recording the region information as first region information; determining the regional information of the object to be monitored in a world coordinate system based on the first regional information and a conversion matrix corresponding to the target image, and recording the regional information as second regional information; and obtaining the area of the object to be monitored based on the second region information.
In this implementation, the executing body detects and divides the target image by using a pre-trained deep learning model, so as to determine the region information of the object to be monitored in the target image, and records the region information as the first region information. And then obtaining the region information of the object to be monitored in the world coordinate system based on the conversion matrix of the target image, marking the region information as second region information, and then calculating the area of the object to be monitored based on the second region information. The contour of the object to be monitored is obtained by analyzing the segmentation result, and the actual coordinates of the contour point are calculated according to the calculated transformation matrix, so that the area of the object to be monitored is obtained, and the calculation accuracy is improved.
In some optional embodiments of this embodiment, when the object to be monitored is a tricycle vendor, the height information of the tricycle vendor needs to be known, and in this case, the height calibration information can be learned by performing semantic segmentation on pedestrians. And then, acquiring the actual height value of the tricycle stall dealer by a tangent plane method according to the height calibration information, specifically, dividing a stall region by taking a connecting line of two tire key points of the tricycle stall dealer as a horizontal direction, thereby acquiring a lowest point and a highest point which are vertical to the direction, and further acquiring the actual height value of the tricycle stall dealer.
In this embodiment, the execution main body may send the information of the object to be monitored to the alarm module when it is determined that the area value is greater than the preset area threshold. For example, if the area of a vendor exceeds a preset area threshold, the vendor needs to be managed, and the execution main body sends the information of the vendor to the alarm module, so that the alarm module alarms the vendor, and the vendor leaves as soon as possible, thereby realizing the management of the vendor.
And 308, in response to the fact that the staying area of the object to be monitored is determined to be the preset staying area based on the second position information, acquiring the time information of the object to be monitored in the staying area.
In this embodiment, the execution main body may further obtain time information of the object to be monitored in the stoppable area, and since the execution main body may pre-configure the operational time information of the object to be monitored, the execution main body may obtain the operational time of the object to be monitored in the stoppable area to determine whether the operational time is within the preset range.
In this embodiment, the execution main body may send the information of the object to be monitored to the alarm module when it is determined that the time information is outside the preset time range. For example, if the time information is out of the preset distribution range time, which indicates that the time information is not currently available for the stall, the execution main body sends the information of the stall to the alarm module, so that the alarm module alarms the stall, and the stall leaves as soon as possible, thereby realizing the management of the stall.
It should be noted that, in the embodiment, the execution sequence of the steps 306-307 and 308-309 is not limited, that is, the steps 306-307 and 308-309 may be executed simultaneously, or the steps 306-307 may be executed before the steps 308-309, or the steps 306-307 may be executed after the steps 308-309.
In some optional implementations of this embodiment, the identification method further includes: identifying the behavior of the object to be monitored by utilizing a pre-trained identification model, and determining the state of the object to be monitored; responding to the situation that the object to be monitored is determined to be in a disappearance state and the object to be monitored is an object which is alarmed, and generating alarm removing information of the object to be monitored; and sending the alarm release information to an alarm module.
In this implementation, the executing entity may identify the behavior of the object to be monitored by using a pre-trained identification model, such as a Person re-identification (ReID) model, to determine the state of the object to be monitored, for example, a stall state, a flow state, a disappearance state, or the like. If the object to be monitored is determined to be in a disappearing state and the object to be monitored is an object which has been alarmed before, the object to be monitored receives the alarm and leaves the alarm area, at the moment, alarm removing information can be generated and sent to the alarm module, and therefore the alarm of the object to be monitored is removed. Therefore, the comprehensive management of the object to be monitored is realized.
In some optional embodiments of this embodiment, after receiving the information of the object to be monitored, the alarm module generates alarm information of the object to be monitored, and sends the alarm information of the object to be monitored to the front-end alarm platform, and the front-end alarm platform counts the number of the objects to be monitored in the corresponding time period and the corresponding region, and sends the number to the corresponding administrator. For example, the front-end warning platform counts the number of vendors in the corresponding time period and the corresponding region, and sends the number to the corresponding manager, so that the manager can know the status of the vendors in time and process the status in time.
As can be seen from fig. 3, compared with the embodiment of fig. 2, the identification method highlights the step of judging the staying area of the object to be monitored based on the second position information of the object to be monitored and executing the operation corresponding to the judgment result, so that the behavior track of the object to be monitored can be determined based on the ReID model, and different management measures are taken for the object to be monitored based on the staying area of the object to be monitored, thereby realizing the automatic monitoring and management of the object to be monitored and improving the management efficiency.
With continued reference to fig. 4, fig. 4 shows a schematic diagram of an application scenario of the recognition method according to the present disclosure. In this application scenario, the executing subject 402 first acquires a target image 401, which may be captured by a camera. Then, the executing body detects the target image by using the depth learning model trained in advance, thereby determining the position information of the vendor in the target image and recording the position information as the first position information. Then, the executing body determines the position information of the vendor in the world coordinate system based on the first position information and the conversion matrix corresponding to the target image, and marks the position information as the second position information. And finally, under the condition that the stall is determined to be in the stall state and the stall time exceeds a preset threshold value, the execution main body judges the stall area of the stall based on the second position information and executes the operation corresponding to the judgment result, so that the automatic identification and management of the stall are realized, and the identification efficiency and the management efficiency of the stall are improved.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an identification apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied in various electronic devices.
As shown in fig. 5, the recognition apparatus 500 of the present embodiment includes: a first obtaining module 501, a first determining module 502, a second determining module 503, and an executing module 504. The first obtaining module 501 is configured to obtain a target image; a first determining module 502 configured to determine position information of an object to be monitored in a target image, which is denoted as first position information; a second determining module 503, configured to determine, based on the first position information and a conversion matrix corresponding to the target image, position information of the object to be monitored in a world coordinate system, which is recorded as second position information, where the conversion matrix is used to convert a position in a pixel coordinate system into a position in the world coordinate system; and the execution module 504 is configured to, in response to determining that the object to be monitored is in the stay state and the stay time exceeds the preset threshold, determine a stay area of the object to be monitored based on the second position information, and execute an operation corresponding to the determination result.
In the present embodiment, in the recognition apparatus 500: the specific processing and the technical effects thereof of the first obtaining module 501, the first determining module 502, the second determining module 503 and the executing module 504 can refer to the related descriptions of step 201 and step 204 in the corresponding embodiment of fig. 2, and are not described herein again.
In some optional implementations of this embodiment, the first determining module includes: the first determining submodule is configured to detect the target image by using a pre-trained deep learning model, and position information of the object to be monitored in the target image is obtained.
In some optional implementations of the present embodiment, the identifying apparatus 500 further includes: and the calibration module is configured to calibrate the target image in a self-learning calibration mode to obtain a conversion matrix corresponding to the target image.
In some optional implementations of this embodiment, the execution module includes: and the second determining submodule is configured to respond to the fact that the staying area of the object to be monitored is determined to be a preset no-stopping area based on the second position information, and send the information of the object to be monitored to the warning module.
In some optional implementations of this embodiment, the execution module includes: a third determining submodule configured to calculate an area of the object to be monitored in response to determining that the staying area of the object to be monitored is a preset staying possible area based on the second position information; and the sending submodule is configured to respond to the condition that the determined area is larger than the preset area threshold value and send the information of the object to be monitored to the alarm module.
In some optional implementations of this embodiment, the third determining sub-module includes: the first determining unit is configured to determine the region information of the object to be monitored in the target image by using a pre-trained deep learning model, and the region information is recorded as first region information; the second determining unit is configured to determine the area information of the object to be monitored in a world coordinate system based on the first area information and the conversion matrix corresponding to the target image, and the area information is recorded as second area information; an obtaining unit configured to obtain an area of the object to be monitored based on the second region information.
In some optional implementations of the present embodiment, the identification apparatus 500 further includes: the second acquisition module is configured to acquire time information of the object to be monitored in the staying area; the first sending module is configured to send information of the object to be monitored to the alarming module in response to the fact that the time information is determined to be out of the preset time range.
In some optional implementations of the present embodiment, the identification apparatus 500 further includes: the identification module is configured to identify the behavior of the object to be monitored by utilizing a pre-trained identification model, and determine the state of the object to be monitored; the generating module is configured to respond to the fact that the object to be monitored is determined to be in a disappearance state and the object to be monitored is an alarmed object, and generate alarm removing information of the object to be monitored; and the second sending module is configured to send the alarm release information to the alarm module.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computational unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computational chips, various computational units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 601 performs the respective methods and processes described above, such as the recognition method. For example, in some embodiments, the identification method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the identification method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the identification method in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium may include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
Cloud computing (cloud computer) refers to a technology architecture that accesses a flexibly extensible shared physical or virtual resource pool through a network, where the resource may include a server, an operating system, a network, software, an application or a storage device, and the like, and can be deployed and managed in an on-demand and self-service manner. Through the cloud computing technology, high-efficiency and strong data processing capacity can be provided for technical application and model training of artificial intelligence, block chains and the like.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a blockchain.
It will be appreciated that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure may be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical aspects of the disclosure can be achieved, and are not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations, and substitutions can be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (19)
1. An identification method, comprising:
acquiring a target image;
determining the position information of an object to be monitored in the target image, and recording the position information as first position information;
determining position information of the object to be monitored in a world coordinate system based on the first position information and a conversion matrix corresponding to the target image, and recording the position information as second position information, wherein the conversion matrix is used for converting positions in a pixel coordinate system into positions in the world coordinate system;
and in response to the fact that the object to be monitored is determined to be in the stopping state and the stopping time exceeds a preset threshold value, judging the stopping area of the object to be monitored based on the second position information, and executing operation corresponding to the judgment result.
2. The method of claim 1, wherein the determining the position information of the object to be monitored in the target image comprises:
and detecting the target image by using a pre-trained deep learning model to obtain the position information of the object to be monitored in the target image.
3. The method of claim 1, further comprising:
and calibrating the target image in a self-learning calibration mode to obtain a conversion matrix corresponding to the target image.
4. The method according to any one of claims 1 to 3, wherein the determining of the staying area of the object to be monitored based on the second position information, and performing an operation corresponding to a determination result includes:
and responding to the fact that the staying area of the object to be monitored is a preset no-stopping area determined based on the second position information, and sending the information of the object to be monitored to an alarm module.
5. The method according to any one of claims 1 to 4, wherein the determining of the staying area of the object to be monitored based on the second position information, and performing an operation corresponding to a determination result includes:
in response to determining that the staying area of the object to be monitored is a preset staying area based on the second position information, calculating the area of the object to be monitored;
and responding to the fact that the area is larger than a preset area threshold value, and sending the information of the object to be monitored to an alarm module.
6. The method of claim 5, wherein the calculating the area of the object to be monitored comprises:
determining the region information of the object to be monitored in the target image by using a pre-trained deep learning model, and recording the region information as first region information;
determining the regional information of the object to be monitored in a world coordinate system based on the first regional information and a conversion matrix corresponding to the target image, and recording the regional information as second regional information;
and obtaining the area of the object to be monitored based on the second region information.
7. The method of claim 5, further comprising:
acquiring time information of an object to be monitored in the staying area;
and responding to the fact that the time information is determined to be out of the preset time range, and sending the information of the object to be monitored to an alarm module.
8. The method of any of claims 1-7, further comprising:
recognizing the behavior of the object to be monitored by using a pre-trained recognition model, and determining the state of the object to be monitored;
responding to the situation that the object to be monitored is determined to be in a disappearance state and the object to be monitored is an object which is alarmed, and generating alarm removing information of the object to be monitored;
and sending the alarm release information to an alarm module.
9. An identification device comprising:
a first acquisition module configured to acquire a target image;
the first determining module is configured to determine position information of an object to be monitored in the target image, and the position information is recorded as first position information;
the second determining module is configured to determine position information of the object to be monitored in a world coordinate system based on the first position information and a conversion matrix corresponding to the target image, and the position information is recorded as second position information, wherein the conversion matrix is used for converting positions in a pixel coordinate system into positions in the world coordinate system;
and the execution module is configured to respond to the fact that the object to be monitored is determined to be in the stopping state and the stopping time exceeds a preset threshold value, judge the stopping area of the object to be monitored based on the second position information, and execute the operation corresponding to the judgment result.
10. The apparatus of claim 9, wherein the first determining means comprises:
the first determining submodule is configured to detect the target image by using a pre-trained deep learning model, and position information of the object to be monitored in the target image is obtained.
11. The apparatus of claim 9, further comprising:
and the calibration module is configured to calibrate the target image in a self-learning calibration mode to obtain a conversion matrix corresponding to the target image.
12. The apparatus of any of claims 9-11, wherein the means for performing comprises:
the second determining submodule is configured to respond to the fact that the staying area of the object to be monitored is determined to be a preset no-stopping area based on the second position information, and send the information of the object to be monitored to an alarm module.
13. The apparatus of any of claims 9-12, wherein the means for performing comprises:
a third determination submodule configured to calculate an area of the object to be monitored in response to determining that a staying area of the object to be monitored is a preset staying available area based on the second position information;
the sending submodule is configured to send the information of the object to be monitored to an alarm module in response to the fact that the area is determined to be larger than a preset area threshold value.
14. The apparatus of claim 13, wherein the third determination submodule comprises:
the first determining unit is configured to determine the region information of the object to be monitored in the target image by using a pre-trained deep learning model, and the region information is marked as first region information;
the second determining unit is configured to determine area information of the object to be monitored in a world coordinate system based on the first area information and a conversion matrix corresponding to the target image, and the area information is recorded as second area information;
an obtaining unit configured to obtain an area of the object to be monitored based on the second region information.
15. The apparatus of claim 13, further comprising:
the second acquisition module is configured to acquire time information of an object to be monitored in the staying area;
the first sending module is configured to send the information of the object to be monitored to an alarm module in response to the fact that the time information is determined to be out of a preset time range.
16. The apparatus of any of claims 9-15, further comprising:
the recognition module is configured to recognize the behavior of the object to be monitored by utilizing a pre-trained recognition model, and determine the state of the object to be monitored;
the generating module is configured to respond to the fact that the object to be monitored is determined to be in a disappearance state and the object to be monitored is an alarmed object, and generate alarm removing information of the object to be monitored;
a second sending module configured to send the alarm release information to an alarm module.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637753.XA CN114267019A (en) | 2021-12-29 | 2021-12-29 | Identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111637753.XA CN114267019A (en) | 2021-12-29 | 2021-12-29 | Identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114267019A true CN114267019A (en) | 2022-04-01 |
Family
ID=80831306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111637753.XA Pending CN114267019A (en) | 2021-12-29 | 2021-12-29 | Identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114267019A (en) |
-
2021
- 2021-12-29 CN CN202111637753.XA patent/CN114267019A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113205037B (en) | Event detection method, event detection device, electronic equipment and readable storage medium | |
| JP2023527265A (en) | Method and device for detecting traffic abnormality, electronic device, storage medium and computer program | |
| CN112287875B (en) | Abnormal license plate recognition method, device, equipment and readable storage medium | |
| US10945888B2 (en) | Intelligent blind guide method and apparatus | |
| CN113420682A (en) | Target detection method and device in vehicle-road cooperation and road side equipment | |
| CN112863187B (en) | Detection method of perception model, electronic equipment, road side equipment and cloud control platform | |
| CN111666821B (en) | Method, device and equipment for detecting personnel aggregation | |
| CN113538963A (en) | Method, apparatus, device and storage medium for outputting information | |
| US10599946B2 (en) | System and method for detecting change using ontology based saliency | |
| KR20220146670A (en) | Traffic anomaly detection methods, devices, devices, storage media and programs | |
| CN114238790A (en) | Method, apparatus, device and storage medium for determining maximum perception range | |
| CN113869258A (en) | Traffic incident detection method and device, electronic equipment and readable storage medium | |
| EP4080479A2 (en) | Method for identifying traffic light, device, cloud control platform and vehicle-road coordination system | |
| CN114267019A (en) | Identification method, device, equipment and storage medium | |
| CN115908816A (en) | Accumulated water identification method, device, equipment and storage medium based on artificial intelligence | |
| JP7258101B2 (en) | Image stabilization method, device, electronic device, storage medium, computer program product, roadside unit and cloud control platform | |
| CN115891868A (en) | Fault detection method, device, electronic apparatus, and medium for autonomous vehicle | |
| CN114549584A (en) | Information processing method and device, electronic equipment and storage medium | |
| CN114708498A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN112861701A (en) | Illegal parking identification method and device, electronic equipment and computer readable medium | |
| CN113806361B (en) | Method, device and storage medium for associating electronic monitoring equipment with road | |
| CN113963322B (en) | Detection model training method and device and electronic equipment | |
| CN113469115B (en) | Method and device for outputting information | |
| CN111126261B (en) | Video data analysis method and device, raspberry group device and readable storage medium | |
| CN114581393A (en) | Object detection method, device, equipment, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |