Image data processing method, camera device and equipment
Through image data processing methods and adaptive shooting parameter adjustment, the problem of low monitoring efficiency and accuracy of the existing monitoring system is solved, and efficient and accurate monitoring and security risk management are achieved.
Patent Information
- Application Number
- CN202410913849.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-12-03
AI Technical Summary
The existing monitoring system requires manual viewing of surveillance videos in real time, which is time-consuming and labor-intensive, low monitoring intensity and efficiency, and is prone to false alarms, resulting in low monitoring accuracy.
Through the image data processing method, image data of the target monitoring area is obtained, abnormal target determination, abnormality analysis and risk analysis are performed, early warning information is generated, and the shooting parameters of the camera device are adjusted adaptively to improve monitoring efficiency and accuracy.
It realizes efficient monitoring of the monitoring area, reduces false alarms and security risks, and improves the accuracy of monitoring and image data quality.
Smart Images

Figure CN119068405A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data analysis, and in particular to an image data processing method, a camera device and equipment. Background Art
[0002] In the fields of security, transportation, urban management, etc., it is usually necessary to monitor an area by installing a video device (such as a camera), and determine whether the area is normal by manually viewing the surveillance video in real time. This method has low requirements for layout and is relatively easy to deploy. It is widely used in monitoring public places such as shopping malls, schools, and hospitals. However, it requires monitoring personnel to view the surveillance video in real time, which is time-consuming and labor-intensive. The monitoring intensity and efficiency of the monitored area are low, and false alarms are prone to occur during the monitoring process, resulting in low monitoring accuracy. Summary of the invention
[0003] In order to improve the monitoring intensity of the monitored area, the present application provides an image data processing method, a camera device and equipment.
[0004] In a first aspect, the present application provides an image data processing method, which adopts the following technical solution:
[0005] A method for processing image data, comprising:
[0006] Acquire image data of the target monitoring area, and identify the image data to obtain corresponding identification results;
[0007] Determining abnormal targets in the image data according to the recognition result;
[0008] Performing an abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data;
[0009] A risk analysis is performed on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data.
[0010] By adopting the above technical solution, the image data of the target monitoring area is obtained, and the image data is identified to obtain the corresponding identification results; according to the identification results, the abnormal targets in the image data are determined; according to the image data, the abnormal targets are analyzed for abnormality to obtain abnormal analysis data; according to the abnormal analysis data and the image data, the abnormal targets are analyzed for risk to obtain risk analysis data. This method saves time and effort, improves the monitoring intensity and efficiency of the monitoring area, reduces the probability of false reporting of risks and safety hazards in the monitoring area, and improves the accuracy of monitoring.
[0011] Optionally, the step of determining an abnormal target in the image data according to the recognition result includes:
[0012] According to the recognition result and the preset division rule, the target monitoring area is divided into at least one recognition area;
[0013] Acquire a monitoring target in the identification area, and determine a behavior of the monitoring target in the identification area according to the identification result;
[0014] Obtaining the authority of the monitoring target in the identification area, and determining whether the behavior of the monitoring target matches the authority of the monitoring target;
[0015] When the behavior of the monitoring target does not match the authority of the monitoring target, the monitoring target is regarded as an abnormal target.
[0016] By adopting the above technical solution, in order to determine whether the monitored target is an abnormal target, the target monitoring area is first divided into at least one identification area according to the identification result and the preset division rule, and then the monitored target in the identification area is obtained, and the behavior of the monitored target in the identification area is determined according to the identification result, and then the authority of the monitored target in the identification area is obtained, and it is determined whether the behavior of the monitored target matches the authority of the monitored target. When the behavior of the monitored target does not match the authority of the monitored target, the monitored target is regarded as an abnormal target.
[0017] Optionally, the step of performing an abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data includes:
[0018] Performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target;
[0019] Extracting environmental features of the target monitoring area from the image data to obtain environmental data of the target monitoring area;
[0020] A correlation analysis is performed on the environmental data and the abnormal behavior data to obtain abnormal analysis data.
[0021] By adopting the above technical solution, in order to obtain abnormal analysis data, firstly, abnormal behavior analysis is performed on the abnormal target according to the image data to obtain the abnormal behavior data of the abnormal target, and then the environmental characteristics of the target monitoring area are extracted from the image data to obtain the environmental data of the target monitoring area, and then the correlation analysis is performed on the environmental data and the abnormal behavior data to obtain the abnormal analysis data. Through the abnormal analysis data, the manager can effectively understand the abnormal situation in the target monitoring area so as to make effective responses in time.
[0022] Optionally, the step of performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target includes: the abnormal target is an abnormal vehicle;
[0023] Extracting abnormal features of the abnormal vehicle according to the image data to obtain abnormal feature data; the abnormal feature data includes the moving track, moving posture, speed and acceleration of the abnormal vehicle;
[0024] Performing behavior pattern recognition on the abnormal vehicle according to the abnormal feature data to obtain an abnormal behavior pattern of the abnormal vehicle;
[0025] Comparing and analyzing the abnormal behavior pattern of the abnormal vehicle with a preset normal behavior pattern to obtain an abnormal event type;
[0026] Abnormal behavior data is generated according to the abnormal feature data, the abnormal behavior pattern, and the abnormal event type.
[0027] By adopting the above technical solution, in order to generate abnormal behavior data, firstly, abnormal features of the abnormal vehicle are extracted according to the image data to obtain abnormal feature data, and the abnormal feature data includes the moving trajectory, moving posture, speed and acceleration of the abnormal vehicle. Then, the behavior pattern of the abnormal vehicle is identified according to the abnormal feature data to obtain the abnormal behavior pattern of the abnormal vehicle. Then, the abnormal behavior pattern of the abnormal vehicle is compared and analyzed with the preset normal behavior pattern to obtain the abnormal event type. Then, the abnormal behavior data is generated according to the abnormal feature data, the abnormal behavior pattern and the abnormal event type.
[0028] Optionally, after the step of performing risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data, the step further includes:
[0029] Acquire the current position of the abnormal target in the target monitoring area according to the image data;
[0030] Determine the risk level of each identified area according to the current position of the abnormal target and the risk analysis data of the target monitoring area;
[0031] The warning information corresponding to each identification area is generated respectively according to the risk level of each identification area.
[0032] By adopting the above technical solution, in order to issue an early warning in a timely manner, the current position of the abnormal target in the target monitoring area is first obtained based on the image data, and then the risk level of each identification area is determined based on the current position of the abnormal target and the risk analysis data of the target monitoring area. Then, according to the risk level of each identification area, early warning information corresponding to each identification area is generated respectively, so that relevant personnel in the target monitoring area can respond or evacuate in time.
[0033] Optionally, in the process of acquiring the image data of the target monitoring area, the method further includes:
[0034] Acquire the ambient brightness of the target monitoring area according to the image data;
[0035] Calculating optimal shooting parameters of a camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target;
[0036] The camera adjustment information is generated according to the optimal shooting parameter to adjust the current shooting parameter of the camera device to the optimal shooting parameter.
[0037] By adopting the above-mentioned technical scheme, in order to enable the camera device to capture clear image data or pictures, the ambient brightness of the target monitoring area is first obtained according to the image data, and then the optimal shooting parameters of the camera device are calculated according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target, and then the camera adjustment information is generated according to the optimal shooting parameters to adjust the current shooting parameters of the camera device to the optimal shooting parameters. The image data or pictures captured by the camera device according to the optimal shooting parameters are clearer than the image data or pictures captured by the previous shooting parameters, which effectively ensures the quality and recognition accuracy of the image data or pictures.
[0038] Optionally, the calculating of the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target specifically includes: the optimal shooting parameters include optimal exposure time, optimal focal length and optimal shutter speed; the abnormal behavior data also includes the current speed of the abnormal target;
[0039] Calculating the optimal exposure time of the camera device according to the ambient brightness; the ambient brightness is the current brightness of the target monitoring area;
[0040] The optimal focal length and the optimal shutter speed of the camera are calculated according to the current speed of the abnormal target.
[0041] By adopting the above technical solution, the optimal shooting parameters include the optimal exposure time, the optimal focal length and the optimal shutter speed, and the abnormal behavior data also includes the current speed of the abnormal target; the optimal exposure time of the camera device is calculated according to the ambient brightness; the ambient brightness is the current brightness of the target monitoring area, and the optimal focal length and the optimal shutter speed of the camera device are calculated according to the current speed of the abnormal target, thereby calculating the optimal exposure time, optimal focal length and optimal shutter speed of the camera device respectively.
[0042] In a second aspect, the present application also provides a camera device, which adopts the following technical solution:
[0043] A camera device, comprising:
[0044] The image acquisition module collects image data of the target monitoring area in real time through the camera device, and recognizes it to obtain the corresponding recognition result. In practical applications, a variety of image recognition technologies can be used, such as face recognition, vehicle recognition, object recognition, etc., to improve the accuracy and comprehensiveness of recognition;
[0045] The abnormal target determination module divides the target monitoring area into at least one identification area according to the identification results and the preset division rules, obtains the monitoring target and its behavior and authority in the identification area, and regards it as an abnormal target when the behavior of the monitoring target does not match the authority. In order to improve the accuracy of abnormal target determination, a comprehensive judgment can be made based on multiple factors, such as the target's moving speed, direction, trajectory, etc. The abnormal target determination module can use a variety of algorithms and technologies, such as target detection, tracking, classification, etc., to improve the accuracy of abnormal target determination
[0046] The abnormal analysis module performs abnormal behavior analysis on abnormal targets to obtain abnormal behavior data; extracts environmental features of the target monitoring area from image data to obtain environmental data; and performs correlation analysis on environmental data and abnormal behavior data to obtain abnormal analysis data. In the abnormal analysis process, a variety of data analysis methods can be used, such as statistical analysis, machine learning, deep learning, etc., to improve the accuracy and efficiency of the analysis.
[0047] The risk analysis module performs risk analysis on abnormal targets based on abnormal analysis data and image data to obtain risk analysis data. Risk analysis can consider multiple factors, such as the type, quantity, behavioral characteristics, environmental factors, etc. of abnormal targets, and adopt multiple risk assessment models and algorithms, such as risk matrix, hierarchical analysis method, etc. to assess the risk level of the target monitoring area.
[0048] Risk warning: The current position of the abnormal target in the target monitoring area is obtained based on the image data, and the risk level of each identification area is determined in combination with the risk analysis data of the target monitoring area, and corresponding warning information is generated according to the risk level. The warning information can be sent to relevant personnel in a variety of ways, such as SMS, email, voice prompts, etc., to ensure that relevant personnel can take timely measures.
[0049] By adopting the above technical solution, the image acquisition module is used to acquire the image data of the target monitoring area and identify the image data to obtain the corresponding identification result. The image acquisition module can adopt a variety of camera devices, such as cameras, video cameras, etc., to meet different application requirements; the abnormal target determination module is used to determine the abnormal target in the image data according to the identification result. The abnormal target determination module can adopt a variety of algorithms and technologies, such as target detection, tracking, classification, etc., to improve the accuracy of determining the abnormal target; the abnormal analysis module is used to perform abnormal analysis on the abnormal target according to the image data to obtain abnormal analysis data. The abnormal analysis module can adopt a variety of data analysis methods, such as statistical analysis, machine learning, deep learning, etc., to improve the accuracy and efficiency of the analysis; the risk analysis module is used to perform risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data. The risk analysis module can adopt a variety of risk assessment models and algorithms, such as risk matrix, hierarchical analysis method, etc., to assess the risk level of the target monitoring area.
[0050] The device also includes a shooting parameter adjustment module, and the shooting parameter adjustment module includes:
[0051] An ambient brightness acquisition module, used to acquire the ambient brightness of the target monitoring area according to the image data;
[0052] A shooting parameter adjustment module, used for calculating the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target;
[0053] The camera adjustment information generation module is used to generate camera adjustment information according to the optimal shooting parameters to adjust the current shooting parameters of the camera device to the optimal shooting parameters; during the shooting parameter adjustment process, automatic adjustment or manual adjustment can be adopted to meet different application requirements.
[0054] By adopting the above technical solution, the shooting parameter adjustment module includes an ambient brightness acquisition module, a shooting parameter adjustment module and a camera adjustment information generation module. The shooting parameter adjustment module is used to calculate the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target, and adjust the current shooting parameters to the optimal shooting parameters. The shooting parameter adjustment module can adopt automatic adjustment or manual adjustment to meet different application requirements.
[0055] In a third aspect, the present application also provides a computer device, which adopts the following technical solution:
[0056] A computer device comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method described in the first aspect when executing the computer program.
[0057] In summary, the present application includes at least the following beneficial technical effects: acquiring image data of the target monitoring area, and identifying the image data to obtain corresponding identification results; determining abnormal targets in the image data based on the identification results; performing abnormal analysis on abnormal targets based on the image data to obtain abnormal analysis data; performing risk analysis on abnormal targets based on the abnormal analysis data and the image data to obtain risk analysis data. This method saves time and effort, improves the monitoring intensity and efficiency of the monitoring area, reduces the probability of false alarms of risks and safety hazards in the monitoring area, and improves the accuracy of monitoring. At the same time, the quality of the image data and the recognition accuracy are guaranteed by adaptively adjusting the shooting parameters of the camera device. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present application.
[0059] Figure 2 It is a schematic diagram of the structure of the system of the embodiment of the present application.
[0060] Figure 3 It is a structural block diagram of the computer device of the present application. DETAILED DESCRIPTION
[0061] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-3 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0062] The embodiment of the present application discloses a method for processing image data.
[0063] Reference Figure 1 , an image data processing method, comprising the following steps:
[0064] Step S11, acquiring image data of the target monitoring area, and identifying the image data to obtain corresponding identification results.
[0065] It should be noted that, in the present application, image data of the target monitoring area is collected in real time by a camera device, such as a high-resolution camera.
[0066] Step S12: determining abnormal targets in the image data according to the recognition results.
[0067] It should be noted that in step S11 and step S12, the image data of the target monitoring area is processed using a deep learning algorithm and a machine learning algorithm to identify abnormal targets in the image data of the target monitoring area, such as people, vehicles, animals, etc. in the target monitoring area.
[0068] Step S13, performing an abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data.
[0069] It should be noted that by tracking and analyzing the behaviors of these abnormal targets, abnormal analysis data is obtained, and the abnormal analysis data includes abnormal event types, such as illegal intrusion, abnormal stay, etc.
[0070] Step S14, performing risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data.
[0071] It should be noted that in step S14, data mining technology and machine learning technology are used to perform big data analysis on the abnormal analysis data and image data to obtain risk analysis data; through the risk analysis data, managers can discover potential risks and safety hazards, thereby providing managers with important decision-making basis and helping managers to effectively understand and respond to safety issues in the target monitoring area.
[0072] It should be further explained that after step S14, the image data, abnormality analysis data and risk analysis data are uploaded to the remote monitoring center. The manager can view the image data of the target monitoring area in real time through remote access, and understand the risks and safety hazards in the target monitoring area through the abnormality analysis data and risk analysis data, so as to respond in time.
[0073] In the above implementation, the image data of the target monitoring area is obtained, and the image data is identified to obtain the corresponding identification result; based on the identification result, the abnormal target in the image data is determined; based on the image data, an abnormal analysis is performed on the abnormal target to obtain abnormal analysis data; based on the abnormal analysis data and the image data, a risk analysis is performed on the abnormal target to obtain risk analysis data. This method saves more time and effort, improves the monitoring intensity and efficiency of the monitoring area, reduces the probability of false reporting of risks and safety hazards in the monitoring area, and improves the accuracy of monitoring.
[0074] As a further implementation of the image data processing method, the step of determining an abnormal target in the image data according to the recognition result includes:
[0075] Step S21, dividing the target monitoring area into at least one identification area according to the identification result and the preset division rule.
[0076] It should be noted that the preset division rules are usually set according to the spatial distribution and functions of the buildings in the target monitoring area.
[0077] Step S22, obtaining the monitoring target in the identification area, and determining the behavior of the monitoring target in the identification area according to the identification result.
[0078] Step S23, obtaining the authority of the monitoring target in the identification area, and determining whether the behavior of the monitoring target matches the authority of the monitoring target.
[0079] Step S24: when the behavior of the monitoring target does not match the authority of the monitoring target, the monitoring target is regarded as an abnormal target.
[0080] In the above embodiment, in order to determine whether the monitored target is an abnormal target, the target monitoring area is first divided into at least one identification area according to the identification result and the preset division rule, and then the monitored target in the identification area is obtained, and the behavior of the monitored target in the identification area is determined according to the identification result, and then the authority of the monitored target in the identification area is obtained, and it is determined whether the behavior of the monitored target matches the authority of the monitored target. When the behavior of the monitored target does not match the authority of the monitored target, the monitored target is treated as an abnormal target.
[0081] As a further implementation of the image data processing method, the step of performing an abnormality analysis on an abnormal target according to the image data to obtain abnormality analysis data includes:
[0082] Step S31, performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target.
[0083] It should be noted that the abnormal behavior data of the abnormal target includes the specific behavior of the abnormal target, such as walking, running, gathering, etc. of the intruder.
[0084] Step S32: extracting environmental features of the target monitoring area from the image data to obtain environmental data of the target monitoring area.
[0085] Step S33, performing correlation analysis on the environment data and the abnormal behavior data to obtain abnormal analysis data.
[0086] In the above-mentioned embodiment, in order to obtain abnormal analysis data, the abnormal behavior analysis of the abnormal target is first performed based on the image data to obtain the abnormal behavior data of the abnormal target, and then the environmental characteristics of the target monitoring area are extracted from the image data to obtain the environmental data of the target monitoring area. Then, the correlation analysis is performed on the environmental data and the abnormal behavior data to obtain the abnormal analysis data. Through the abnormal analysis data, the manager can effectively understand the abnormal situation occurring in the target monitoring area so as to make effective responses in a timely manner.
[0087] As a further implementation of the image data processing method, the step of performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target includes: the abnormal target is an abnormal vehicle;
[0088] Step S41, extracting abnormal features of abnormal vehicles according to image data to obtain abnormal feature data.
[0089] Among them, the abnormal feature data includes the movement trajectory, movement posture, speed and acceleration of the abnormal vehicle.
[0090] Step S42, identifying the behavior pattern of the abnormal vehicle according to the abnormal feature data to obtain the abnormal behavior pattern of the abnormal vehicle.
[0091] It should be noted that abnormal behavior patterns include abnormal vehicles intruding out of control, abnormal vehicles intruding with a purpose, and other behavior patterns.
[0092] Step S43, comparing and analyzing the abnormal behavior pattern of the abnormal vehicle with the preset normal behavior pattern to obtain the abnormal event type.
[0093] It should be noted that abnormal event types include break-ins, robberies, attacks, etc.
[0094] Step S44, generating abnormal behavior data according to the abnormal feature data, abnormal behavior pattern, and abnormal event type.
[0095] In the above embodiment, in order to generate abnormal behavior data, abnormal features of the abnormal vehicle are first extracted based on the image data to obtain abnormal feature data, which includes the moving trajectory, moving posture, speed and acceleration of the abnormal vehicle. Then, the behavior pattern of the abnormal vehicle is identified based on the abnormal feature data to obtain the abnormal behavior pattern of the abnormal vehicle. Then, the abnormal behavior pattern of the abnormal vehicle is compared and analyzed with the preset normal behavior pattern to obtain the abnormal event type. Then, abnormal behavior data is generated based on the abnormal feature data, the abnormal behavior pattern and the abnormal event type.
[0096] As a further implementation of the image data processing method, after the step of performing risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain the risk analysis data, the method further includes:
[0097] Step S51, obtaining the current position of the abnormal target in the target monitoring area according to the image data.
[0098] Step S52, determining the risk level of each identification area according to the current position of the abnormal target and the risk analysis data of the target monitoring area.
[0099] Step S53: generating warning information corresponding to each identification area according to the risk level of each identification area.
[0100] It is understandable that the content of the warning information is usually different for identification areas of different risk levels. For example, for a certain identification area, the corresponding risk levels are A, B, and C from high to low. For identification area X1 with risk level A, the warning information is "Please evacuate personnel in area X1 immediately", and the warning indicator lights in area X1 are all red; for identification area X2 with risk level B, the warning information is "Please evacuate personnel in area X2 within half an hour", and the warning indicator lights in area X1 are all yellow; for identification area X3 with risk level C, the warning information is "Please evacuate personnel in area X3 within 1 hour", and the warning indicator lights in area X1 are all green.
[0101] In the above embodiment, in order to issue an early warning in time, the current position of the abnormal target in the target monitoring area is first obtained based on the image data, and then the risk level of each identification area is determined based on the current position of the abnormal target and the risk analysis data of the target monitoring area. Then, early warning information corresponding to each identification area is generated according to the risk level of each identification area, so that relevant personnel in the target monitoring area can respond or evacuate in time.
[0102] As a further implementation of the image data processing method, in the process of real-time acquisition of image data of the target monitoring area, the image data processing method further includes:
[0103] Step S61, obtaining the ambient brightness of the target monitoring area according to the image data.
[0104] Step S62, calculating the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target.
[0105] Step S63: Generate camera adjustment information according to the optimal shooting parameters to adjust the current shooting parameters of the camera device to the optimal shooting parameters.
[0106] In the above-mentioned embodiment, in order to enable the camera device to capture clear image data or pictures, the ambient brightness of the target monitoring area is first obtained based on the image data, and then the optimal shooting parameters of the camera device are calculated based on the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target. Then, the camera adjustment information is generated based on the optimal shooting parameters to adjust the current shooting parameters of the camera device to the optimal shooting parameters. The image data or pictures captured by the camera device according to the optimal shooting parameters are clearer than the image data or pictures captured by the previous shooting parameters, which effectively ensures the quality and recognition accuracy of the image data or pictures.
[0107] As a further implementation of the image data processing method, the optimal shooting parameters of the camera device are calculated according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target, which specifically includes:
[0108] The optimal shooting parameters include the optimal exposure time, optimal focal length and optimal shutter speed; the abnormal behavior data also includes the current speed of the abnormal target;
[0109] Step S71, calculating the optimal exposure time of the camera device according to the ambient brightness.
[0110] The ambient brightness is the current brightness of the target monitoring area.
[0111] Step S72, calculating the optimal focal length and the optimal shutter speed of the camera device according to the current speed of the abnormal target.
[0112] In the above embodiment, the optimal shooting parameters include the optimal exposure time, the optimal focal length and the optimal shutter speed, and the abnormal behavior data also includes the current speed of the abnormal target; the optimal exposure time of the camera device is calculated according to the ambient brightness; the ambient brightness is the current brightness of the target monitoring area, and the optimal focal length and the optimal shutter speed of the camera device are calculated according to the current speed of the abnormal target, thereby calculating the optimal exposure time, optimal focal length and optimal shutter speed of the camera device respectively.
[0113] The embodiment of the present application also discloses a camera device.
[0114] refer to Figure 2 , a camera device, comprising:
[0115] An image acquisition module is used to acquire image data of a target monitoring area and identify the image data to obtain a corresponding identification result;
[0116] An abnormal target determination module, used to determine abnormal targets in the image data according to the recognition result;
[0117] An abnormality analysis module, used for performing abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data;
[0118] The risk analysis module is used to perform risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data.
[0119] The device also includes a shooting parameter adjustment module, and the shooting parameter adjustment module includes:
[0120] An ambient brightness acquisition module is used to acquire the ambient brightness of the target monitoring area according to the image data;
[0121] A shooting parameter adjustment module is used to calculate the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target;
[0122] The camera adjustment information generating module is used to generate the camera adjustment information according to the optimal shooting parameters, so as to adjust the current shooting parameters of the camera device to the optimal shooting parameters.
[0123] It should be noted that the camera device of this embodiment can be a camera; the camera device of this embodiment realizes efficient identification, tracking and behavior analysis of targets in the target monitoring area by integrating advanced artificial intelligence and big data analysis technology, thereby being able to provide managers with accurate decision-making basis. At the same time, it has functions such as adaptive adjustment of shooting parameters and remote monitoring management, and can adapt to various complex environmental conditions to ensure monitoring effects. In addition, the function of remote monitoring management also enables managers to monitor and manage the target monitoring area anytime and anywhere, thereby improving work efficiency. Therefore, the camera device of the present invention has broad application prospects in the fields of security monitoring, urban management, traffic supervision, etc. It can be used for monitoring public places such as shopping malls, schools, hospitals, etc., and can also be used for the supervision of major traffic routes such as highways and railways, and can also be used in important fields such as urban security.
[0124] It should be further explained that in a dimly lit environment, the camera device will automatically increase the exposure time to increase the image brightness; when the target moves quickly, the camera device will adjust the camera's focal length and shutter speed to ensure a clear image.
[0125] The camera device of the present invention can implement any one of the above-mentioned image data processing methods, and the specific working process of the camera device of the present invention can refer to the corresponding process in the above-mentioned image data processing method.
[0126] The embodiment of the present application also discloses a computer device.
[0127] refer to Figure 3 A computer device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, any one of the above-mentioned image data processing methods is implemented.
[0128] The memory is connected to the camera, and the processor includes a CPU and an NPU.
[0129] In the above embodiments disclosed in the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0130] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.
Claims
1. A method for processing image data, characterized in that: include: Acquire image data of the target monitoring area, and identify the image data to obtain corresponding identification results; Determining abnormal targets in the image data according to the recognition result; Performing an abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data; A risk analysis is performed on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data.
2. The image data processing method according to claim 1, characterized in that: The step of determining the abnormal target in the image data according to the recognition result comprises: According to the recognition result and the preset division rule, the target monitoring area is divided into at least one recognition area; Acquire a monitoring target in the identification area, and determine a behavior of the monitoring target in the identification area according to the identification result; Obtaining the authority of the monitoring target in the identification area, and determining whether the behavior of the monitoring target matches the authority of the monitoring target; When the behavior of the monitoring target does not match the authority of the monitoring target, the monitoring target is regarded as an abnormal target.
3. The image data processing method according to claim 2, characterized in that: The step of performing an abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data comprises: Performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target; Extracting environmental features of the target monitoring area from the image data to obtain environmental data of the target monitoring area; A correlation analysis is performed on the environmental data and the abnormal behavior data to obtain abnormal analysis data.
4. The image data processing method according to claim 3, characterized in that: The step of performing abnormal behavior analysis on the abnormal target according to the image data to obtain abnormal behavior data of the abnormal target includes: the abnormal target is an abnormal vehicle; Extracting abnormal features of the abnormal vehicle according to the image data to obtain abnormal feature data; the abnormal feature data includes the moving track, moving posture, speed and acceleration of the abnormal vehicle; Performing behavior pattern recognition on the abnormal vehicle according to the abnormal feature data to obtain an abnormal behavior pattern of the abnormal vehicle; Comparing and analyzing the abnormal behavior pattern of the abnormal vehicle with a preset normal behavior pattern to obtain an abnormal event type; Abnormal behavior data is generated according to the abnormal feature data, the abnormal behavior pattern, and the abnormal event type.
5. The image data processing method according to claim 2, characterized in that: After the step of performing risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data, the method further includes: Acquire the current position of the abnormal target in the target monitoring area according to the image data; Determine the risk level of each identified area according to the current position of the abnormal target and the risk analysis data of the target monitoring area; The warning information corresponding to each identification area is generated respectively according to the risk level of each identification area.
6. The image data processing method according to claim 3, characterized in that: In the process of acquiring the image data of the target monitoring area, the method further includes: Acquire the ambient brightness of the target monitoring area according to the image data; Calculating optimal shooting parameters of a camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target; The camera adjustment information is generated according to the optimal shooting parameter to adjust the current shooting parameter of the camera device to the optimal shooting parameter.
7. The image data processing method according to claim 6, characterized in that: The calculating of the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target specifically includes: the optimal shooting parameters include optimal exposure time, optimal focal length and optimal shutter speed; the abnormal behavior data also includes the current speed of the abnormal target; Calculating the optimal exposure time of the camera device according to the ambient brightness; the ambient brightness is the current brightness of the target monitoring area; The optimal focal length and the optimal shutter speed of the camera are calculated according to the current speed of the abnormal target.
8. A camera device, characterized in that: include: An image acquisition module is used to acquire image data of a target monitoring area and identify the image data to obtain a corresponding identification result; An abnormal target determination module, used to determine abnormal targets in the image data according to the recognition result; An abnormality analysis module, used for performing abnormality analysis on the abnormal target according to the image data to obtain abnormality analysis data; The risk analysis module is used to perform risk analysis on the abnormal target according to the abnormal analysis data and the image data to obtain risk analysis data.
9. The camera device according to claim 8, characterized in that: The device also includes a shooting parameter adjustment module, and the shooting parameter adjustment module includes: An ambient brightness acquisition module, used to acquire the ambient brightness of the target monitoring area according to the image data; A shooting parameter adjustment module, used for calculating the optimal shooting parameters of the camera device according to the ambient brightness of the target monitoring area and the abnormal behavior data of the abnormal target; The camera adjustment information generating module is used to generate the camera adjustment information according to the optimal shooting parameters, so as to adjust the current shooting parameters of the camera device to the optimal shooting parameters.
10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.
Citation Information
Patent Citations
Device and method for monitoring abnormal behavior of motor vehicle on expressway
CN104506804A
Shutter speed acquisition method and device
CN105959587A
Illegal behavior detection method and device
CN115019400A
Video monitoring management method, system and equipment for smart office and medium
CN118155357A
Video monitoring system and method
US20140043480A1
