A detection method for monitoring an area, a monitoring device and a storage medium

Abstract

The embodiment of the application discloses a kind of detection method and monitoring device of monitoring area, the detection method of monitoring area includes: image collected by monitoring device is carried out virtual focus detection;When detecting that the image collected exists virtual focus, according to the mode pre-set in the monitoring device, judge whether to report monitoring area exception.Through the scheme of the present application, the execution process of monitoring area exception reporting is triggered by detecting the situation of virtual focus, and whether to report exception is judged according to the pre-set mode, so that the processing flow under different conditions can be flexibly set, not only can effectively detect monitoring area exception condition, but also can be appropriately handled according to the requirement of exception condition.

Description

Technical Field

[0001] The embodiments of this application relate to, but are not limited to, the field of detection, and particularly to a detection method, monitoring equipment, and storage medium for a monitored area. Background Technology

[0002] As surveillance equipment, cameras need to maintain constant monitoring of the monitored area. In practical applications, obstacles may arise that cause abnormal monitoring images. For example, raindrops falling on a passport or lens, foliage growth, spider webs, and other uncontrollable situations can prevent the monitoring footage from providing a clear image or obstruct the monitored area, thus compromising the effectiveness of the monitoring.

[0003] In some technologies, when there are obstructions or other anomalies between the area monitored by the surveillance equipment and the camera lens, manual confirmation is required, which consumes a significant amount of manpower. These obstructions include, but are not limited to, leaves, rain stains, and cobwebs. Furthermore, in remote areas, there may still be cases where obstructions go undetected, resulting in the loss of monitored scenes. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] This disclosure provides a method and equipment for detecting monitoring areas. It cleverly triggers the execution process of abnormal reporting of monitoring areas by detecting out-of-focus conditions. By determining whether to report abnormalities based on preset modes, the processing flow can be flexibly set for different situations. It can not only effectively detect abnormalities in the monitoring area, but also handle abnormalities appropriately according to needs.

[0006] This disclosure provides a method for detecting a monitored area, including:

[0007] Defocus detection is performed on images acquired by monitoring equipment;

[0008] When a defocused image is detected in the acquired image, the monitoring device determines whether to report an anomaly in the monitored area according to a preset mode.

[0009] In one exemplary embodiment, determining whether to report an anomaly in the monitored area according to a preset mode in the monitoring device includes:

[0010] When the preset mode is the quality priority mode, the images collected by the monitoring device within the preset time range are compared with the original images collected by the monitoring device to obtain the comparison results.

[0011] Based on the comparison results, determine whether it is necessary to report;

[0012] When reporting is required, any anomalies in the monitored area will be reported to the designated platform.

[0013] In one exemplary embodiment, the original image is obtained in the following manner:

[0014] Start the monitoring equipment;

[0015] Once the monitoring device is initialized, it acquires an image when predetermined conditions are met and uses that image as the original image.

[0016] In one exemplary embodiment, comparing the acquired image with the original image acquired by the monitoring device to obtain the comparison result includes:

[0017] The macroblocks of the acquired image are encoded sequentially, and pre-set weight values ​​are assigned to each macroblock.

[0018] The acquired images are compared with the original images one by one according to macroblocks to obtain the difference of each macroblock;

[0019] Divide the difference of each macroblock by the corresponding macroblock data in the original image to obtain the percentage value of each macroblock;

[0020] The percentage value of each macroblock is multiplied by the weight value corresponding to that macroblock, and the sum of the products is used as the comparison result.

[0021] In one exemplary embodiment, determining whether the monitoring area of ​​the monitoring device is normal based on the comparison result includes:

[0022] When the comparison result exceeds a preset threshold range, it is determined that the monitoring area of ​​the monitoring device is abnormal.

[0023] When the comparison result is within the preset threshold range, it is determined that the monitoring area of ​​the monitoring device is normal.

[0024] In one exemplary embodiment, it further includes:

[0025] When it is detected that the acquired image is not out of focus, a new image is acquired according to a preset period and used to update the original image.

[0026] In one exemplary embodiment, detecting that the acquired image is out of focus includes:

[0027] Collect n images at a preset time interval;

[0028] If the data of out-of-focus macroblocks in the n acquired images are confirmed to be fixed, it is determined that the acquired images are out of focus.

[0029] In one exemplary embodiment, determining whether to report an anomaly in the monitored area according to a preset mode in the monitoring device includes:

[0030] When the preset mode is event-priority mode, abnormalities in the monitored area are directly reported to the designated platform.

[0031] This disclosure also provides a monitoring device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the program, it implements the detection method for the monitoring area described in any of the above embodiments.

[0032] This disclosure also provides a computer-readable storage medium storing computer-executable instructions for performing the detection method for the monitoring area described in any of the above embodiments.

[0033] This disclosure provides a method and device for detecting a monitored area. The method includes: detecting out-of-focus images acquired by the monitoring device; and when out-of-focus images are detected, determining whether to report an anomaly in the monitored area according to a preset mode in the monitoring device. This disclosure cleverly triggers the reporting process for anomalies in the monitored area by detecting out-of-focus images. By determining whether to report anomalies according to a preset mode, the processing flow can be flexibly set for different situations. This not only effectively detects anomalies in the monitored area but also allows for appropriate handling of anomalies as needed.

[0034] After reading and understanding the accompanying diagrams and detailed descriptions, the other aspects can be understood. Attached Figure Description

[0035] Figure 1 This is a flowchart of the detection method for the monitoring area according to an embodiment of this application;

[0036] Figure 2 This is a schematic diagram of the monitoring device according to an embodiment of this application;

[0037] Figure 3 Here is a flowchart of the detection method in some exemplary embodiments;

[0038] Figure 4 This is a flowchart illustrating the acquisition of raw images in some exemplary embodiments;

[0039] Figure 5 This is a flowchart of a detection method in some exemplary embodiments. Detailed Implementation

[0040] The embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments of this application and the features therein can be arbitrarily combined with each other.

[0041] The steps illustrated in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in a different order than that shown here.

[0042] Figure 1 Here is a flowchart of the detection method for the monitored area disclosed herein, as follows: Figure 1 As shown, steps 100-101 are included:

[0043] Step 100. Perform defocus detection on the images acquired by the monitoring equipment;

[0044] Step 101. When a defocused image is detected in the acquired image, determine whether to report an anomaly in the monitored area according to the preset mode in the monitoring device.

[0045] In step 100, the image acquired by the monitoring equipment is subjected to defocus detection.

[0046] In one exemplary embodiment, the monitoring device may be a camera or other image acquisition device. The technique for detecting out-of-focus areas of the image can employ any existing technology, and this document does not specifically limit it.

[0047] In one exemplary embodiment, detecting that the acquired image is out of focus includes: acquiring n images at a preset time interval; and determining that the acquired image is out of focus when it is confirmed that the out-of-focus macroblock data in the acquired n images is fixed.

[0048] In some exemplary embodiments, during the operation of the monitoring equipment, when a defocused image is detected, n images are acquired at preset time intervals, assuming the monitoring equipment's operating data is relatively stable, to determine whether the acquired image is defocused. The number of images acquired, n, can be adjusted according to user needs. A larger value of n results in a smaller judgment error, but also reduces real-time performance. Considering both the accuracy and real-time performance of image defocus determination, the value of n can be set to 3. In this embodiment, when the monitoring equipment's operating data is relatively stable, macroblock monitoring is initiated. If the defocused macroblock is consistently present and relatively fixed, it can be determined that the image acquired by the monitoring equipment is defocused. The condition of relatively stable monitoring equipment operating data can be one with few interference factors.

[0049] In one exemplary embodiment, the relative stability of the monitoring equipment's operating data can be determined by the following method: performing macroblock data analysis on the images acquired by the monitoring equipment. The more macroblocks are segmented, the finer the details, and the higher the accuracy of subsequent data analysis results. Image macroblock data analysis can be performed by detecting and monitoring several dimensions of image macroblocks, including sharpness, brightness, and chroma. The overall edge condition and pixel condition of the image macroblock are reflected by the correlation values ​​of these dimensions. If the overall edge condition and pixel condition change, i.e., the correlation values ​​of these dimensions fluctuate according to environmental changes, the monitoring equipment's operating data is considered unstable. If, under relatively static conditions, the changes in the correlation values ​​of these dimensions are all within a preset numerical fluctuation threshold range, the monitoring equipment's operating data is considered relatively stable. The monitoring of macroblock data involved in this application can be seen as the detection of the monitoring equipment's environment. By detecting the stability of the monitoring equipment's operating data as described above, interference from moving objects in the image can be eliminated, and a stable environment or scene can be determined.

[0050] In one exemplary embodiment, in step 101, when out-of-focus images are detected in the acquired image, it is determined whether to report an anomaly in the monitored area according to a preset mode in the monitoring device. For example, if the acquired image contains leaves, resulting in out-of-focus images, the corresponding operation for an anomaly in the monitored area can be triggered upon confirmation of out-of-focus images. In this embodiment, the preset modes in the monitoring device include: event-priority mode and quality-priority mode. Other embodiments may include different modes, each corresponding to different operations, which can be set as needed.

[0051] In one implementation of this embodiment, a mode, either an event-priority mode or a quality-priority mode, can be pre-set in the monitoring device. When a defocused image is detected in the acquired image, the event-priority mode or the quality-priority mode can be selected and executed according to the set mode. Different modes can be set in different monitoring devices, and the mode can be changed.

[0052] In another implementation of this embodiment, an event-priority mode or a quality-priority mode can be selected based on a judgment criterion. For example, when a defocused image is detected, the monitoring device can determine whether to select an event-priority mode or a quality-priority mode based on the judgment criterion, and then perform the corresponding operation according to the selected mode. For example, the judgment criterion may be, but is not limited to, the value of a predetermined flag bit or register in the monitoring device. For instance, if the value is a first value, it is determined to be an event-priority mode, and if it is a second value, it is determined to be a quality-priority mode. Another example is whether a parameter meets a preset condition. For instance, if the current time is between 6 AM and 10 PM (i.e., the time parameter is within a preset range), it is determined to be an event-priority mode; if the current time is other times, it is determined to be a quality-priority mode. Different judgment criteria can be preset in different monitoring devices, and these judgment criteria can be changed.

[0053] In one exemplary embodiment, determining whether to report an anomaly in the monitoring area according to a preset mode in the monitoring device includes: comparing the images collected by the monitoring device within a preset time range with the original images collected by the monitoring device to obtain a comparison result; determining whether the monitoring area of ​​the monitoring device is normal based on the comparison result; and reporting to a predetermined platform when the monitoring area is abnormal.

[0054] In one exemplary embodiment, determining whether to report an anomaly in the monitored area according to a preset mode in the monitoring device includes: when the preset mode is event-priority mode, directly reporting the anomaly in the monitored area to a predetermined platform. In this embodiment, when a defocused image is detected in the acquired image, selecting event-priority mode will report the anomaly in the monitored area to the predetermined platform. In event-priority mode, directly reporting the anomaly in the monitored area to the predetermined platform ensures timely reporting and guarantees efficiency.

[0055] In one exemplary embodiment, the original image is acquired by: starting the monitoring device; after the monitoring device has initialized, acquiring an image when predetermined conditions are met, and using that image as the original image. In this embodiment, the process of acquiring the original image includes: after the device is started, the first image saved is used as the original image.

[0056] In one exemplary embodiment, such as Figure 3 As shown, the process of acquiring the original image can be as follows: Under conditions of no environmental interference, the monitoring device is started; after the device starts, it is initialized, and after ensuring the monitoring device is stable, the first image is acquired and saved as the base image. In this embodiment, the initialization of the device can be considered as the monitoring device being stable. The specific technical features related to the stable debugging of the monitoring device are not limited here.

[0057] In one exemplary embodiment, comparing the acquired image with the original image acquired by the monitoring device to obtain the comparison result includes: sequentially encoding the macroblocks of the acquired image and assigning a pre-set weight value to each macroblock; comparing the acquired image with the original image one by one according to macroblocks to obtain the difference of each macroblock; dividing the difference of each macroblock by the corresponding macroblock data in the original image to obtain the percentage value of each macroblock; multiplying the percentage value of each macroblock by the weight value corresponding to the macroblock, and using the sum of the products as the comparison result.

[0058] In one exemplary embodiment, determining whether the monitoring area of ​​the monitoring device is normal based on the comparison result includes: determining that the monitoring area of ​​the monitoring device is abnormal when the comparison result exceeds a preset threshold range; and determining that the monitoring area of ​​the monitoring device is normal when the comparison result is within the preset threshold range. In this embodiment, a threshold range is preset, and the comparison result with the threshold is used to determine whether it affects the monitoring area. When the threshold range is exceeded, and the monitoring area is affected, an event is reported, and human intervention is notified. Through the occlusion recognition in this embodiment, by judging the difference fluctuation of macroblock data, some situations that do not affect monitoring are filtered out, improving the hit rate of actual application, thereby improving the efficiency of human resource utilization.

[0059] In one exemplary embodiment, when it is detected that the acquired image is not out of focus, a new image is acquired according to a preset period and used to update the original image.

[0060] This application embodiment triggers monitoring of the surveillance scene through defocus detection. By detecting defocus and comparing it with the original image, it confirms whether there are any factors affecting the surveillance scene, and notifies the monitor through an event reporting platform for investigation. This ensures the effectiveness of the surveillance scene and is compatible with small-scale obstructions that do not affect the monitoring effect, reducing the manpower required for monitoring the scene. In addition, iteratively updating the original image improves the adaptability of the surveillance scene, ensuring and identifying the actual surveillance scene.

[0061] Figure 2 This is a schematic diagram of the monitoring device structure disclosed herein. This disclosure also provides a monitoring device, including a memory and a processor; the memory 200 is used to store a program for the monitoring device; the processor 201 is used to read and execute the program for the monitoring device, and execute any one of the monitoring area detection methods in the above embodiments.

[0062] This disclosure also provides a computer-readable storage medium storing computer-executable instructions for performing any of the detection methods for monitoring areas in the above embodiments.

[0063] The above embodiments are illustrated below with four examples.

[0064] Example 1

[0065] A method for detecting a monitored area includes the following steps 401-403:

[0066] Step 401. Start the monitoring equipment and acquire raw images.

[0067] In this step, after the monitoring equipment is initialized, it acquires an image when predetermined conditions are met, and the first acquired image is used as the original image. The initialization of the monitoring equipment can be configured according to the environment and the equipment's own information; no specific limitations are imposed.

[0068] Step 402. Perform defocus detection on the images acquired by the monitoring equipment;

[0069] Step 403. When a defocused image is detected in the acquired image, determine whether to report an anomaly in the monitored area according to the preset mode in the monitoring device.

[0070] In this step, the preset modes in the monitoring device include: event-priority mode and quality-priority mode. Other embodiments may include different modes, each corresponding to different operations, which can be set as needed. In one implementation of this embodiment, a mode, either event-priority mode or quality-priority mode, can be preset in the monitoring device; when a defocused image is detected, either event-priority mode or quality-priority mode can be selected to be executed according to the preset mode. Different monitoring devices can be set with different modes, and these modes can be changed.

[0071] In this embodiment, the execution process of abnormal reporting in the monitoring area is cleverly triggered by detecting out-of-focus conditions. By determining whether to report abnormalities based on preset modes, the processing flow under different conditions can be flexibly set. This not only effectively detects abnormalities but also allows for appropriate handling of abnormalities as needed.

[0072] Example 2

[0073] A method for detecting a monitored area includes the following steps 501-503:

[0074] Step 501. Start the monitoring equipment and acquire raw images.

[0075] In this step, after the monitoring equipment is initialized, the first image is captured when the predetermined conditions are met, and this first image is used as the original image.

[0076] Step 502. Perform defocus detection on the images acquired by the monitoring equipment;

[0077] Step 503. When it is detected that the acquired image is not out of focus, acquire a new image and update the original image according to the preset period.

[0078] In this example, during actual operation, when the monitoring equipment is used to monitor certain scenarios that require special attention from users, if the captured image is not out of focus after a certain period of operation, it will periodically determine if the scene is out of focus and then recapture a new image to update the original image. This can cope with changes in the environment, reduce manual correction, and improve scene adaptability.

[0079] Example 3

[0080] A method for detecting a monitored area, such as Figure 4 As shown, this includes the following steps 601-608:

[0081] Step 601. Perform defocus detection on the images acquired by the monitoring equipment;

[0082] Step 602. When a defocused image is detected in the acquired image, trigger the corresponding operation for when an anomaly occurs in the monitored area;

[0083] Step 603. Acquire n images at preset time intervals; and perform real-time analysis on the macroblock data of the acquired images;

[0084] Step 604. Confirm whether the out-of-focus macroblock data exists in all n acquired images; if the out-of-focus macroblock data always exists, it is determined that the acquired image is out of focus, and jump to step 605; if the out-of-focus macroblock data does not exist, it is determined that the acquired image has a certain error and is not out of focus, and jump to step 608.

[0085] Step 605. Confirm whether it is event priority mode; if it is event priority mode, proceed to step 606; if it is quality priority mode, proceed to step 607.

[0086] Step 606. When switching to event priority mode, report the anomalies in the monitored area to the designated platform.

[0087] Step 607. Perform the corresponding operation in the quality priority mode;

[0088] Step 608. Execution complete.

[0089] In this example, when a defocused image is detected, the event priority mode is triggered, which can promptly report to the predetermined platform to notify human intervention, thus realizing a timely and effective detection method for the monitored area; and by distinguishing macroblocks and changes in sharpness within macroblocks, the stability of the scene is judged, thereby assisting in judging the validity of the results.

[0090] Example 4

[0091] A method for detecting a monitored area, such as Figure 5 As shown, this includes the following steps 701-708:

[0092] Step 701. Start the monitoring equipment; acquire raw images.

[0093] In this step, after the monitoring device is initialized, it acquires an image when predetermined conditions are met and uses that image as the original image.

[0094] Step 702. Perform a self-test on the monitoring equipment within a preset time and check the quality priority mode flag.

[0095] Step 703. When the quality priority mode flag is active, count the response macroblock data of the acquired image;

[0096] Step 704. When the relevant values ​​of the macroblock data are within the preset threshold range, the macroblock data is determined to be stable;

[0097] Step 705. Once the macroblock data has stabilized, acquire images within a preset time range;

[0098] In step 705, the preset time range can be set according to the user's needs. For example, it can be set to 2 a.m., which can reduce light source interference at different times of the day.

[0099] Step 706. Compare the acquired image data with the original image base acquired by the monitoring device;

[0100] In step 706, the acquired image is compared with the original image acquired by the monitoring device. The process includes:

[0101] Step 7061. Encode the macroblocks of the acquired image sequentially and assign the preset weight values ​​to each macroblock;

[0102] Step 7062. Compare the acquired image data with the original image base one by one according to macroblocks to obtain the difference of each macroblock;

[0103] Step 7063. Divide the difference of each macroblock by the corresponding macroblock data in the original image to obtain the percentage value of each macroblock;

[0104] Step 7064. Multiply the percentage value of each macroblock by the weight value corresponding to that macroblock, and use the sum of the products as the comparison result;

[0105] Step 707. Based on the comparison results, determine whether reporting is required and perform the corresponding operations accordingly;

[0106] Step 7071. When the comparison result exceeds the preset threshold range, it is determined that the obstruction of the monitoring equipment affects the monitoring area, and it needs to be reported. Then proceed to step 708.

[0107] Step 7072. When the comparison result is within the preset threshold range, it is determined that the obstruction of the monitoring device does not affect the monitoring area, and the position is restored.

[0108] Step 708. When reporting is required, report any abnormalities in the monitored area to the designated platform and notify the relevant personnel to intervene.

[0109] In this example, the detection of the monitored area is triggered by defocus detection, and the acquired image is compared with the original image. The relevant monitor is notified to investigate based on the comparison results, which can effectively ensure the normal operation of the monitored area. The stability of the scene is judged by distinguishing macroblocks and changes in sharpness within macroblocks, thereby assisting in judging the validity of the results. The impact on the scene is judged by assigning macroblock weights, which reduces invalid reports of local occlusion that do not affect the actual monitoring scene, thereby improving the effect.

[0110] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for detecting a monitored area, characterized in that, The method includes: Defocus detection is performed on images acquired by monitoring equipment; When a defocused image is detected in the acquired image, the monitoring device determines whether to report an anomaly in the monitored area according to a preset mode. The step of determining whether to report an anomaly in the monitored area based on a preset mode in the monitoring device includes: When the preset mode is the quality priority mode, the images collected by the monitoring device within the preset time range are compared with the original images collected by the monitoring device to obtain the comparison results. Based on the comparison results, determine whether it is necessary to report; When reporting is required, anomalies in the monitored area will be reported to the designated platform; and When the preset mode is event-priority mode, abnormalities in the monitored area are directly reported to the designated platform.

2. The detection method for the monitored area according to claim 1, characterized in that, The original image was obtained in the following way: Start the monitoring equipment; Once the monitoring device is initialized, it acquires an image when predetermined conditions are met and uses that image as the original image.

3. The detection method for the monitored area according to claim 2, characterized in that, The step of comparing the images acquired by the monitoring device within a preset time range with the original images acquired by the monitoring device to obtain the comparison results includes: The macroblocks of the images acquired by the monitoring device within a preset time range are encoded sequentially, and a preset weight value is assigned to each macroblock. The images acquired by the monitoring device within a preset time range are compared with the original images acquired by the monitoring device by macroblock, and the difference of each macroblock is obtained. The difference of each macroblock is divided by the corresponding macroblock data in the original image acquired by the monitoring device to obtain the percentage value of each macroblock; The percentage value of each macroblock is multiplied by the weight value corresponding to that macroblock, and the sum of the products is used as the comparison result.

4. The detection method for the monitoring area according to claim 3, characterized in that, The step of determining whether the monitoring area of ​​the monitoring device is normal based on the comparison result includes: When the comparison result exceeds a preset threshold range, it is determined that the monitoring area of ​​the monitoring device is abnormal. When the comparison result is within the preset threshold range, it is determined that the monitoring area of ​​the monitoring device is normal.

5. The detection method for the monitored area according to claim 1, characterized in that, Also includes: When it is detected that the acquired image is not out of focus, a new image is acquired according to a preset period and used to update the original image.

6. The detection method for the monitored area according to claim 1, characterized in that, The detection of out-of-focus images includes: Collect n images at a preset time interval; If the data of out-of-focus macroblocks in the n acquired images are confirmed to be fixed, it is determined that the acquired images are out of focus.

7. A monitoring device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the program, implements the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 6.

Images