CN114359828A - Target behavior recording method, device, storage medium and electronic device - Google Patents
Target behavior recording method, device, storage medium and electronic device Download PDFInfo
- Publication number
- CN114359828A CN114359828A CN202111633620.5A CN202111633620A CN114359828A CN 114359828 A CN114359828 A CN 114359828A CN 202111633620 A CN202111633620 A CN 202111633620A CN 114359828 A CN114359828 A CN 114359828A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- preset point
- similarity
- behavior
- 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
Abstract
The embodiment of the invention provides a method and a device for recording target behaviors, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring actual preset point information of target shooting equipment at a target moment; analyzing the behavior included in the target multimedia information shot by the target shooting equipment under the condition that the actual preset point information is consistent with the preset point information to determine an analysis result, wherein the preset point information is preset point information which is required to be reached by the preset target shooting equipment at the target moment; and under the condition that the target behaviors are determined to be included in the target multimedia information based on the analysis result, caching the target image included in the target multimedia information, wherein the target behaviors are recorded in the target image. The method and the device solve the problem of poor accuracy of the recording method of the target behavior in the related technology, and achieve the effect of improving the accuracy of the recording of the target behavior.
Description
Technical Field
The embodiment of the invention relates to the technical field of monitoring, in particular to a method and a device for recording target behaviors, a storage medium and an electronic device.
Background
At present, the camera is widely applied to various safety monitoring fields, such as road traffic, safety production, power systems and the like, plays an important role in production, life and safety management, can prevent safety accidents and provides great convenience for safety management. Taking the application of the camera in the event monitoring system processed by the management department as an example, in recent years, contradiction events are caused frequently in the event processing process of the management department, or whether the two parties dispute whether illegal behaviors exist or not, and the like, the evidence is particularly important, because the illegal behaviors need to exist for a period of time in the event processing of the management department, the illegal behaviors can be judged as the illegal behaviors, and the vehicle can be judged as the illegal behaviors after the vehicle stays for a period of time, and because the real-time requirement is not particularly high, one camera is usually used for analyzing a plurality of preset points, because of the requirement of handling events by personnel of the management department, the illegal behaviors need to be captured and fused for a plurality of times, and in the related technology, because the camera is operated, the recognized capture map is possibly not the preset point, therefore, providing a method for accurately recording the target behaviors has become an urgent problem to be solved.
Aiming at the problem of poor accuracy of a recording method of target behaviors in the related technology, no effective solution is provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for recording a target behavior, a storage medium and an electronic device, which are used for at least solving the problem of poor accuracy of a method for recording the target behavior in the related technology.
According to an embodiment of the present invention, there is provided a recording method of a target behavior, including: acquiring actual preset point information of target shooting equipment at a target moment; analyzing behaviors included in target multimedia information shot by the target shooting equipment under the condition that the actual preset point information is consistent with preset point information to determine an analysis result, wherein the preset point information is preset point information which is configured in advance and is required to be reached by the target shooting equipment at the target moment; and under the condition that the target behaviors are determined to be included in the target multimedia information based on the analysis result, caching a target image included in the target multimedia information, wherein the target behaviors are recorded in the target image.
In an exemplary embodiment, after caching the target image included in the target multimedia information, the method further includes: acquiring a pre-cached first image shot by the target shooting equipment at a first moment, wherein the first moment is a moment before the target moment, and the preset point information of the target shooting equipment at the first moment is the preset point information; continuing to cache the target image when the similarity of the target image and the first image is determined to exceed a similarity threshold; deleting the target image and the first image if it is determined that the similarity of the target image and the first image does not exceed a similarity threshold.
In one exemplary embodiment, the method further comprises: comparing the background similarity between a target background image included in the target image and a first background image included in the first image; determining the similarity of the target image and the first image based on the background similarity.
In one exemplary embodiment, comparing the background similarity between the target background map included in the target image and the first background map included in the first image includes: determining a target histogram of the target image, and a first histogram of the first image; calculating the distance between the target histogram and the first histogram to obtain a distance calculation result; determining the background similarity based on the distance calculation result.
In one exemplary embodiment, determining the similarity of the target image and the first image based on the background similarity comprises: determining behavior information of target behaviors respectively recorded in the target image and the first image, wherein the behavior information comprises behavior type information and behavior position information; comparing the behavior similarity of the behavior information recorded in the target image with the behavior information recorded in the first image; determining a similarity of the target image and the first image based on the background similarity and the behavior similarity.
In an exemplary embodiment, in a case that it is determined that the similarity of the target image and the first image exceeds a similarity threshold, the method further comprises: determining the number of the cached images continuously shot by the target shooting equipment in a target time period, wherein the target time period comprises the target time and the first time, and the preset point information of the target shooting equipment in the target time period is the preset point information all the time; under the condition that the number reaches a number threshold value, splicing the cached images shot by the target shooting equipment in a target time period to obtain a spliced image; and reporting the spliced image.
In an exemplary embodiment, after obtaining the analysis result, the method further comprises: discarding the target multimedia information if it is determined that the target behavior does not exist in the target multimedia information based on the analysis result.
According to another embodiment of the present invention, there is also provided a recording apparatus of a target behavior, including: the first acquisition module is used for acquiring the actual preset point information of the target shooting equipment at the target moment; the analysis module is used for analyzing the behaviors contained in the target multimedia information shot by the target shooting equipment under the condition that the actual preset point information is consistent with the preset point information to determine an analysis result, wherein the preset point information is the preset point information which is configured in advance and is required to be reached by the target shooting equipment at the target moment; the first caching module is used for caching a target image included in the target multimedia information under the condition that the target behavior is determined to be included in the target multimedia information based on the analysis result, wherein the target behavior is recorded in the target image.
According to a further embodiment of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the method and the device, the actual preset point information of the target shooting equipment at the target moment is obtained, the behavior included in the target multimedia information shot by the target shooting equipment is analyzed under the condition that the actual preset point information is consistent with the preset point information which is required to be reached by the target shooting equipment at the target moment, and the target image recorded with the target behavior is cached under the condition that the target multimedia information is determined to include the target behavior. The method and the device avoid the problems that the recorded target behaviors are not accurate enough due to the fact that the shot multimedia information is inconsistent with the preset point position caused by the fact that the target shooting equipment is operated by people in the related technology, therefore, the problem that the recording method of the target behaviors in the related technology is poor in accuracy is solved, and the effect of improving the recording accuracy of the target behaviors is achieved.
Drawings
Fig. 1 is a block diagram of a hardware structure of a mobile terminal of a recording method of a target behavior according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of recording target behavior according to an embodiment of the invention;
FIG. 3 is a flow diagram of a method of recording target behaviors in accordance with a specific embodiment of the present invention;
FIG. 4 is an illustration of a histogram according to an embodiment of the present invention;
FIG. 5 is an exemplary diagram of a detection box intersection according to a specific embodiment of the present invention;
FIG. 6 is an exemplary diagram of image stitching according to an embodiment of the present invention;
fig. 7 is a block diagram of a structure of a recording apparatus of a target behavior according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking the example of the operation on the mobile terminal, fig. 1 is a block diagram of a hardware structure of the mobile terminal of the recording method of the target behavior according to the embodiment of the present invention. As shown in fig. 1, the mobile terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 104 for storing data, wherein the mobile terminal may further include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and is not intended to limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the recording method of the target behavior in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the present embodiment, a method for recording a target behavior is provided, and fig. 2 is a flowchart of a method for recording a target behavior according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, acquiring actual preset point information of the target shooting equipment at a target moment;
step S204, under the condition that the actual preset point information is determined to be consistent with preset point information, analyzing behaviors included in target multimedia information shot by the target shooting equipment to determine an analysis result, wherein the preset point information is preset point information which is configured in advance and is required to be reached by the target shooting equipment at the target moment;
step S206, under the condition that the target multimedia information comprises the target behaviors based on the analysis result, caching the target image comprised in the target multimedia information, wherein the target behaviors are recorded in the target image.
Through the steps, the actual preset point information of the target shooting equipment at the target moment is obtained, the behavior included in the target multimedia information shot by the target shooting equipment is analyzed under the condition that the actual preset point information is consistent with the preset point information required to be reached by the target shooting equipment at the target moment, and the target image recorded with the target behavior is cached under the condition that the target multimedia information is determined to include the target behavior. The method and the device avoid the problems that the recorded target behaviors are not accurate enough due to the fact that the shot multimedia information is inconsistent with the preset point position caused by the fact that the target shooting equipment is operated by people in the related technology, therefore, the problem that the recording method of the target behaviors in the related technology is poor in accuracy is solved, and the effect of improving the recording accuracy of the target behaviors is achieved.
The executing agent of the above steps may be a monitoring system, such as a management department event processing monitoring system, a multimedia information processing device, a pan/tilt control device, a processor with human-computer interaction capability configured on a storage device, or a processing device or a processing unit with similar processing capability, but is not limited thereto. The following description is given by taking the monitoring system to perform the above operations as an example (which is only an exemplary description, and in actual operation, other devices or modules may also perform the above operations):
in the above embodiment, the monitoring system obtains actual preset point information of the target shooting device (such as a camera, or a dome camera, or a gun) at the target time, and compares the actual preset point information with the preset point information, taking as an example that the dome camera needs to capture images and evidence of multiple preset points in a round-robin manner in event monitoring system round-robin by management department, in practical application, the dome camera periodically rotates to each preset point according to a preset rule to capture images, and also needs to obtain that the dome camera captures multiple times (such as 2 times, 3 times, 4 times, or more) of a preset point (such as preset point a) within a period of time to obtain evidence of recording the target behavior, for example, the target behavior is vehicle violation, or a garbage bin is full, or a material is piled up; in practical application, when the ball machine needs to capture a preset point (such as the preset point a) for multiple times within a period of time, the target shooting device may rotate to other positions due to human or other reasons during the period, that is, the multimedia information captured by the target shooting device may not necessarily be the multimedia information of the preset point (such as the preset point a), so that the target behavior analyzed according to the target multimedia information may not be accurate, therefore, the actual preset point information at the target moment needs to be obtained, and whether the actual preset point information is consistent with the preset point information or not is determined, only under the condition that the actual preset point information is consistent with the preset point information, target behaviors obtained through analysis according to target multimedia information shot by target shooting equipment can be used as evidences; in the case where it is determined that the target behavior is included in the target multimedia information based on the analysis result, the target image included in the target multimedia information is cached, the target image records target behaviors, and in practical application, the target multimedia information can comprise video and/or target images, and the target image may be a frame of image included in the video, such as a vehicle parking violation, and in practical applications, in order to improve the accuracy of the recorded target behavior, it may be necessary to take several continuous snap-shots for evidence at a certain preset point over a period of time, under the condition that the actual preset point information of each time is consistent with the preset threshold point information, the target behavior obtained by analyzing the target multimedia information obtained each time can be used as an evidence for managing personnel to process events, and a target image is stored to record the target behavior. The method and the device avoid the problems that the recorded target behaviors are not accurate enough due to the fact that the shot multimedia information is inconsistent with the preset point position caused by the fact that the target shooting equipment is operated manually in the related technology, therefore, the problem that the recording method of the target behaviors in the related technology is poor in accuracy is solved, and the effect of improving the recording accuracy of the target behaviors is achieved.
In an optional embodiment, after caching the target image included in the target multimedia information, the method further includes: acquiring a pre-cached first image shot by the target shooting equipment at a first moment, wherein the first moment is a moment before the target moment, and the preset point information of the target shooting equipment at the first moment is the preset point information; continuing to cache the target image when the similarity of the target image and the first image is determined to exceed a similarity threshold; deleting the target image and the first image if it is determined that the similarity of the target image and the first image does not exceed a similarity threshold. In this embodiment, after caching the target image corresponding to the target time, obtaining a first image cached in advance at the first time, where the information of the preset point corresponding to the target time is the same at the first time and the target time, where the first time may be a time when a time difference between the first time and the target time is smaller than a time difference threshold, for example, a time interval between the first time and the target time is 5 minutes, or 10 minutes, or another time threshold, comparing the target image with the first image to determine a similarity between the target image and the first image, continuing to cache the target image when the similarity between the target image and the first image is determined to be greater than or equal to a similarity threshold (e.g., 95%, or 90%, or another value), and conversely, deleting the target image and the first image when the similarity is smaller than the similarity threshold, because an event that the target imaging apparatus is operated by a person may occur, for example, a ball machine is manually rotated, and in practical application, according to a method similar to this embodiment, the target image at the current time is compared with the target image at the previous time more times (e.g. 3 times, or 4 times, or other times), for example, the 3 rd cached target image is compared with the 2 nd cached target image, and the 4 th cached target image is compared with the 3 rd cached target image, and so on, it should be noted that the 2 nd time, the 3 rd time, and the 4 th time refer to the time when the actual preset point same as the preset point information is photographed, and the target behaviors recorded in the plurality of target images are determined to be accurate when the target image ratios are performed for a plurality of times (i.e. a plurality of different times) and the similarity between the determined images all reach the similarity threshold, the accuracy of the recording of the target behavior is improved, namely the reliability of the evidence chain is improved.
In an optional embodiment, the method further comprises: comparing the background similarity between a target background image included in the target image and a first background image included in the first image; determining the similarity of the target image and the first image based on the background similarity. In this embodiment, the similarity between the target background image in the target image and the background image in the first image is determined by comparing the similarity between the target background image in the target image and the background image in the first image, in practical applications, when the ball machine needs to capture a preset point (e.g., preset point a) for multiple times (e.g., 4 times or other times) within a period of time, a plurality of (e.g., 4 or other numbers) target images need to be cached, at this time, the similarity comparison needs to be performed on the 4 target images, and also, pairwise comparison can be performed on the background images respectively included in the 4 target images, for example, the similarity between every two background images can be calculated. Through the embodiment, the situation that the preset point is transferred away and then transferred back to the original position in the analysis process can be eliminated, so that the aim of further improving the accuracy of the record of the target behavior and the aim of further improving the reliability of the evidence chain are fulfilled.
In an optional embodiment, comparing the background similarity between the target background map included in the target image and the first background map included in the first image comprises: determining a target histogram of the target image, and a first histogram of the first image; calculating the distance between the target histogram and the first histogram to obtain a distance calculation result; determining the background similarity based on the distance calculation result. In this embodiment, when comparing the similarity between the target background map and the first background map, the target histogram of the target image and the first histogram of the first image may be determined, and then the distance between the target histogram and the first histogram may be calculated, so as to determine the similarity between the target background map and the first background map. Through the embodiment, the purpose of determining the similarity between the target background image and the first background image through the distance calculation method of the histogram is achieved.
In an optional embodiment, determining the similarity of the target image and the first image based on the background similarity comprises: determining behavior information of target behaviors respectively recorded in the target image and the first image, wherein the behavior information comprises behavior type information and behavior position information; comparing the behavior similarity of the behavior information recorded in the target image with the behavior information recorded in the first image; determining a similarity of the target image and the first image based on the background similarity and the behavior similarity. In this embodiment, the target image and the behavior information of the target behavior recorded in the first image may be determined, and then the behavior similarity between the behavior information included in the two images is compared, where the behavior information may include behavior type information, such as vehicle parking violation, non-vehicle parking violation, exposed garbage, scram materials, and the like, and the behavior information may further include behavior location information, such as a location where the target behavior occurs in the target image and the first image, and then the similarity between the target image and the first image is further determined by combining the background similarity and the behavior similarity.
In an optional embodiment, in a case that it is determined that the similarity of the target image and the first image exceeds a similarity threshold, the method further comprises: determining the number of the cached images continuously shot by the target shooting equipment in a target time period, wherein the target time period comprises the target time and the first time, and the preset point information of the target shooting equipment in the target time period is the preset point information all the time; under the condition that the number reaches a number threshold value, splicing the cached images shot by the target shooting equipment in a target time period to obtain a spliced image; and reporting the spliced image. In this embodiment, in the case that it is determined that the similarity between the target image and the first image exceeds the similarity threshold (e.g. 95%, or 90%, or other values), the number of buffered images is determined, wherein the buffered images are obtained by analyzing multimedia information captured by the target capturing device at different times (including the target time and the first time) within a target time period (e.g. 10 minutes, or 30 minutes, or other time periods), and are buffered in the case that it is determined that the actual preset point information at each time is the same as the preset point information, and when it is determined that the number of images reaches the number threshold (e.g. 3, or 4, or other numbers), the buffered images are concatenated to form an evidence chain picture, and the concatenated images are reported, for example, in an actual application, in a management department event monitoring system, after the analysis, the buffered images are analyzed, After comparison, splicing and the like, the evidence chain picture (i.e. the spliced image) can be reported to relevant departments or other systems or other equipment, and the evidence chain picture (i.e. the spliced image) can be stored at the same time. Through the embodiment, the purpose of splicing the images for recording the target behaviors is achieved, and the problems that the accuracy rate of recording the target behaviors is low and an evidence chain is incomplete in the related technology are effectively solved.
In an optional embodiment, after obtaining the analysis result, the method further comprises: discarding the target multimedia information if it is determined that the target behavior does not exist in the target multimedia information based on the analysis result. In this embodiment, when the target multimedia information shot by the target shooting device is analyzed to have no target behavior, the target multimedia information can be discarded, so as to achieve the purpose of saving storage resources.
It is obvious that the above described embodiments are only a part of the embodiments of the present invention, and not all of them. The present invention will be specifically described with reference to the following embodiments, which take the example of the management department processing the event monitoring system intelligently detecting the ball machine training as an example.
Fig. 3 is a flowchart of a recording method of target behavior according to an embodiment of the present invention, and as shown in fig. 3, the flowchart includes the following steps:
s302, the ball machine (corresponding to the target shooting equipment) trains to a certain point location in turn, and current preset point information (corresponding to the preset point information) is cached;
s304, simultaneously, using the management rule of the management department configured by the preset point to send the code stream into an algorithm to perform corresponding intelligent analysis (corresponding to the target multimedia information shot by the analysis target shooting equipment) of the management department event processing monitoring system;
s306, obtaining analysis snapshot pictures and results (corresponding to the analysis results and the target images), and obtaining the preset point information (corresponding to the actual preset point information) of the current ball machine again through the results of the analysis of the intelligent algorithm;
s308, judging whether the preset points before and after analysis are consistent, namely corresponding to the compared actual preset point information and the preset point information;
s310, under the condition that the judgment result in the step 308 is negative, discarding the current analysis result and the analysis result before the preset point, namely, if the current analysis result and the analysis result before the preset point are inconsistent, indicating that the ball machine rotates in the analysis process and can cause error identification, discarding the current analysis result of the preset point and the result cached before the preset point, and continuing to perform round training detection;
s312, if the determination result in the step 308 is yes, further determining whether multiple continuous analyses of the same preset point are completed, that is, if the previous and subsequent preset points are consistent, determining whether multiple continuous analyses of the same preset point are completed, that is, the previous and subsequent preset points are consistent during the analysis of the same preset point, and taking the identification of the vehicle parking violation as an example, the corresponding evidence chain is formed by the snapshot results that are continuously performed for 4 times;
s314, under the condition that the judgment result in the step 312 is negative, caching the analysis result of the preset point, and returning to the step S302 to continue the round training; namely, if the front preset point and the rear preset point are inconsistent, caching the analysis result of the current preset point, and continuing to perform the round training detection;
s316, under the condition that the judgment result in the step 312 is yes, the consistency of the snapshot backgrounds of a plurality of results is analyzed; for example, if several continuous snapshots of the same preset point have been completed, the similarity of the background (corresponding to the aforementioned background similarity) is calculated by performing two-by-two histogram calculation on the results of several snapshots, and the distance calculation of the histogram uses the correlation calculation formula as follows:
wherein
When the distance of the histograms of the multiple snapshot images is close to 0, the background probability is similar; the situation that the preset point is transferred away and then transferred back to the original position in the analysis process can be eliminated through the process, and the situation that scenes are inconsistent is preliminarily eliminated; FIG. 4 is a histogram illustration, in accordance with an embodiment of the present invention, with an example of the histogram of FIG. 4 corresponding to a different scene;
s318, judging whether the backgrounds are consistent;
s320, when the determination result of the step 318 is yes, and when the distance of the histogram is close to 0 in the step 316, analyzing the target consistency (behavior information corresponding to the target behavior) of the results of the plurality of times, for example, determining whether the types (corresponding to the behavior type information) of the results of the target analysis are the same, in the event detection processed by the management department, the target type is a motor vehicle illegal parking, a non-motor vehicle illegal parking, exposed garbage, garbage bin overflow, random material, and the like; if the types of the detected targets are consistent, further performing target detection frame intersection comparison calculation, judging that the targets are at the same position (corresponding to the behavior position information), continuously and repeatedly capturing the same preset point for a plurality of times, wherein the types and the positions are consistent, indicating that the current detection is a normal result, otherwise discarding the current detection result and the detection result before the preset point, and continuing to perform round training detection;
the intersection-to-parallel ratio of the detection frames can be calculated according to a formula
Calculating, where a ≧ B is an intersection of the two detection regions, and a ∞ B is a union of all regions of the two detection regions, fig. 5 is a cross-section of detection frames according to an embodiment of the present invention, which shows that the larger the IOU, the more portions of the two detection frames overlap; if the determination result in the step 318 is negative, the process returns to the step S310, and discards the current analysis result and the analysis result before the preset point;
it should be noted that, in practical applications, after the above steps S302 to S318 and the judgment that the backgrounds are consistent, the situation of the backgrounds with similar scenes still cannot be excluded, and in order to improve the completeness and the reliability of the evidence chain, the target consistency of the multiple results also needs to be analyzed;
s322, judging whether the targets are consistent;
s324, in the case that the judgment result of the step 322 is yes, that is, when the targets are consistent, the images at multiple consecutive times of the same preset point are spliced to form an evidence chain picture, and the result is reported, stored and displayed, and at the same time, detection is continuously performed, taking the detection of the illegal parking of the motor vehicle by the management department as an example, fig. 6 is an exemplary diagram of image splicing according to an embodiment of the present invention; if the determination result in step 322 is negative, the process returns to step S310, and the current analysis result and the analysis results before the preset point are discarded.
In the related art, a ball machine needs to be used for carrying out analysis by adopting a round-robin training mode at a plurality of preset points, and because the requirement of an evidence chain of a management department is that an illegal action lasts for a period of event and a plurality of snap shots, the ball machine needs to go to a certain preset point to check information due to human reasons in the round-robin training analysis process, the situation can occur: when the dome camera is operated to a certain preset point for analysis, the dome camera is manually operated to other point positions, the analysis result can generate a lot of false alarms, the identified snap chart can not be the preset point position, and due to the fact that the preset point can be snapped for many times, the evidence of illegal parking is not feasible due to different backgrounds in the spliced result;
in the above embodiment, when a certain preset point in the ball machine round train is found, the current preset point information is cached first, and the code stream is sent to the algorithm for detection, when the detection is finished, the current preset point information is obtained, if the preset points are inconsistent, the possibility that the ball machine is operated manually exists, the current detection of the preset point and the caches of the previous detections are discarded, if the preset points are consistent and the preset points are continuously detected for multiple times, the background consistency and the target consistency are further checked, and if the backgrounds are consistent and the targets are consistent for multiple times, the images are spliced to form an evidence chain, and the results are stored and displayed. In the process of forming an evidence chain by capturing the same preset point for multiple times, the error pictures or results generated by manual operation are eliminated, so that the continuously spaced multiple capturing pictures are consistent, and the completion of the evidence chain is ensured.
By the embodiment of the invention, the problem of error identification caused by inconsistent positions of the dome cameras before and after analysis is solved by comparing the preset points before and after analysis; the consistency of the snapshot backgrounds is judged by comparing the histogram similarity of the images after the same preset point is snapshot for multiple times, so that the problem of false recognition caused by the fact that the dome camera moves to analyze the background in the analysis process is solved; finally confirming that the snapshot is taken at the same preset point at multiple times through intersection and comparison calculation of the violation type of the same preset point and the violation detection frame of the analysis result, and achieving the purpose of improving the accuracy of evidence chain detection; by the evidence chain detection method provided by the embodiment of the invention, the condition that the candid evidence at multiple moments is incomplete or wrong can be effectively solved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, but may also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solution of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
There is also provided in this embodiment a recording apparatus of target behaviors, and fig. 7 is a block diagram of a structure of the recording apparatus of target behaviors according to an embodiment of the present invention, as shown in fig. 7, the apparatus includes:
a first obtaining module 702, configured to obtain actual preset point information of a target shooting device at a target time;
an analyzing module 704, configured to analyze a behavior included in target multimedia information captured by the target capturing device to determine an analysis result when it is determined that the actual preset point information coincides with preset point information, where the preset point information is preset point information that the target capturing device needs to reach at the target time and is configured in advance;
a first caching module 706, configured to cache a target image included in the target multimedia information when it is determined that a target behavior is included in the target multimedia information based on the analysis result, where the target behavior is recorded in the target image.
In an optional embodiment, the apparatus further comprises: a second obtaining module, configured to obtain a first image, which is captured by the target shooting device at a first time and is cached in advance, after caching a target image included in the target multimedia information, where the first time is a time before the target time, and the preset point information of the target shooting device at the first time is the preset point information; the second caching module is used for continuing caching the target image under the condition that the similarity between the target image and the first image is determined to exceed a similarity threshold value; a deletion module for deleting the target image and the first image if it is determined that the similarity between the target image and the first image does not exceed a similarity threshold.
In an optional embodiment, the apparatus further comprises: a comparison module, configured to compare a background similarity between a target background image included in the target image and a first background image included in the first image; a first determining module, configured to determine a similarity between the target image and the first image based on the background similarity.
In an optional embodiment, the alignment module includes: a first determining unit, configured to determine a target histogram of the target image and a first histogram of the first image; the calculation unit is used for calculating the distance between the target histogram and the first histogram to obtain a distance calculation result; a second determining unit configured to determine the background similarity based on the distance calculation result.
In an optional embodiment, the first determining module includes: a third determining unit, configured to determine behavior information of the target behavior respectively recorded in the target image and the first image, where the behavior information includes behavior type information and behavior location information; a comparison unit, configured to compare behavior similarity between behavior information recorded in the target image and behavior information recorded in the first image; a fourth determining unit, configured to determine a similarity between the target image and the first image based on the background similarity and the behavior similarity.
In an optional embodiment, the apparatus further comprises: a second determining module, configured to determine, when it is determined that a similarity between the target image and the first image exceeds a similarity threshold, a number of images that have been continuously captured by the target capturing device in a target time period, where the target time period includes the target time and the first time, and preset point information of the target capturing device in the target time period is the preset point information all the time; the splicing module is used for splicing the cached images shot by the target shooting equipment in a target time period to obtain a spliced image under the condition that the number is determined to reach a number threshold; and the reporting module is used for reporting the spliced image.
In an optional embodiment, the apparatus further comprises: a discarding module, configured to discard the target multimedia information after obtaining the analysis result and if it is determined that the target behavior does not exist in the target multimedia information based on the analysis result.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, where the computer program is arranged to, when executed, perform the steps in any of the above-mentioned method embodiments.
In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and they may be implemented in program code that is executable by the computing devices, such that they may be stored in a memory device and executed by the computing devices, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into separate integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the principle of the present invention shall be included in the protection scope of the present invention.
Claims (10)
1. A method for recording a target behavior, comprising:
acquiring actual preset point information of target shooting equipment at a target moment;
analyzing behaviors included in target multimedia information shot by the target shooting equipment under the condition that the actual preset point information is consistent with preset point information to determine an analysis result, wherein the preset point information is preset point information which is configured in advance and is required to be reached by the target shooting equipment at the target moment;
and under the condition that the target behaviors are determined to be included in the target multimedia information based on the analysis result, caching a target image included in the target multimedia information, wherein the target behaviors are recorded in the target image.
2. The method of claim 1, wherein after buffering the target image included in the target multimedia information, the method further comprises:
acquiring a pre-cached first image shot by the target shooting equipment at a first moment, wherein the first moment is a moment before the target moment, and the preset point information of the target shooting equipment at the first moment is the preset point information;
continuing to cache the target image when the similarity of the target image and the first image is determined to exceed a similarity threshold;
deleting the target image and the first image if it is determined that the similarity of the target image and the first image does not exceed a similarity threshold.
3. The method of claim 2, further comprising:
comparing the background similarity between a target background image included in the target image and a first background image included in the first image;
determining a similarity of the target image and the first image based on the background similarity.
4. The method of claim 3, wherein comparing the background similarity between the target background map included in the target image and the first background map included in the first image comprises:
determining a target histogram of the target image, and a first histogram of the first image;
calculating the distance between the target histogram and the first histogram to obtain a distance calculation result;
determining the background similarity based on the distance calculation result.
5. The method of claim 3, wherein determining the similarity of the target image to the first image based on the background similarity comprises:
determining behavior information of target behaviors respectively recorded in the target image and the first image, wherein the behavior information comprises behavior type information and behavior position information;
comparing the behavior similarity of the behavior information recorded in the target image with the behavior information recorded in the first image;
determining a similarity of the target image and the first image based on the background similarity and the behavior similarity.
6. The method of claim 2, wherein in the event that it is determined that the similarity of the target image to the first image exceeds a similarity threshold, the method further comprises:
determining the number of the cached images continuously shot by the target shooting equipment in a target time period, wherein the target time period comprises the target time and the first time, and the preset point information of the target shooting equipment in the target time period is the preset point information all the time;
under the condition that the number reaches a number threshold value, splicing the cached images shot by the target shooting equipment in a target time period to obtain a spliced image;
and reporting the spliced image.
7. The method of claim 1, wherein after obtaining the analysis results, the method further comprises:
discarding the target multimedia information if it is determined that the target behavior does not exist in the target multimedia information based on the analysis result.
8. A recording apparatus of a target behavior, comprising:
the first acquisition module is used for acquiring the actual preset point information of the target shooting equipment at the target moment;
the analysis module is used for analyzing the behaviors contained in the target multimedia information shot by the target shooting equipment under the condition that the actual preset point information is consistent with preset point information to determine an analysis result, wherein the preset point information is preset point information which is configured in advance and is required to be reached by the target shooting equipment at the target moment;
the first caching module is used for caching a target image included in the target multimedia information under the condition that the target behavior is determined to be included in the target multimedia information based on the analysis result, wherein the target behavior is recorded in the target image.
9. A computer-readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method as claimed in any of claims 1 to 7 are implemented when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633620.5A CN114359828A (en) | 2021-12-28 | 2021-12-28 | Target behavior recording method, device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633620.5A CN114359828A (en) | 2021-12-28 | 2021-12-28 | Target behavior recording method, device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114359828A true CN114359828A (en) | 2022-04-15 |
Family
ID=81102947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111633620.5A Pending CN114359828A (en) | 2021-12-28 | 2021-12-28 | Target behavior recording method, device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114359828A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958707A (en) * | 2023-08-18 | 2023-10-27 | 武汉市万睿数字运营有限公司 | Image classification method, device and related medium based on spherical machine monitoring equipment |
-
2021
- 2021-12-28 CN CN202111633620.5A patent/CN114359828A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958707A (en) * | 2023-08-18 | 2023-10-27 | 武汉市万睿数字运营有限公司 | Image classification method, device and related medium based on spherical machine monitoring equipment |
| CN116958707B (en) * | 2023-08-18 | 2024-04-23 | 武汉市万睿数字运营有限公司 | Image classification method, device and related medium based on spherical machine monitoring equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| CN110225299B (en) | Video monitoring method and device, computer equipment and storage medium | |
| CN109299703B (en) | Method and device for carrying out statistics on mouse conditions and image acquisition equipment | |
| CN112291520B (en) | Abnormal event identification method and device, storage medium and electronic device | |
| WO2020094091A1 (en) | Image capturing method, monitoring camera, and monitoring system | |
| WO2020094088A1 (en) | Image capturing method, monitoring camera, and monitoring system | |
| CN110659391A (en) | Video detection method and device | |
| CN110738178A (en) | Garden construction safety detection method and device, computer equipment and storage medium | |
| CN111010547A (en) | Target object tracking method and device, storage medium and electronic device | |
| CN110610610B (en) | Vehicle access management method and device and storage medium | |
| CN112818173A (en) | Method and device for identifying associated object and computer readable storage medium | |
| CN113992893A (en) | Park inspection method and device, storage medium and electronic device | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN111553231B (en) | Face snapshot and deduplication system, method, terminal and medium based on information fusion | |
| CN112651398A (en) | Vehicle snapshot control method and device and computer readable storage medium | |
| CN113674314A (en) | Method and device for detecting throwing event, electronic device and storage medium | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device | |
| CN113190700B (en) | Face snapshot, screening and storage method and system for real estate transaction | |
| CN114863364B (en) | Security detection method and system based on intelligent video monitoring | |
| CN113438286B (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN112201047B (en) | Suspected vehicle foothold analysis method and device based on Flink framework | |
| CN112040325B (en) | Video playing method and device, electronic equipment and storage medium | |
| CN112738387B (en) | Target snapshot method, device and storage medium | |
| CN113592427A (en) | Method and apparatus for counting man-hours and computer readable storage medium |
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 |