CN113807445B - File rechecking method and device, electronic device and readable storage medium - Google Patents
File rechecking method and device, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN113807445B CN113807445B CN202111110920.5A CN202111110920A CN113807445B CN 113807445 B CN113807445 B CN 113807445B CN 202111110920 A CN202111110920 A CN 202111110920A CN 113807445 B CN113807445 B CN 113807445B
- Authority
- CN
- China
- Prior art keywords
- event
- picture
- acquiring
- post
- identification data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012552 review Methods 0.000 claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 8
- 238000007726 management method Methods 0.000 description 18
- 238000004364 calculation method Methods 0.000 description 8
- 238000012806 monitoring device Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a file rechecking method, which comprises the following steps: acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures; acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture; acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data; and judging the case rechecking state of the target case according to the event state corresponding to each post picture. According to the method, the monitoring equipment installed in each place of the city uploads the acquired data to the monitoring system, the incident picture and the post picture of the urban management file are acquired from the acquired data, the relevant information of the illegal event corresponding to the same urban management file is extracted and compared, so that the automatic review of the urban management file is realized, the labor is saved, and the disposal efficiency and the disposal accuracy of the urban management file are improved.
Description
Technical Field
The present invention relates to the field of urban management, and in particular, to a method and apparatus for checking a case, an electronic device, and a computer program product.
Background
With the continuous development of cities, the treatment of urban appearance is more and more important and more strict. In the management process of urban and local features, the urban management center records the monitored relevant information of each illegal event into a case, and the case in which the information of the illegal event in the city is recorded can be called as an urban management case, so that the treatment efficiency of the urban management case is an important index for judging the management level of the urban and local features.
In the prior art, the monitoring system is generally utilized to acquire illegal event data and record the illegal event data in the corresponding urban management files, then an executive is timely dispatched to the place of occurrence for disposal, the result is fed back to the urban management center after the disposal is completed, and the urban management files are rechecked and archived by the staff in the urban management center according to the feedback result. However, the urban management center can capture countless illegal events every day, if the urban management center manually rechecks and files the urban management files, a great deal of manpower is needed, and the treatment efficiency and the treatment accuracy of the urban management files are low due to the fact that different staff are easily influenced by personal subjective reasons.
Disclosure of Invention
In a first aspect, an embodiment of the present application provides a method for checking a case, where the method uploads collected data to a monitoring system through monitoring devices installed in various places of a city, acquires an incident image and a post-incident image of a case of the city from the collected data, and extracts relevant information corresponding to an offence event in the same case of the city to compare and implement automatic checking of the case of the city. The method comprises the following steps:
acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture;
acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data;
and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
In some application embodiments, the method for acquiring the incident picture and the corresponding post picture set of the target file includes the following steps: acquiring file information of a target file; acquiring the incident picture and a subsequent picture set according to the file information, wherein the subsequent picture set at least comprises a subsequent picture; calculating scene similarity of the subsequent picture and the incident picture; and if the scene similarity is greater than a scene similarity threshold, the subsequent picture is a post picture corresponding to the target case.
In some embodiments of the application, the method for acquiring the event frame and the subsequent frame set according to the case information includes the following steps: acquiring monitoring equipment for acquiring the target file according to the file information; and the monitoring system acquires the incident picture and the subsequent picture set from the monitoring equipment.
In some application embodiments, a scene similarity of the subsequent picture and the event picture is calculated: acquiring a first background area of the incident picture and a second background area of the subsequent picture; and calculating the scene similarity of the first background area and the second background area according to the scene similarity of the first background area and the second background area.
In some application embodiments, the first identification data includes a first event type, a first event coordinate frame, and a first event confidence, and the second identification data includes a second event type, a second event coordinate frame, and a second event confidence.
Specifically, in some application embodiments, the method for obtaining the review similarity includes the following steps: acquiring the second identification data containing the same event type as the first identification data; acquiring a first overlapping proportion according to the first event coordinate frame, and acquiring a second overlapping proportion according to the second event coordinate frame; acquiring the difference of the event confidence degrees according to the first event confidence degrees and the second event confidence degrees; calculating the distance between the event center points of the event picture and the post picture; and acquiring the rechecking similarity according to the first overlapping proportion, the second overlapping proportion, the event confidence difference and the event center point distance.
The first overlapping proportion is the proportion of the first event coordinate frame to the event picture, and the second overlapping proportion is the proportion of the second event coordinate frame to the post picture. And the event center point distance is a Hamming distance between the event picture and the post picture calculated by using a perceptual hash algorithm.
In some embodiments, if the review similarity is less than a first threshold, the event state is absent; and if the rechecking similarity is not smaller than a first threshold value, the event state is present.
In some application embodiments, the method for judging the case review status of the target case according to the event status corresponding to each post picture includes the following steps: counting the number of pictures of the post picture which is in the event state, and calculating the proportion of the number of pictures to the number of post pictures contained in the post picture set; and if the proportion does not exceed the second threshold, the case review state is changed, and if the proportion exceeds the second threshold, the case review state is not changed.
In a second aspect, an embodiment of the present application provides a case review device, including the following modules:
the acquisition module is used for: the method comprises the steps of acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
and an identification module: the method comprises the steps of acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture;
the first rechecking module: the event state corresponding to the post picture is obtained according to the rechecking similarity of the first identification data and the second identification data;
and a second rechecking module: and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
In a third aspect, embodiments of the present application provide an electronic device, including a memory, and a processor, where the memory stores a computer program, and the processor is configured to run the computer program to implement the case review method according to any of the embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a computer program product comprising software code portions for performing the case review method as described in any of the embodiments of the present application, when the computer program product is run on a computer.
In a fifth aspect, embodiments of the present application provide a readable storage medium having a computer program stored therein, the computer program comprising program code for controlling a process to perform a process, the process comprising a case review method according to any of the embodiments of the present application above.
The main contributions and innovation points of the embodiments of the present application are as follows: the embodiment of the application provides a method, a device and a computer program product for automatically rechecking a city management file, wherein the method uploads collected data to a monitoring system through monitoring equipment installed in various places of a city, acquires an incident picture and a post picture of the city management file from the collected data, extracts relevant information of an illegal event corresponding to the same city management file, and compares the relevant information to realize the automatic rechecking of the city management file. Not only saves the manpower, but also improves the disposal efficiency and the disposal accuracy of the urban management files.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
fig. 1 is a flowchart of a case review method according to an embodiment of the present application;
fig. 2 is a block diagram of a case review device according to an embodiment of the present application;
fig. 3 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with aspects of one or more embodiments of the present description as detailed in the accompanying claims.
It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. Furthermore, individual steps described in this specification, in other embodiments, may be described as being split into multiple steps; while various steps described in this specification may be combined into a single step in other embodiments.
Example 1
In this embodiment, the method collects monitoring data from monitoring devices arranged in various places in a city at preset collection time intervals and collection times, uploads the data to a monitoring system in a city management center, records an incident picture by using the monitoring device corresponding to a target case, and continuously records the incident picture at preset collection time intervals and collection times after an illegal event occurs. Therefore, the processing progress of the illegal event in each subsequent collected picture is confirmed by comparing the data information contained in the event picture and the subsequent collected picture, finally the case rechecking state of the target case is comprehensively judged according to the processing progress of the illegal event in all subsequent collected pictures, and the target case and the information contained in the target case are filed.
Specifically, referring to FIG. 1, the method includes steps S1-S4:
step S1: and acquiring an event picture of the target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures.
In the step, the picture when the illegal event occurs in the target case is obtained through the monitoring system and the monitoring equipment to serve as an incident picture, and the picture forms a post picture set when the corresponding incident picture is continuously recorded after the incident picture is obtained.
The specific method for acquiring the incident picture and the corresponding post picture set of the target file in some embodiments includes the following steps: acquiring file information of a target file; acquiring the incident picture and a subsequent picture set according to the file information, wherein the subsequent picture set at least comprises a subsequent picture; calculating scene similarity of the subsequent picture and the incident picture; and if the scene similarity is greater than a scene similarity threshold, the subsequent picture is a post picture corresponding to the target case.
That is, firstly, the monitoring device for collecting the target file is determined according to the file information of the target file, the monitoring system obtains the event picture of the target file through the monitoring device, and based on the preset collection time interval and collection times, the monitoring device is controlled to continuously collect the subsequent pictures to form a subsequent picture set. And then calculating the scene similarity of each subsequent picture in the subsequent picture set and the incident picture, and if the calculated scene similarity is larger than a preset scene similarity threshold value, indicating that the subsequent picture is shot corresponding to the same scene of the target case, so that the subsequent picture can be used as the subsequent picture of the target case.
Specifically, calculating the scene similarity of the subsequent frame and the event frame includes, in some embodiments, the following steps: acquiring a first background area of the incident picture and a second background area of the subsequent picture; and calculating the scene similarity of the first background area and the second background area according to the scene similarity of the first background area and the second background area.
In this embodiment, semantic segmentation is adopted to separate foreground and background areas in an event picture, the semantic segmentation performs a dense segmentation task on an image, segments each pixel onto a designated category, namely segments the image into a plurality of meaningful targets, assigns designated category labels to the segmented image, and after label assignment work is completed, foreground information which is already labeled is removed through counter selection, background area information in the event picture is reserved as a first background area, and similarly, background area information in a subsequent picture is reserved as a second background area.
After the first background area and the second background area are obtained, the scene similarity of the first background area and the second background area is calculated by adopting the existing similarity calculation method. In some embodiments, scene similarity is calculated by comparing the plain fingerprint encodings of the two. For example, converting an image into fingerprint coding generally comprises the steps of: inputting an image; graying the image; unifying the image size; simplifying the gray scale in the image; calculating an average gray value of the image; comparing the actual gray value and the average gray value of each pixel of the image, and arranging the comparison results into 2-system fingerprint codes according to a certain sequence. The first background area and the second background area are processed according to the method, fingerprint codes of the first background area and the second background area are compared, and scene similarity is calculated. It should be noted that, the existing calculation methods of the scene similarity are many, only one of the methods is provided, the intermediate actual calculation process is complex, and only a simple example is provided here without excessive description.
Step S2: and acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture.
In this step, relevant information of the corresponding violation event is extracted from the event picture and the post-event face by the recognition algorithm as recognition data, and specifically, the relevant information at least includes: the event type of the violation event, the coordinate frame of the violation event in the picture, and the event confidence. That is, the information related to the offending event in the target case in the event picture is extracted as the first identification data, and similarly, the information related to the offending event in the target case in the post picture is extracted as the second identification data. Wherein, the event confidence is that the recognition algorithm scores the correct probability of the extracted coordinate frame of the violation event in the picture, that is, the higher the score, the higher the probability that the coordinate frame is the correct coordinate frame, but not absolute. Specifically, the first identification data comprises a first event type, a first event coordinate frame and a first event confidence level, and the second identification data comprises a second event type, a second event coordinate frame and a second event confidence level.
The recognition algorithm is an algorithm model trained by a deep learning neural network algorithm, for example, the current deep learning neural network algorithm comprises: YOLO, R-CNN, fast R-CNN, etc. In this embodiment, a YOLO series algorithm (YOLOv 1-YOLOv 5) is adopted, in brief, an algorithm model is trained by using a training data algorithm and can be used for image recognition, and a specific process of collecting recognition data is that all possible candidate frames are firstly drawn on an image by a feature extractor (an internal structure of the algorithm) according to feature values, then regression calculation is performed in the algorithm, incorrect candidate frames are removed, and the last correct candidate frame output is reserved.
Step S3: and acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data.
After the first identification data and the second identification data are obtained in the step S2, the similarity of the first identification data and the second identification data is obtained through calculation by comparing the related information of the corresponding illegal events in the first identification data and the second identification data, the similarity is used as the rechecking similarity, and then the event state of the post-picture is determined according to the magnitude of the rechecking similarity.
However, if the multiple pieces of related information in the corresponding identification data of each post picture are directly used as the necessary data for calculating the recheck similarity, the resource cost is extremely high and the automatic recheck efficiency is low, so in order to reduce unnecessary calculation and resource cost, the second identification data which is different from the event type of the illegal event in the target case is firstly removed, that is, only the second identification data which is the same as the first event type is reserved, and then the first identification data and the related information of the corresponding illegal event in the reserved second identification data are compared to calculate the recheck similarity.
Specifically, the method for computing the recheck similarity includes the following steps in some embodiments: acquiring the second identification data containing the same event type as the first identification data; acquiring a first overlapping proportion according to the first event coordinate frame, and acquiring a second overlapping proportion according to the second event coordinate frame; acquiring the difference of the event confidence degrees according to the first event confidence degrees and the second event confidence degrees; calculating the distance between the event center points of the event picture and the post picture; and acquiring the rechecking similarity according to the first overlapping proportion, the second overlapping proportion, the event confidence difference and the event center point distance.
The first overlapping proportion is the proportion of the first event coordinate frame to the event picture, and the second overlapping proportion is the proportion of the second event coordinate frame to the post picture. And the event center point distance is a Hamming distance between the event picture and the post picture calculated by using a perceptual hash algorithm.
In some embodiments, the calculation of the rechecking similarity is to perform a weighted calculation on the first overlapping proportion, the second overlapping proportion, the event confidence difference and the event center point distance, and then compare the calculated rechecking similarity with a first threshold value set by implementation to determine the event state of the corresponding post picture.
That is, if the review similarity is less than a first threshold, the event state is absent; and if the rechecking similarity is not smaller than a first threshold value, the event state is present. The event status represents the treatment progress of the offending event recorded by the record file, and if the event status is present, the offending event still exists and is not effectively solved.
Step S4: and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
Step S3, obtaining an event coincidence state of each post picture, in the step, firstly counting the number of pictures of the post picture in which the event state exists, and then calculating the proportion of the number of the pictures to the number of the post pictures contained in the post picture set; and if the proportion does not exceed the second threshold, the case review state is changed, and if the proportion exceeds the second threshold, the case review state is not changed. Urban management files which are not modified and exceed the modification time limit enter a field processing link, and if the urban management files have illegal objects, namely main responsible persons can be found, the illegal objects are penalized under the line, such as issuing a ticket; if there is no specific offending object, then the executive is dispatched to handle, such as moving away the offending vehicle. And finally, arranging and archiving the automatically rechecked files.
That is, when the case conforming state of the target case is unmodified, the operator needs to be dispatched for offline treatment, but when the case conforming state of the target case is modified, the operator does not need to be dispatched for offline treatment, so that the city management center can conveniently and quickly determine the unmodified case which needs to be dispatched for offline treatment, wherein for the method and flow for disposing the city management case, please refer to the section 8 of the digital city management information system: setting up, disposing and settling.
Example two
Based on the same concept, the present embodiment further provides a case review device, which is configured to implement the case review method described in the first embodiment, and specifically referring to fig. 2, fig. 2 is a block diagram of a case review device according to an embodiment of the present application, and as shown in fig. 2, the device includes:
the acquisition module is used for: the method comprises the steps of acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
and an identification module: the method comprises the steps of acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture;
the first rechecking module: the event state corresponding to the post picture is obtained according to the rechecking similarity of the first identification data and the second identification data;
and a second rechecking module: and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
Example III
The present embodiment also provides an electronic device, referring to fig. 3, comprising a memory 404 and a processor 402, the memory 404 storing a computer program, the processor 402 being configured to run the computer program to perform the steps of any of the case review methods of the above-described embodiment.
In particular, the processor 402 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
The memory 404 may include, among other things, mass storage 404 for data or instructions. By way of example, and not limitation, memory 404 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, solid state Drive (Solid State Drive, SSD), flash memory, optical Disk, magneto-optical Disk, tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 404 may include removable or non-removable (or fixed) media, where appropriate. Memory 404 may include removable or non-removable (or fixed) media, where appropriate. Memory 404 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 404 is a Non-Volatile (Non-Volatile) memory. In a particular embodiment, the Memory 404 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (Electrically Alterable Read-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory 404 (Fast Page Mode Dynamic Random Access Memory FPMDRAM), extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory SDRAM), etc., as appropriate.
Memory 404 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions for execution by processor 402.
The processor 402 implements any of the case review methods of the above embodiments by reading and executing computer program instructions stored in the memory 404.
Optionally, the electronic apparatus may further include a transmission device 406 and an input/output device 408, where the transmission device 406 is connected to the processor 402 and the input/output device 408 is connected to the processor 402.
The transmission device 406 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through the base station to communicate with the internet. In one example, the transmission device 406 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
The input-output device 408 is used to input or output information. In this embodiment, the input information may be a current data table, such as an epidemic situation stream adjustment document, feature data, a template table, and the like, and the output information may be a feature fingerprint, a fingerprint template, text classification recommendation information, a file template configuration mapping table, a file template configuration information table, and the like.
Alternatively, in the present embodiment, the above-mentioned processor 402 may be configured to execute the following steps by a computer program:
acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture;
acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data;
and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and this embodiment is not repeated herein.
In addition, in combination with any of the above-described case review methods in the first embodiment, the embodiments of the present application may be implemented by a computer program product. The computer program product comprises software code portions for performing a case review method implementing any of the above embodiments, when the computer program product is run on a computer.
In addition, in combination with any one of the above case review methods in the first embodiment, the embodiment of the present application may be implemented by providing a readable storage medium. The readable storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements any of the case review methods of the first embodiment described above.
In general, the various embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the invention is not limited thereto. While various aspects of the invention may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
Embodiments of the invention may be implemented by computer software executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets, and/or macros can be stored in any apparatus-readable data storage medium and they include program instructions for performing particular tasks. The computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. The one or more computer-executable components may be at least one software code or a portion thereof. In addition, in this regard, it should be noted that any blocks of the logic flows as illustrated may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on a physical medium such as a memory chip or memory block implemented within a processor, a magnetic medium such as a hard disk or floppy disk, and an optical medium such as, for example, a DVD and its data variants, a CD, etc. The physical medium is a non-transitory medium.
It should be understood by those skilled in the art that the technical features of the above embodiments may be combined in any manner, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as being within the scope of the description provided herein, as long as there is no contradiction between the combinations of the technical features.
The foregoing examples merely represent several embodiments of the present application, the description of which is more specific and detailed and which should not be construed as limiting the scope of the present application in any way. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. The case rechecking method is characterized by comprising the following steps:
acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
acquiring first identification data according to the event picture, and acquiring second identification data according to the post picture, wherein the first identification data comprises a first event type, a first event coordinate frame and a first event confidence coefficient, and the second identification data comprises a second event type, a second event coordinate frame and a second event confidence coefficient;
acquiring the second identification data containing the same event type as the first identification data;
acquiring a first overlapping proportion according to the first event coordinate frame, and acquiring a second overlapping proportion according to the second event coordinate frame, wherein the first overlapping proportion is the proportion of the first event coordinate frame to the event picture, and the second overlapping proportion is the proportion of the second event coordinate frame to the post picture;
acquiring the difference of the event confidence degrees according to the first event confidence degrees and the second event confidence degrees;
calculating the distance between the event center points of the event picture and the post picture;
acquiring the rechecking similarity according to the first overlapping proportion, the second overlapping proportion, the event confidence coefficient difference and the event center point distance;
acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data;
and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
2. The case review method of claim 1, wherein the method of acquiring the incident picture and the corresponding post picture set of the target case comprises:
acquiring file information of a target file;
acquiring the incident picture and a subsequent picture set according to the file information, wherein the subsequent picture set at least comprises a subsequent picture;
calculating scene similarity of the subsequent picture and the incident picture;
and if the scene similarity is greater than a scene similarity threshold, the subsequent picture is a post picture corresponding to the target case.
3. The case review method of claim 2, wherein the method of acquiring the incident screen and the subsequent screen set according to the case information comprises:
acquiring monitoring equipment for acquiring the target file according to the file information;
and the monitoring system acquires the incident picture and the subsequent picture set from the monitoring equipment.
4. The case review method of claim 2, wherein calculating the scene similarity of the subsequent picture and the incident picture comprises:
acquiring a first background area of the incident picture and a second background area of the subsequent picture;
and calculating the scene similarity of the first background area and the second background area according to the scene similarity of the first background area and the second background area.
5. The case review method of claim 1, wherein the event center point distance is a hamming distance between the event picture and the post picture calculated using a perceptual hash algorithm.
6. The case review method of claim 1 wherein the event status is absent if the review similarity is less than a first threshold; and if the rechecking similarity is not smaller than a first threshold value, the event state is present.
7. The case review method of claim 1, wherein the method of judging the case review state of the target case according to the event state corresponding to each of the post pictures comprises:
counting the number of pictures of the post picture which is in the event state, and calculating the proportion of the number of pictures to the number of post pictures contained in the post picture set; and if the proportion does not exceed the second threshold, the case review state is changed, and if the proportion exceeds the second threshold, the case review state is not changed.
8. The case rechecking device is characterized by comprising the following modules:
the acquisition module is used for: the method comprises the steps of acquiring an incident picture of a target file and a corresponding post picture set, wherein the post picture set at least comprises post pictures;
and an identification module: the method comprises the steps that first identification data are obtained according to an event picture, second identification data are obtained according to a post picture, the first identification data comprise a first event type, a first event coordinate frame and a first event confidence level, and the second identification data comprise a second event type, a second event coordinate frame and a second event confidence level;
the first rechecking module: the method comprises the steps of acquiring second identification data which contains the same event type as the first identification data, acquiring a first overlapping proportion according to the first event coordinate frame, acquiring a second overlapping proportion according to the second event coordinate frame, wherein the first overlapping proportion is the proportion of the first event coordinate frame to the event picture, the second overlapping proportion is the proportion of the second event coordinate frame to the event picture, acquiring event confidence coefficient difference sizes according to the first event confidence coefficient and the second event confidence coefficient, calculating event center point distances between the event picture and the event picture, and acquiring the rechecking similarity according to the first overlapping proportion, the second overlapping proportion, the event confidence coefficient difference sizes and the event center point distances; acquiring an event state corresponding to the post picture according to the rechecking similarity of the first identification data and the second identification data;
and a second rechecking module: and judging the case rechecking state of the target case according to the event state corresponding to each post picture.
9. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of case review according to any of claims 1 to 7.
10. A readable storage medium, characterized in that the readable storage medium has stored therein a computer program comprising program code for controlling a process to execute a process comprising the case review method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111110920.5A CN113807445B (en) | 2021-09-23 | 2021-09-23 | File rechecking method and device, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111110920.5A CN113807445B (en) | 2021-09-23 | 2021-09-23 | File rechecking method and device, electronic device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113807445A CN113807445A (en) | 2021-12-17 |
| CN113807445B true CN113807445B (en) | 2024-04-16 |
Family
ID=78940092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111110920.5A Active CN113807445B (en) | 2021-09-23 | 2021-09-23 | File rechecking method and device, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113807445B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930566A (en) * | 2019-11-20 | 2020-03-27 | 杭州四方博瑞科技股份有限公司 | Safe rechecking method, system and device for vehicles to and from prisons and storable medium |
| WO2020108573A1 (en) * | 2018-11-28 | 2020-06-04 | 杭州海康威视数字技术股份有限公司 | Blocking method for video image, device, apparatus, and storage medium |
| CN113011497A (en) * | 2021-03-19 | 2021-06-22 | 城云科技（中国）有限公司 | Image comparison method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3811323A4 (en) * | 2018-06-19 | 2022-03-09 | Thomson Reuters Enterprise Centre GmbH | Systems and methods for determining structured proceeding outcomes |
-
2021
- 2021-09-23 CN CN202111110920.5A patent/CN113807445B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020108573A1 (en) * | 2018-11-28 | 2020-06-04 | 杭州海康威视数字技术股份有限公司 | Blocking method for video image, device, apparatus, and storage medium |
| CN110930566A (en) * | 2019-11-20 | 2020-03-27 | 杭州四方博瑞科技股份有限公司 | Safe rechecking method, system and device for vehicles to and from prisons and storable medium |
| CN113011497A (en) * | 2021-03-19 | 2021-06-22 | 城云科技（中国）有限公司 | Image comparison method and system |
Non-Patent Citations (1)
| Title |
|---|
| 视频监控系统在公安工作中的深度应用;李蕊;杨静;;河北公安警察职业学院学报(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807445A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2742442B1 (en) | A method for detecting a copy of a reference video, corresponding apparatus for extracting a spatio-temporal signature from video data and corresponding computer readable storage medium | |
| CN110033018B (en) | Graph similarity judging method and device and computer readable storage medium | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
| CN113298080B (en) | Target detection enhancement model, target detection method, target detection device and electronic device | |
| CN111368867B (en) | File classifying method and system and computer readable storage medium | |
| CN107133629B (en) | Picture classification method and device and mobile terminal | |
| CN111444793A (en) | Bill recognition method, equipment, storage medium and device based on OCR | |
| CN110910360B (en) | Positioning method of power grid image and training method of image positioning model | |
| CN112668423B (en) | Corridor sundry detection method and device, terminal equipment and storage medium | |
| CN115828112A (en) | Fault event response method and device, electronic equipment and storage medium | |
| CN114638633A (en) | Abnormal flow detection method and device, electronic equipment and storage medium | |
| CN115424053B (en) | Small sample image recognition method, device, equipment and storage medium | |
| CN111882034A (en) | Neural network processing and face recognition method, device, equipment and storage medium | |
| CN112183542A (en) | Text image-based recognition method, device, equipment and medium | |
| CN112966687B (en) | Image segmentation model training method and device and communication equipment | |
| CN111488829A (en) | Pole tower inspection photo classification method and device, electronic equipment and storage medium | |
| CN113505261B (en) | Data labeling method and device and data labeling model training method and device | |
| CN114387062A (en) | Training of housekeeper recommendation model, housekeeper recommendation method and electronic equipment | |
| CN113705468A (en) | Digital image identification method based on artificial intelligence and related equipment | |
| CN113807445B (en) | File rechecking method and device, electronic device and readable storage medium | |
| CN111626313B (en) | Feature extraction model training method, image processing method and device | |
| CN111461905A (en) | Vehicle insurance fraud and claim evasion method and device, computer equipment and storage medium | |
| CN112990350B (en) | Target detection network training method and target detection network-based coal and gangue identification method | |
| CN114218383A (en) | Method, device and application for judging repeated events |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |