CN113724478A - Intelligent security inspection system based on edge calculation - Google Patents
Intelligent security inspection system based on edge calculation Download PDFInfo
- Publication number
- CN113724478A CN113724478A CN202111014937.0A CN202111014937A CN113724478A CN 113724478 A CN113724478 A CN 113724478A CN 202111014937 A CN202111014937 A CN 202111014937A CN 113724478 A CN113724478 A CN 113724478A
- Authority
- CN
- China
- Prior art keywords
- contraband
- security inspection
- edge computing
- intelligent
- equipment
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 49
- 238000004364 calculation method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims description 16
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 19
- 238000007726 management method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000001503 joint Anatomy 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention relates to an intelligent security inspection system based on edge calculation, which belongs to the technical field of contraband detection and comprises the following components: the system comprises acquisition equipment, edge computing equipment, a security check identification cloud platform and an intelligent monitoring service system, so that online management is performed after an X-ray picture is acquired, the security check efficiency of logistics is improved, and the labor cost is greatly reduced; meanwhile, the security check picture is stored, so that the remote operation of a professional is realized, and the cheapness of security check identification is improved; and the pictures of the contraband are stored, so that the sharing learning of the contraband pictures is realized.
Description
Technical Field
The invention belongs to the technical field of contraband detection, and particularly relates to an intelligent security inspection system based on edge calculation.
Background
In the field of logistics, there is a need to ensure that express packages are free of contraband. In the prior art, the forbidden articles are detected by locally arranging a traditional X-ray security check machine device.
After the X-ray picture is taken, a professional security check worker is often required to manually check the X-ray picture locally, which has a high requirement on the checking level of the security check worker, and for example, the security check worker is required to be familiar with X-ray imaging of objects made of different materials such as a control cutter, powder, liquid, an electronic product, a battery, a pressure tank and the like. Meanwhile, after the security inspector judges the material classification of the X-ray, the security inspector further judges the outline and the imaging effect of the article to finally confirm whether the article in the package belongs to contraband or not.
The whole process of shooting and identification needs to be carried out in a local environment, the accumulated experience of the current security inspector in X-ray imaging article judgment is completely relied on, and a team master needs to conduct oral-oral mutual teaching by relying on the experience before a new security inspector goes on duty, so that the time consumption is long, and the experience sharing is poor.
Disclosure of Invention
The invention provides an intelligent security inspection system based on edge calculation, which aims to solve the technical problems of poor experience sharing, high labor consumption and long time consumption for contraband identification in the prior art.
The technical scheme provided by the invention is as follows:
on one hand, the intelligent security inspection system based on edge computing comprises acquisition equipment, edge computing equipment, a security inspection identification cloud platform and an intelligent monitoring service system; the acquisition equipment is connected with the edge computing equipment, the security inspection identification cloud platform is connected with the edge detection equipment, and the intelligent monitoring service system is connected with the security inspection identification cloud platform;
the acquisition equipment is used for acquiring an original X-ray picture and respectively transmitting the original X-ray picture to the security check machine and the edge computing equipment;
the edge computing equipment is used for processing the received original X-ray picture through a deep learning algorithm model and outputting structured information data and video streams for local viewing or remote viewing;
the security inspection identification cloud platform is used for acquiring a video stream consisting of X-ray images through the edge computing equipment, inputting the X-ray images into a contraband identification model and identifying whether the X-ray images contain contraband or not;
and the intelligent monitoring service system is used for storing pictures and package information corresponding to the contraband after the contraband is identified, and triggering corresponding warning equipment to give an alarm.
Optionally, the security inspection identification cloud platform is further configured to obtain a contraband sample picture; carrying out segmentation contour labeling on the contraband picture, and determining an initial contraband identification model; and training the initial contraband recognition model according to a preset segmentation network to obtain the contraband recognition model.
Optionally, the initial contraband identification model is yolactt + + model.
Optionally, the case identification cloud platform is further configured to update the contraband identification model through a stored new contraband picture.
Optionally, the method further includes: the alarm device is connected with the edge computing device through a reserved IO driving port;
and the alarm equipment is used for giving an alarm prompt after the video stream contains contraband.
Optionally, the method further includes: an intercept arm coupled to the edge computing device;
the intercepting arm is used for intercepting the corresponding package after the contraband is detected.
The invention has the beneficial effects that:
the intelligent security inspection system based on edge calculation provided by the embodiment of the invention comprises: the system comprises acquisition equipment, edge computing equipment, a security check identification cloud platform and an intelligent monitoring service system, so that online management is performed after an X-ray picture is acquired, the security check efficiency of logistics is improved, and the labor cost is greatly reduced; meanwhile, the security check picture is stored, so that the remote operation of a professional is realized, and the cheapness of security check identification is improved; and the pictures of the contraband are stored, so that the sharing learning of the contraband pictures is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an intelligent security inspection system based on edge computing according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
In order to at least solve the technical problem provided by the present invention, an embodiment of the present invention provides an intelligent security inspection system based on edge calculation.
Fig. 1 is a schematic structural diagram of an intelligent security inspection system based on edge computing according to an embodiment of the present invention.
Referring to fig. 1, the intelligent security inspection system based on edge computing provided in the embodiment of the present invention may include an acquisition device 1, an edge computing device 2, a security inspection identification cloud platform 3, and an intelligent monitoring service system 4; the acquisition equipment 1 is connected with the edge computing equipment 2, the security inspection identification cloud platform 3 is connected with the edge detection equipment 2, and the intelligent monitoring service system is connected with the security inspection identification cloud platform.
The acquisition equipment is used for acquiring original X-ray pictures and respectively transmitting the original X-ray pictures to the security check machine and the edge computing equipment. And the edge computing equipment is used for processing the received original X-ray picture through the deep learning algorithm model and outputting the structured information data and the video stream for local viewing or remote viewing. And the security inspection identification cloud platform is used for acquiring a video stream consisting of X-ray images through the edge computing equipment, inputting the X-ray images into the contraband identification model and identifying whether the X-ray images contain contraband or not. And the intelligent monitoring service system is used for storing pictures and package information corresponding to the contraband after the contraband is identified, and triggering corresponding warning equipment to give an alarm.
For example, the acquisition device may be a nano desktop operation display system, the nano desktop operation display system adopts a pipeline flow technology of video streams, and the GStreamer-based plug-in development performs split-screen processing on the output of the display by using a traditional X-ray security inspection machine, wherein one path is displayed by an original security inspection machine, and the other path is accessed to an existing edge computing box, so that seamless video access to the traditional security inspection machine is realized.
The edge computing device belongs to computing devices, structured information data can be output after processing of a deep learning algorithm model, meanwhile, a video stream of rtsp _ out is output, and display of rtsp output can be accessed locally (real-time processing results can be viewed locally) or rtsp output can be accessed at a far end (real-time processing results can be viewed remotely, and remote operation is achieved).
Optionally, the security inspection identification cloud platform is further configured to obtain a contraband sample picture; carrying out segmentation contour labeling on the contraband picture, and determining an initial contraband identification model; and training an initial forbidden identification model according to a preset segmentation network to obtain the forbidden identification model.
Optionally, the initial violation identification model is yolactt + + model.
Optionally, the case identification cloud platform is further configured to update the contraband identification model through the stored new contraband picture.
For example, video data acquired by the acquisition device can be transmitted to a cloud platform to serve as a data warehouse, and in addition, manually identified data (pictures) can also serve as a labeled sample set and serve as data storage of an algorithm. The data storage with strong integration inclusion can be directly connected with the labeling platform to obtain labeled sample data, and the algorithm can directly use the sample data and output the result calculated by the algorithm. The output result is in butt joint with the intelligent monitoring service system, and related workers feed back the error result through the system to be used as a basis for optimizing and improving the algorithm, so that a closed loop system is formed. Thus, data transfer storage is a precondition for the entire hierarchy.
For example, various core algorithms can be integrated on a case identification cloud platform, so that the case identification cloud platform serves the whole intelligent security check system, and the case identification cloud platform can comprise data input, calculation and output; the case recognition cloud platform can be responsible for algorithms, the algorithms in the case recognition cloud platform can be added, deleted, changed and checked, the fact that the iteration can be updated at any time along with the diversity of the changing scenes can be guaranteed, efficiency is high, and cost is low. The method comprises the steps that a contraband identification model can be built, when the model is built, edge computing equipment can be adopted to collect X-ray images of a security inspection machine, samples of contraband are obtained, the X-ray images are labeled by using labelme to segment outlines, and an initial contraband identification model is determined; and training an initial forbidden identification model according to a preset segmentation network to obtain the forbidden identification model.
The method can adopt a segmentation network training forbidden identification model and a deep learning model yolact + + for model training, and because a large amount of samples of prohibited articles are difficult to collect, a small amount of models can be used for realizing rapid convergence by adopting the yolact + + model. The model adopts a one-stage method, leads the MaskRcnn of the two-stage on the reasoning speed, and simultaneously provides a new NMS algorithm called Fast-NMS, which has only slight precision loss compared with the traditional NMS algorithm but greatly improves the segmentation speed. The yloct + + introduces variable convolution in the backhaul, and uses free-form sampling to replace rigid grid sampling used in the traditional CNN, so that the precision of each detection segmentation model is completely refreshed.
In the application, a trained yolac + + model can be converted into onx and then subjected to Tensorrt acceleration, the separation pretreatment, the Tensorrt part and the post-treatment part are carried out, then the plugin of Gstreamer is developed and integrated into the whole pipeline, the real-time identification of contraband is carried out, the video stream of rtsp is output at the same time, the real-time playing of a web browser end is supported, and the remote sharing of a working screen of security supervision is realized. And based on the realized algorithm, completing the work of software interface and the like, constructing a dangerous goods image library based on the X-ray machine image on the basis of the realization of the traditional algorithm, and completing the marking of the dangerous goods image. Therefore, a dangerous goods identification system based on the deep neural network can be realized on the basis of the library, and the identification accuracy is further improved.
In the application, the intelligent security inspection system based on the edge calculation improves the intelligent identification capability of a contraband machine by learning a large number of contraband X-ray samples manually identified by security inspectors through a deep learning model, and the deep learning model is deployed to an ARM chip edge GPU calculation power box after being accelerated through branch subtraction to solve the problem that the experience of the traditional security inspectors cannot be shared.
Optionally, the method further includes: the alarm device is connected with the edge computing device through the reserved IO driving port; the alarm device is used for giving an alarm prompt after the video stream contains contraband.
Optionally, the method further includes: an intercept arm connected to the edge computing device; the interception arm is used for intercepting the corresponding package after detecting the contraband.
For example, the alarm device includes a voice prompt and an interception arm, the signal input source of the interception arm is accessed through a reserved IO driver port of the edge computing device, and when the video stream detects contraband, the voice prompt drives the interception arm to intercept the contraband to the dangerous goods area.
For example, in the application, web multi-client continuous and stable video stream playing can be supported according to video stream protocol conversion. The original video collected from the security inspection machine camera comprises H264 and H265 codes, and rtsp video streaming service is provided through NVR equipment. In the application, a server and a client can be designed. The server side reads rtsp video stream data, transcodes the rtsp video stream data into h264 video coding in an flv format in a unified mode, outputs each frame of video data by using stream api provided by nodejs, and transmits the video data to the web side through websocket. The client side, namely a web browser side, creates a video label in the browser by using MSE (media Source extensions) characteristics of the browser, uses the media Source as a data Source thereof, starts decoding the flv format when receiving data transmitted from the websocket, and can realize real-time playing by adding the decoded data into a Buffer of the media Source.
In the application, the video is in an flv format, and no common fMP4 packaging is adopted, the flv packaging has the advantages of small size and simplicity in coding and decoding, is suitable for network transmission, and has the characteristic of low delay by adopting websocket transmission.
The intelligent monitoring service system can be provided for relevant personnel to carry out work processing. And (4) concentrating the hardware equipment of the security check machine of the whole network and the monitoring data of the whole network into a unified system, and managing the security check process. For example, the method can be used for butt-jointing each business system of a logistics enterprise to obtain the bill information, the appearance picture and the X-ray picture of the express, and if contraband is detected, the contraband identification picture is synchronously stored, so that real-time updating and after-the-fact tracing are facilitated. For example, the monitoring picture of the security check machine can be checked and played, the security check personnel can remotely and simultaneously monitor a plurality of security check machines, if abnormal dangerous articles occur, the system can synchronously perform early warning except for local early warning of the security check machines, and the security check personnel judge whether violation occurs or contact field personnel to perform related processing by checking pictures in early warning information. For example, the security check machine and other related devices related to the system can be used for inputting basic information, operation conditions and the like of the devices into the system for unified management, so that the efficiency is improved, and the personnel cost is reduced.
The intelligent security check system based on the edge calculation can be connected with an intelligent security check machine in a butt joint mode, overcomes the defects that the intelligent security check machine cannot share data with the traditional security check machine and cannot form overall management, manages the operation condition of the security check machine by storing and fusing the data of the intelligent security check machine, and improves the identification accuracy and the management efficiency by complementing the algorithm of the intelligent security check machine.
According to the intelligent security inspection system based on edge computing, provided by the embodiment of the invention, the traditional security inspection machine and the advanced intelligent security inspection machine are integrated through hardware equipment, edge computing equipment, a security inspection identification cloud platform, an intelligent monitoring service system and the like, so that overall management is realized, the waste of resources is avoided, the security inspection management efficiency of enterprises, particularly logistics enterprises, is improved, and the labor cost is greatly reduced.
The intelligent security inspection system based on the edge calculation, provided by the embodiment of the invention, preprocesses the image in the distribution center through the edge calculation equipment, can perform on-site early warning in real time while reducing the pressure transmitted to the headquarter for processing, can perform related processing on site according to the early warning, and stores early warning and processing records by the system, so that the remote operation of professional security inspection personnel is realized, and the processing process of no security inspection personnel on site is realized.
The intelligent security inspection system based on edge calculation provided by the embodiment of the invention realizes the construction and scraping of samples. Which may be understood as the storage and processing of data. Taking the Zhongtong as an example, the whole network has 20000 security check machines, the average daily total processing unit amount is 5000w-6000w units, each security check machine cannot store the processed data, and the abnormal data cannot be stored as a sample, so that the method is extremely resource-wasting. This application carries out the mark of sample with the data of anomaly through hardware equipment, data platform with the data storage of whole net, as the sample set of study for 20000 platform safety inspection machine can share sample resource in step, gets the strong point and makes up the weak point, and the degree of accuracy is higher.
The algorithm has strong pertinence and high plasticity. The application aims at the security inspection operation of logistics enterprises, various dangerous goods are identified through the algorithm platform, the existing algorithm of the intelligent security inspection machine can be fused, the complementation of the algorithm is formed, the inclusion is stronger, and the plasticity is higher.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (6)
1. An intelligent security inspection system based on edge calculation, comprising: the system comprises acquisition equipment, edge computing equipment, a security inspection identification cloud platform and an intelligent monitoring service system; the acquisition equipment is connected with the edge computing equipment, the security inspection identification cloud platform is connected with the edge detection equipment, and the intelligent monitoring service system is connected with the security inspection identification cloud platform;
the acquisition equipment is used for acquiring an original X-ray picture and respectively transmitting the original X-ray picture to the security check machine and the edge computing equipment;
the edge computing equipment is used for processing the received original X-ray picture through a deep learning algorithm model and outputting structured information data and video streams for local viewing or remote viewing;
the security inspection identification cloud platform is used for acquiring a video stream consisting of X-ray images through the edge computing equipment, inputting the X-ray images into a contraband identification model and identifying whether the X-ray images contain contraband or not;
and the intelligent monitoring service system is used for storing pictures and package information corresponding to the contraband after the contraband is identified, and triggering corresponding warning equipment to give an alarm.
2. The intelligent security inspection system of claim 1, wherein the security inspection identification cloud platform is further configured to obtain a sample picture of contraband; carrying out segmentation contour labeling on the contraband picture, and determining an initial contraband identification model; and training the initial contraband recognition model according to a preset segmentation network to obtain the contraband recognition model.
3. The intelligent security inspection system of claim 2, wherein the initial contraband identification model is yolactt + + model.
4. The intelligent security inspection system of claim 1, wherein the security inspection recognition cloud platform is further configured to update the contraband recognition model with the stored new contraband picture.
5. The intelligent security check system of claim 1, further comprising: the alarm device is connected with the edge computing device through a reserved IO driving port;
and the alarm equipment is used for giving an alarm prompt after the video stream contains contraband.
6. The intelligent security check system of claim 5, further comprising: an intercept arm coupled to the edge computing device;
the intercepting arm is used for intercepting the corresponding package after the contraband is detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014937.0A CN113724478A (en) | 2021-08-31 | 2021-08-31 | Intelligent security inspection system based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014937.0A CN113724478A (en) | 2021-08-31 | 2021-08-31 | Intelligent security inspection system based on edge calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113724478A true CN113724478A (en) | 2021-11-30 |
Family
ID=78680091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111014937.0A Pending CN113724478A (en) | 2021-08-31 | 2021-08-31 | Intelligent security inspection system based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724478A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200273A (en) * | 2022-02-21 | 2022-03-18 | 东营市沃格艾迪石油技术有限公司 | Fault prediction system for online insulation monitoring of electric submersible pump |
| CN114727062A (en) * | 2022-03-28 | 2022-07-08 | 慧之安信息技术股份有限公司 | Penetration detection method and device based on common security video monitoring |
| CN115563396A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Degradable centralized intelligent pushing method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN110889329A (en) * | 2019-10-25 | 2020-03-17 | 浙江大华技术股份有限公司 | Security check machine, security check machine inspection system, video stream processing method and storage medium |
| CN210691345U (en) * | 2019-11-01 | 2020-06-05 | 武汉星形线科技有限公司 | Cloud intelligence safety inspection auxiliary system based on degree of depth learning |
| US20210142636A1 (en) * | 2017-03-01 | 2021-05-13 | Panasonic Intellectual Property Management Co., Ltd. | Three-dimensional intrusion detection system and three-dimensional intrusion detection method |
| CN112967289A (en) * | 2021-02-08 | 2021-06-15 | 上海西井信息科技有限公司 | Security check package matching method, system, equipment and storage medium |
| CN213954809U (en) * | 2020-12-15 | 2021-08-13 | 杭州亿圣信息技术有限公司 | Security check system composed of camera, edge computing terminal and local server |
-
2021
- 2021-08-31 CN CN202111014937.0A patent/CN113724478A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210142636A1 (en) * | 2017-03-01 | 2021-05-13 | Panasonic Intellectual Property Management Co., Ltd. | Three-dimensional intrusion detection system and three-dimensional intrusion detection method |
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN110889329A (en) * | 2019-10-25 | 2020-03-17 | 浙江大华技术股份有限公司 | Security check machine, security check machine inspection system, video stream processing method and storage medium |
| CN210691345U (en) * | 2019-11-01 | 2020-06-05 | 武汉星形线科技有限公司 | Cloud intelligence safety inspection auxiliary system based on degree of depth learning |
| CN213954809U (en) * | 2020-12-15 | 2021-08-13 | 杭州亿圣信息技术有限公司 | Security check system composed of camera, edge computing terminal and local server |
| CN112967289A (en) * | 2021-02-08 | 2021-06-15 | 上海西井信息科技有限公司 | Security check package matching method, system, equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200273A (en) * | 2022-02-21 | 2022-03-18 | 东营市沃格艾迪石油技术有限公司 | Fault prediction system for online insulation monitoring of electric submersible pump |
| CN114200273B (en) * | 2022-02-21 | 2022-05-03 | 东营市沃格艾迪石油技术有限公司 | Fault prediction system for online insulation monitoring of electric submersible pump |
| CN114727062A (en) * | 2022-03-28 | 2022-07-08 | 慧之安信息技术股份有限公司 | Penetration detection method and device based on common security video monitoring |
| CN115563396A (en) * | 2022-12-06 | 2023-01-03 | 成都智元汇信息技术股份有限公司 | Degradable centralized intelligent pushing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113724478A (en) | Intelligent security inspection system based on edge calculation | |
| WO2019137196A1 (en) | Image annotation information processing method and device, server and system | |
| CN110516529A (en) | It is a kind of that detection method and system are fed based on deep learning image procossing | |
| CN104333736A (en) | Intelligent recognition monitoring system and method for unmanned substation | |
| CN107145821A (en) | A kind of crowd density detection method and system based on deep learning | |
| CN112434880A (en) | Patrol route planning and patrol personnel management system based on deep learning | |
| CN111798572A (en) | Machine room virtual inspection method and system | |
| JP2022000776A (en) | Test method, device and apparatus for traffic flow monitoring measurement system | |
| CN114419556A (en) | Abnormal drainage image identification method and system for drainage pipe network drainage port | |
| CN111353436A (en) | Super store operation analysis method and device based on image deep learning algorithm | |
| CN114071232B (en) | Audio and video quality visualization method and device, equipment, medium and product thereof | |
| CN113094325B (en) | Device deployment method, device, computer system and computer readable storage medium | |
| CN109074300A (en) | Bottleneck in detection and prediction complication system | |
| CN211184122U (en) | Intelligent video analysis system for linkage of railway operation safety prevention and control and large passenger flow early warning | |
| CN111951258A (en) | Goods shelf out-of-stock early warning analysis system and method based on edge calculation | |
| CN113516102A (en) | Deep learning parabolic behavior detection method based on video | |
| CN107643730A (en) | Production safety management device based on technology of Internet of things | |
| CN115019008B (en) | Intelligent 3D model design analysis service management platform | |
| CN102984503A (en) | Network video storage server system | |
| KR20220004606A (en) | Signal lamp recognition method, device, apparatus, and storage medium and computer program | |
| CN111709928A (en) | Video-based near-shore wave height real-time detection system | |
| CN114419502A (en) | Data analysis method and device and storage medium | |
| CN102355575A (en) | Distributed video monitoring device with pre-warning function | |
| CN117037059A (en) | Equipment management method and device based on inspection monitoring and electronic equipment | |
| CN112333434A (en) | Intelligent video analysis system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211130 |