CN110765990A - Intelligent article detection method and system, computing device and storage medium - Google Patents
Intelligent article detection method and system, computing device and storage medium Download PDFInfo
- Publication number
- CN110765990A CN110765990A CN201911387449.7A CN201911387449A CN110765990A CN 110765990 A CN110765990 A CN 110765990A CN 201911387449 A CN201911387449 A CN 201911387449A CN 110765990 A CN110765990 A CN 110765990A
- Authority
- CN
- China
- Prior art keywords
- security inspection
- image
- images
- view
- detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 238000007689 inspection Methods 0.000 claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 description 14
- 238000013135 deep learning Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010606 normalization Methods 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 3
- 239000002360 explosive Substances 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 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
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 150000002739 metals Chemical class 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
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
- G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
- G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
- G06V10/422—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation for representing the structure of the pattern or shape of an object therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- High Energy & Nuclear Physics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The application provides an article intelligent detection method and system, a computing device and a storage medium, wherein the method comprises the steps of acquiring at least two security inspection images comprising the same target object by using a multi-view security inspection machine; preprocessing an image; inputting the preprocessed security inspection images into a preset twin convolutional neural network model for feature extraction, and inputting the extracted features into a target detection network model to obtain candidate predictions of targets on the security inspection images; associating the same target in the obtained target area according to a preset algorithm to obtain a screened prediction result; and outputting a final detection and identification result. An efficient intelligent security inspection system is formed, and the accuracy and the detection speed of identifying dangerous goods by an intelligent method are improved.
Description
Technical Field
The application relates to the technical field of security check, in particular to an intelligent article detection method and system, a computing device and a storage medium.
Background
Security inspection is always an important link for ensuring the security of public places including subways, stations, airports, logistics transit places and the like, security inspection objects are human bodies and objects generally, security inspection targets include but are not limited to metals, compulsories, props, liquids, explosives and the like, after the U.S. 9.11 event, the requirements for security inspection equipment are further improved, security inspection equipment needs to be updated and expanded continuously, in the prior art, magnetic needles, metal weapon detection doors, X-ray detectors, photo and video acquisition equipment, scanning equipment and the like are developed continuously, but in order to enable the equipment to play the roles better in security inspection work, the development of multi-party technology is also needed. For example, the security inspection effect of the equipment such as X-ray detection, scanning and image acquisition can be more fully exerted by increasing the viewing angles, the influence of external factors such as the placement angle of a detection target and the background environment is greatly reduced, the occurrence of the situation that part of dangerous goods are missed and the security inspection purpose cannot be achieved is reduced.
However, the method for manually identifying and positioning contraband at the present stage has obvious disadvantages: 1. the staff carries out object identification for a long time and is bound to generate fatigue, so that the attention is reduced, the identification rate of contraband is reduced, and lawbreakers can take the opportunity; 2. the speed of visual identification by workers is slow, so that the safety inspection working efficiency is low, and the requirement of a large amount of quick safety inspection in the express industry is more difficult to meet; 3. the staff who undertakes the security check monitoring work needs to carry out long-time training before going on duty, can consume a large amount of manpower and materials. The artificial intelligence, particularly the deep learning method, is motivated to establish and simulate the human brain for analysis and learning, the data is explained by simulating the mechanism of the human brain, and the identification of the security inspection contraband is possible by using the deep learning method.
Therefore, developing a method for identifying contraband for multi-view security inspection equipment with artificial intelligence becomes a key problem for security monitoring.
Disclosure of Invention
In view of the above, the present application mainly aims to provide an article intelligent detection method and system, a computing device and a storage medium, so as to solve the technical problem of gaps and defects in the prior art and ensure safety of people and society.
In order to achieve the above object, according to one aspect of the present invention, an intelligent article detection method based on multi-view security inspection is provided.
According to the application, the intelligent article detection method based on multi-view security inspection comprises the following steps:
utilizing a multi-view security inspection machine to perform security inspection scanning on the articles, and acquiring at least two security inspection images including the same target object;
preprocessing an image;
simultaneously inputting the preprocessed security inspection images into a preset twin convolutional neural network model for feature extraction, outputting image features of the images according to the neural network model, and inputting the image features into a target detection network model to obtain a target area of the security inspection images;
the twin convolutional neural network is a weight sharing multilayer neural network based on a deep learning theory;
associating the same target in the obtained target area according to a preset algorithm;
the preset algorithm comprises the following steps:
performing probability matching on the targets in the target areas on the images with different visual angles obtained by the security inspection, and performing size matching on the targets on the associated side according to the image acquisition visual angle of the security inspection machine to form associated targets with high matching degree;
and outputting a final detection and identification result.
Wherein the articles include parcels, luggage, bags, etc., and the number of the target objects in S1 may be one or more.
The preprocessing comprises one or more of image normalization, denoising, background differentiation, artifact removal and edge detection.
The output final detection and recognition results relate to the position and confidence results displayed on the multi-view image.
In a second aspect, an embodiment of the present specification provides an article intelligent detection system based on multi-view security inspection, including:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring at least two security images obtained by scanning articles by a multi-view security inspection machine;
the preprocessing module is used for preprocessing the security inspection image, and the processing mode includes but is not limited to one or more of image normalization, denoising, background differentiation, artifact removal and edge detection.
And the target area extraction module is used for simultaneously inputting the preprocessed images into a pre-trained twin convolutional neural network model for feature extraction, outputting the image features of the images according to the neural network model, and inputting the image features into a target detection network model to obtain the target area of the security inspection image.
And the association module is used for associating the same target on images with different visual angles.
And the identification module is used for outputting a final detection and identification result.
In a third aspect, the present specification discloses a computing device, which includes a memory, a processor, and computer instructions stored in the memory and executable on the processor, wherein the processor executes the instructions to implement the steps of the detection method described above.
In a fourth aspect, embodiments of the present specification disclose a computer-readable storage medium storing computer instructions, which when executed by a processor, implement the steps of the detection method described above.
Has the advantages that: the invention provides an intelligent detection method and system, a computing device and a storage medium suitable for the existing multi-view security inspection equipment, which not only solve the problems of low manual identification efficiency, high cost and low accuracy rate in the security inspection process, but also eliminate the influence of external factors such as the placement angle and the background environment of a detection target on the detection rate by matching security inspection images with different view angles, further improve the accuracy and the detection speed of identifying dangerous goods by using an intelligent method, and form a high-efficiency intelligent security inspection system capable of instantly and accurately acquiring whether the detected goods contain prohibited goods and related prohibited goods information.
Drawings
FIG. 1 is a block diagram of a computing device provided in one or more embodiments of the present description;
fig. 2 is a flowchart of an intelligent article detection method based on multi-view security inspection according to one or more embodiments of the present disclosure;
fig. 3 is a schematic view of a multi-angle security check image of a pistol as a target object in an intelligent article detection method based on a dual-view security check machine according to one or more embodiments of the present disclosure;
fig. 4 is a system block diagram of an intelligent article detection method based on a dual-view security inspection machine according to one or more embodiments of the present disclosure;
fig. 5 is a schematic diagram illustrating size matching of a pistol as a target object in an intelligent article detection method based on a dual-view security inspection machine according to one or more embodiments of the present disclosure;
fig. 6 is a system block diagram of a training process of an intelligent article detection network based on multi-view security inspection according to one or more embodiments of the present disclosure.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
First, the noun terms to which one or more embodiments of the present invention relate are explained.
Contraband: articles that are not legally required to be manufactured, purchased, used, held, stored, transported in and out of the mouth, such as weapons, ammunition, explosive articles (e.g., explosives, detonators, fuse cords, etc.), and the like.
And (4) security inspection images: the security inspection equipment or security inspection machine related to the invention is not limited to the X-ray security inspection equipment by using the image acquired by the security inspection equipment, and the security inspection equipment and/or security inspection machine which can be realized by scanning are both the protection scope of the invention, such as terahertz imaging equipment and the like.
In the present application, an article intelligent detection method and system based on multi-view security inspection, a computing device and a computer readable storage medium are provided, which are described in detail in the following embodiments one by one.
Fig. 1 is a block diagram illustrating a configuration of a computing device 100 according to an embodiment of the present specification. The components of the computing device 100 include, but are not limited to, memory 110 and processor 120. The processor 120 is coupled to the memory 110 via a bus 130 and a database 150 is used to store data.
Computing device 100 also includes access device 140, access device 140 enabling computing device 100 to communicate via one or more networks 160. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 140 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present description, the above-described components of computing device 100 and other components not shown in FIG. 1 may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 1 is for purposes of example only and is not limiting as to the scope of the description. Those skilled in the art may add or replace other components as desired.
Computing device 100 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), a mobile phone (e.g., smartphone), a wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 100 may also be a mobile or stationary server.
Wherein the processor 120 may perform the steps of the method shown in fig. 2. Fig. 2 is a schematic flow chart of an article intelligent detection method based on multi-view security inspection according to an embodiment of the present specification, including steps 202 to 210.
Step 202: utilizing a multi-view security inspection machine to perform security inspection scanning on the articles, and acquiring at least two security inspection images of the same target object; including but not limited to packages, luggage, bags, and the like. The target objects refer to contraband, and due to different image segmentation principles obtained by image acquisition of the security inspection machine and the fact that the number of the contraband in the actual package is not fixed, one or more objects can be arranged in the image obtained by one angle scanning, and one or more target objects can be arranged in the image obtained by one angle scanning. Generally, the number of target objects in images obtained by scanning at different angles is the same, for example, in actual scanning, 3 express packages connected tightly enter a security check machine, and there are usually 3 packages on images at different angles.
The multi-view security inspection machine is a security inspection machine with an X-ray imaging system with more than or equal to two views, and the invention does not limit the specific structure of the multi-view security inspection equipment except the structure described above, as long as the multi-view security inspection equipment can be realized.
For convenience of description, the multi-view security inspection machine in one or more embodiments of the present disclosure is illustrated as a dual-view security inspection machine with X-ray sources located at the bottom (bottom view) and side (side view) of a security chamber, and as an example, a courier package with a pistol.
Referring to fig. 3, in the case that the multi-view security inspection machine is a dual-view security inspection machine with a bottom view and a side view, an express package with a pistol is randomly placed on a security inspection channel, and security inspection is performed on the express package once to obtain two security inspection images containing a target object, namely a bottom view image and a side view image; the target object is a pistol; the bottom-lighting view angle image is 3a and is called as a first view angle image; the side-view image is 3b, referred to as a second-view image.
Step 204: and preprocessing the security inspection image, wherein the processing mode comprises one or more of image normalization, denoising, background differentiation and artifact removing.
The image is normalized by a predetermined size, for example 500 × 500 in this embodiment.
Denoising the image by using a Gaussian smoothing algorithm, wherein the value of each point of the image after the Gaussian smoothing is obtained by weighting and averaging the value of each point and other pixel values in the field; the specific operation is that each pixel in the image is scanned by using a template, the weighted average gray value of the pixels in the field determined by the template is used for replacing the value of the central pixel point of the template, and the filtered image is marked as Ifg：
Represents a center point If(I, j) in the neighborhood IfWeight value of (k, l) point.
After gaussian smoothing, fine noise on the image is removed,although there is some attenuation to the edge information in the image, the edge is preserved against the noise; the background difference algorithm extracts the gray value median of the whole image (500 × 500) as the gray value of the background, and then calculates the difference absolute value between the gray value of each pixel point in the image and the background: i issub＝|IfgBg | where bg is the median of the entire image, and it is known that a foreign object point is a larger difference than the difference between the background point and the background gray scale value, so the absolute value of the difference IsubRegarding the probability that a pixel belongs to a foreign object point, the larger the value, the more likely the corresponding pixel is to be a foreign object point.
Step 206: referring to fig. 4, the preprocessed first perspective image and the preprocessed second perspective image are simultaneously input into a pre-trained twinborn convolutional neural network model for feature extraction, so as to obtain image features, and then the image features are input into a target detection network model, so as to obtain candidate predictions of targets on the security check image, namely the first perspective image and the second perspective image.
The twin convolutional neural network is a weight sharing multilayer neural network based on a deep learning theory, and comprises an architecture of two or more sub-networks, the sub-networks have the same network structure, parameters and weights, the parameters are updated on the two or more sub-networks simultaneously, the weight sharing can reduce the number of parameters for training, and the training efficiency is improved. The Convolutional Neural network model is CNN, which is called Convolutional Neural Networks in english.
Step 208: and (4) aligning the images, and associating the same target obtained in the step 206 according to a preset algorithm to obtain a screened prediction result.
The preset algorithm comprises the following steps:
and performing probability matching on the candidate prediction results of the targets on the first view image and the second view image, and performing size (see figure 5) and position matching on the targets on the associated side according to the image acquisition view of the security inspection machine, so as to form associated targets with high matching degree. The position matching is carried out by taking an express package containing a plurality of articles as an example, and the same target in images obtained from different angles is matched from the plurality of articles according to position information.
Step 210: and post-processing the screened prediction result, outputting the prediction result through drawing and rendering, and displaying the prediction result on a multi-view image of a display terminal by taking a position and confidence coefficient result as content.
The post-processing includes non-maxima suppression, etc.
The invention eliminates the influence of external factors such as the placement angle, the background environment and the like of the detection target on the detection rate, further improves the accuracy and the detection speed of identifying the dangerous goods by the intelligent method, and forms the high-efficiency intelligent security inspection system which can instantly and accurately acquire whether the detected goods contain the contraband and the related contraband information.
Referring to fig. 6, a training process of the multi-view detection network (taking dual-view detection as an example) is shown, which mainly includes the following steps:
1. and collecting the multi-view image set, acquiring the image set and the corresponding target label, and constructing a multi-view training data set.
2. The preset deep learning network model comprises a twin network feature extraction module, a target detection network, an alignment module and a loss calculation module.
The twin network feature extraction module is a twin convolutional neural network model; the target detection network is a convolutional neural network model.
3. The twin network feature extraction module and the target detection network can be pre-trained through the single-view image and the corresponding preset target label, and initial network weight is obtained through pre-training.
The pre-training can accelerate the subsequent multi-view training process and improve the robustness of the network.
4. Initializing a preset deep learning network model according to the pre-training step, inputting the multi-view training data set into the preset deep learning network model for training, and obtaining a trained multi-view target detection model.
The training process comprises: inputting the preprocessed first visual angle image and the preprocessed second visual angle image into a twin network model simultaneously for feature extraction to obtain image features, inputting the image features into a target detection network model to obtain candidate predictions of the images, aligning the probability, the size and the position of the alignment module according to the incidence relation of multiple visual angles to obtain the screened candidate predictions, inputting the screened predictions into a loss calculation module to calculate a loss function, and training the preset deep learning network model through a gradient back-propagation algorithm.
One or more embodiments of the present specification provide an article intelligent detection system, including:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring at least two security images obtained by scanning articles by a multi-view security inspection machine;
the preprocessing module is used for preprocessing the security inspection image, and the processing mode includes but is not limited to one or more of image normalization, denoising, background difference, artifact removal and edge detection;
the twin network feature extraction module is used for simultaneously inputting the preprocessed images into a pre-trained twin convolutional neural network model for feature extraction;
the target detection module is used for inputting the extracted features into a target detection network model to obtain a candidate prediction result of the security check image;
and the image alignment module is used for associating the same target on images with different visual angles. The association is obtained by selecting the high matching degree in a mode of matching the probability, the size and the position of the obtained candidate prediction results of each target on the security inspection images at different angles;
and the result output module is used for outputting the final detection and identification result.
The above is a schematic scheme of an article intelligent detection system based on multi-view security inspection according to this embodiment. It should be noted that the technical solution of the detection system and the technical solution of the detection method belong to the same concept, and details that are not described in detail in the technical solution of the detection system can be referred to the description of the technical solution of the detection method.
An embodiment of the present application further provides a computer readable storage medium, which stores computer instructions, and when the instructions are executed by a processor, the instructions implement the steps of the detection method as described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the detection method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the detection method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or system capable of carrying said computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and the practical application, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.
Claims (8)
1. An article intelligent detection method based on multi-view security inspection is characterized by comprising the following steps:
s1, performing security check scanning on the article by using a multi-view security check machine, and acquiring at least two security check images including the same target object;
s2 preprocessing the image;
s3, inputting the preprocessed security check images into a preset convolutional neural network model for feature extraction, outputting image features of the images according to the neural network model, and inputting the image features into a target detection network model to obtain a target area of the security check images;
s4, associating the same target in the obtained target area according to a preset algorithm;
s5 outputs the final detection and recognition result.
2. The intelligent article detection method based on multi-view security inspection of claim 1, wherein the predetermined convolutional neural network in S3 is a twin convolutional neural network, and comprises an architecture of two or more sub-networks, the sub-networks have the same multi-layer network structure, parameters and weights, and the parameters are updated simultaneously on the two or more sub-networks; the number of the sub-networks is the same as the number of the security inspection images acquired at one time in S1.
3. The intelligent detection method for articles based on multi-view security inspection according to claim 1, wherein the preset algorithm in S4 includes:
and performing probability matching on the targets in the target areas on the images with different visual angles obtained by the primary security inspection, and performing size matching on the targets on the associated side according to the image acquisition visual angle of the security inspection machine, so as to form the associated targets with high matching degree.
4. The intelligent article detection method based on multi-view security inspection according to claim 1, wherein the output final detection and recognition result related to position and confidence level result is displayed on the multi-view image.
5. The utility model provides an article intelligent detection system based on multi-view security check which characterized in that includes:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring at least two security images obtained by scanning articles by a multi-view security inspection machine;
the preprocessing module is used for preprocessing the security inspection image;
the target area extraction module is used for simultaneously inputting the preprocessed images into a pre-trained twin convolutional neural network model for feature extraction, outputting the image features of the images according to the neural network model, and then inputting the image features into a target detection network model to obtain the target area of the security inspection image;
the association module is used for associating the same target on images with different visual angles;
and the identification module is used for outputting a final detection and identification result.
6. The intelligent detection system for articles based on multi-view security inspection according to claim 5, wherein the system is used for implementing the method of any one of claims 1 to 4.
7. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-4 when executing the instructions.
8. A computer-readable storage medium storing computer instructions, which when executed by a processor, perform the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911387449.7A CN110765990A (en) | 2019-12-30 | 2019-12-30 | Intelligent article detection method and system, computing device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911387449.7A CN110765990A (en) | 2019-12-30 | 2019-12-30 | Intelligent article detection method and system, computing device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110765990A true CN110765990A (en) | 2020-02-07 |
Family
ID=69341680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911387449.7A Pending CN110765990A (en) | 2019-12-30 | 2019-12-30 | Intelligent article detection method and system, computing device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765990A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290040A (en) * | 2020-03-12 | 2020-06-16 | 安徽启新明智科技有限公司 | Active double-view-angle correlation method based on image recognition |
| CN111337989A (en) * | 2020-03-20 | 2020-06-26 | 安徽启新明智科技有限公司 | Active double-visual-angle screening method and device for multistage security inspection instrument |
| CN111399073A (en) * | 2020-03-26 | 2020-07-10 | 浙江大华技术股份有限公司 | Intelligent security check method, intelligent security check machine and computer readable storage medium |
| CN111680647A (en) * | 2020-06-12 | 2020-09-18 | 中华人民共和国杭州海关 | Goggles for hazardous chemical substance detection and detection method thereof |
| CN111856604A (en) * | 2020-07-31 | 2020-10-30 | 李国军 | Gate type oblique angle bottom lighting X-ray machine |
| CN112464698A (en) * | 2020-07-27 | 2021-03-09 | 三一重工股份有限公司 | Method and device for identifying material quantity change categories |
| 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 |
| CN113391776A (en) * | 2021-05-24 | 2021-09-14 | 浙江大华技术股份有限公司 | Article information display method, article information display device, electronic device, and storage medium |
| CN114092783A (en) * | 2020-08-06 | 2022-02-25 | 清华大学 | Dangerous goods detection method based on attention mechanism continuous visual angle |
| CN114255344A (en) * | 2020-09-11 | 2022-03-29 | 同方威视技术股份有限公司 | Security check image segmentation method and device, electronic equipment and computer readable medium |
| CN114494891A (en) * | 2022-04-15 | 2022-05-13 | 中国科学院微电子研究所 | Dangerous article identification device and method based on multi-scale parallel detection |
| CN115049620A (en) * | 2022-06-17 | 2022-09-13 | 中轻长泰(长沙)智能科技股份有限公司 | Paper stack appearance detection method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110133741A (en) * | 2019-05-08 | 2019-08-16 | 常州大学 | A kind of automatic safety inspection method of multi-angle of view matching and tracking |
| CN110532886A (en) * | 2019-07-31 | 2019-12-03 | 国网江苏省电力有限公司 | A kind of algorithm of target detection based on twin neural network |
-
2019
- 2019-12-30 CN CN201911387449.7A patent/CN110765990A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110133741A (en) * | 2019-05-08 | 2019-08-16 | 常州大学 | A kind of automatic safety inspection method of multi-angle of view matching and tracking |
| CN110532886A (en) * | 2019-07-31 | 2019-12-03 | 国网江苏省电力有限公司 | A kind of algorithm of target detection based on twin neural network |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290040A (en) * | 2020-03-12 | 2020-06-16 | 安徽启新明智科技有限公司 | Active double-view-angle correlation method based on image recognition |
| CN111337989A (en) * | 2020-03-20 | 2020-06-26 | 安徽启新明智科技有限公司 | Active double-visual-angle screening method and device for multistage security inspection instrument |
| CN111399073A (en) * | 2020-03-26 | 2020-07-10 | 浙江大华技术股份有限公司 | Intelligent security check method, intelligent security check machine and computer readable storage medium |
| CN111680647A (en) * | 2020-06-12 | 2020-09-18 | 中华人民共和国杭州海关 | Goggles for hazardous chemical substance detection and detection method thereof |
| CN112464698A (en) * | 2020-07-27 | 2021-03-09 | 三一重工股份有限公司 | Method and device for identifying material quantity change categories |
| CN112464698B (en) * | 2020-07-27 | 2024-08-23 | 盛景智能科技(嘉兴)有限公司 | Material quantity change category identification method and device |
| CN111856604A (en) * | 2020-07-31 | 2020-10-30 | 李国军 | Gate type oblique angle bottom lighting X-ray machine |
| CN114092783A (en) * | 2020-08-06 | 2022-02-25 | 清华大学 | Dangerous goods detection method based on attention mechanism continuous visual angle |
| CN114255344A (en) * | 2020-09-11 | 2022-03-29 | 同方威视技术股份有限公司 | Security check image segmentation method and device, electronic equipment and computer readable medium |
| 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 |
| CN113391776A (en) * | 2021-05-24 | 2021-09-14 | 浙江大华技术股份有限公司 | Article information display method, article information display device, electronic device, and storage medium |
| CN114494891A (en) * | 2022-04-15 | 2022-05-13 | 中国科学院微电子研究所 | Dangerous article identification device and method based on multi-scale parallel detection |
| CN114494891B (en) * | 2022-04-15 | 2022-07-22 | 中国科学院微电子研究所 | Hazardous article identification device and method based on multi-scale parallel detection |
| CN115049620A (en) * | 2022-06-17 | 2022-09-13 | 中轻长泰(长沙)智能科技股份有限公司 | Paper stack appearance detection method, device, equipment and storage medium |
| CN115049620B (en) * | 2022-06-17 | 2024-03-26 | 中轻长泰(长沙)智能科技股份有限公司 | Paper stack appearance detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765990A (en) | Intelligent article detection method and system, computing device and storage medium | |
| CN110956225B (en) | Contraband detection method and system, computing device and storage medium | |
| US20240046105A1 (en) | Image Quality Assessment Using Similar Scenes as Reference | |
| CN109584248B (en) | Infrared target instance segmentation method based on feature fusion and dense connection network | |
| US20200012923A1 (en) | Computer device for training a deep neural network | |
| US10013615B2 (en) | Inspection methods and devices | |
| CN107563433B (en) | Infrared small target detection method based on convolutional neural network | |
| Narihira et al. | Learning lightness from human judgement on relative reflectance | |
| CN111223099B (en) | Contraband detection method, computing equipment and storage medium | |
| CN109544563B (en) | Passive millimeter wave image human body target segmentation method for security inspection of prohibited objects | |
| Lopez-Tapia et al. | Deep CNNs for object detection using passive millimeter sensors | |
| Smeureanu et al. | Real-time deep learning method for abandoned luggage detection in video | |
| CN108009560B (en) | Commodity image similarity category judgment method and device | |
| CN107292229A (en) | A kind of image-recognizing method and device | |
| Freitas et al. | Convolutional neural network target detection in hyperspectral imaging for maritime surveillance | |
| Chumuang et al. | Analysis of X-ray for locating the weapon in the vehicle by using scale-invariant features transform | |
| CN111144220B (en) | Personnel detection method, device, equipment and medium suitable for big data | |
| CN111931558A (en) | Ship category identification method and system | |
| Taghipour et al. | A bottom-up and top-down human visual attention approach for hyperspectral anomaly detection | |
| CN116778214A (en) | Behavior detection method, device, equipment and storage medium thereof | |
| CN116958615A (en) | Picture identification method, device, equipment and medium | |
| CN113610832A (en) | Logo defect detection method, device, equipment and storage medium | |
| CN113822302A (en) | Training method and device for target detection model | |
| CN108229518B (en) | Statement-based image detection method, device and system | |
| Gong et al. | Enhancing Feature Extraction in DBNet: A Novel Approach with Squeeze-and-Excitation Block and CBAM Module |
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 |
Application publication date: 20200207 |
|
| RJ01 | Rejection of invention patent application after publication |