CN110543857A - Contraband identification method, device and system based on image analysis and storage medium - Google Patents
Contraband identification method, device and system based on image analysis and storage medium Download PDFInfo
- Publication number
- CN110543857A CN110543857A CN201910837281.9A CN201910837281A CN110543857A CN 110543857 A CN110543857 A CN 110543857A CN 201910837281 A CN201910837281 A CN 201910837281A CN 110543857 A CN110543857 A CN 110543857A
- Authority
- CN
- China
- Prior art keywords
- contraband
- detailed information
- image
- module
- ray image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention relates to the technical field of security inspection, in particular to a contraband identification method, a device, a system and a storage medium based on image analysis, wherein the method comprises the following steps: the method comprises the steps of obtaining an output video stream through a collection card, inputting the video stream to obtain an X-ray image, preprocessing the X-ray image, establishing a deep convolutional neural network model, inputting the preprocessed X-ray image into a deep convolutional neural network to extract features, obtaining detailed information of an object to be detected, eliminating elements with confidence coefficients smaller than a certain threshold value and elements with overlarge confidence coefficients to obtain a final predicted forbidden object list and a region of the forbidden object on the X-ray image, inputting the features of the object to be detected into the forbidden object list to identify, sending the detailed information of the forbidden object to a display terminal of a security inspection machine, and repeating the method within a specified time to realize efficient and real-time detection.
Description
Technical Field
The invention relates to the technical field of security inspection, in particular to a contraband identification method, a contraband identification device, a contraband identification system and a storage medium based on image analysis.
background
the security inspection machine is an electronic device which sends the checked luggage into an X-ray inspection channel by means of a conveyor belt to complete inspection, and is widely applied to places such as airports, stations, subway stations, government buildings, conference centers, industrial inspection and the like.
Regarding the recognition accuracy of the current intelligent security inspection system, the level of replacing manual adherence security inspection cannot be achieved, and the function of the current intelligent detection system for intelligent detection of bright and forbidden objects is mainly to assist security inspection personnel to perform intelligent screening processing of security inspection images in the security inspection environment with low or medium security inspection intensity requirements, so as to reduce the working intensity of the security inspection personnel or improve the working efficiency, even reduce the configuration of the security inspection personnel, and reduce the security cost. Therefore, the intelligent security check system is used in a security check environment without high security check intensity requirements, and with the improvement of identification accuracy, the intelligent security check system is expected to replace manual adherence in the future.
disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides an efficient and real-time security inspection method, which includes the following steps:
Step S1: acquiring an output video stream of a security check machine through an acquisition card;
step S2: taking the output video stream obtained in the step S1 as an input video stream V of the method, obtaining video frames at a certain time interval, wherein each obtained video frame is an X-ray image generated by a security inspection machine, and preprocessing the obtained X-ray image by Canny operator for edge detection and cutting to obtain a preprocessed X-ray image;
Step S3: collecting a large number of real security check machine images to form a training image data set I, determining a contraband classification set to be detected, carrying out a fine artificial labeling set G on the images, noting that the contraband information comprises positions and corresponding classifications, expanding image enhancement technologies such as overturning, noise adding, zooming and the like on the image set I, establishing a deep convolutional neural network model F, and carrying out training on a high-performance computer to obtain a trained convolutional neural network F with excellent performance;
step S4: inputting the preprocessed X-ray image obtained in the step S2 into a trained convolutional neural network F for feature extraction to obtain detailed information of the article to be detected, wherein the detailed information comprises position, category, confidence coefficient and the like;
Step S5: removing elements with confidence degrees smaller than a certain threshold value and elements with over-high overlap from the detailed information obtained in the step S4 to obtain a final predicted forbidden object list and a region of the forbidden object on the x-ray image;
Step S6: after the detection is finished, carrying out template matching on the X-ray picture of the article to be detected and the video frame G, obtaining the position P of the article area to be detected in the next X-ray video frame G after the matching is finished, and drawing the detailed information of the predicted forbidden object list by using a drawing line frame at the position P in the X-ray video frame G so that the label of the detected forbidden object is stable at the same position and cannot flash;
step S7: sending the detailed information of the contraband in the identified X-ray image to a display terminal of a security check machine;
Step S8: acquiring images from the video stream every 10 frames by a timer, and repeating the above steps S2 to S7.
Preferably, the edge detection in step S2 is performed by OPENCV, and the preprocessing includes the following steps:
step S21: removing blank parts in the blank parts;
Step S22: deleting error pictures generated by a security check machine;
step S23: extracting a luggage wrapping area from the luggage wrapping area;
step S24: and unifying the styles.
Specifically, the training of the deep convolutional neural network model in step S3 includes the following steps: for each image I belongs to I, the corresponding label G belongs to G, and G is (true position, true category, true confidence), p is (predicted position, predicted category, predicted confidence) f (I), and L is | G-p |; and F is continuously adjusted through ten million-level calculated amount, so that L is optimized to the minimum value.
in order to achieve the above object, the present invention further provides an apparatus for identifying contraband based on image analysis, comprising
The information acquisition module acquires an output video stream of the security check machine through an acquisition card;
the input and preprocessing module is used for preprocessing the input video to obtain a preprocessed X-ray image;
The deep convolutional neural network model establishing and training module is used for establishing a deep convolutional neural network model and performing training to obtain a well-trained convolutional neural network with excellent performance;
The article detection module is used for extracting the characteristics of the preprocessed X-ray image to obtain the detailed information of the article to be detected;
The dangerous goods labeling module is used for labeling the dangerous goods to obtain a final predicted forbidden object list;
The identification module is used for inputting the characteristics of the object to be detected into the contraband list for identification to obtain detailed information of the contraband;
the system comprises a sending module, a receiving module and a display module, wherein the sending module is used for sending detailed information of contraband to a display terminal of a security check machine and displaying the detailed information of the contraband in the current display terminal, and the detailed information of the contraband comprises a position, a category, a confidence coefficient and the like;
And the timing module is used for setting time to carry out efficient and real-time detection on the method.
In order to achieve the above object, the present invention further provides an identification system for contraband based on image analysis, which includes an X-ray security inspection apparatus, a memory, a processor, a display terminal, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of the above method.
the invention has the beneficial effects that:
(1) can provide auxiliary function for the security check personnel, promote security check work efficiency, reduce the false retrieval rate, can reduce the human cost more than 20%.
(2) An efficient and real-time convolutional neural network is designed, a channel is established, and dangerous and suspected dangerous article picture data in a real security inspection scene are collected quickly.
drawings
Fig. 1 is an overall flowchart of a contraband identification method according to embodiment 1 of the present invention.
FIG. 2 is a flow chart of a pre-processing process according to an embodiment of the present invention.
Fig. 3 is a block diagram of a contraband identification apparatus according to embodiment 2 of the present invention.
FIG. 4 is a raw X-ray image of an embodiment of the present invention.
FIG. 5 is an X-ray image after pretreatment according to an embodiment of the present invention.
fig. 6 shows X-ray image information after convolutional neural network analysis according to an embodiment of the present invention.
fig. 7 is a display diagram of contraband in a terminal according to an embodiment of the present invention.
Detailed Description
the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 is a flowchart of the whole embodiment 1 of the method for identifying contraband based on image analysis according to the present invention. As shown in figure 1, the power transmission line corridor forest fire danger early warning method based on satellite remote sensing comprises the following steps:
step S1: the output VGA wire of the security check machine is connected to the acquisition card which the software depends on, and the output video stream of the VGA of the security check machine is acquired through the acquisition card SDK, the video stream is the embodiment of the sensitivity of the security check machine to the X-ray of an object passing through the security check machine, and the video stream has an obvious digital X-ray imaging (DR) style, so that the style of the video stream is maintained during acquisition, and the definition and the fluency are not lower than those of the source video stream.
step S2: taking the output video stream obtained in the step S1 as the input video stream V of the method, obtaining video frames at a certain time interval, wherein each obtained video frame is an X-ray image generated by a security inspection machine, and performing edge detection and clipping preprocessing on the obtained X-ray image through a Canny operator to obtain a preprocessed X-ray image.
in this step, the edge detection is performed using OPENCV, and the preprocessing includes the following steps:
step S21: removing blank parts in the blank parts;
Step S22: deleting error pictures generated by a security check machine;
Step S23: extracting a luggage wrapping area from the luggage wrapping area;
Step S24: unifying the styles;
If the image U belongs to a part of the image V, the method can determine the position and the similarity of the image U in the image V, and the Canny operator of the two images is calculated by continuously sliding the image U on the image V to obtain the matching degree and the matching degree.
Step S3: collecting a large number of real security check machine images to form a training image data set I, determining a contraband classification set to be detected, carrying out a fine artificial labeling set G on the images, noting that the contraband information comprises positions and corresponding classifications, expanding image enhancement technologies such as overturning, noise adding, zooming and the like on the image set I, establishing a deep convolutional neural network model F, carrying out training on a high-performance computer to obtain a trained convolutional neural network F with excellent performance, and training the network to have high recognition rate for x-ray imaging.
In this step, the training of the deep convolutional neural network model includes the following: for each image I belongs to I, the corresponding label G belongs to G, and G is (true position, true category, true confidence), p is (predicted position, predicted category, predicted confidence) f (I), and L is | G-p |; and F is continuously adjusted through ten million-level calculated amount, so that L is optimized to the minimum value.
step S4: inputting the preprocessed X-ray image obtained in the step S2 into a trained convolutional neural network F for feature extraction, and obtaining detailed information of the article to be detected, wherein the detailed information comprises a position, a category, a confidence coefficient and the like.
step S5: and eliminating elements with confidence degrees smaller than a certain threshold value and elements with excessively high overlap from the detailed information obtained in the step S4 to obtain a final predicted forbidden object list and a region of the forbidden object on the x-ray image.
step S6: after the detection is finished, in order to track the position of the detected contraband in the next video frame, the next X-ray video frame G is obtained, the X-ray picture of the object to be detected is matched with the video frame G through a template, the position P of the object area to be detected in the next X-ray video frame G is obtained after the matching is finished, and then the detailed information of the predicted contraband list is drawn by drawing a line frame at the position P in the X-ray video frame G, so that the detected contraband is marked stably at the same position and cannot flicker.
Step S7: and sending the detailed information of the contraband in the identified X-ray image to a display terminal of the security check machine, and displaying the detailed information in the current display terminal so as to be conveniently checked and identified by a security check staff.
Step S8: acquiring images from the video stream every 10 frames by a timer, and repeating the above steps S2 to S7.
example 2
fig. 2 is a block diagram of an embodiment 2 of the contraband identification apparatus based on image analysis according to the present invention. As shown in fig. 2, the present embodiment provides an apparatus for identifying contraband based on image analysis, which includes
The information acquisition module acquires an output video stream of the security check machine through an acquisition card;
The input and preprocessing module is used for preprocessing the input video to obtain a preprocessed X-ray image;
the deep convolutional neural network model establishing and training module is used for establishing a deep convolutional neural network model and carrying out a large amount of training to obtain a well-trained convolutional neural network with excellent performance;
the article detection module is used for extracting the characteristics of the preprocessed X-ray image to obtain the detailed information of the article to be detected;
the dangerous goods labeling module is used for labeling the dangerous goods to obtain a final predicted forbidden object list;
the identification module is used for inputting the characteristics of the object to be detected into the contraband list for identification to obtain detailed information of the contraband;
the system comprises a sending module, a receiving module and a display module, wherein the sending module is used for sending detailed information of contraband to a display terminal of a security check machine and displaying the detailed information of the contraband in the current display terminal, and the detailed information of the contraband comprises a position, a category, a confidence coefficient and the like;
and the timing module is used for setting time to carry out efficient and real-time detection on the method.
Example 3
the embodiment provides an identification system of contraband based on image analysis, which comprises an X-ray security check instrument, a memory, a processor, a display terminal and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the steps of the method when executing the computer program.
Example 4
the present embodiment provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the above-mentioned method.
in summary, the method, the apparatus, the system and the storage medium for identifying contraband based on image analysis disclosed in the above embodiments of the present invention can provide an auxiliary function for security personnel, improve the security efficiency, reduce the false detection rate and reduce the labor cost.
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 understand that the changes or modifications within the technical scope of the present invention are included in the scope of the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.
Claims (6)
1. The method for identifying contraband based on image analysis is characterized by comprising the following steps:
Step S1: acquiring an output video stream of a security check machine through an acquisition card;
Step S2: taking the output video stream obtained in the step S1 as an input video stream V of the method, obtaining video frames at a certain time interval, wherein each obtained video frame is an X-ray image generated by a security inspection machine, and preprocessing the obtained X-ray image by Canny operator for edge detection and cutting to obtain a preprocessed X-ray image;
step S3: collecting a large number of real security check machine images to form a training image data set I, determining a contraband classification set to be detected, carrying out a fine artificial labeling set G on the images, noting that the contraband information comprises positions and corresponding classifications, expanding image enhancement technologies such as overturning, noise adding, zooming and the like on the image set I, establishing a deep convolutional neural network model F, and carrying out training on a high-performance computer to obtain a trained convolutional neural network F with excellent performance;
Step S4: inputting the preprocessed X-ray image obtained in the step S2 into a trained convolutional neural network F for feature extraction to obtain detailed information of the article to be detected, wherein the detailed information comprises position, category, confidence coefficient and the like;
step S5: removing elements with confidence degrees smaller than a certain threshold value and elements with over-high overlap from the detailed information obtained in the step S4 to obtain a final predicted forbidden object list and a region of the forbidden object on the x-ray image;
step S6: after the detection is finished, carrying out template matching on the X-ray picture of the article to be detected and the video frame G, obtaining the position P of the article area to be detected in the next X-ray video frame G after the matching is finished, and drawing the detailed information of the predicted forbidden object list by using a drawing line frame at the position P in the X-ray video frame G so that the label of the detected forbidden object is stable at the same position and cannot flash;
step S7: sending the detailed information of the contraband in the identified X-ray image to a display terminal of a security check machine;
step S8: acquiring images from the video stream every 10 frames by a timer, and repeating the above steps S2 to S7.
2. The method for identifying contraband based on image analysis as claimed in claim 1, wherein: in step S2, the edge detection is performed by OPENCV, and the preprocessing includes the following steps:
Step S21: removing blank parts in the blank parts;
Step S22: deleting error pictures generated by a security check machine;
step S23: extracting a luggage parcel area;
step S24: and unifying the styles.
3. The method for identifying contraband based on image analysis as claimed in claim 1, wherein: the training of the deep convolutional neural network model in step S3 includes the following: for each image I belongs to I, the corresponding label G belongs to G, and G is (true position, true category, true confidence), p is (predicted position, predicted category, predicted confidence) f (I), and L is | G-p |; and F is continuously adjusted through ten million-level calculated amount, so that L is optimized to the minimum value.
4. an identification device of contraband based on image analysis, characterized in that: comprises that
the information acquisition module acquires an output video stream of the security check machine through an acquisition card;
the input and preprocessing module is used for preprocessing the input video to obtain a preprocessed X-ray image;
The deep convolutional neural network model establishing and training module is used for establishing a deep convolutional neural network model and performing training to obtain a well-trained convolutional neural network with excellent performance;
The article detection module is used for extracting the characteristics of the preprocessed X-ray image to obtain the detailed information of the article to be detected;
The dangerous goods labeling module is used for labeling the dangerous goods to obtain a final predicted forbidden object list;
The identification module is used for inputting the characteristics of the object to be detected into the contraband list for identification to obtain detailed information of the contraband;
the system comprises a sending module, a receiving module and a display module, wherein the sending module is used for sending detailed information of contraband to a display terminal of a security check machine and displaying the detailed information of the contraband in the current display terminal, and the detailed information of the contraband comprises a position, a category, a confidence coefficient and the like;
and the timing module is used for setting time to carry out efficient and real-time detection on the method.
5. An identification system of contraband based on image analysis, comprising an X-ray security inspection instrument, a memory, a processor, a display terminal and a computer program stored in the memory and capable of running on the processor, characterized in that: the processor, when executing the computer program, realizes the steps of the method of any of the preceding claims 1 to 3.
6. a computer-readable storage medium having stored thereon a computer program, characterized in that: the program when executed by a processor implements the steps of the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910837281.9A CN110543857A (en) | 2019-09-05 | 2019-09-05 | Contraband identification method, device and system based on image analysis and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910837281.9A CN110543857A (en) | 2019-09-05 | 2019-09-05 | Contraband identification method, device and system based on image analysis and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110543857A true CN110543857A (en) | 2019-12-06 |
Family
ID=68712625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910837281.9A Pending CN110543857A (en) | 2019-09-05 | 2019-09-05 | Contraband identification method, device and system based on image analysis and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543857A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126238A (en) * | 2019-12-19 | 2020-05-08 | 华南理工大学 | X-ray security inspection system and method based on convolutional neural network |
| 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 |
| CN111310635A (en) * | 2020-02-10 | 2020-06-19 | 上海应用技术大学 | Security inspection contraband identification system and method based on TensorFlow |
| CN111323835A (en) * | 2020-03-20 | 2020-06-23 | 安徽启新明智科技有限公司 | Security inspection method and device based on personal bag association |
| 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 |
| CN111582367A (en) * | 2020-05-07 | 2020-08-25 | 电子科技大学 | Small metal threat detection method |
| CN111860510A (en) * | 2020-07-29 | 2020-10-30 | 浙江大华技术股份有限公司 | X-ray image target detection method and device |
| CN112162324A (en) * | 2020-09-02 | 2021-01-01 | 海深智能科技(上海)有限公司 | Intelligent security inspection method for effectively improving contraband identification rate |
| CN112256906A (en) * | 2020-10-23 | 2021-01-22 | 安徽启新明智科技有限公司 | Method, device and storage medium for marking annotation on display screen |
| CN112365450A (en) * | 2020-10-23 | 2021-02-12 | 安徽启新明智科技有限公司 | Method, device and storage medium for classifying and counting articles based on image recognition |
| CN112371540A (en) * | 2020-09-14 | 2021-02-19 | 海深智能科技(上海)有限公司 | Security inspection system capable of automatically sorting contraband |
| CN112884085A (en) * | 2021-04-02 | 2021-06-01 | 中国科学院自动化研究所 | Method, system and equipment for detecting and identifying contraband based on X-ray image |
| CN113326753A (en) * | 2021-05-20 | 2021-08-31 | 同济大学 | X-ray security inspection contraband detection method aiming at overlapping problem |
| CN113449556A (en) * | 2020-03-26 | 2021-09-28 | 顺丰科技有限公司 | Contraband detection method and device, edge computing equipment and storage medium |
| CN113724478A (en) * | 2021-08-31 | 2021-11-30 | 上海中通吉网络技术有限公司 | Intelligent security inspection system based on edge calculation |
| CN113721299A (en) * | 2021-08-31 | 2021-11-30 | 成都智元汇信息技术股份有限公司 | Subway security inspection mode configuration management method |
| CN114049575A (en) * | 2021-10-09 | 2022-02-15 | 国家邮政局邮政业安全中心 | Intelligent detection method and system for contraband of security check machine and electronic equipment |
| CN114113165A (en) * | 2021-12-08 | 2022-03-01 | 北京航星机器制造有限公司 | Luggage interpretation method for security inspection equipment |
| CN114155473A (en) * | 2021-12-09 | 2022-03-08 | 成都智元汇信息技术股份有限公司 | Picture cutting method based on frame compensation, electronic equipment and medium |
| CN114255436A (en) * | 2020-09-11 | 2022-03-29 | 同方威视技术股份有限公司 | Security image recognition system and method based on artificial intelligence |
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
| CN115620385A (en) * | 2022-11-07 | 2023-01-17 | 湖南苏科智能科技有限公司 | Multivariate data-based security check worker attention detection method and system |
| CN117197787A (en) * | 2023-08-09 | 2023-12-08 | 海南大学 | Intelligent security inspection method, device, equipment and medium based on improved YOLOv5 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107871122A (en) * | 2017-11-14 | 2018-04-03 | 深圳码隆科技有限公司 | Safety check detection method, device, system and electronic equipment |
| CN109884721A (en) * | 2018-12-10 | 2019-06-14 | 深圳极视角科技有限公司 | Safety check prohibited items detection method, device and electronic equipment based on artificial intelligence |
| CN109902643A (en) * | 2019-03-07 | 2019-06-18 | 浙江啄云智能科技有限公司 | Intelligent safety inspection method, device, system and its electronic equipment based on deep learning |
| CN109978827A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Violated object recognition methods, device, equipment and storage medium based on artificial intelligence |
| CN110018524A (en) * | 2019-01-28 | 2019-07-16 | 同济大学 | A kind of X-ray safety check contraband recognition methods of view-based access control model-attribute |
-
2019
- 2019-09-05 CN CN201910837281.9A patent/CN110543857A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107871122A (en) * | 2017-11-14 | 2018-04-03 | 深圳码隆科技有限公司 | Safety check detection method, device, system and electronic equipment |
| CN109884721A (en) * | 2018-12-10 | 2019-06-14 | 深圳极视角科技有限公司 | Safety check prohibited items detection method, device and electronic equipment based on artificial intelligence |
| CN110018524A (en) * | 2019-01-28 | 2019-07-16 | 同济大学 | A kind of X-ray safety check contraband recognition methods of view-based access control model-attribute |
| CN109978827A (en) * | 2019-02-25 | 2019-07-05 | 平安科技（深圳）有限公司 | Violated object recognition methods, device, equipment and storage medium based on artificial intelligence |
| CN109902643A (en) * | 2019-03-07 | 2019-06-18 | 浙江啄云智能科技有限公司 | Intelligent safety inspection method, device, system and its electronic equipment based on deep learning |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126238B (en) * | 2019-12-19 | 2023-06-20 | 华南理工大学 | X-ray security inspection system and method based on convolutional neural network |
| CN111126238A (en) * | 2019-12-19 | 2020-05-08 | 华南理工大学 | X-ray security inspection system and method based on convolutional neural network |
| CN111310635A (en) * | 2020-02-10 | 2020-06-19 | 上海应用技术大学 | Security inspection contraband identification system and method based on TensorFlow |
| CN111310635B (en) * | 2020-02-10 | 2024-04-19 | 上海应用技术大学 | TensorFlow-based security inspection contraband identification system and TensorFlow-based security inspection contraband identification method |
| 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 |
| CN111323835A (en) * | 2020-03-20 | 2020-06-23 | 安徽启新明智科技有限公司 | Security inspection method and device based on personal bag association |
| 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 |
| CN111323835B (en) * | 2020-03-20 | 2022-09-16 | 安徽启新明智科技有限公司 | Security inspection method and device based on personal bag association |
| CN113449556A (en) * | 2020-03-26 | 2021-09-28 | 顺丰科技有限公司 | Contraband detection method and device, edge computing equipment and storage medium |
| CN113449556B (en) * | 2020-03-26 | 2024-06-04 | 顺丰科技有限公司 | Contraband detection method and device, edge computing equipment and storage medium |
| CN111582367A (en) * | 2020-05-07 | 2020-08-25 | 电子科技大学 | Small metal threat detection method |
| CN111860510A (en) * | 2020-07-29 | 2020-10-30 | 浙江大华技术股份有限公司 | X-ray image target detection method and device |
| CN112162324A (en) * | 2020-09-02 | 2021-01-01 | 海深智能科技(上海)有限公司 | Intelligent security inspection method for effectively improving contraband identification rate |
| CN114255436A (en) * | 2020-09-11 | 2022-03-29 | 同方威视技术股份有限公司 | Security image recognition system and method based on artificial intelligence |
| CN114255436B (en) * | 2020-09-11 | 2024-03-19 | 同方威视技术股份有限公司 | Security check image recognition system and method based on artificial intelligence |
| CN112371540A (en) * | 2020-09-14 | 2021-02-19 | 海深智能科技(上海)有限公司 | Security inspection system capable of automatically sorting contraband |
| CN112365450A (en) * | 2020-10-23 | 2021-02-12 | 安徽启新明智科技有限公司 | Method, device and storage medium for classifying and counting articles based on image recognition |
| CN112256906A (en) * | 2020-10-23 | 2021-01-22 | 安徽启新明智科技有限公司 | Method, device and storage medium for marking annotation on display screen |
| CN112884085A (en) * | 2021-04-02 | 2021-06-01 | 中国科学院自动化研究所 | Method, system and equipment for detecting and identifying contraband based on X-ray image |
| CN113326753A (en) * | 2021-05-20 | 2021-08-31 | 同济大学 | X-ray security inspection contraband detection method aiming at overlapping problem |
| CN113326753B (en) * | 2021-05-20 | 2022-04-19 | 同济大学 | X-ray security inspection contraband detection method aiming at overlapping problem |
| CN113724478A (en) * | 2021-08-31 | 2021-11-30 | 上海中通吉网络技术有限公司 | Intelligent security inspection system based on edge calculation |
| CN113721299A (en) * | 2021-08-31 | 2021-11-30 | 成都智元汇信息技术股份有限公司 | Subway security inspection mode configuration management method |
| CN113721299B (en) * | 2021-08-31 | 2023-01-10 | 成都智元汇信息技术股份有限公司 | Subway security inspection mode configuration management method |
| CN114049575A (en) * | 2021-10-09 | 2022-02-15 | 国家邮政局邮政业安全中心 | Intelligent detection method and system for contraband of security check machine and electronic equipment |
| CN114113165B (en) * | 2021-12-08 | 2023-08-08 | 北京航星机器制造有限公司 | Row package interpretation method for security inspection equipment |
| CN114113165A (en) * | 2021-12-08 | 2022-03-01 | 北京航星机器制造有限公司 | Luggage interpretation method for security inspection equipment |
| CN114155473A (en) * | 2021-12-09 | 2022-03-08 | 成都智元汇信息技术股份有限公司 | Picture cutting method based on frame compensation, electronic equipment and medium |
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
| CN115620385A (en) * | 2022-11-07 | 2023-01-17 | 湖南苏科智能科技有限公司 | Multivariate data-based security check worker attention detection method and system |
| CN115620385B (en) * | 2022-11-07 | 2023-07-28 | 湖南苏科智能科技有限公司 | Safety inspection staff attention detection method and system based on multivariate data |
| CN117197787A (en) * | 2023-08-09 | 2023-12-08 | 海南大学 | Intelligent security inspection method, device, equipment and medium based on improved YOLOv5 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110543857A (en) | Contraband identification method, device and system based on image analysis and storage medium | |
| CN110363140B (en) | Human body action real-time identification method based on infrared image | |
| CN110705405B (en) | Target labeling method and device | |
| CN110751079A (en) | Article detection method, apparatus, system and computer readable storage medium | |
| CN110070029B (en) | Gait recognition method and device | |
| CN110008909B (en) | Real-name system business real-time auditing system based on AI | |
| CN113365147B (en) | Video editing method, device, equipment and storage medium based on music card point | |
| CN105678213B (en) | Dual-mode mask person event automatic detection method based on video feature statistics | |
| CN109344864B (en) | Image processing method and device for dense object | |
| CN110441320B (en) | Coal gangue detection method, device and system | |
| CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
| CN112784835A (en) | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium | |
| CN110502962A (en) | Mesh object detection method, device, equipment and medium in video flowing | |
| CN112149690A (en) | Tracing method and tracing system based on biological image feature recognition | |
| CN111259763A (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN111126112B (en) | Candidate region determination method and device | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN112581495A (en) | Image processing method, device, equipment and storage medium | |
| CN108563997B (en) | Method and device for establishing face detection model and face recognition | |
| CN108197563B (en) | Method and device for acquiring information | |
| CN107145820B (en) | Binocular positioning method based on HOG characteristics and FAST algorithm | |
| CN104102911A (en) | Image processing for AOI (automated optical inspection)-based bullet appearance defect detection system | |
| CN107403192B (en) | Multi-classifier-based rapid target detection method and system | |
| CN110728316A (en) | Classroom behavior detection method, system, device and storage medium | |
| CN114038010B (en) | Pedestrian attribute identification method, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191206 |