CN114241607B - Personnel swivel chair detection method and system thereof - Google Patents
Personnel swivel chair detection method and system thereof Download PDFInfo
- Publication number
- CN114241607B CN114241607B CN202210146580.XA CN202210146580A CN114241607B CN 114241607 B CN114241607 B CN 114241607B CN 202210146580 A CN202210146580 A CN 202210146580A CN 114241607 B CN114241607 B CN 114241607B
- Authority
- CN
- China
- Prior art keywords
- human body
- detection
- axis data
- filtered
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a personnel swivel chair detection method and a system thereof, comprising the following steps: acquiring a detection image; acquiring a pre-trained neural network model, and inputting the detection images into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points; filtering the x-axis data of the coordinate information to generate filtered x-axis data, and generating a moving curve based on the filtered x-axis data and time information of an image frame corresponding to the filtered x-axis data; carrying out normalization processing on the filtered x-axis data and constructing a standard cosine curve; and performing similarity calculation based on the moving curve and the standard cosine curve and generating a detection result.
Description
Technical Field
The invention relates to the technical field of image detection, in particular to a personnel swivel chair detection method and a personnel swivel chair detection system.
Background
At present, for the external service posts (such as banks, public institutions, insurance companies and the like) of most enterprises, the regulations of the behavior of the ceremony instrument exist, such as the fact that the staff is not allowed to sit on a swivel chair to rotate, and the like, and therefore, the real-time detection of the behavior of the staff is needed.
However, the conventional deep learning network is identified based on the action identification model and is limited by the influence of insufficient materials, insufficient generalization, different practical application scenes and other factors of the training set, so that the action identification accuracy or the reliability of the deep learning network is low.
In conclusion, the existing personnel swivel chair detection method has the problem of low accuracy.
Disclosure of Invention
In view of this, the invention provides a method and a system for detecting a swivel chair, which solve the problem of low accuracy in the conventional method for detecting a swivel chair by improving a data extraction and processing method of the swivel chair.
In order to solve the problems, the technical scheme of the invention is to adopt a personnel revolving chair detection method, which comprises the following steps: acquiring a detection image; acquiring a pre-trained neural network model, and inputting the detection images into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points; filtering the x-axis data of the coordinate information to generate filtering x-axis data, and generating a moving curve based on the filtering x-axis data and time information of the image frame corresponding to the filtering x-axis data; carrying out normalization processing on the filtered x-axis data and constructing a standard cosine curve; and performing similarity calculation based on the moving curve and the standard cosine curve and generating a detection result.
Optionally, inputting the detection image frame by frame into the neural network model to generate coordinate information of the human body key point, including: predicting and generating human body detection frame information and key point coordinates in the detection image based on the neural network model; updating the coordinates of the lower left corner of the detection frame contained in the human body detection frame information to the origin of a coordinate system, and establishing a human body target frame coordinate system; carrying out affine transformation on the updated human body detection frame information (x, y, w, h) and a preset rectangular region to generate an affine matrix; and generating coordinate information of the human body key points by the key point coordinates through the affine matrix.
Optionally, a filtering method used for filtering the x-axis data of the coordinate information is kalman filtering.
Optionally, the normalizing the filtered x-axis data and constructing a standard cosine curve includes: extracting unit image acquisition period of the filtered x-axis data; extracting peaks and troughs of the filtered x-axis data in a unit image acquisition period; and generating the standard cosine curve based on the unit image acquisition period and the wave crests and wave troughs.
Optionally, training the neural network model comprises: constructing an initialization network model, wherein the network model comprises a semantic segmentation model; acquiring a training data set and a testing data set which are formed by image samples containing multi-class marks, wherein the mark classes comprise human body detection frames and human body key points; training and testing the neural network model based on the training dataset and the testing dataset.
Optionally, performing similarity calculation based on the moving curve and the standard cosine curve and generating a detection result, including: performing Pearson similarity calculation based on the movement curve and the standard cosine curve and generating a similarity value; and if the similarity value is not higher than the preset threshold value, generating a detection result of the non-revolving chair.
Optionally, the human body key point is any one point of a human body double shoulder point, a human body left shoulder point and a human body right shoulder point.
Accordingly, the present invention provides a person swivel chair detection system, comprising: the camera shooting unit is used for collecting a detection image; the data processing unit is used for acquiring a pre-trained neural network model, inputting the detection image into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points, filtering x-axis data of the coordinate information to generate filtering x-axis data, generating a moving curve based on the filtering x-axis data and time information of an image frame corresponding to the filtering x-axis data, normalizing the filtering x-axis data and constructing a standard cosine curve, and performing similarity calculation based on the moving curve and the standard cosine curve to generate a detection result.
Optionally, the data processing unit further includes a cache module, configured to store the detection image, the human body detection frame information, the coordinate information of the human body key point, and the swivel chair detection result.
The invention has the primary improvement that the provided swivel chair detection method utilizes the characteristic that the shoulders of a person regularly sway left and right in the swivel chair process, extracts human body detection frame information and key point coordinates through a neural network, reconstructs a human body target frame coordinate system based on the human body detection frame information and generates an affine matrix, further generates coordinate information of the human body key points based on the affine matrix and the key point coordinates, and avoids the influence of the change of the human body key point coordinates caused by the position movement of the human body. Meanwhile, similarity calculation is carried out by constructing the actually measured moving curve and the standard cosine curve generated by the theoretical revolving chair behavior, so that whether personnel are transferred or not is judged, and the problem of low accuracy in the traditional personnel revolving chair detection method is effectively solved.
Drawings
FIG. 1 is a simplified flow diagram of a person swivel detection method of the present invention;
fig. 2 is a simplified unit connection diagram of the person swivel detection system of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a method for detecting a revolving chair for people includes: acquiring a detection image; acquiring a pre-trained neural network model, and inputting the detection images into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points; filtering the x-axis data of the coordinate information to generate filtered x-axis data, and generating a moving curve based on the filtered x-axis data and time information of an image frame corresponding to the filtered x-axis data; carrying out normalization processing on the filtered x-axis data and constructing a standard cosine curve; and performing similarity calculation based on the moving curve and the standard cosine curve and generating a detection result. Filtering the x-axis data of the coordinate information by using a Kalman filtering method; the human body key point is any one point of a human body double shoulder point, a human body left shoulder point and a human body right shoulder point.
Further, inputting the detection image frame by frame into the neural network model to generate coordinate information of the human body key points, including: predicting and generating human body detection frame information and key point coordinates in the detection image based on the neural network model; updating the coordinates of the lower left corner of the detection frame contained in the human body detection frame information to the origin of a coordinate system, and establishing a human body target frame coordinate system; carrying out affine transformation on the updated human body detection frame information (x, y, w, h) and a preset rectangular region to generate an affine matrix; and generating coordinate information of the human body key points by the key point coordinates through the affine matrix. The size of the preset rectangular area can be defined by a user according to the detection precision of the camera, the actual monitoring requirement and the distance between the camera and a detected person, and the numerical value of the preset rectangular area is not specifically limited in the application.
Furthermore, to facilitate understanding of the working principle of generating coordinate information of key points of a human body, an example is given: in the 1920-1080 detected image, the position of a human body target frame is x:200, y:100, w:80 and h120, one key point of the shoulder is x:220, and y:110, after the coordinate system of the human body target frame is converted, the coordinate of the key point is x:20 and y:10, the human body detection frame is changed into x:0, y:0, w:80 and h120, and affine transformation is carried out on the translated position of the human body detection frame, namely x:0, y:0, w:80 and h120, and a preset rectangular area { (0,0) (200 ) (0,200) }, so that an affine matrix is obtained. Therefore, the coordinate information of the key points of the human body is generated by the key points x:20 and y:10 of the shoulders through an affine matrix, and the influence of the coordinate change of the key points of the human body caused by the position movement of the human body is avoided.
Further, the normalizing the filtered x-axis data and constructing a standard cosine curve includes: extracting unit image acquisition period of the filtered x-axis data; extracting peaks and troughs of the filtered x-axis data in a unit image acquisition period; and generating the standard cosine curve based on the unit image acquisition period and the wave crests and wave troughs.
Further, training the neural network model includes: constructing an initialization network model, wherein the network model comprises a semantic segmentation model; acquiring a training data set and a testing data set which are formed by image samples containing multi-class marks, wherein the mark classes comprise human body detection frames and human body key points; training and testing the neural network model based on the training dataset and the testing dataset. It should be noted that the neural network model used in the present application is conventional in the art, and does not relate to further improvement of the model architecture, and therefore, the type and architecture of the neural network model are not specifically limited. The type of the neural network model can be YOLO-V3, FASTER RCNN, and the like.
Further, performing similarity calculation based on the motion curve and the standard cosine curve and generating a detection result, including: performing Pearson similarity calculation based on the movement curve and the standard cosine curve and generating a similarity value; and if the similarity value is not higher than the preset threshold value, generating a detection result of the non-revolving chair. The preset threshold value can be defined by a user according to the detection precision of the camera, the actual monitoring requirement and the distance between the camera and a detected person, and the numerical value of the preset threshold value is not specifically limited in the application.
Further, generating a motion curve based on the filtered x-axis data and the time information of the image frame corresponding to the filtered x-axis data comprises: determining acquisition time information of the image frame corresponding to the filtering x-axis data based on the filtering x-axis data; and constructing a moving curve by taking the acquisition time as an x-axis and the value of the filtered x-axis data as a value of a y-axis.
According to the invention, the characteristic that the shoulders of a person regularly shake left and right in the process of rotating the chair is utilized, after the human body detection frame information and the key point coordinates are extracted through the neural network, the human body target frame coordinate system is reconstructed based on the human body detection frame information and an affine matrix is generated, and then the coordinate information of the human body key points is generated based on the affine matrix and the key point coordinates, so that the influence of the change of the human body key point coordinates caused by the position movement of the human body is avoided. Meanwhile, similarity calculation is carried out by constructing the actually measured moving curve and the standard cosine curve generated by the theoretical revolving chair behavior, so that whether personnel are transferred or not is judged, and the problem of low accuracy in the traditional personnel revolving chair detection method is effectively solved.
Accordingly, as shown in fig. 2, the present invention provides a system for detecting a revolving chair for people, comprising: the camera shooting unit is used for collecting a detection image; the data processing unit is used for acquiring a pre-trained neural network model, inputting the detection image into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points, filtering x-axis data of the coordinate information to generate filtered x-axis data, generating a moving curve based on the filtered x-axis data and time information of an image frame corresponding to the filtered x-axis data, performing normalization processing on the filtered x-axis data and constructing a standard cosine curve, and performing similarity calculation based on the moving curve and the standard cosine curve to generate a detection result.
Further, the data processing unit extracts a unit image acquisition period of the filtered x-axis data; extracting peaks and troughs of the filtered x-axis data in a unit image acquisition period; and generating the standard cosine curve based on the unit image acquisition period and the wave crests and wave troughs.
Further, the data processing unit generates human body detection frame information and key point coordinates in the detection image based on the neural network model prediction; updating the coordinates of the lower left corner of the detection frame contained in the human body detection frame information to the origin of a coordinate system, and establishing a human body target frame coordinate system; carrying out affine transformation on the updated human body detection frame information (x, y, w, h) and a preset rectangular region to generate an affine matrix; and generating coordinate information of the human body key points by the key point coordinates through the affine matrix.
Furthermore, the data processing unit further comprises a cache module for storing the detection image, the human body detection frame information, the coordinate information of the human body key point and the detection result of the swivel chair.
The personnel swivel chair detection method and the system thereof provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (8)
1. A personnel swivel chair detection method is characterized by comprising the following steps:
acquiring a detection image;
acquiring a pre-trained neural network model, and inputting the detection images into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points;
filtering the x-axis data of the coordinate information to generate filtered x-axis data, and generating a moving curve based on the filtered x-axis data and time information of an image frame corresponding to the filtered x-axis data;
carrying out normalization processing on the filtered x-axis data and constructing a standard cosine curve, wherein the normalization processing comprises the following steps: extracting unit image acquisition period of the filtered x-axis data; extracting peaks and troughs of the filtered x-axis data in a unit image acquisition period; generating the standard cosine curve based on the unit image acquisition period and the wave crests and wave troughs;
and performing similarity calculation based on the moving curve and the standard cosine curve and generating a detection result.
2. The method for detecting the swivel chair according to claim 1, wherein inputting the detection image into the neural network model frame by frame to generate coordinate information of key points of a human body comprises:
predicting and generating human body detection frame information and key point coordinates in the detection image based on the neural network model;
updating the coordinates of the lower left corner of the detection frame contained in the human body detection frame information to the origin of a coordinate system, and establishing a human body target frame coordinate system;
carrying out affine transformation on the updated human body detection frame information (x, y, w, h) and a preset rectangular region to generate an affine matrix;
and generating coordinate information of the human body key points by the key point coordinates through the affine matrix.
3. The method of claim 1, wherein the filtering method used for filtering the x-axis data of the coordinate information is kalman filtering.
4. The method of claim 1, wherein training the neural network model comprises:
constructing an initialization network model, wherein the network model comprises a semantic segmentation model;
acquiring a training data set and a testing data set which are formed by image samples containing multi-class marks, wherein the mark classes comprise human body detection frames and human body key points;
training and testing the neural network model based on the training dataset and the testing dataset.
5. The method for detecting the swivel chair according to claim 1, wherein performing similarity calculation based on the movement curve and the standard cosine curve and generating a detection result comprises:
performing Pearson similarity calculation based on the movement curve and the standard cosine curve and generating a similarity value;
and if the similarity value is not higher than the preset threshold value, generating a detection result of the non-revolving chair.
6. The method for detecting the swivel chair according to claim 4, wherein the human body key point is any one point of a human body double shoulder point, a human body left shoulder point and a human body right shoulder point.
7. A person swivel chair detection system, comprising:
the camera shooting unit is used for collecting a detection image;
the data processing unit is used for acquiring a pre-trained neural network model, inputting the detection image into the neural network model frame by frame to generate human body detection frame information and coordinate information of human body key points, filtering x-axis data of the coordinate information to generate filtered x-axis data, generating a moving curve based on the filtered x-axis data and time information of image frames corresponding to the filtered x-axis data, normalizing the filtered x-axis data and constructing a standard cosine curve, and performing similarity calculation based on the moving curve and the standard cosine curve to generate a detection result, wherein the normalizing the filtered x-axis data and constructing the standard cosine curve comprises: extracting unit image acquisition period of the filtered x-axis data; extracting peaks and troughs of the filtered x-axis data in a unit image acquisition period; and generating the standard cosine curve based on the unit image acquisition period and the wave crests and wave troughs.
8. The swivel chair detection system according to claim 7, wherein the data processing unit further comprises a buffer module for storing the detection image, the human body detection frame information, the coordinate information of the human body key point, and the swivel chair detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146580.XA CN114241607B (en) | 2022-02-17 | 2022-02-17 | Personnel swivel chair detection method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210146580.XA CN114241607B (en) | 2022-02-17 | 2022-02-17 | Personnel swivel chair detection method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114241607A CN114241607A (en) | 2022-03-25 |
| CN114241607B true CN114241607B (en) | 2022-05-17 |
Family
ID=80747569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210146580.XA Active CN114241607B (en) | 2022-02-17 | 2022-02-17 | Personnel swivel chair detection method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241607B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005346390A (en) * | 2004-06-02 | 2005-12-15 | Toyota Motor Corp | Object recognition means |
| CN105229666A (en) * | 2013-03-14 | 2016-01-06 | 微软技术许可有限责任公司 | Motion analysis in 3D rendering |
| CN107443396A (en) * | 2017-08-25 | 2017-12-08 | 魔咖智能科技（常州）有限公司 | A kind of intelligence for imitating human action in real time accompanies robot |
| WO2020145835A2 (en) * | 2019-01-09 | 2020-07-16 | Al Qebaisi Rooda Omran | System and method of smart seating management |
| CN112015261A (en) * | 2019-05-29 | 2020-12-01 | 华为技术有限公司 | Intelligent terminal driving mode identification method |
| CN113435364A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Head rotation detection method, electronic device, and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3018059B1 (en) * | 2014-03-03 | 2016-03-11 | Jtekt Europe Sas | METHOD FOR DETECTING A REVERSING INVERSION BY MONITORING THE TORQUE PROVIDED BY A STEERING ASSISTANCE MOTOR AND APPLYING SAID METHOD FOR EVALUATING THE FRICTION |
| CN109095354A (en) * | 2018-09-12 | 2018-12-28 | 北京起重运输机械设计研究院有限公司 | Automatic rotary seat and its method of controlling rotation |
-
2022
- 2022-02-17 CN CN202210146580.XA patent/CN114241607B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005346390A (en) * | 2004-06-02 | 2005-12-15 | Toyota Motor Corp | Object recognition means |
| CN105229666A (en) * | 2013-03-14 | 2016-01-06 | 微软技术许可有限责任公司 | Motion analysis in 3D rendering |
| CN107443396A (en) * | 2017-08-25 | 2017-12-08 | 魔咖智能科技（常州）有限公司 | A kind of intelligence for imitating human action in real time accompanies robot |
| WO2020145835A2 (en) * | 2019-01-09 | 2020-07-16 | Al Qebaisi Rooda Omran | System and method of smart seating management |
| CN112015261A (en) * | 2019-05-29 | 2020-12-01 | 华为技术有限公司 | Intelligent terminal driving mode identification method |
| CN113435364A (en) * | 2021-06-30 | 2021-09-24 | 平安科技（深圳）有限公司 | Head rotation detection method, electronic device, and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| Action Recognition by Motion Detection in Posture Space;Stefanie Theusner等;《The Journal of Neuroscience》;20140115;第34卷(第3期);第909-921页 * |
| Action Recognition in Video Using Human Keypoint Detection;Luona Song等;《2020 15th International Conference on Computer Science & Education (ICCSE)》;20200922;第465-470页 * |
| Hough算法在人体脊柱动态检测中的应用研究;肖晓青;《中国优秀博硕士学位论文全文数据库(硕士) 医药卫生科技辑》;20180415(第04期);第E066-263页 * |
| Towards Environment Independent Device Free Human Activity Recognition;Wenjun Jiang等;《MobiCom "18: Proceedings of the 24th Annual International Conference on Mobile Computing and Networking》;20181102;第289-304页 * |
| 面向下肢康复机器人的运动意图识别技术研究;王昕;《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》;20190815(第08期);第I140-253页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114241607A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2905724B1 (en) | Object detection system and method | |
| Goodfellow et al. | Multi-digit number recognition from street view imagery using deep convolutional neural networks | |
| CN111754541B (en) | Target tracking method, device, equipment and readable storage medium | |
| Chou et al. | Privacy-preserving action recognition for smart hospitals using low-resolution depth images | |
| CN109086718A (en) | Biopsy method, device, computer equipment and storage medium | |
| CN112052731B (en) | Intelligent portrait identification card punching attendance system and method | |
| CN112419202B (en) | Automatic wild animal image recognition system based on big data and deep learning | |
| CN114841990A (en) | Self-service nucleic acid collection method and device based on artificial intelligence | |
| CN112116635A (en) | Visual tracking method and device based on rapid human body movement | |
| CN111275686A (en) | Method and device for generating medical image data for artificial neural network training | |
| CN110826610A (en) | Method and system for intelligently detecting whether dressed clothes of personnel are standard | |
| CN111523537A (en) | Character recognition method, storage medium and system | |
| CN113706481A (en) | Sperm quality detection method, sperm quality detection device, computer equipment and storage medium | |
| CN115862113A (en) | Stranger abnormity identification method, device, equipment and storage medium | |
| CN111753587B (en) | Ground falling detection method and device | |
| JP6166981B2 (en) | Facial expression analyzer and facial expression analysis program | |
| CN111488779A (en) | Video image super-resolution reconstruction method, device, server and storage medium | |
| CN114241607B (en) | Personnel swivel chair detection method and system thereof | |
| CN110555406B (en) | Video moving target identification method based on Haar-like characteristics and CNN matching | |
| CN115116119A (en) | Face recognition system based on digital image processing technology | |
| De Stefano et al. | A saliency-based segmentation method for online cursive handwriting | |
| Chen et al. | Urban damage estimation using statistical processing of satellite images | |
| CN114469139A (en) | Electroencephalogram signal recognition model training method, electroencephalogram signal recognition device and medium | |
| CN110991267A (en) | Density map generation method and device based on image or video crowd counting | |
| Majidpour et al. | Unreadable offline handwriting signature verification based on generative adversarial network using lightweight deep learning architectures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and system for detecting personnel swivel chairs Effective date of registration: 20230524 Granted publication date: 20220517 Pledgee: Industrial Bank Limited by Share Ltd. Chengdu branch Pledgor: CHENGDU KOALA YOURAN TECHNOLOGY CO.,LTD. Registration number: Y2023510000130 |