CN114625333B - Method and system capable of recording gesture instructions to control liquid crystal splicing LCD - Google Patents
Method and system capable of recording gesture instructions to control liquid crystal splicing LCD Download PDFInfo
- Publication number
- CN114625333B CN114625333B CN202210239125.4A CN202210239125A CN114625333B CN 114625333 B CN114625333 B CN 114625333B CN 202210239125 A CN202210239125 A CN 202210239125A CN 114625333 B CN114625333 B CN 114625333B
- Authority
- CN
- China
- Prior art keywords
- gesture
- lcd
- video image
- key point
- threshold
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
- G06F3/147—Digital output to display device ; Cooperation and interconnection of the display device with other functional units using display panels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
- G06F3/1423—Digital output to display device ; Cooperation and interconnection of the display device with other functional units controlling a plurality of local displays, e.g. CRT and flat panel display
- G06F3/1446—Digital output to display device ; Cooperation and interconnection of the display device with other functional units controlling a plurality of local displays, e.g. CRT and flat panel display display composed of modules, e.g. video walls
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
Abstract
A liquid crystal splicing LCD system and method capable of recording gesture instructions for control comprises the following steps: acquiring gesture video image information in front of a liquid crystal splicing LCD; preprocessing gesture video image information, and forming a one-dimensional characteristic vector by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal; inputting the preprocessed gesture video image information feature vectors into a trained deep neural network; and recognizing the gesture and the gesture key point by the neural network, and further determining the operation type to finish the operation. According to the invention, through the combination of the discrete Fourier transform and the continuous phase modulation of the zero-order elliptic spherical wave signal and the fault-tolerant setting, the accuracy and the speed of the gesture command operation are improved, so that the user experience is improved.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a liquid crystal splicing LCD method and system capable of recording gesture instructions for control.
Background
At present, with the rapid development of electronic technology, LCD liquid crystal splicing screens are widely applied more and more, the position and angle of an LCD picture are adjusted in real time through gestures, and the effect of displaying according to an actual scene is more and more concerned, which is a hot spot that is concerned by the field of computer vision and human-computer interaction in recent years.
In the prior art, although the LCD gesture records are used for controlling, the effect of the LCD gesture records on the aspect of gesture control positioning precision and speed is not obvious; the realization of the high fusion matching of the gesture and the image display of the LCD splicing screen is the key for realizing the flow operation. However, in the prior art, a technology for appropriately matching gesture recognition and an LCD spliced screen picture is provided, and how to enable the spliced screen gesture operation to be more intelligent and humanized, improve the operation efficiency and enhance the comfort of a user becomes a new research subject, but the information matching accuracy and efficiency of the existing gesture operation technology are lower; and the acquisition of the feature vector is not ideal, and acquisition of information of gesture key points and fault-tolerant mechanism setting are not available, so that an enhanced display matching technology capable of increasing the intelligent degree of a gesture operation LCD splicing screen is an urgent need for improving the LCD effect, and the user experience is improved.
Disclosure of Invention
In order to solve the technical problems, the invention provides the liquid crystal splicing LCD method and the liquid crystal splicing LCD system which can record the gesture command for control.
The technical scheme is realized as follows:
a liquid crystal splicing LCD method capable of recording gesture instructions for control comprises the following steps: acquiring gesture video image information in front of a liquid crystal splicing LCD; preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; inputting the preprocessed gesture video image information feature vectors into a trained deep neural network; recognizing a gesture and a gesture key point by the deep neural network;
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press times: ((x 1+ s, y1+ s), T1-T2+ T1)
The key points of the gesture are that when dragging: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, and y1 represents the ordinate of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault-tolerant threshold; t1 represents a response time fault-tolerant threshold, and operation accuracy fault-tolerant thresholds and response time fault-tolerant thresholds of different people are different, T1 represents a time point of a first touch screen of a gesture key point in an LCD video image pixel axis, and T2 represents a time point of a second touch screen of the gesture key point in the LCD video image pixel axis; x2 represents the abscissa of the gesture keypoint after exceeding the threshold time T in the LCD video image pixel axis; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents the response time tolerance threshold after the threshold time T is exceeded.
Preferably, the preprocessing the gesture video image information further includes filtering, denoising and feature extraction on the gesture video frame image information.
Preferably, before the features of each domain are connected end to form a one-dimensional feature vector, the method further comprises a normalization processing module of LCD video frame data, which is used for performing normalization processing on the posture and gesture video frame data of the person before the LCD screen is acquired.
Preferably, before the step of acquiring the image information in front of the display surface, the method further comprises an LCD model number judging module for determining the information of the LCD splicing number, size and resolution.
Preferably, the operation accuracy fault-tolerant threshold and the response time fault-tolerant threshold of different people are different and are determined according to the ages, the sexes and historical gesture operation records of people.
The invention also comprises a liquid crystal splicing LCD system capable of recording the gesture command for control, which comprises a liquid crystal splicing LCD video image acquisition module used for acquiring gesture video image information in front of the liquid crystal splicing LCD; the LCD preprocessing module is used for preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; the deep neural network recognition module is used for inputting the preprocessed gesture video image information feature vectors into the trained deep neural network; the gesture key point output module is used for recognizing a gesture and a gesture key point by the deep neural network; gesture key point judgment module includes:
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press: ((x 1+ s, y1+ s), T1-T2+ T1)
The key points of the gesture are that when dragging: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, and y1 represents the ordinate of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault tolerance threshold; t1 represents a response time fault-tolerant threshold, and operation accuracy fault-tolerant thresholds and response time fault-tolerant thresholds of different people are different, T1 represents a time point of a first touch screen of a gesture key point in an LCD video image pixel axis, and T2 represents a time point of a second touch screen of the gesture key point in the LCD video image pixel axis; x2 represents the abscissa of the gesture keypoint after exceeding the threshold time T in the LCD video image pixel axis; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents the response time tolerance threshold after the threshold time T is exceeded.
Preferably, the preprocessing the gesture video image information further includes filtering, denoising and feature extraction on the gesture video frame image information.
Preferably, before the features of each domain are connected end to form a one-dimensional feature vector, the method further comprises a normalization processing module of LCD video frame data, which is used for performing normalization processing on the posture and gesture video frame data of the person before the LCD screen is acquired.
Preferably, before the step of acquiring the image information in front of the display surface, the method further comprises an LCD model number judging module for determining the information of the LCD splicing number, size and resolution.
Preferably, the operation accuracy fault-tolerant threshold and the response time fault-tolerant threshold of different people are different and are determined according to the ages, the sexes and historical gesture operation records of people.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
the invention solves the problems that the acquisition of the feature vector is not ideal, and the acquisition of the information of the gesture key points and the fault-tolerant mechanism setting are not available in the traditional technology; the method adopts discrete Fourier transform and continuous phase modulation of zero-order elliptic spherical wave signals to extract one-dimensional characteristic vectors, thereby greatly improving the processing efficiency of gesture control LCD splicing screen; inputting the preprocessed gesture video image information feature vectors into a trained deep neural network, and recognizing gestures and gesture key points by the deep neural network, so that the problem that only single feature is emphasized in the traditional technology is solved; the operation accuracy is improved by setting the operation accuracy fault-tolerant threshold and the reaction time fault-tolerant threshold, so that the operation efficiency and accuracy are greatly improved by controlling the LCD splicing screen through the gesture, and the user experience is improved.
Drawings
FIG. 1 is a diagram of an LCD system capable of recording gesture commands for control according to the present invention.
Detailed Description
Those skilled in the art understand that, as mentioned in the background, the conventional existing gesture operation technology has low information matching accuracy and efficiency; and the acquisition of the feature vector is not ideal, and acquisition of information of gesture key points and fault-tolerant mechanism setting are not available, so that an enhanced display matching technology capable of increasing the intelligent degree of a gesture operation LCD splicing screen is an urgent need for improving the LCD effect, and the user experience is improved. In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Example 1:
a liquid crystal splicing LCD method capable of recording gesture instructions for control comprises the following steps: acquiring gesture video image information in front of a liquid crystal splicing LCD; preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; inputting the preprocessed gesture video image information feature vectors into a trained deep neural network; recognizing a gesture and a gesture key point by a neural network;
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press: ((x 1+ s, y1+ s), T1-T2+ T1)
The key points of the gesture are that when dragging: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, and y1 represents the ordinate of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault-tolerant threshold; t1 represents a response time fault-tolerant threshold, and operation accuracy fault-tolerant thresholds and response time fault-tolerant thresholds of different people are different, T1 represents a time point of a first touch screen of a gesture key point in an LCD video image pixel axis, and T2 represents a time point of a second touch screen of the gesture key point in the LCD video image pixel axis; x2 represents the abscissa of the gesture keypoint after exceeding the threshold time T in the LCD video image pixel axis; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents the response time tolerance threshold after the threshold time T is exceeded.
Preferably, the preprocessing the gesture video image information further includes filtering, denoising and feature extraction on the gesture video frame image information.
In some embodiments, before the connecting the features of each domain end to form a one-dimensional feature vector, the method further includes a normalization processing module for normalizing the pose and gesture video frame data of the person before the LCD screen is acquired.
In some embodiments, before the step of acquiring the image information in front of the display surface, the method further includes an LCD model number determining module that determines the LCD splicing number, size, and resolution information.
In some embodiments, the operation accuracy tolerance threshold and the response time tolerance threshold of different people are different and are determined according to the ages, the sexes and historical gesture operation records of people.
Example 2:
the invention also comprises a liquid crystal splicing LCD system capable of recording the gesture instruction for control, which comprises a liquid crystal splicing LCD video image acquisition module used for acquiring gesture video image information in front of the liquid crystal splicing LCD; the LCD preprocessing module is used for preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; the deep neural network recognition module is used for inputting the preprocessed gesture video image information feature vectors into the trained deep neural network; the gesture key point output module is used for recognizing the gesture and the gesture key points by the neural network; gesture key point judgment module includes:
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press times: ((x 1+ s, y1+ s), T1-T2+ T1)
When the gesture key points are dragged: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, and y1 represents the ordinate of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault-tolerant threshold; t1 represents a response time fault-tolerant threshold, and operation accuracy fault-tolerant thresholds and response time fault-tolerant thresholds of different people are different, T1 represents a time point of a first touch screen of a gesture key point in an LCD video image pixel axis, and T2 represents a time point of a second touch screen of the gesture key point in the LCD video image pixel axis; x2 represents the abscissa of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents the response time tolerance threshold after the threshold time T is exceeded.
In some embodiments, the preprocessing the gesture video image information further includes filtering and denoising the gesture video frame image information, and extracting features.
In some embodiments, before the connecting the features of each domain end to form a one-dimensional feature vector, the method further includes a normalization processing module for normalizing the pose and gesture video frame data of the person before the LCD screen is acquired.
In some embodiments, before the step of acquiring the image information in front of the display surface, the method further includes an LCD model number determination module for determining LCD splicing number, size, and resolution information.
In some embodiments, the operation accuracy tolerance threshold and the response time tolerance threshold of different people are different and are determined according to the ages, the sexes and historical gesture operation records of people.
The invention solves the problems that the acquisition of the feature vector is not ideal, and the acquisition of the information of the gesture key points and the fault-tolerant mechanism setting are not available in the traditional technology; the invention adopts discrete Fourier transform and continuous phase modulation of zero-order elliptic spherical wave signals to extract one-dimensional characteristic vectors, thereby greatly improving the processing efficiency of gesture control LCD spliced screen; inputting the preprocessed gesture video image information feature vectors into a trained deep neural network, and recognizing gestures and gesture key points by the deep neural network, thereby solving the problem that only single feature is emphasized in the traditional technology; the operation accuracy is improved by setting the operation accuracy fault-tolerant threshold and the response time fault-tolerant threshold, so that the operation efficiency and accuracy are greatly improved by controlling the LCD splicing screen through the gesture, and the user experience is improved.
Those skilled in the art will appreciate that embodiments of the present application may be provided as a method, system, or computer program product and thus the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A method for controlling a liquid crystal splicing LCD by a recordable gesture instruction is characterized by comprising the following steps: acquiring gesture video image information in front of a liquid crystal splicing LCD; preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; inputting the one-dimensional feature vector into the trained deep neural network; recognizing a gesture and a gesture key point by the deep neural network; determining that the gesture key points are single click, double click, long press, drag and slide;
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press: ((x 1+ s, y1+ s), T1-T2+ T1)
When the gesture key points are dragged: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, y1 represents the ordinate of the gesture key point in the LCD video image pixel axis, t1 represents the time point of the first touch screen of the gesture key point in the LCD video image pixel axis, and t2 represents the time point of the second touch screen of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault tolerance threshold; t1 represents a response time fault-tolerant threshold, and the operation accuracy fault-tolerant threshold and the response time fault-tolerant threshold of different people are different; x2 represents the abscissa of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents a response time fault-tolerant threshold value after the threshold time T is exceeded;
before the features of each domain are connected end to form a one-dimensional feature vector, the system also comprises an LCD video frame data normalization processing module which is used for performing normalization processing on the acquired gesture and gesture video frame data of the person in front of the LCD screen;
the LCD command is completed.
2. The method of claim 1, wherein the preprocessing of the gesture video image information further comprises filtering, denoising, and feature extraction of the gesture video frame image information.
3. The method for controlling the liquid crystal splicing LCD through the recordable gesture instruction according to claim 1, wherein an LCD model number judging module is further included before the step of acquiring the image information in front of the display surface, and the information of the splicing number, size and resolution of the LCDs is determined.
4. The method of claim 1, wherein the tolerance threshold for operation accuracy and the tolerance threshold for reaction time of different people are different and determined according to the age, gender and historical gesture operation records of people.
5. A system capable of recording gesture instructions to control a liquid crystal splicing LCD is characterized by comprising a liquid crystal splicing LCD video image acquisition module, a gesture video image processing module and a gesture processing module, wherein the liquid crystal splicing LCD video image acquisition module is used for acquiring gesture video image information in front of the liquid crystal splicing LCD; the LCD preprocessing module is used for preprocessing gesture video image information, extracting time-frequency domain and space domain characteristics by adopting discrete Fourier transform and continuous phase modulation of a zero-order elliptic spherical wave signal, and connecting the characteristics of each domain end to form a one-dimensional characteristic vector; the deep neural network recognition module is used for inputting the one-dimensional characteristic vector to the trained deep neural network; the gesture key point output module is used for recognizing a gesture and a gesture key point by the deep neural network; the gesture key point judgment module determines whether the gesture key point is single click, double click, long press, drag and slide, and comprises the following steps:
when the gesture key point is single click, then ((x 1+ s, y1+ s), T1+ T1)
When the gesture key point is double-click: ((x 1+ s, y1+ s), T1+ T1) & ((x 1+ s, y1+ s), T2+ T1)
The key points of the gesture are long press times: ((x 1+ s, y1+ s), T1-T2+ T1)
When the gesture key points are dragged: ((x 1+ s, y1+ s), T1-T2+ T1) - ((x 2+ s, y2+ s), T3+ T1)
When the gesture key points are sliding: (x 1+ s, T1+ T1) - (x 2+ s, T2+ T2);
wherein x1 represents the abscissa of the gesture key point in the LCD video image pixel axis, and y1 represents the ordinate of the gesture key point in the LCD video image pixel axis; s represents an operation accuracy fault-tolerant threshold; t1 represents a response time fault-tolerant threshold, and operation accuracy fault-tolerant thresholds and response time fault-tolerant thresholds of different people are different, T1 represents a time point of a first touch screen of a gesture key point in an LCD video image pixel axis, and T2 represents a time point of a second touch screen of the gesture key point in the LCD video image pixel axis; x2 represents the abscissa of the gesture keypoint after exceeding the threshold time T in the LCD video image pixel axis; y2 represents the ordinate of the gesture key point in the LCD video image pixel axis after exceeding the threshold time T; t2 represents a response time fault tolerance threshold value after the threshold time T is exceeded;
before the features of each domain are connected end to form a one-dimensional feature vector, the system also comprises an LCD video frame data normalization processing module which is used for performing normalization processing on the gesture of the person in front of the obtained LCD screen and the gesture video frame data;
the LCD command is completed.
6. The system of claim 5, wherein the pre-processing of the gesture video image information further comprises filtering, de-noising, and feature extraction of the gesture video frame image information.
7. The system for controlling the liquid crystal splicing LCD through the recordable gesture instruction as claimed in claim 5, further comprising an LCD model number judging module for determining the splicing number, size and resolution information of the LCDs before the step of acquiring the image information in front of the display surface.
8. The system of claim 5, wherein the tolerance threshold for operation accuracy and the tolerance threshold for reaction time of different people are different and determined according to the age, sex and historical gesture operation records of people.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210239125.4A CN114625333B (en) | 2022-03-08 | 2022-03-08 | Method and system capable of recording gesture instructions to control liquid crystal splicing LCD |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210239125.4A CN114625333B (en) | 2022-03-08 | 2022-03-08 | Method and system capable of recording gesture instructions to control liquid crystal splicing LCD |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114625333A CN114625333A (en) | 2022-06-14 |
CN114625333B true CN114625333B (en) | 2022-10-18 |
Family
ID=81901765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210239125.4A Active CN114625333B (en) | 2022-03-08 | 2022-03-08 | Method and system capable of recording gesture instructions to control liquid crystal splicing LCD |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114625333B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104834922A (en) * | 2015-05-27 | 2015-08-12 | 电子科技大学 | Hybrid neural network-based gesture recognition method |
KR102021531B1 (en) * | 2019-03-28 | 2019-11-04 | 세종대학교 산학협력단 | Apparatus for micro hand motion recognition using continuous wave radar and method thereof |
CN110891038A (en) * | 2019-12-06 | 2020-03-17 | 中国人民解放军海军航空大学 | Frequency domain multi-carrier modulation and demodulation method for elliptical spherical wave |
CN111104820A (en) * | 2018-10-25 | 2020-05-05 | 中车株洲电力机车研究所有限公司 | Gesture recognition method based on deep learning |
CN112906550A (en) * | 2021-02-09 | 2021-06-04 | 哈尔滨理工大学 | Static gesture recognition method based on watershed transformation |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105373785B (en) * | 2015-11-30 | 2019-08-02 | 北京地平线机器人技术研发有限公司 | Gesture identification detection method and device based on deep neural network |
CN112527224B (en) * | 2020-12-02 | 2023-03-07 | 上海三思电子工程有限公司 | Spliced screen video layout device, method, terminal device, system and medium |
-
2022
- 2022-03-08 CN CN202210239125.4A patent/CN114625333B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104834922A (en) * | 2015-05-27 | 2015-08-12 | 电子科技大学 | Hybrid neural network-based gesture recognition method |
CN111104820A (en) * | 2018-10-25 | 2020-05-05 | 中车株洲电力机车研究所有限公司 | Gesture recognition method based on deep learning |
KR102021531B1 (en) * | 2019-03-28 | 2019-11-04 | 세종대학교 산학협력단 | Apparatus for micro hand motion recognition using continuous wave radar and method thereof |
CN110891038A (en) * | 2019-12-06 | 2020-03-17 | 中国人民解放军海军航空大学 | Frequency domain multi-carrier modulation and demodulation method for elliptical spherical wave |
CN112906550A (en) * | 2021-02-09 | 2021-06-04 | 哈尔滨理工大学 | Static gesture recognition method based on watershed transformation |
Non-Patent Citations (1)
Title |
---|
基于零阶椭圆球面波信号的连续相位调制及;杨大伟等;《***工程与电子技术》;20210831;第43卷(第8期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114625333A (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Park et al. | Learning to find eye region landmarks for remote gaze estimation in unconstrained settings | |
WO2020199931A1 (en) | Face key point detection method and apparatus, and storage medium and electronic device | |
US20220261968A1 (en) | Image optimization method and apparatus, computer storage medium, and electronic device | |
CN104123007B (en) | Multidimensional weighted 3D recognition method for dynamic gestures | |
JP6288530B2 (en) | Method for eye tracking | |
WO2018120329A1 (en) | Single-frame super-resolution reconstruction method and device based on sparse domain reconstruction | |
WO2019237942A1 (en) | Line-of-sight tracking method and apparatus based on structured light, device, and storage medium | |
EP4053735A1 (en) | Method for structuring pedestrian information, device, apparatus and storage medium | |
EP1854051B1 (en) | Intelligent importation of information from foreign application user interface using artificial intelligence | |
Zhao et al. | Applying contrast-limited adaptive histogram equalization and integral projection for facial feature enhancement and detection | |
CN114445904A (en) | Iris segmentation method, apparatus, medium, and device based on full convolution neural network | |
CN112597872A (en) | Gaze angle estimation method and device, storage medium, and electronic device | |
Jachimski et al. | A comparative study of English viseme recognition methods and algorithms | |
CN106814853A (en) | A kind of eye control tracking based on machine learning | |
US11625754B2 (en) | Method for providing text-reading based reward-type advertisement service and user terminal for executing same | |
CN106778574A (en) | Detection method and device for face image | |
Ahmed | Real-time accurate eye center localization for low-resolution grayscale images | |
US20220207917A1 (en) | Facial expression image processing method and apparatus, and electronic device | |
Dai et al. | Binocular feature fusion and spatial attention mechanism based gaze tracking | |
JP4348202B2 (en) | Face image recognition apparatus and face image recognition program | |
CN108647605B (en) | Human eye gaze point extraction method combining global color and local structural features | |
CN114625333B (en) | Method and system capable of recording gesture instructions to control liquid crystal splicing LCD | |
CN112965602A (en) | Gesture-based human-computer interaction method and device | |
CN112184580A (en) | Face image enhancement method, device, equipment and storage medium | |
WO2023109086A1 (en) | Character recognition method, apparatus and device, and storage 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |