CN110059541A - A kind of mobile phone usage behavior detection method and device in driving - Google Patents
A kind of mobile phone usage behavior detection method and device in driving Download PDFInfo
- Publication number
- CN110059541A CN110059541A CN201910148552.XA CN201910148552A CN110059541A CN 110059541 A CN110059541 A CN 110059541A CN 201910148552 A CN201910148552 A CN 201910148552A CN 110059541 A CN110059541 A CN 110059541A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- model
- specimen page
- caffe
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000010606 normalization Methods 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 22
- 238000004590 computer program Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses the mobile phone usage behavior detection method and device in a kind of driving, are suitable for field of image processing.The method include that driver uses the picture specimen page of mobile phone in acquisition vehicle driving, frame selects the mobile phone in the picture specimen page, and by picture specimen page after framed choosing be converted into LMDB format；Using the picture specimen page of LMDB format as training set, the Mobilenet model is trained；Mobilenet model described in mass normalization obtains caffe_model；Whether mobile phone is used using the driver in caffe_model detection traveling.The present invention can shorten the training time, and improve detection accuracy and speed, guarantee traffic safety while reducing hardware cost.
Description
Technical field
The invention belongs to the mobile phone usage behavior detection methods and dress in field of traffic safety more particularly to a kind of driving
It sets.
Background technique
More and more using the people of mobile phone with popularizing for smart phone, daily life also increasingly be unable to do without mobile phone.But
It is to be found according to research: drives to make a phone call to cause the Hazard ratio of accident to be higher by 4 times under normal conditions, degree of danger is no less than wine
After drive, or even terminate call after 10 minutes risks it is still very high, it is seen that in time discovery driver's driving procedure use
Mobile phone, for ensuring traffic safety with extremely important effect.
Currently, the image that can be captured by high-definition camera, analysis driver whether there is the behavior using mobile phone, or
By the behavior of biosensor analysis user, former image analysis method is driven by traditional feature extraction, classification method identification
Whether the person of sailing uses mobile phone, and this method training process is complicated, and is difficult to meet the requirement of real-time of detection, and later approach is then
It will increase cost.
In view of this, the embodiment of the present invention provides driver's mobile phone usage behavior inspection that a kind of detection speed is fast, at low cost
Survey method.
Summary of the invention
In view of this, being used the embodiment of the invention provides the mobile phone usage behavior detection method and device in a kind of driving
Whether mobile phone is used in driving procedure in quick and precisely detection driver.
The embodiment of the present invention in a first aspect, providing the mobile phone usage behavior detection method in a kind of driving, comprising:
The picture specimen page that driver in vehicle driving uses mobile phone is acquired, frame selects the mobile phone in the picture specimen page, and will
Picture specimen page after framed choosing be converted into LMDB format；
The parameter for modifying original Mobilenet model training network and test network makees the picture specimen page of LMDB format
For training set, the Mobilenet model is trained, caffe_model is obtained；
Mobilenet model described in mass normalization obtains caffe_model；
Whether mobile phone is used using the driver in caffe_model detection traveling.
The second aspect of the embodiment of the present invention provides the mobile phone usage behavior detection device in a kind of driving, comprising:
Acquisition module, the picture specimen page of mobile phone is used for acquiring driver in vehicle driving, and frame selects the picture specimen page
In mobile phone, and by picture specimen page after framed choosing be converted into LMDB format；
Training module, for modifying the parameter of original Mobilenet model training network and test network, by LMDB format
Picture specimen page as training set, the Mobilenet model is trained, caffe_model is obtained；
BN module obtains caffe_model for Mobilenet model described in mass normalization；
Detection module, for whether using mobile phone using the driver in caffe_model detection traveling.
The third aspect of the embodiment of the present invention, provides a kind of computer readable storage medium, described computer-readable to deposit
Storage media is stored with computer program, realizes that first aspect of the embodiment of the present invention mentions when the computer program is executed by processor
The step of the method for confession.
The fourth aspect of the embodiment of the present invention provides a kind of computer program product, the computer program product packet
Computer program is included, realizes that first aspect of the embodiment of the present invention mentions when the computer program is executed by one or more processors
The step of the method for confession.
In the embodiment of the present invention, the picture specimen page of mobile phone is used by acquisition driver, after format conversion, by right
Mobilenet convolutional neural networks are trained, the driver after batch normalized caffe_model, in detection traveling
Whether mobile phone is used.By the R. concomitans of MobileNet depth convolutional neural networks and caffe-ssd frame, shorten training
Time, and detection accuracy and speed are improved, the real-time of detection is ensured, and reduce hardware cost, by being connected to camera shooting
The mobile phone usage behavior detection of driver can be realized in head.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is one embodiment process of the mobile phone usage behavior detection method in driving provided in an embodiment of the present invention
Figure；
Fig. 2 is the structural schematic diagram of the mobile phone usage behavior detection device in driving provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the invention provides the mobile phone usage behavior detection method and device in a kind of driving, drive for detecting
In driver whether use mobile phone, and to ensure traffic safety.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
Embodiment one:
Referring to Fig. 1, the flow diagram of the mobile phone usage behavior detection method in driving provided in an embodiment of the present invention,
The following steps are included:
Driver uses the picture specimen page of mobile phone in S101, acquisition vehicle driving, and frame selects the mobile phone in the picture specimen page,
And by picture specimen page after framed choosing be converted into LMDB format；
The picture specimen page is the picture of driver in the vehicle driving of camera shooting, includes to drive in picture specimen page
The person of sailing uses the behavior image of mobile phone.It is described to be not limited to make a phone call using mobile phone, it can also include face orientation mobile phone screen
Behavior.
Illustratively, by label-img block diagram tool outline in 2,000 multiple specimen page pictures include mobile phone figure
The picture is converted into xml formatted file, and specimen page picture name is converted into txt format by piece, by txt file, specimen page picture
And xml document is converted to LMDB format.
The parameter of S102, modification original Mobilenet model training network and test network, by the picture sample of LMDB format
Zhang Zuowei training set is trained the Mobilenet model；
The trained network and test network are respectively MobileNet_test network and MobileNet_train, modification
After parameter, it is suitable to carry out to the hyper parameter of solver_train.prototxt and solvor_test.prototxt file
Finetune (adjustment).
The Mobilenet model is based on depth and separates convolution, and Standard convolution can be resolved into depth convolution sum point
Convolution (1*1 core).Each convolution kernel is used each channel by depth convolution, and separation convolution (1*1 core) is rolled up with each channel is combined
Long-pending output is that a step of Standard convolution is divided into two steps to calculate, and a step does Filter calculating, and another step does joint account,
The last two steps are added to obtain new scale output.So theoretically the convolution algorithm of standard and depth separate convolution
The ratio of the calculation amount of (Depthwise Separable Convolution) operation are as follows:
Wherein, DkWide and high for convolution kernel, M is input channel number, and N is convolution kernel number.
Under normal circumstances, N is bigger, it is assumed that using the convolution kernel of 3*3, depth separates convolution can compared with Standard convolution network
To reduce about nine times of calculation amount.
Whole features carry out Pooling, i.e. feature is extracted again, and main function is to retain more advanced feature, reduce ginseng
Several and calculation amount simultaneously maintains the invariance (translation, rotation and scale etc.).Mobilenet Web vector graphic is averaged pond, to filter
Corresponding receptive field is averaged.
It is connected to Softmax classifier by the feature that average pond obtains, the classification carried out as needed, to all points
Class normalizes, and the classification of maximum probability is finally therefrom exported, in the feature map process that entire convolution sum pond is extracted
In also have Prior Box target prediction carried out to it, connect and be Bounding Box Regression after Softmax and obtain frame
The actual position of target out, to export result.
Mobilenet model described in S103, mass normalization obtains caffe_model；
The mass normalization (batch normalization) can be used in neural net layer, to each
The inside of minibatch data is standardized, and is made output standardization being just distributed very much to N (0,1), is reduced intrinsic nerve
The change of member distribution.Fast convergence may be implemented by mass normalizing, improve network generalization.Specifically, in conjunction with
MobileNet depth convolutional neural networks and caffe-ssd frame, by the Mobilenet model after training in BN (Batch
Normalization) it is laminated simultaneously.
S104, whether mobile phone is used using the driver in caffe_model detection traveling.
Optionally, after detecting driver using mobile phone, warning against danger or prompt can be generated, from the background to prevent to drive
The risky operation behavior of member.
Above-mentioned steps combine mobilenet network on the basis of caffe-ssd frame, and training is obtained
Model combination BN (Batch Normalization) layer, can quick and precisely complete model training,
It realizes real-time mobile phone usage behavior detection, and reduces cost.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment two:
The mobile phone usage behavior detection method in a kind of driving is essentially described above, it below will be to the hand in a kind of driving
Machine usage behavior detection device is described in detail.
Fig. 2 shows the structural schematic diagrams of the mobile phone usage behavior detection device in driving, comprising:
Acquisition module 210, the picture specimen page of mobile phone is used for acquiring driver in vehicle driving, and frame selects the picture sample
Mobile phone in, and by picture specimen page after framed choosing be converted into LMDB format；
Training module 220, for modifying the parameter of original Mobilenet model training network and test network, by LMDB
The picture specimen page of format is trained the Mobilenet model as training set；
Optionally, the whole features for extracting the picture specimen page of the LMDB format carry out average pond, and pond result is passed
Enter softmax classifier.The classification carried out as needed normalizes all classification, finally therefrom exports maximum probability
Classification, Prior Box is also had during the feature map that entire convolution sum pond is extracted, and to carry out target to it pre-
It surveys, connects and be Bounding Box Regression after Softmax and obtain outlining the actual position of target, to export result.
BN module 230, for the caffe_model that Mobilenet model training obtains described in batch normalized；
Optionally, in conjunction with MobileNet depth convolutional neural networks and caffe-ssd frame, after training
Mobilenet model is laminated simultaneously at BN (Batch Normalization).
Detection module 240, for whether using mobile phone using the driver in caffe_model detection traveling.
Optionally, after detecting driver's current mobile phone usage behavior, driving information is recorded and obtained, is generated dangerous
Warning or prompt.
Real-time accurate detection driver mobile phone usage behavior may be implemented in the device provided through this embodiment.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (5)
1. the mobile phone usage behavior detection method in a kind of driving characterized by comprising
The picture specimen page that driver in vehicle driving uses mobile phone is acquired, frame selects the mobile phone in the picture specimen page, and will own
Picture specimen page after frame choosing is converted into LMDB format；
The parameter for modifying original Mobilenet model training network and test network, using the picture specimen page of LMDB format as instruction
Practice collection, the Mobilenet model is trained, caffe_model is obtained；
Mobilenet model described in mass normalization obtains caffe_model；
Whether mobile phone is used using the driver in caffe_model detection traveling.
2. the method according to claim 1, wherein described using the picture specimen page of LMDB format as training set,
The Mobilenet model is trained specifically:
The whole features for extracting the picture specimen page of the LMDB format carry out average pond, and pond result is passed to softmax points
Class device.
3. according to the method described in claim 2, it is characterized in that, Mobilenet model described in the mass normalization
Obtain caffe_model specifically:
Mobilenet model after training is laminated simultaneously in BN.
4. the method according to claim 1, wherein described using in caffe_model detection traveling
Whether driver uses mobile phone further include:
After detecting driver's current mobile phone usage behavior, driving information is recorded and obtained, generates warning against danger or prompt.
5. the mobile phone usage behavior detection device in a kind of driving characterized by comprising
Acquisition module, the picture specimen page of mobile phone is used for acquiring driver in vehicle driving, and frame selects in the picture specimen page
Mobile phone, and by picture specimen page after framed choosing be converted into LMDB format；
Training module, for modifying the parameter of original Mobilenet model training network and test network, by the figure of LMDB format
Piece specimen page is trained the Mobilenet model, obtains caffe_model as training set；
BN module obtains caffe_model for Mobilenet model described in mass normalization；
Detection module, for whether using mobile phone using the driver in caffe_model detection traveling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910148552.XA CN110059541A (en) | 2019-02-28 | 2019-02-28 | A kind of mobile phone usage behavior detection method and device in driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910148552.XA CN110059541A (en) | 2019-02-28 | 2019-02-28 | A kind of mobile phone usage behavior detection method and device in driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059541A true CN110059541A (en) | 2019-07-26 |
Family
ID=67316028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910148552.XA Pending CN110059541A (en) | 2019-02-28 | 2019-02-28 | A kind of mobile phone usage behavior detection method and device in driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059541A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110682860A (en) * | 2019-09-19 | 2020-01-14 | 佛吉亚好帮手电子科技有限公司 | Vehicle-mounted intelligent alarm method and system for communication in gas station |
| CN113276869A (en) * | 2021-05-17 | 2021-08-20 | 海南师范大学 | Device and method for automatically detecting that driver plays mobile phone |
| CN113378653A (en) * | 2021-05-19 | 2021-09-10 | 海南师范大学 | Method and device for detecting in-vehicle behavior of driver |
| CN113506436A (en) * | 2021-05-19 | 2021-10-15 | 海南师范大学 | System and method for monitoring and detecting whether driver plays mobile phone in vehicle |
| WO2022241598A1 (en) * | 2021-05-17 | 2022-11-24 | 海南师范大学 | Device and method for automatically detecting mobile phone usage of driver |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056071A (en) * | 2016-05-30 | 2016-10-26 | 北京智芯原动科技有限公司 | Method and device for detection of driver' behavior of making call |
| CN106203385A (en) * | 2016-07-20 | 2016-12-07 | 东方网力科技股份有限公司 | A kind of driver's hand-held phone behavioral value method and device |
| CN106611169A (en) * | 2016-12-31 | 2017-05-03 | 中国科学技术大学 | Dangerous driving behavior real-time detection method based on deep learning |
| CN108446645A (en) * | 2018-03-26 | 2018-08-24 | 天津大学 | Vehicle-mounted face identification method based on deep learning |
| CN109389068A (en) * | 2018-09-28 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | The method and apparatus of driving behavior for identification |
-
2019
- 2019-02-28 CN CN201910148552.XA patent/CN110059541A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056071A (en) * | 2016-05-30 | 2016-10-26 | 北京智芯原动科技有限公司 | Method and device for detection of driver' behavior of making call |
| CN106203385A (en) * | 2016-07-20 | 2016-12-07 | 东方网力科技股份有限公司 | A kind of driver's hand-held phone behavioral value method and device |
| CN106611169A (en) * | 2016-12-31 | 2017-05-03 | 中国科学技术大学 | Dangerous driving behavior real-time detection method based on deep learning |
| CN108446645A (en) * | 2018-03-26 | 2018-08-24 | 天津大学 | Vehicle-mounted face identification method based on deep learning |
| CN109389068A (en) * | 2018-09-28 | 2019-02-26 | 百度在线网络技术（北京）有限公司 | The method and apparatus of driving behavior for identification |
Non-Patent Citations (3)
| Title |
|---|
| ANDREW G.HOWARD 等: "MobileNets：Efficient convolutional neural networks for mobile vision applications", 《ARXIV：1704.04861V》 * |
| CIKY奇: "Mobilenet-SSD实现步骤", 《BLOG.CSDN.NET/C20081052/ARTICLE/DETAILS/81747719》 * |
| XIAOMAOMAO6: "MobileNet SSD 训练自己的数据集", 《BLOG.CSDN.NET/WEIXIN_39750664/ARTICLE/DETAILS/82502302》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110682860A (en) * | 2019-09-19 | 2020-01-14 | 佛吉亚好帮手电子科技有限公司 | Vehicle-mounted intelligent alarm method and system for communication in gas station |
| CN113276869A (en) * | 2021-05-17 | 2021-08-20 | 海南师范大学 | Device and method for automatically detecting that driver plays mobile phone |
| WO2022241598A1 (en) * | 2021-05-17 | 2022-11-24 | 海南师范大学 | Device and method for automatically detecting mobile phone usage of driver |
| CN113378653A (en) * | 2021-05-19 | 2021-09-10 | 海南师范大学 | Method and device for detecting in-vehicle behavior of driver |
| CN113506436A (en) * | 2021-05-19 | 2021-10-15 | 海南师范大学 | System and method for monitoring and detecting whether driver plays mobile phone in vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059541A (en) | A kind of mobile phone usage behavior detection method and device in driving | |
| US20210232813A1 (en) | Person re-identification method combining reverse attention and multi-scale deep supervision | |
| EP4006831A1 (en) | Image processing method and apparatus, server, medical image processing device and storage medium | |
| CN111524106B (en) | Skull fracture detection and model training method, device, equipment and storage medium | |
| CN103679168B (en) | Detection method and detection device for character region | |
| WO2021196873A1 (en) | License plate character recognition method and apparatus, electronic device, and storage medium | |
| CN108596277A (en) | A kind of testing vehicle register identification method, apparatus and storage medium | |
| CN110223292A (en) | Image evaluation method, device and computer readable storage medium | |
| CN111444826B (en) | Video detection method, device, storage medium and computer equipment | |
| CN108960288B (en) | Three-dimensional model classification method and system based on convolutional neural network | |
| CN108596338A (en) | A kind of acquisition methods and its system of neural metwork training collection | |
| CN102968623B (en) | Face Detection system and method | |
| CN107103616A (en) | A kind of method for tracking target and system | |
| CN109544564A (en) | A kind of medical image segmentation method | |
| CN112364803B (en) | Training method, terminal, equipment and storage medium for living body identification auxiliary network | |
| CN111080670A (en) | Image extraction method, device, equipment and storage medium | |
| CN103984954B (en) | Image combining method based on multi-feature fusion | |
| CN109241951A (en) | Porny recognition methods, identification model construction method and identification model and computer readable storage medium | |
| CN109670517A (en) | Object detection method, device, electronic equipment and target detection model | |
| CN111046858A (en) | Image-based animal species fine classification method, system and medium | |
| CN106303296A (en) | A kind of image mosaic emerging system | |
| CN106709431A (en) | Iris recognition method and device | |
| CN111723239A (en) | Multi-mode-based video annotation method | |
| CN109145723A (en) | A kind of seal recognition methods, system, terminal installation and storage medium | |
| CN112132812A (en) | Certificate checking method and device, electronic 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 |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |