CN110032930A - A kind of classroom demographic method and its system, device, storage medium - Google Patents
A kind of classroom demographic method and its system, device, storage medium Download PDFInfo
- Publication number
- CN110032930A CN110032930A CN201910154012.2A CN201910154012A CN110032930A CN 110032930 A CN110032930 A CN 110032930A CN 201910154012 A CN201910154012 A CN 201910154012A CN 110032930 A CN110032930 A CN 110032930A
- Authority
- CN
- China
- Prior art keywords
- classroom
- seat portion
- region
- seat
- human
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 29
- 230000015654 memory Effects 0.000 claims description 20
- 210000000746 body region Anatomy 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 19
- 230000000903 blocking effect Effects 0.000 claims description 15
- 239000003550 marker Substances 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 4
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 description 5
- 230000001052 transient effect Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- 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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Abstract
The invention discloses a kind of classroom demographic method and its system, device, storage mediums, detection model is generated by training, after obtaining human region, human region is verified by the seat portion in classroom, there is no the human region of lap with seat portion to filter out, it is removed as error result, further improves the accuracy of human region detection, improve the accuracy of demographics.
Description
Technical field
The present invention relates to field of image recognition, especially a kind of classroom demographic method and its system, device, storage Jie
Matter.
Background technique
In general, teacher can count the number of ginseng class at the beginning of classroom, and traditional mode is artificial
Demographics are carried out, it is long to occupy time in classroom for this mode inefficiency.With the development of science and technology, start to utilize
The identification of characteristics of human body carries out the mode of demographics, and this mode is easy to be influenced by factors such as angle, light, so that most
There is deviation in whole statistical result, therefore how to improve final demographics the result is that urgent problem.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide a kind of classroom demographic method and its system, device,
Storage medium can verify the result of human bioequivalence, improve the accuracy of demographics.
Technical solution used by the present invention solves the problems, such as it is:
In a first aspect, the embodiment of the present invention proposes a kind of classroom demographic method, comprising:
Input training pictures;
Training generates detection model;
Picture to be detected is detected using detection model, obtains human region;
Classroom seat distribution map is inputted, seat portion is obtained;
Seat portion and human region are judged with the presence or absence of lap, if so, tying the people's body region as detection
Otherwise human body zone marker is error result and removed it by fruit output.
Further, the input training pictures, comprising:
Input classroom picture;
Human body in the picture of classroom is marked.
Further, input classroom seat distribution map, obtains seat portion, comprising:
Reference axis is added on the seat distribution map of classroom;
Seat is divided in the form of a grid, includes a seat in each grid.
Further, the judgement seat portion and human region whether there is lap, if so, by the people's body region
It is exported as testing result, is otherwise error result by human body zone marker and removes it, comprising:
The seat being blocked is filtered out, obtains blocking seat portion;
Judgement blocks seat portion and human region with the presence or absence of lap, if so, using the people's body region as inspection
Result output is surveyed, is otherwise error result by human body zone marker and removes it.
Further, if blocking seat portion and human region, there is no intersections, this is also blocked seat portion as detection
As a result it exports.
Second aspect, the embodiment of the invention also provides a kind of classroom passenger number statistical systems, comprising:
Input unit obtains seat portion for inputting trained pictures, classroom seat distribution map and picture to be detected;
Training unit generates detection model for training;
Detection unit obtains human region for detecting to picture to be detected;
Verification unit, for judging seat portion and human region with the presence or absence of lap, if so, by human body area
Domain is exported as testing result, is otherwise error result by human body zone marker and is removed it.
Further, the verification unit filters out the seat being blocked, and obtains blocking seat portion, and judge to block seat
Region and human region whether there is lap, if so, exporting the people's body region as testing result, otherwise by the people
Body region is labeled as error result and removes it.
Further, if blocking seat portion and human region there is no intersection, this is also blocked seat by the verification unit
Region is exported as testing result.
The third aspect, the embodiment of the invention also provides a kind of classroom people counting devices characterized by comprising
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
A processor executes, so that at least one described processor is able to carry out method described in first aspect of the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, which is characterized in that the meter
Calculation machine readable storage medium storing program for executing is stored with computer executable instructions, and the computer executable instructions are for making computer execute sheet
Method described in inventive embodiments first aspect.
The one or more technical solutions provided in the embodiment of the present invention at least have the following beneficial effects: of the invention real
A kind of classroom demographic method for applying example offer generates detection model by training, after obtaining human region, passes through classroom
Seat portion verifies human region, so that filtering out does not have the human region of lap with seat portion, as mistake
Accidentally result removal further improves the accuracy of human region detection, improves the accuracy of demographics.
A kind of classroom passenger number statistical system provided in an embodiment of the present invention generates detection model by training unit training,
After obtaining human region, verification unit verifies human region by the seat portion in classroom, to filter out and seat
Region does not have the human region of lap, removes as error result, further improves the accuracy of human region detection,
Improve the accuracy of demographics.
Detailed description of the invention
The invention will be further described with example with reference to the accompanying drawing.
Fig. 1 is the flow chart of one embodiment of classroom demographic method of the present invention;
Fig. 2 is the flow chart that training pictures are inputted in one embodiment of classroom demographic method of the present invention;
Fig. 3 is that seat distribution map in classroom is inputted in one embodiment of classroom demographic method of the present invention, obtains seat
The flow chart in region;
Fig. 4 be classroom demographic method of the present invention one embodiment in judge whether seat portion deposits with human region
It is otherwise error result by human body zone marker if so, being exported the people's body region as testing result in lap
And the flow chart removed it;
Fig. 5 is the schematic diagram of one of experimental result under the fitting of classroom demographic method of the present invention is tested;
Fig. 6 be classroom demographic method of the present invention extensive experiment under one of experimental result schematic diagram;
Fig. 7 is the schematic diagram of one embodiment of classroom passenger number statistical system of the present invention;
Fig. 8 is the schematic diagram of one embodiment of classroom people counting device of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
It should be noted that each feature in the embodiment of the present invention can be combined with each other, in this hair if do not conflicted
Within bright protection scope.In addition, though having carried out functional unit division in system schematic, shows patrol in flow charts
Sequence is collected, but in some cases, it can be different from shown in the dividing elements in system or the execution of the sequence in flow chart
The step of out or describing.
In general, teacher can count the number of ginseng class at the beginning of classroom, and traditional mode is artificial
Demographics are carried out, it is long to occupy time in classroom for this mode inefficiency.With the development of science and technology, start to utilize
The identification of characteristics of human body carries out the mode of demographics, and this mode is easy to be influenced by factors such as angle, light, so that most
There is deviation in whole statistical result, therefore how to improve final demographics the result is that urgent problem.
Based on this, the present invention provides a kind of classroom demographic method and its system, device, storage mediums, pass through instruction
Practice and generates detection model, after obtaining human region, by judging that the case where classroom seat is blocked verifies human region,
The region that human body but seat are not blocked is detected the presence of to filter out detection model, is removed as error result, further
The accuracy of human region detection is improved, the accuracy of demographics is improved.
With reference to the accompanying drawing, the embodiment of the present invention is further elaborated.
Referring to Fig.1, in a kind of one embodiment of classroom demographic method of the present invention, including but not limited to following step
It is rapid:
S100: training pictures are inputted;
S200: training generates detection model;
S300: picture to be detected is detected using detection model, obtains human region;
S400: input classroom seat distribution map obtains seat portion;
S500: seat portion and human region are judged with the presence or absence of lap, if so, using the people's body region as inspection
Result output is surveyed, is otherwise error result by human body zone marker and removes it.
Specifically, referring to Fig. 2, step S100: inputting training pictures, comprising the following steps:
S110: input classroom picture;
S120: the human body in the picture of classroom is marked.
The training pictures of input can be obtained from the monitoring in classroom, also, the picture number in training pictures is most
Possible more, in the present embodiment, the picture number of training pictures is 1500, and the picture number of training pictures is more,
It is better then to train the detection model performance come.Human body in the picture of classroom is marked, can be marked using labelImg
Tool, and the mode marked mainly uses rectangle frame.
Preferably, the present embodiment carries out the training of detection model using YOLOv3 frame.Its core concept is to utilize whole
Input of the picture as network, the directly position in output layer recurrence bounding box (bounding box) and its affiliated classification.
Classifier or locator are reused for executing Detection task by priori detection (Prior detection) system of YOLOv3, will
Model is applied to multiple positions and the scale of image, and those higher regions of scoring can be considered as testing result.In addition, phase
For other object detection methods, YOLOv3 has used entirely different method, and a single Application of Neural Network is schemed in whole
Picture, which divides an image into different regions, thus predicts the bounding box and probability in each piece of region, these bounding box meetings
Pass through the probability weight of prediction.The model of YOLOv3 has some advantages compared to the system based on classifier, its meeting in test
Whole image is checked, so the global information in image is utilized in its prediction.And there are also R-CNN for traditional frame, with needs
The R-CNN of thousands of simple target images is different, and YOLOv3 is predicted by single network assessment, therefore YOLOv3 is very
Fastly, it is general it 1000 times faster than R-CNN, it is 100 times faster than Fast R-CNN, be conducive to the performance for improving detection model.
The cardinal principle of YOLOv3 are as follows: feature is extracted to training picture by feature extraction network first, is obtained certain big
Then training picture is divided into 13*13 grid cell, then if ground truth by small feature image, such as 13*13
Which grid cell the centre coordinate of some target falls in in (correct mark), then just predicting the mesh by the grid cell
Mark, because each grid cell can predict 3 bounding boxes.It can be seen that dimension there are two the output feature images that prediction obtains
It is the dimension for the feature extracted, such as 13*13, is B* (5+C) there are one dimension (depth), wherein B indicates each grid
The quantity of the bounding box of unit prediction, this value is 3, and C indicates the classification number of bounding box, and 5 indicate 4 coordinate informations and one
Confidence level (objectness score).
However, only improved in the level of algorithm above, due to by angle and light when actually detected
The phenomenon that influencing, being easy to appear false retrieval and missing inspection, the accuracy of number finally counted is influenced, therefore pass through religion in the present embodiment
Room seat portion verifies human region, removes the human region of mistake.
It firstly the need of input classroom seat distribution map, preferably faces entire seat portion and is acquired, input classroom
After seat distribution map, need to carry out preliminary treatment to it, specifically, referring to Fig. 3, step S400: input classroom seat distribution
Figure, obtains seat portion, comprising the following steps:
S410: reference axis is added on the seat distribution map of classroom;
S420: seat is divided in the form of a grid, includes a seat in each grid.
Reference axis is added on the seat distribution map of classroom, and each seat is divided in the form of a grid, so that each
There is specific coordinate representation in region where opening seat, convenient for subsequent judgement seat portion with human region with the presence or absence of Chong Die
Part.
Since the position of classroom seat is relatively fixed, and be distributed it is regular, student's upper class hour generally all on the seat, therefore
By judge seat whether be blocked i.e. can determine whether the region whether someone, therefore scheme as a further preference, to improve
The accuracy of verification can filter out the seat being blocked from seat portion, then be verified, specifically, referring to Fig. 4, step
Rapid S500: seat portion and human region are judged with the presence or absence of lap, if so, using the people's body region as testing result
Otherwise human body zone marker is error result and removed it by output, comprising the following steps:
S510: filtering out the seat being blocked, and obtains blocking seat portion;
S520: judgement blocks seat portion and human region with the presence or absence of lap, if so, the people's body region is made
For testing result output, it is otherwise error result by human body zone marker and removes it.
In step S510, the seat being blocked is filtered out, specific standards are to judge blocking for grid where the seat
Area is more than 70%, that is, is used as and blocks seat portion.
In step S520, judgement blocks seat portion and human region with the presence or absence of lap, sits due to introducing
Parameter can be carried out by the relationship between specific coordinate.Such as the apex angle coordinate for blocking seat portion is taken, judge that the coordinate is
It is no to be located in human region, if so, being judged as that there are laps.It is of course also possible to take the apex angle coordinate of human region, sentence
Whether the coordinate that breaks is located at and blocks in seat portion, or is judged using other modes, it is not limited here, but using sitting
The mode of mark judgement has the advantages that simple and convenient.
The human region that detection model detected can be verified through the above way, judge the detection of erroneous detection
Model.Further, in order to enable final testing result is more accurate, in the present embodiment, if blocking seat portion and people
Intersection is not present in body region, this is also blocked seat portion as testing result and is exported, when there is detection leakage phenomenon in detection model,
The region of original someone was not detected as human region, then there is no intersections with seat portion is blocked, therefore by will be with
There is no the seat portions of blocking of intersection to export as testing result for human region, can play the role of avoiding missing inspection, into one
Step improves the accuracy of demographics.
Illustrate a kind of performance of classroom demographic method of the present invention below by experimental data.
A kind of classroom demographic method of the present invention is verified by fitting experiment first:
Referring to Fig. 5, the laboratory test results of serial number 1 are illustrated.As a whole, under fitting experiment, of the invention one
The accuracy rate of kind classroom demographic method is up to 100%.
And under extensive experiment, the experimental data are shown in the following table:
Referring to Fig. 6, by taking the experimental result of serial number 9 as an example, there is the case where repeating detection and false retrieval.But generally,
Under extensive experiment, a kind of Average Accuracy of classroom demographic method of the invention also reaches 97.22%.
Referring to Fig. 7, in a kind of one embodiment of classroom passenger number statistical system of the present invention, comprising: for inputting trained figure
Piece collection, the input unit of classroom seat distribution map and picture to be detected generate the training unit of detection model for training, are used for
Picture to be detected is detected, obtains the detection unit of human region, for judging whether seat portion and human region deposit
In the verification unit of lap.
Specifically, the verification unit filters out the seat being blocked, and obtains blocking seat portion, and judge to block seat
Region and human region whether there is lap, if so, exporting the people's body region as testing result, otherwise by the people
Body region is labeled as error result and removes it.Further, if blocking seat portion and human region, there is no intersection, institutes
It states verification unit and this is also blocked into seat portion as testing result output.
One of the present embodiment classroom passenger number statistical system and above-mentioned classroom demographic method use identical invention
Design generates detection model by training unit training, and after obtaining human region, verification unit passes through the seat portion pair in classroom
Human region is verified, so that filtering out does not have the human region of lap with seat portion, is removed as error result,
The accuracy of human region detection is further improved, the accuracy of demographics is improved.
Referring to Fig. 8, one embodiment of the present of invention additionally provides a kind of classroom people counting device, comprising:
At least one processor;
And the memory being connect at least one described processor communication;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, and described instruction is described
At least one processor executes, so that at least one described processor is able to carry out any one in above method embodiment such as and teaches
Room demographic method.
The device can be any type of intelligent terminal, such as mobile phone, tablet computer, personal computer etc..
Processor can be connected with memory by bus or other modes, in Fig. 8 for being connected by bus.
Memory as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, it is non-temporarily
State property computer executable program and module, as the corresponding program of classroom demographic method in the embodiment of the present invention refers to
Order/module.Processor is by running non-transient software program, instruction and module stored in memory, thereby executing religion
The various function application and data processing of room people counting device realize the classroom number system of any of the above-described embodiment of the method
Meter method.
Memory may include storing program area and storage data area, wherein storing program area can storage program area, extremely
Application program required for a few function;Storage data area can be stored to be created according to using for classroom people counting device
Data etc..In addition, memory may include high-speed random access memory, it can also include non-transient memory, for example, at least
One disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, memory is optional
Including the memory remotely located relative to processor, these remote memories can be united by network connection to the classroom number
Counter device.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of module storages in the memory, are executed when by one or more of processors
When, the classroom demographic method in above-mentioned any means embodiment is executed, for example, executing the method in Fig. 1 described above
Step S100 to S500.
One embodiment of the present of invention additionally provides a kind of computer readable storage medium, the computer-readable storage medium
Matter is stored with computer executable instructions, which is executed by one or more control processors, for example, by
A processor in Fig. 8 executes, and said one or multiple processors may make to execute the religion of one of above method embodiment
Room demographic method, for example, executing method and step of the method and step S100 into S500, Fig. 2 in Fig. 1 described above
Method and step S510 to S520 of method and step S410 of the S110 into S120, Fig. 3 into S420, Fig. 4 realizes classroom in Fig. 7
The function of passenger number statistical system each unit.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, it can it is in one place, or may be distributed over multiple network lists
In member.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment
The mode of general hardware platform can be added to realize by software, naturally it is also possible to pass through hardware.Those of ordinary skill in the art can
With understand all or part of the process realized in above-described embodiment method be can be instructed by computer program it is relevant hard
Part is completed, and the program can be stored in a computer-readable storage medium, the program is when being executed, it may include as above
State the process of the embodiment of each method.Wherein, the storage medium can be magnetic disk, CD, read-only memory (Read-
Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
It is to be illustrated to preferable implementation of the invention, but the invention is not limited to above-mentioned embodiment party above
Formula, those skilled in the art can also make various equivalent variations on the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent deformations or replacement are all included in the scope defined by the claims of the present application.
Claims (10)
1. a kind of classroom demographic method characterized by comprising
Input training pictures;
Training generates detection model;
Picture to be detected is detected using detection model, obtains human region;
Classroom seat distribution map is inputted, seat portion is obtained;
Seat portion and human region are judged with the presence or absence of lap, if so, the people's body region is defeated as testing result
Out, it is otherwise error result by human body zone marker and removes it.
2. a kind of classroom demographic method according to claim 1, which is characterized in that the input training pictures,
Include:
Input classroom picture;
Human body in the picture of classroom is marked.
3. a kind of classroom demographic method according to claim 1, which is characterized in that the input classroom seat distribution
Figure, obtains seat portion, comprising:
Reference axis is added on the seat distribution map of classroom;
Seat is divided in the form of a grid, includes a seat in each grid.
4. a kind of classroom demographic method according to claim 1, which is characterized in that the judgement seat portion and people
Body region whether there is lap, if so, exporting the people's body region as testing result, otherwise by the people's body region mark
It is denoted as error result and removes it, comprising:
The seat being blocked is filtered out, obtains blocking seat portion;
Judgement blocks seat portion and human region with the presence or absence of lap, if so, tying the people's body region as detection
Otherwise human body zone marker is error result and removed it by fruit output.
5. a kind of classroom demographic method according to claim 4, it is characterised in that: if blocking seat portion and human body
Intersection is not present in region, this is also blocked seat portion as testing result and is exported.
6. a kind of classroom passenger number statistical system characterized by comprising
Input unit obtains seat portion for inputting trained pictures, classroom seat distribution map and picture to be detected;
Training unit generates detection model for training;
Detection unit obtains human region for detecting to picture to be detected;
Verification unit, for judging seat portion and human region with the presence or absence of lap, if so, the people's body region is made
For testing result output, it is otherwise error result by human body zone marker and removes it.
7. a kind of classroom passenger number statistical system according to claim 6, it is characterised in that: the verification unit filter out by
The seat blocked obtains blocking seat portion, and judges to block seat portion and human region with the presence or absence of lap, if
It is then to be exported the people's body region as testing result, is otherwise error result by human body zone marker and removes it.
8. a kind of classroom passenger number statistical system according to claim 6, it is characterised in that: if blocking seat portion and human body
Intersection is not present in region, this is also blocked seat portion as testing result and exported by the verification unit.
9. a kind of classroom people counting device characterized by comprising
At least one processor;And
The memory being connect at least one described processor communication;Wherein,
The memory is stored with the instruction that can be executed by least one described processor, and described instruction is by described at least one
It manages device to execute, so that at least one described processor is able to carry out the method according to claim 1 to 5.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer can
It executes instruction, the computer executable instructions are for making computer execute the method according to claim 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910154012.2A CN110032930A (en) | 2019-03-01 | 2019-03-01 | A kind of classroom demographic method and its system, device, storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910154012.2A CN110032930A (en) | 2019-03-01 | 2019-03-01 | A kind of classroom demographic method and its system, device, storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110032930A true CN110032930A (en) | 2019-07-19 |
Family
ID=67235699
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910154012.2A Pending CN110032930A (en) | 2019-03-01 | 2019-03-01 | A kind of classroom demographic method and its system, device, storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110032930A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009223693A (en) * | 2008-03-17 | 2009-10-01 | Glory Ltd | Person counting device and person counting method |
CN101770642A (en) * | 2008-12-26 | 2010-07-07 | 深圳先进技术研究院 | Method and system for counting number of people in car |
CN104156729A (en) * | 2014-07-21 | 2014-11-19 | 武汉理工大学 | Counting method for people in classroom |
CN106897698A (en) * | 2017-02-24 | 2017-06-27 | 常州常工电子科技股份有限公司 | Classroom number detection method and system based on machine vision Yu binocular coordination technique |
CN107122698A (en) * | 2016-07-19 | 2017-09-01 | 安徽大学 | A kind of real-time attendance statistical method of cinema based on convolutional neural networks |
CN107766784A (en) * | 2016-08-20 | 2018-03-06 | 宋坤骏 | A kind of novel video people counting algorithm |
US20180247132A1 (en) * | 2017-02-28 | 2018-08-30 | Microsoft Technology Licensing, Llc | System and method for person counting in image data |
-
2019
- 2019-03-01 CN CN201910154012.2A patent/CN110032930A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009223693A (en) * | 2008-03-17 | 2009-10-01 | Glory Ltd | Person counting device and person counting method |
CN101770642A (en) * | 2008-12-26 | 2010-07-07 | 深圳先进技术研究院 | Method and system for counting number of people in car |
CN104156729A (en) * | 2014-07-21 | 2014-11-19 | 武汉理工大学 | Counting method for people in classroom |
CN107122698A (en) * | 2016-07-19 | 2017-09-01 | 安徽大学 | A kind of real-time attendance statistical method of cinema based on convolutional neural networks |
CN107766784A (en) * | 2016-08-20 | 2018-03-06 | 宋坤骏 | A kind of novel video people counting algorithm |
CN106897698A (en) * | 2017-02-24 | 2017-06-27 | 常州常工电子科技股份有限公司 | Classroom number detection method and system based on machine vision Yu binocular coordination technique |
US20180247132A1 (en) * | 2017-02-28 | 2018-08-30 | Microsoft Technology Licensing, Llc | System and method for person counting in image data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102635987B1 (en) | Method, apparatus, device and storage medium for training an image semantic segmentation network | |
CN110020592B (en) | Object detection model training method, device, computer equipment and storage medium | |
CN111046980B (en) | Image detection method, device, equipment and computer readable storage medium | |
EP3806064A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
CN110851835A (en) | Image model detection method and device, electronic equipment and storage medium | |
CN108985155A (en) | Mouth model training method, mouth recognition methods, device, equipment and medium | |
CN112200081A (en) | Abnormal behavior identification method and device, electronic equipment and storage medium | |
CN113688957A (en) | Target detection method, device, equipment and medium based on multi-model fusion | |
CN110490882B (en) | Cell membrane staining image analysis method, device and system | |
CN110889421A (en) | Target detection method and device | |
CN110245544A (en) | A kind of method and device of determining dead ship condition | |
CN105405130A (en) | Cluster-based license image highlight detection method and device | |
CN109598931A (en) | Group based on traffic safety risk divides and difference analysis method and system | |
CN109242165A (en) | A kind of model training and prediction technique and device based on model training | |
CN113516144A (en) | Target detection method and device and computing equipment | |
CN112560584A (en) | Face detection method and device, storage medium and terminal | |
CN111241873A (en) | Image reproduction detection method, training method of model thereof, payment method and payment device | |
CN105426915A (en) | Support vector machine-based prediction method and system | |
CN114926791A (en) | Method and device for detecting abnormal lane change of vehicles at intersection, storage medium and electronic equipment | |
CN108280388A (en) | The method and apparatus and type of face detection method and device of training face detection model | |
CN112597995B (en) | License plate detection model training method, device, equipment and medium | |
EP3176726A1 (en) | Method and device for positioning human eyes | |
CN116189063B (en) | Key frame optimization method and device for intelligent video monitoring | |
CN110032930A (en) | A kind of classroom demographic method and its system, device, storage medium | |
CN111199357B (en) | Express delivery point electronic fence diagnosis method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190719 |