CN106780435A - A kind of object count method and device - Google Patents
A kind of object count method and device Download PDFInfo
- Publication number
- CN106780435A CN106780435A CN201611034545.XA CN201611034545A CN106780435A CN 106780435 A CN106780435 A CN 106780435A CN 201611034545 A CN201611034545 A CN 201611034545A CN 106780435 A CN106780435 A CN 106780435A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- statistics
- region
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Abstract
This application discloses a kind of object count method, including:Image acquisition and processing is carried out to target object group, target image is obtained;Binary conversion treatment is carried out to target image, bianry image is obtained;The sum of target area is counted, statistics is obtained, wherein, target area is that binaryzation numerical value meets the region of preset range in bianry image, wherein, preset range is the area of section scope set in advance based on target object.It can be seen that, the object count method that the application is provided carries out binaryzation and analysis of accounts by obtaining target object group image to target area image, completes the Counts for object, artificial disturbance factor is eliminated, while greatly improving counting rate.In addition, the application further correspondingly discloses a kind of object count device.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of object count method and device.
Background technology
With advances in technology, many simple job steps are gradually replaced by original artificial operation by various instruments
In generation, for example, Counts, but generally count tool can only, influence factor simple to working environment be few, count condition is simply walked
Suddenly counted, and picture is more to tying up this changing factor of bar counting, working environment is unstable, the difficult counting step of Rule of judgment
Suddenly, artificial mode can only be temporarily continuing with to be counted.
Present situation is that workman needs to count substantial amounts of bar of tying up in noisy and mixed and disorderly workshop or warehouse, and such as
This hard work transfers to artificial treatment to occur unavoidably, and because of miscount caused by workman's individual factors, and counting efficiency is low,
If in order to improve efficiency and the degree of accuracy, needing plus sending workman to be counted, and this greatly improves cost.
Which kind of therefore, method is taken to replace manually becoming the difficult point that needs overcome to tying up bar and count.
The content of the invention
In view of this, it is an object of the invention to provide a kind of object count method and device, improve and object count is imitated
Rate.Its concrete scheme is as follows:
A kind of object count method, including:
Image acquisition and processing is carried out to target object group, target image is obtained;
Binary conversion treatment is carried out to the target image, binary image is obtained;
The sum of target area is counted, statistics is obtained, wherein, the target area is two in the binary image
Value numerical value meets the region of preset range, wherein, the preset range is that the area of section based on target object presets
Scope.
Preferably, also include:Before carrying out binary conversion treatment to the target image, using image noise reduction method and/or ash
Degreeization method is pre-processed to the target image.
Preferably, also include:
The statistics is sent to server, so as to the server stores to database the statistics protect
Deposit.
Preferably, also include:The target area that will have been counted is marked, and allows the user to distinguish the target for having counted
Region and the target area of no count.
Preferably, after the target area that will have been counted is marked, also include:
The statistics is corrected using the control information of user input, the statistics after being corrected.
Preferably, it is described to carry out image acquisition and processing to target object group, including:
IMAQ is carried out to target object group by image collecting device, original target image is obtained;
Region is carried out to original image using the region selection information of user input to select, and obtains the target image.
The invention also discloses a kind of object count device, including:
Image capture module, for carrying out image acquisition and processing to target object group, obtains target image;
Image processing module, for carrying out binary conversion treatment to the target image, obtains bianry image;
Statistical module, the sum for counting target area, obtains statistics, wherein, the target area is described
Binaryzation numerical value meets the region of preset range in bianry image, wherein, the preset range is the section based on target object
Area scope set in advance.
Preferably, also include:Image pre-processing module, for before carrying out binary conversion treatment to the target image, using
Image noise reduction method and/or gray processing method are pre-processed to target image.
Preferably, also include:Correction module, school is carried out for the control information using user input to the statistics
Just, the statistics after being corrected.
Preferably, described image acquisition module includes:
Unit is chosen in region, and region is carried out to original image for the region selection information using user input selectes, and obtains
To the target image.
In the present invention, object count method includes:Image acquisition and processing is carried out to target object group, target figure is obtained
Picture;Binary conversion treatment is carried out to target image, bianry image is obtained;The sum of target area is counted, statistics is obtained, its
In, target area is that binaryzation numerical value meets the region of preset range in bianry image, wherein, preset range is based on object
The area of section scope set in advance of body.It can be seen that, the object count method that the present invention is provided is by obtaining target object group
Image, binaryzation and analysis of accounts are carried out to target area image, complete the Counts for object, are eliminated artificial dry
Factor is disturbed, while greatly improving counting rate.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Inventive embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of object count method flow diagram provided in an embodiment of the present invention;
Fig. 2 is another object count method flow diagram provided in an embodiment of the present invention;
Fig. 3 is a kind of object count apparatus structure schematic diagram provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
The embodiment of the invention discloses a kind of object count method, shown in Figure 1, the method includes:
Step S11:Image acquisition and processing is carried out to target object group, target image is obtained.
In actual applications, by image capture device, such as camera and camera are carried out system to target object group
Image acquisition and processing, obtains target image.The image for collecting can also be chosen by user, obtain target image, have
Body step includes:
Step S110:IMAQ is carried out to target object group by image collecting device, original target image is obtained.
Step S111:Region is carried out to original image using the region selection information of user input to select, and obtains target figure
Picture.
Specifically, user is presented the original target image that image capture device before eyes is gathered according to system, choosing needs
The region wanted, the region that system will be selected in original target image as target image, so that subsequent step is used.
Step S12:Binary conversion treatment is carried out to target image, bianry image is obtained.
Specifically, the pixel value of target image is calculated first, then using related algorithm, for example, Two-peak method, P parameters
Method, iterative method and OTSU methods etc., calculate threshold value, and image is divided into the pixel group more than threshold value and the pixel less than threshold value
Group, the pixel group gray value that finally will be greater than being equal to threshold value is set as 255, and the pixel group gray value less than threshold value is set as into 0,
Can certainly be that the pixel group gray value that will be greater than threshold value is set as 255, the pixel group gray value less than or equal to threshold value is set
It is set to 0.
It should be noted that before carrying out binary conversion treatment to target image, can also be pre-processed to image, system
Can be using in OpenCV function libraries (Open Source Computer Vision Library, computer vision of increasing income storehouse)
Algorithm, for example, image noise reduction method and/or gray processing method and/or dilation erosion computing, it is possible, firstly, to be carried out to target image
Noise reduction process, removal image is done because image is subjected to imaging device in digitlization and transmitting procedure with the noise of external environment condition
Disturb, so that image is more accurate in subsequent processes;Secondly, can be to carrying out gray processing treatment to image, using component
Method or the gray value computational algorithm such as maximum value process or mean value method or weighted mean method, obtain the rational gray value of target image;
Further according to the grey level histogram of gray level image, the characteristics of two one paddy of peak of analysis, binary conversion treatment is carried out;Finally, to bianry image
The operation such as expanded, corroded, being obtained the bianry image that can clearly debate, being beneficial to the follow-up calculating to target area.
Step S13:The sum of target area is counted, statistics is obtained, wherein, target area is two-value in bianry image
Change the region that numerical value meets preset range, wherein, preset range is the area of section scope set in advance based on target object.
In actual applications, after target object group being shot for into image, in target image by mesh after binary conversion treatment
Mark object group is in multiple target areas in bianry image, in order to be counted to target object exactly, it is necessary to right
How to select target area to be preset, the establishing method of specific preset range includes:
Sets target area grayscale value is 0 or 255, and based on target object area of section, sets target object is in binary map
Target area areal extent as in is the first preset range, and specific range size can be set according to the actual requirements, model
Enclose excessive or too small, be likely to cause erroneous judgement, so that not statistical uncertainty true, specific setting range will be according to target object two
Target area area in value image sets;According to target area areal extent set in advance, sets target area grayscale
The scope for being worth sum is the second preset range.
During the sum of statistics target area, determine whether to meet the region of the first preset range, if it is not, then explanation does not have
Target area, if it has, then continue to judge whether have the region for meeting the second preset range in bianry image, if it is not, then saying
Bright no target area, if it has, then illustrating that qualified region is target area, i.e., only meets first and presets simultaneously
The region of the second preset range of scope and satisfaction, is only the target area for needing statistics, and statistics meets above-mentioned first preset range
With the sum of the target area of the second preset range, statistics is obtained.
For example, sets target area grayscale value is 0, it is necessary to the bianry image of statistics is to tie up bar, target object is single
Individual bar, it is contemplated that single bar standard area is 100, reserves 20 as error range up and down, therefore sets single bar two
In value image area be 80 to 120 as the first preset range, set bar in the picture area gray value sum as 0 to 5100
Used as the second preset range, the computational methods of the second preset range can be that 255 gray values are multiplied with error range 20 to obtain
Maximum gradation value sum 5100;When statistics ties up the single bar in bar image, while meeting the first preset range and second
The region of preset range be single bar, pair simultaneously meet two preset ranges region count, obtain statistics.
Wherein, when sets target area grayscale value is 255, mesh of the target object that will can be set in bianry image
Mark region area scope is multiplied with gray value 255, the 3rd preset range is obtained, it therefore meets the region of the 3rd preset range is just
It is target area;When target area sum is counted, the region of the 3rd preset range is met in statistics bianry image, counted
As a result.
For example, sets target area grayscale value is 255, it is necessary to the bianry image of statistics is to tie up bar, target object is
Single bar, it is contemplated that single bar standard area is 100, reserves 20 and exists as error range, therefore the single bar of setting up and down
Area is 80 to 120, area of the 3rd preset range by single bar in bianry image and the phase of gray value 255 in bianry image
Multiply, show that the 3rd preset range is 20400 to 30600;When statistics ties up the single bar in bar image, meet the 3rd and preset
The region of scope is just single bar, and the region to meeting the 3rd preset range counts, and obtains statistics.
It should be noted that above-mentioned two methods and form are not limited to for the establishing method of above-mentioned preset range,
The algorithm counted to target area can be reached using other;For the gray value setting of target area, can be with root
It is configured according to user's actual need, is not limited herein.
In the embodiment of the present invention, when mistake occurs in statistics, user can directly select and count again, and without weighing again
New collection objective community image, saves the time.
It can be seen that, the present invention provide object count method by obtaining target object group image, to target area image
Binaryzation and analysis of accounts are carried out, the Counts for object are completed, artificial disturbance factor is eliminated, while greatly promoting
Counting rate.
The embodiment of the invention discloses a kind of specific object count method, relative to a upper embodiment, the present embodiment pair
Technical scheme has made further instruction and optimization.It is shown in Figure 2, specifically:
Step S21:Image acquisition and processing is carried out to target object group, target image is obtained.
Step S22:Binary conversion treatment is carried out to target image, bianry image is obtained.
Step S23:The sum of target area is counted, statistics is obtained, wherein, target area is two-value in bianry image
Change the region that numerical value meets preset range, wherein, preset range is the area of section scope set in advance based on target object.
It should be noted that step S21 to step S23 is identical with a upper embodiment, will not be described here.
Step S24:The target area that will have been counted is marked, allow the user to distinguish the target area that has counted and
The target area of no count.
Specifically, after obtaining statistics, statistics and bianry image are shown to user by system, in bianry image
The target area of counting has been labeled, for example, by target area Fill Color, it is such as red, allow the user to intuitively distinguish
The target area for having counted and the target area of no count.
It is understood that labeling method can certainly select other method, for example, being irised out often with colored lines
One marked target area, does not limit herein.
In actual applications, although by artificial counting transformation in order to use unit count, it is to avoid the interference of human factor,
But unit count as a variety of causes and cause occur error in count results, this when can by it is artificial to count
Result is modified, therefore can also include step S25 in embodiments of the present invention, specifically:
Step S25:Statistics is corrected using the control information of user input, the statistics knot after being corrected
Really.
It is understood that user is according to target area marked in bianry image in step S24 and statistics,
Judge whether statistics is correct, without operation if correct;If incorrect, user can voluntarily to the system in system
Meter result is corrected, and specific bearing calibration includes:
Target area to having counted is filled using color, allows the user to intuitively distinguish the target for having counted
Region and the target area of no count, user can again be entered by clicking on the target area of no count in bianry image to it
Line flag, is filled using the color different from the target area color for having counted, and is distinguished by the target of user's mark with this
Region and the target area marked during by system counts, then the markd target area of institute is counted again again by system, obtain
Statistics after to correction.
For example, the target area to having counted is filled using red, user is clicked in bianry image by touch-screen
The target area of no count, makes it be filled by yellow after click, after user confirms exhaustive, allow service system again to all marks
The target area of note counts again, the statistics after being corrected.
Certainly, if could not still obtain correct result after once correcting, correction is can proceed with, until correctly being united
Meter result.
Bearing calibration can also be that user is provided by being marked in bianry image to count target area by system
, statistics modification dialog box, user directly inputs correct statistics, statistics is modified.
To sum up, the embodiment of the present invention is by increasing manual synchronizing link, it is ensured that the accuracy of statistics, eliminates and sets
The standby miscount that may occur in counting.
It is understood that to ensure that user can inspect historical statistics result as correction reference information, while being also
Convenience record and statistical counting result, allow user to be applied to elsewhere statistics, increase local storage region,
To store each statistics.Because counting process is in the case of without mistake, may only it is sufficient that need to count one time, and
Counts amount may be very huge, therefore excessive storage statistics is nonsensical, and when memory space using it is full after,
New statistics cannot be stored again, when user needs to store significant statistics, cannot stored on the contrary,
Therefore the automatic stored number upper limit of statistics can be preset according to practical application request, when more than on set in advance
In limited time, then new data will cover the legacy data for storing at first, and remaining memory space leaves user's storage for be needed for a long time
The statistics of record, for example, in the environment of to tying up bar counting, it usually needs tie up bar to 50 and count,
Therefore automatic stored number can be set for 50, when tying up bar to next group and counting, new statistics will be covered
The old statistics of lid, user can also at any time store the statistics for needing storage for a long time.
External interface can also be increased simultaneously, it is possible to use External memory equipment is carried out to the statistics that Installed System Memory is stored up
Copy.
Further, statistics and worker information can also be sent to server, so that server will be counted
Result storage is in database, being that follow-up data analysis and staff's process task situation are monitored;Can also count
Increase worker information certification in equipment, logon information is sent to server, taken by staff's input log-on message, system
The log-on message that business device will be received is compared with the worker information of storage in database, when consistent, then allows work
Personnel log in and use equipment, when inconsistent, then refuse unlatching equipment.
In addition, the embodiment of the invention also discloses a kind of object count device, shown in Figure 3, the device includes:
Image capture module 11, for carrying out image acquisition and processing to target object group, obtains target image.
Specifically, the picture processing chip of image capture module 11 can select EM2800/2710, and by image collector
Put integrated with picture processing chip, image is obtained efficiency and improve several times.
Image processing module 12, for carrying out binary conversion treatment to target image, obtains bianry image.
Specifically, the OpenCV function libraries that can be based on Android platform carry out binary conversion treatment to image.
Statistical module 13, the sum for counting target area, obtains statistics, wherein, target area is binary map
Binaryzation numerical value meets the region of preset range as in, wherein, preset range is that the area of section based on target object sets in advance
Fixed scope.
Specifically, searching algorithm is write with Java programming languages in Android system based on OpenCV, to realize to target
The statistics in region.
The object count device of the embodiment of the present invention also includes:
Image pre-processing module, for before carrying out binary conversion treatment to target image, with image noise reduction method and/or gray scale
Change method is pre-processed to target image.
Correction module, is corrected for the control information using user input to statistics, the system after being corrected
Meter result.
Data uploading module, for statistics to be sent into server, so that statistics storage is arrived number by server
According in storehouse.
Module is locally stored, for by statistics storage to local storage space.
Image capture module 11 in the embodiment of the present invention, specifically includes region and chooses unit, wherein,
Unit is chosen in region, and region is carried out to original image for the region selection information using user input selectes, and obtains
To target image.
Object count device provided in an embodiment of the present invention, can be designed as Portable integral machine, can easily by with
Family pick-up operation, wherein, above-mentioned picture processing chip can also select other process chips, and image capture module 11 can also be used
Split type acquiring and processing device;Image processing module 12 is also not limited on Android platform to the binary conversion treatment of image
OpenCV function libraries;The searching algorithm that statistical module 13 is used can also use the algorithm of other equal functions, not do herein
Limit.
Finally, in addition it is also necessary to explanation, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.And, term " including ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include for this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", does not arrange
Except also there is other identical element in the process including the key element, method, article or equipment.
A kind of object count method and device provided by the present invention is described in detail above, it is used herein
Specific case is set forth to principle of the invention and implementation method, and the explanation of above example is only intended to help and understands this
The method and its core concept of invention;Simultaneously for those of ordinary skill in the art, according to thought of the invention, specific
Be will change in implementation method and range of application, in sum, this specification content should not be construed as to of the invention
Limitation.
Claims (10)
1. a kind of object count method, it is characterised in that including:
Image acquisition and processing is carried out to target object group, target image is obtained;
Binary conversion treatment is carried out to the target image, binary image is obtained;
The sum of target area is counted, statistics is obtained, wherein, the target area is binaryzation in the binary image
Numerical value meets the region of preset range, wherein, the preset range is the area of section model set in advance based on target object
Enclose.
2. object count method according to claim 1, it is characterised in that also include:
Before carrying out binary conversion treatment to the target image, using image noise reduction method and/or gray processing method to the target figure
As being pre-processed.
3. object count method according to claim 1, it is characterised in that also include:
The statistics is sent to server, so as to the server stores to database the statistics preserve.
4. object count method according to claim 1, it is characterised in that also include:
The target area that will have been counted is marked, and allows the user to distinguish the target of the target area and no count for having counted
Region.
5. object count method according to claim 4, it is characterised in that rower is entered in the target area that will have been counted
After note, also include:
The statistics is corrected using the control information of user input, the statistics after being corrected.
6. the object count method according to any one of claim 1 to 5, it is characterised in that described to target object group
Image acquisition and processing is carried out, including:
IMAQ is carried out to target object group by image collecting device, original target image is obtained;
Region is carried out to original image using the region selection information of user input to select, and obtains the target image.
7. a kind of object count device, it is characterised in that including:
Image capture module, for carrying out image acquisition and processing to target object group, obtains target image;
Image processing module, for carrying out binary conversion treatment to the target image, obtains bianry image;
Statistical module, the sum for counting target area, obtains statistics, wherein, the target area is the two-value
Binaryzation numerical value meets the region of preset range in image, wherein, the preset range is the area of section based on target object
Scope set in advance.
8. object count device according to claim 7, it is characterised in that also include:
Image pre-processing module, for before carrying out binary conversion treatment to the target image, with image noise reduction method and/or gray scale
Change method is pre-processed to target image.
9. object count device according to claim 7, it is characterised in that also include:
Correction module, is corrected for the control information using user input to the statistics, the system after being corrected
Meter result.
10. the object count device according to any one of claim 7 to 9, it is characterised in that described image acquisition module bag
Include:
Unit is chosen in region, and region is carried out to original image for the region selection information using user input selectes, and obtains institute
State target image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611034545.XA CN106780435A (en) | 2016-11-18 | 2016-11-18 | A kind of object count method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611034545.XA CN106780435A (en) | 2016-11-18 | 2016-11-18 | A kind of object count method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106780435A true CN106780435A (en) | 2017-05-31 |
Family
ID=58971423
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611034545.XA Pending CN106780435A (en) | 2016-11-18 | 2016-11-18 | A kind of object count method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106780435A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
CN108961250A (en) * | 2018-07-20 | 2018-12-07 | 中国科学院深圳先进技术研究院 | A kind of object statistical method, device, terminal and storage medium |
CN111178354A (en) * | 2019-12-23 | 2020-05-19 | 深圳市铁汉生态环境股份有限公司 | Mangrove pest monitoring method and system |
CN113283439A (en) * | 2021-06-15 | 2021-08-20 | 深圳诺博医疗科技有限公司 | Intelligent counting method, device and system based on image recognition |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722715A (en) * | 2012-05-21 | 2012-10-10 | 华南理工大学 | Tumble detection method based on human body posture state judgment |
CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
CN102930272A (en) * | 2012-09-27 | 2013-02-13 | 无锡天授信息科技有限公司 | Image target detection-based system and method for counting number of people |
CN103246920A (en) * | 2013-03-22 | 2013-08-14 | 浙江理工大学 | Automatic counting method and system for silkworm cocoons |
CN103793923A (en) * | 2014-01-24 | 2014-05-14 | 华为技术有限公司 | Method and device for acquiring moving object in image |
CN103971103A (en) * | 2014-05-23 | 2014-08-06 | 西安电子科技大学宁波信息技术研究院 | People counting system |
CN104966060A (en) * | 2015-06-16 | 2015-10-07 | 广东欧珀移动通信有限公司 | Target identification method and device for moving object |
CN105844256A (en) * | 2016-04-07 | 2016-08-10 | 广州盈可视电子科技有限公司 | Panorama video frame image processing method and device |
-
2016
- 2016-11-18 CN CN201611034545.XA patent/CN106780435A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102722715A (en) * | 2012-05-21 | 2012-10-10 | 华南理工大学 | Tumble detection method based on human body posture state judgment |
CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
CN102930272A (en) * | 2012-09-27 | 2013-02-13 | 无锡天授信息科技有限公司 | Image target detection-based system and method for counting number of people |
CN103246920A (en) * | 2013-03-22 | 2013-08-14 | 浙江理工大学 | Automatic counting method and system for silkworm cocoons |
CN103793923A (en) * | 2014-01-24 | 2014-05-14 | 华为技术有限公司 | Method and device for acquiring moving object in image |
CN103971103A (en) * | 2014-05-23 | 2014-08-06 | 西安电子科技大学宁波信息技术研究院 | People counting system |
CN104966060A (en) * | 2015-06-16 | 2015-10-07 | 广东欧珀移动通信有限公司 | Target identification method and device for moving object |
CN105844256A (en) * | 2016-04-07 | 2016-08-10 | 广州盈可视电子科技有限公司 | Panorama video frame image processing method and device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108648181A (en) * | 2018-04-25 | 2018-10-12 | 佛山科学技术学院 | A kind of automobile quantity statistics method and its system based on particle filter algorithm |
CN108961250A (en) * | 2018-07-20 | 2018-12-07 | 中国科学院深圳先进技术研究院 | A kind of object statistical method, device, terminal and storage medium |
CN111178354A (en) * | 2019-12-23 | 2020-05-19 | 深圳市铁汉生态环境股份有限公司 | Mangrove pest monitoring method and system |
CN111178354B (en) * | 2019-12-23 | 2024-02-27 | 中节能铁汉生态环境股份有限公司 | Mangrove pest monitoring method and system |
CN113283439A (en) * | 2021-06-15 | 2021-08-20 | 深圳诺博医疗科技有限公司 | Intelligent counting method, device and system based on image recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106780435A (en) | A kind of object count method and device | |
CN110348441B (en) | Value-added tax invoice identification method and device, computer equipment and storage medium | |
CN109003390A (en) | A kind of commodity recognition method, self-service machine and computer readable storage medium | |
WO2020119419A1 (en) | Image recognition-based testing and apparatus, and computer device and storage medium | |
CN104573000B (en) | Automatic call answering arrangement and method based on sequence study | |
CN110147367B (en) | Temperature missing data filling method and system and electronic equipment | |
CN105512815A (en) | Enterprise risk assessment system | |
CN104966159A (en) | Risk assessment method for small and medium-sized enterprises | |
CN110222336A (en) | Analysis of financial statement method, apparatus, computer equipment and storage medium | |
CN111783785A (en) | Water meter identification system and method | |
CN113407651A (en) | Progress information feedback and deviation real-time display method | |
CN104966160A (en) | Risk assessment system for small and medium-sized enterprises | |
CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
CN109948613A (en) | A kind of Infrared image recognition and device of arrester | |
CN107944005B (en) | Data display method and device | |
CN110704044A (en) | Visual programming system | |
CN111369279A (en) | Revit-based engineering settlement method, system, device and storage medium | |
CN105893938A (en) | Oil temperature gauge reading method and system | |
US20220327452A1 (en) | Method for automatically updating unit cost of inspection by using comparison between inspection time and work time of crowdsourcing-based project for generating artificial intelligence training data | |
CN110084814A (en) | Surface covering measurement method, device, computer equipment and storage medium | |
CN101469986B (en) | Automatic point search system and method for fuzzy boundary | |
CN105893943A (en) | Oil level detection method and system | |
CN110222704A (en) | A kind of Weakly supervised object detection method and device | |
CN109783681B (en) | Agricultural product price information acquisition and processing device and method | |
CN113673759A (en) | Real-time marshalling method and terminal for hydrological data |
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: 20170531 |