CN109711257A - A kind of banister condition detection method and system based on image recognition - Google Patents
A kind of banister condition detection method and system based on image recognition Download PDFInfo
- Publication number
- CN109711257A CN109711257A CN201811425342.2A CN201811425342A CN109711257A CN 109711257 A CN109711257 A CN 109711257A CN 201811425342 A CN201811425342 A CN 201811425342A CN 109711257 A CN109711257 A CN 109711257A
- Authority
- CN
- China
- Prior art keywords
- banister
- value
- characteristic value
- picture
- present position
- 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 28
- 238000000034 method Methods 0.000 abstract description 8
- 238000009434 installation Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of banister condition detection method and system based on image recognition, this method comprises: shooting banister obtains the first picture and second picture under banister completely closed state and under fully open state；The characteristic value of banister present position in the first picture and second picture is obtained respectively as closing characteristics value and opening feature value；In the banister course of work, captured in real-time banister obtains current image；It obtains to be used as in current image with the characteristic value of banister present position and compares characteristic value；Characteristic value will be compared to compare with closing characteristics value and opening feature value progress similarity respectively；If the similarity for comparing characteristic value and closing characteristics value is greater than preset value, then determine that banister is in close state, if the similarity for comparing characteristic value and opening feature value is greater than preset value, determine that banister is in the open state, otherwise determines banister in opening or in closing.The present invention can realize the detection of banister state not against sensor.
Description
Technical field
The present invention relates to wisdom parking management technical field, especially a kind of banister state-detection side based on image recognition
Method and system.
Background technique
The demand of parking lot unmanned management is more and more at present, and unwatched parking lot needs to accomplish the reality of equipment
When monitor, avoid the occurrence of equipment fault and the case where manager knows nothing.Banister is the necessaries of the current control in parking lot,
Therefore the state-detection of banister is just particularly important.
Current banister existing on the market itself does not have banister status detection function, in order to increase banister state-detection function
Can, the way of the prior art is to add sensor on banister to detect banister state, however, the construction of the banister of different manufacturers
It is different, cause the sensor mounting location of different banisters different, installation difficulty is big, and constructs need according to different banisters
Otherwise same sensor.
Summary of the invention
Goal of the invention of the invention is: in view of the above problems, providing a kind of banister shape based on image recognition
State detection method and system can realize the detection of banister state not against sensor.
In order to solve the above technical problems, one technical scheme adopted by the invention is that: it provides a kind of based on image recognition
Banister condition detection method, comprising the following steps: S1: shooting banister under banister completely closed state and obtain the first picture, with
And banister is shot under banister fully open state and obtains second picture；S2: banister present position in first picture is obtained
Characteristic value as closing characteristics value, and obtain the characteristic value of banister present position in the second picture as opening feature
Value；S3: in the banister course of work, captured in real-time banister obtains current image；S4: obtain in the current image with banister institute
Locate the characteristic value of position as comparison characteristic value；S5: the comparison characteristic value is special with the closing characteristics value and unlatching respectively
Value indicative carries out similarity comparison；S6: if the similarity for comparing characteristic value and the closing characteristics value is sentenced greater than preset value
Determine banister to be in close state, if the similarity for comparing characteristic value and the opening feature value determines greater than preset value
Banister is in the open state, if the similarity for comparing characteristic value and the closing characteristics value and opening feature value is respectively less than pre-
If value, then determine that banister is in unlatching or in closing.
Preferably, further includes: S7: if banister generates banister failure for a long time or repeatedly in opening or in closing
Alarm.
Preferably, the step S2 specifically: according to locating for banister in the edge contour of banister acquisition first picture
The characteristic value of position is as closing characteristics value, and obtains the characteristic value of banister present position in the second picture as unlatching
Characteristic value；The step S4 specifically: according to the edge contour of banister obtain in the current image with banister present position
Characteristic value is as comparison characteristic value.
Preferably, the step S2 specifically: banister present position in first picture is obtained according to the color of banister
Characteristic value as closing characteristics value, and obtain the characteristic value of banister present position in the second picture as opening feature
Value；The step S4 specifically: obtained in the current image according to the color of banister and made with the characteristic value of banister present position
To compare characteristic value.
Preferably, the characteristic value includes coordinate and color value.
In order to solve the above technical problems, another technical solution used in the present invention is: providing a kind of based on image recognition
Banister condition detecting system, including image collection module, characteristic value acquisition module, characteristic value comparison module and state-detection mould
Block；Described image obtains module and obtains the first picture for shooting banister under banister completely closed state, opens completely in banister
It opens shooting banister under state and obtains second picture, and in the banister course of work, captured in real-time banister obtains current image；Institute
Characteristic value of the characteristic value acquisition module for obtaining banister present position in first picture is stated as closing characteristics value, is obtained
The characteristic value of banister present position is as opening feature value in the second picture, and obtain in the current image with banister
The characteristic value of present position is as comparison characteristic value；The characteristic value comparison module be used for by the comparison characteristic value respectively with institute
It states closing characteristics value and opening feature value carries out similarity comparison；The state detection module be used in the comparisons characteristic value and
When the similarity of the closing characteristics value is greater than preset value, determine that banister is in close state, in the comparison characteristic value and institute
State opening feature value similarity be greater than preset value when, determine banister it is in the open state, the comparison characteristic value with it is described
When the similarity of closing characteristics value and opening feature value is respectively less than preset value, determine that banister is in unlatching or in closing.
It preferably, further include fault warning module, the fault warning module is used to be in for a long time or repeatedly in banister
When in unlatching or in closing, banister fault warning is generated.
Preferably, the characteristic value acquisition module is specifically used for being obtained in first picture according to the edge contour of banister
The characteristic value of banister present position obtains the characteristic value conduct of banister present position in the second picture as closing characteristics value
Opening feature value, and obtain to be used as in the current image with the characteristic value of banister present position and compare characteristic value.
Preferably, the characteristic value acquisition module is specifically used for obtaining banister in first picture according to the color of banister
The characteristic value of present position obtains the characteristic value of banister present position in the second picture as unlatching as closing characteristics value
Characteristic value, and obtain to be used as in the current image with the characteristic value of banister present position and compare characteristic value.
Preferably, the characteristic value includes coordinate and color value.
In conclusion by adopting the above-described technical solution, the beneficial effects of the present invention are: passing through shooting banister difference shape
Picture under state obtains the characteristic value under the characteristic value and open state under banister closed state, by real-time banister picture
Characteristic value is compared with the first two characteristic value, therefore, it is determined that banister state, so as to realize banister shape not against sensor
The detection of state, due to only needing to be arranged near banister video camera, installation difficulty is small, and does not need to install on banister
Sensor, video camera also can use existing Car license recognition video camera, therefore very save the cost.
Detailed description of the invention
Fig. 1 is the flow diagram of the banister condition detection method based on image recognition of the embodiment of the present invention.
Fig. 2 is the functional block diagram of the banister condition detecting system based on image recognition of the embodiment of the present invention.
Specific embodiment
All features disclosed in this specification or disclosed all methods or in the process the step of, in addition to mutually exclusive
Feature and/or step other than, can combine in any way.
Any feature disclosed in this specification (including any accessory claim, abstract), unless specifically stated,
It is replaced by other equivalent or with similar purpose alternative features.That is, unless specifically stated, each feature is a series of
An example in equivalent or similar characteristics.
As shown in Figure 1, in embodiments of the present invention, the banister condition detection method based on image recognition includes following step
It is rapid:
S1: banister is shot under banister completely closed state and obtains the first picture, and under banister fully open state
Shooting banister obtains second picture.
Wherein it is possible to video camera be arranged near banister to shoot banister, or utilize the license plate at parking lot entrance
Video camera is identified to shoot banister.
S2: the characteristic value of banister present position in the first picture is obtained as closing characteristics value, and obtains second picture
The characteristic value of middle banister present position is as opening feature value.
S3: in the banister course of work, captured in real-time banister obtains current image.
S4: it is used as in acquisition current image with the characteristic value of banister present position and compares characteristic value.
S5: characteristic value will be compared and compared respectively with closing characteristics value and opening feature value progress similarity.
Wherein, if the banister in current image is in fully open state, characteristic value and opening feature value are compared
Similarity it is inevitable very high, it is believed that the two is identical, whereas if the banister in current image is in the completely closed state,
The similarity for so comparing characteristic value and closing characteristics value is inevitable very high, it is believed that the two is identical.If in current image
During banister is in unlatching or closes, then comparison characteristic value is low with the similarity-rough set of opening feature value or closing characteristics value,
It is considered that the two is not identical.
S6: if the similarity for comparing characteristic value and closing characteristics value is greater than preset value, determining that banister is in close state,
If the similarity for comparing characteristic value and opening feature value is greater than preset value, determine that banister is in the open state, if comparing feature
The similarity of value and closing characteristics value and opening feature value is respectively less than preset value, then determines that banister is in unlatching or in closing.
Wherein, preset value can be set according to actual needs, as long as similarity is greater than preset value, then it is assumed that characteristic value phase
Together, similarity is less than preset value, then it is assumed that characteristic value is not identical.
In the present embodiment, the acquisition modes of characteristic value can there are many mode, for example, by using based on edge, be based on face
The modes such as color, machine learning.
For the mode based on edge, in the present embodiment, step S2 specifically: obtain the according to the edge contour of banister
The characteristic value of banister present position is as closing characteristics value in one picture, and obtains the spy of banister present position in second picture
Value indicative is as opening feature value；Step S4 specifically: according to the edge contour of banister obtain current image in position locating for banister
The characteristic value set is as comparison characteristic value.
For the mode based on color, in the present embodiment, step S2 specifically: the first figure is obtained according to the color of banister
The characteristic value of banister present position is as closing characteristics value in piece, and obtains the characteristic value of banister present position in second picture
As opening feature value；Step S4 specifically: the feature in current image with banister present position is obtained according to the color of banister
Value is as comparison characteristic value.
In the present embodiment, characteristic value may include coordinate and color value, can be first to picture before calculating color value
Carry out binary conversion treatment.
In order to notify manager, in the present embodiment, this method in time when banister breaks down further include:
S7: if banister generates banister fault warning for a long time or repeatedly in opening or in closing.
Wherein, banister fault warning can prompt in time manager to overhaul banister failure.
As shown in Fig. 2, in embodiments of the present invention, the banister condition detecting system based on image recognition includes including image
Obtain module 21, characteristic value acquisition module 22, characteristic value comparison module 23 and state detection module 24.
Image collection module 21, which is used to shoot banister under banister completely closed state, obtains the first picture, complete in banister
Banister is shot under open state and obtains second picture, and in the banister course of work, captured in real-time banister obtains current image.
Wherein, image collection module 21 can be also possible to video camera sheet by controlling the photography picture being arranged near banister
Body, the video camera can also be the Car license recognition video camera at parking lot entrance, reduce hardware cost with this.
Characteristic value acquisition module 22 is used to obtain the characteristic value of banister present position in the first picture as closing characteristics value,
The characteristic value of banister present position in second picture is obtained as opening feature value, and is obtained in current image and locating for banister
The characteristic value of position is as comparison characteristic value.
Characteristic value comparison module 23 is similar to closing characteristics value and the progress of opening feature value respectively for that will compare characteristic value
Degree compares.Wherein, if the banister in current image is in fully open state, characteristic value and opening feature value are compared
Similarity is inevitable very high, it is believed that and the two is identical, whereas if the banister in current image is in the completely closed state, that
The similarity for comparing characteristic value and closing characteristics value is inevitable very high, it is believed that the two is identical.If the road in current image
During lock is in unlatching or closes, then comparison characteristic value is low with the similarity-rough set of opening feature value or closing characteristics value, it can
To think that the two is not identical.
State detection module 24 is used to determine road when the similarity for comparing characteristic value and closing characteristics value is greater than preset value
Lock is in close state, and when the similarity for comparing characteristic value and opening feature value is greater than preset value, is determined that banister is in and is opened
State determines that banister is in when the similarity for comparing characteristic value and closing characteristics value and opening feature value is respectively less than preset value
In unlatching or in closing.Wherein, preset value can be set according to actual needs, as long as similarity is greater than preset value, then it is assumed that special
Value indicative is identical, and similarity is less than preset value, then it is assumed that characteristic value is not identical.
Characteristic value acquisition module 22, characteristic value comparison module 23 and state detection module 24 can be managing system of car parking
The functional module of background server or other hardware modules.
In the present embodiment, characteristic value acquisition module 22 obtain characteristic value mode can there are many mode, for example, by using
Characteristic value is obtained based on edge, based on modes such as color, machine learning.
For the mode based on edge, in the present embodiment, characteristic value acquisition module 22 is specifically used for the side according to banister
Edge profile obtains the characteristic value of banister present position in the first picture as closing characteristics value, obtains in second picture locating for banister
The characteristic value of position is as opening feature value, and obtains to be used as in current image with the characteristic value of banister present position and compare spy
Value indicative.
For the mode based on color, in the present embodiment, characteristic value acquisition module 22 is specifically used for the face according to banister
Color obtains the characteristic value of banister present position in the first picture as closing characteristics value, obtains banister present position in second picture
Characteristic value as opening feature value, and obtain characteristic value in current image with banister present position as comparing feature
Value.
In the present embodiment, characteristic value may include coordinate and color value, and before calculating color value, characteristic value obtains mould
Block 22 first can carry out binary conversion treatment to picture.
In order to notify manager in time when banister breaks down, in the present embodiment, which further includes fault warning
Module 25 generates banister failure when fault warning module 25 is used in banister is in unlatching for a long time or repeatedly or closes
Alarm.Wherein, banister fault warning can prompt in time manager to overhaul banister failure.
By the above-mentioned means, the banister condition detection method based on image recognition and system of the present embodiment are complete in banister
Under open state and picture is shot under completely closed state, the characteristic value and unlatching under banister closed state are obtained by picture
The characteristic value of real-time banister picture is compared characteristic value under state with the first two characteristic value, it is possible to determine that goes out banister shape
State, so as to realize the detection of banister state not against sensor, due to only needing that video camera is arranged near banister,
Installation difficulty is small, and does not need to install sensor on banister, and video camera also can use existing Car license recognition video camera,
Therefore very save the cost.
The invention is not limited to specific embodiments above-mentioned.The present invention, which expands to, any in the present specification to be disclosed
New feature or any new combination, and disclose any new method or process the step of or any new combination.
Claims (10)
1. a kind of banister condition detection method based on image recognition, which comprises the following steps:
S1: banister is shot under banister completely closed state and obtains the first picture, and is shot under banister fully open state
Banister obtains second picture；
S2: the characteristic value of banister present position in first picture is obtained as closing characteristics value, and obtains described second
The characteristic value of banister present position is as opening feature value in picture；
S3: in the banister course of work, captured in real-time banister obtains current image；
S4: it obtains in the current image and compares characteristic value with the conduct of the characteristic value of banister present position；
S5: the comparison characteristic value is subjected to similarity with the closing characteristics value and opening feature value respectively and is compared；
S6: if the similarity for comparing characteristic value and the closing characteristics value determines that banister is in and close greater than preset value
State, if the similarity for comparing characteristic value and the opening feature value determines that banister is in opening state greater than preset value
State determines if the similarity for comparing characteristic value and the closing characteristics value and opening feature value is respectively less than preset value
During lock is in unlatching or closes.
2. banister condition detection method according to claim 1, which is characterized in that further include:
S7: if banister generates banister fault warning for a long time or repeatedly in opening or in closing.
3. banister condition detection method according to claim 1, which is characterized in that the step S2 specifically:
The characteristic value of banister present position in first picture is obtained as closing characteristics value according to the edge contour of banister, with
And the characteristic value of banister present position in the second picture is obtained as opening feature value；
The step S4 specifically:
It is obtained to be used as with the characteristic value of banister present position in the current image according to the edge contour of banister and compares characteristic value.
4. banister condition detection method according to claim 1, which is characterized in that the step S2 specifically:
The characteristic value of banister present position in first picture is obtained as closing characteristics value according to the color of banister, and is obtained
Take the characteristic value of banister present position in the second picture as opening feature value；
The step S4 specifically:
It is obtained to be used as with the characteristic value of banister present position in the current image according to the color of banister and compares characteristic value.
5. according to claim 1, banister condition detection method described in 3 or 4, which is characterized in that the characteristic value includes coordinate
And color value.
6. a kind of banister condition detecting system based on image recognition, which is characterized in that obtained including image collection module, characteristic value
Modulus block, characteristic value comparison module and state detection module；
Described image obtains module and obtains the first picture for shooting banister under banister completely closed state, opens completely in banister
It opens shooting banister under state and obtains second picture, and in the banister course of work, captured in real-time banister obtains current image；
The characteristic value acquisition module is used to obtain the characteristic value of banister present position in first picture as closing characteristics
Value obtains the characteristic value of banister present position in the second picture as opening feature value, and obtains the current image
In with the characteristic value of banister present position as comparing characteristic value；
The characteristic value comparison module be used for by the comparison characteristic value respectively with the closing characteristics value and opening feature value into
Row similarity compares；
The state detection module is used for when the similarity of the comparison characteristic value and the closing characteristics value is greater than preset value,
Determine that banister is in close state, when the similarity of the comparison characteristic value and the opening feature value is greater than preset value, sentences
Determine that banister is in the open state, is respectively less than in the similarity for comparing characteristic value and the closing characteristics value and opening feature value
When preset value, determine that banister is in unlatching or in closing.
7. banister condition detecting system according to claim 6, which is characterized in that it further include fault warning module, it is described
When fault warning module is used in banister is in unlatching for a long time or repeatedly or closes, banister fault warning is generated.
8. banister condition detecting system according to claim 6, which is characterized in that the characteristic value acquisition module is specifically used
In the characteristic value that the edge contour according to banister obtains banister present position in first picture as closing characteristics value, obtain
The characteristic value of banister present position is as opening feature value in the second picture, and obtain in the current image with banister
The characteristic value of present position is as comparison characteristic value.
9. banister condition detecting system according to claim 6, which is characterized in that the characteristic value acquisition module is specifically used
The characteristic value of banister present position in first picture is obtained as closing characteristics value, described in acquisition in the color according to banister
The characteristic value of banister present position is as opening feature value in second picture, and obtains in the current image and locating for banister
The characteristic value of position is as comparison characteristic value.
10. according to banister condition detecting system described in claim 6,8 or 9, which is characterized in that the characteristic value includes coordinate
And color value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811425342.2A CN109711257A (en) | 2018-11-27 | 2018-11-27 | A kind of banister condition detection method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811425342.2A CN109711257A (en) | 2018-11-27 | 2018-11-27 | A kind of banister condition detection method and system based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711257A true CN109711257A (en) | 2019-05-03 |
Family
ID=66255094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811425342.2A Pending CN109711257A (en) | 2018-11-27 | 2018-11-27 | A kind of banister condition detection method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711257A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264448A (en) * | 2019-06-06 | 2019-09-20 | 中南大学 | A kind of insulator breakdown detection method based on machine vision |
| CN110276747A (en) * | 2019-06-06 | 2019-09-24 | 中南大学 | A kind of insulator breakdown detection and failure ranking method based on image analysis |
| CN110288571A (en) * | 2019-06-06 | 2019-09-27 | 中南大学 | A kind of high iron catenary insulator method for detecting abnormality based on image procossing |
| CN110717995A (en) * | 2019-08-26 | 2020-01-21 | 江苏慧泽信息技术有限公司 | Parking lot gate monitoring method and system |
| CN112699864A (en) * | 2021-03-24 | 2021-04-23 | 成都宜泊信息科技有限公司 | Parking lot equipment detection method and system, electronic equipment and storage medium |
| CN114928720A (en) * | 2022-05-13 | 2022-08-19 | 重庆云凯科技有限公司 | System and method for detecting state of parking barrier gate rod |
| CN110717995B (en) * | 2019-08-26 | 2024-05-24 | 江苏慧泽信息技术有限公司 | Parking lot gate monitoring method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101179710A (en) * | 2007-11-30 | 2008-05-14 | 浙江工业大学 | Intelligent video monitoring apparatus of railway crossing |
| JP2013056754A (en) * | 2011-09-08 | 2013-03-28 | East Japan Railway Co | Door opening and closing determination device, device for monitoring state in car, door opening and closing determination method, and program |
| CN104200219A (en) * | 2014-08-20 | 2014-12-10 | 深圳供电局有限公司 | Method and device for automatically identifying substation breaker and switch indicator |
| CN105894015A (en) * | 2016-03-28 | 2016-08-24 | 国网浙江省电力公司宁波供电公司 | Gate state analyzing method and system |
| CN106250902A (en) * | 2016-07-29 | 2016-12-21 | 武汉大学 | Power system on off state detection method based on characteristics of image template matching |
| CN108804987A (en) * | 2017-05-04 | 2018-11-13 | 株式会社日立制作所 | Door open and-shut mode detection method and device and stream of people's detecting system |
-
2018
- 2018-11-27 CN CN201811425342.2A patent/CN109711257A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101179710A (en) * | 2007-11-30 | 2008-05-14 | 浙江工业大学 | Intelligent video monitoring apparatus of railway crossing |
| JP2013056754A (en) * | 2011-09-08 | 2013-03-28 | East Japan Railway Co | Door opening and closing determination device, device for monitoring state in car, door opening and closing determination method, and program |
| CN104200219A (en) * | 2014-08-20 | 2014-12-10 | 深圳供电局有限公司 | Method and device for automatically identifying substation breaker and switch indicator |
| CN105894015A (en) * | 2016-03-28 | 2016-08-24 | 国网浙江省电力公司宁波供电公司 | Gate state analyzing method and system |
| CN106250902A (en) * | 2016-07-29 | 2016-12-21 | 武汉大学 | Power system on off state detection method based on characteristics of image template matching |
| CN108804987A (en) * | 2017-05-04 | 2018-11-13 | 株式会社日立制作所 | Door open and-shut mode detection method and device and stream of people's detecting system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264448A (en) * | 2019-06-06 | 2019-09-20 | 中南大学 | A kind of insulator breakdown detection method based on machine vision |
| CN110276747A (en) * | 2019-06-06 | 2019-09-24 | 中南大学 | A kind of insulator breakdown detection and failure ranking method based on image analysis |
| CN110288571A (en) * | 2019-06-06 | 2019-09-27 | 中南大学 | A kind of high iron catenary insulator method for detecting abnormality based on image procossing |
| CN110288571B (en) * | 2019-06-06 | 2021-03-23 | 中南大学 | High-speed rail contact net insulator abnormity detection method based on image processing |
| CN110276747B (en) * | 2019-06-06 | 2021-03-23 | 中南大学 | Insulator fault detection and fault rating method based on image analysis |
| CN110264448B (en) * | 2019-06-06 | 2021-04-23 | 中南大学 | Insulator fault detection method based on machine vision |
| CN110717995A (en) * | 2019-08-26 | 2020-01-21 | 江苏慧泽信息技术有限公司 | Parking lot gate monitoring method and system |
| CN110717995B (en) * | 2019-08-26 | 2024-05-24 | 江苏慧泽信息技术有限公司 | Parking lot gate monitoring method |
| CN112699864A (en) * | 2021-03-24 | 2021-04-23 | 成都宜泊信息科技有限公司 | Parking lot equipment detection method and system, electronic equipment and storage medium |
| CN114928720A (en) * | 2022-05-13 | 2022-08-19 | 重庆云凯科技有限公司 | System and method for detecting state of parking barrier gate rod |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711257A (en) | A kind of banister condition detection method and system based on image recognition | |
| CN107292870B (en) | Track plug pin fault detection method and system based on image alignment and detection network model | |
| CN105913528B (en) | Access control data processing method and device, access control method and device | |
| US20130148852A1 (en) | Method, apparatus and system for tracking an object in a sequence of images | |
| JP6148064B2 (en) | Face recognition system | |
| CN110379050A (en) | A kind of gate control method, apparatus and system | |
| JP2018501586A (en) | Image identification system and method | |
| Xu et al. | Partial Observation vs. Blind Tracking through Occlusion. | |
| CN108710857A (en) | People's vehicle recognition methods based on infrared light filling and device | |
| US9317765B2 (en) | Human image tracking system, and human image detection and human image tracking methods thereof | |
| CN111353451A (en) | Battery car detection method and device, computer equipment and storage medium | |
| CN106780875A (en) | A kind of recognition of face gate inhibition integrated apparatus and its recognition methods | |
| US8244649B2 (en) | Structured differential learning | |
| JP2007206898A (en) | Face authentication device and access management device | |
| KR101371647B1 (en) | Apparatus for detecting fire flame based image data and method of the same | |
| KR20150058881A (en) | Air circulation control method for vehicle based on image recognition | |
| JP2009032116A (en) | Face authentication apparatus, face authentication method, and access management apparatus | |
| US20120268237A1 (en) | System and method for controlling door | |
| Xiang et al. | Vehicle detection and tracking for gas station surveillance based on AdaBoosting and optical flow | |
| CN114359839A (en) | Method and system for identifying entrance of electric vehicle into elevator | |
| Li et al. | Teamgl at acrv robotic vision challenge 1: Probabilistic object detection via staged non-suppression ensembling | |
| Lee et al. | Fire detection using color and motion models | |
| CN208346689U (en) | Visitor's gate with multiple check function | |
| CN105740788A (en) | In-vehicle abnormality anti-theft method based on inter-frame histogram disturbance detection | |
| Zhu et al. | A transform domain approach to real-time foreground segmentation in video sequences |
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: 20190503 |