CN110217205A - Vehicle cleaning method and system based on image recognition - Google Patents
Vehicle cleaning method and system based on image recognition Download PDFInfo
- Publication number
- CN110217205A CN110217205A CN201910487171.4A CN201910487171A CN110217205A CN 110217205 A CN110217205 A CN 110217205A CN 201910487171 A CN201910487171 A CN 201910487171A CN 110217205 A CN110217205 A CN 110217205A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- cleaned
- cleaning
- bodywork surface
- image
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60S—SERVICING, CLEANING, REPAIRING, SUPPORTING, LIFTING, OR MANOEUVRING OF VEHICLES, NOT OTHERWISE PROVIDED FOR
- B60S3/00—Vehicle cleaning apparatus not integral with vehicles
- B60S3/04—Vehicle cleaning apparatus not integral with vehicles for exteriors of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of vehicle cleaning method and system based on image recognition, wherein method includes the following steps: detecting the clean level of the bodywork surface of vehicle to be cleaned；Cleaning vehicle is treated using corresponding cleaning program according to bodywork surface clean level detected to be cleaned.The invention has the beneficial effects that the vehicle cleaning method and system based on image recognition provided, it can identify the clean level of different vehicle, so as to formulate corresponding cleaning program according to different clean levels, there is the carry out vehicle cleaning being directed to, both it can ensure that stolen car cleaned up, the wasting of resources can also be reduced, while saving the car-cleaning time of car owner for not in contrast being that very dirty vehicle reduces scavenging period and car washing liquid dosage simultaneously.
Description
Technical field
The present invention relates to a kind of vehicle cleaning method and system based on image recognition.
Background technique
With economic rapid development, automobile more and more enters family, and quickling increase for automobile is lived with people
The increasingly quickening of rhythm, so that the automatic unmanned carwash favor increasingly by numerous car owners now.Current unmanned carwash industry,
Unified cleaning way is used for vehicle to be cleaned, the vehicle of different clean levels is not distinguish, dirty vehicle is caused
It does not wash clean or the phenomenon that the wastings of resources such as car washing liquid.
Summary of the invention
To solve the deficiencies in the prior art, the present invention provides it is a kind of can solve the above problem based on image recognition
Vehicle cleaning method and system.
In order to achieve the above objectives, the present invention adopts the following technical scheme that:
A kind of vehicle cleaning method based on image recognition comprising the steps of:
Detect the clean level of the bodywork surface of vehicle to be cleaned；
Cleaning vehicle is treated using corresponding cleaning program according to bodywork surface clean level detected to be cleaned.
Further, the clean level of the bodywork surface of vehicle to be cleaned is detected method particularly includes:
Acquire the bodywork surface image of vehicle to be cleaned；
The bodywork surface image of collected vehicle to be cleaned is handled；
To treated, the bodywork surface image of vehicle to be cleaned carries out the judgement of clean level.
Further, the bodywork surface image of collected vehicle to be cleaned is handled method particularly includes:
Size normalization is carried out to the bodywork surface image of collected vehicle to be cleaned；
Image enhancement is carried out to bodywork surface image after size normalization；
Pixel normalization is carried out to the bodywork surface image after image enhancement.
Further, to treated, the bodywork surface image of vehicle to be cleaned carries out the specific method of clean level judgement
Are as follows:
The clean level of bodywork surface image is judged by convolutional neural networks.
Further, cleaning program includes the following contents: car washing liquid dosage and scavenging period；
Clean level includes extremely dirty, very dirty and general dirty three ranks；
For different clean levels, car washing liquid dosage and the scavenging period in corresponding cleaning program are preset.
Further, according to bodywork surface clean level detected using corresponding cleaning program treat cleaning vehicle into
Row cleaning method particularly includes:
Bodywork surface clean level detected is sent to car owner；
Car owner selects corresponding carwash scheme according to clean level；
Further according to car owner selection carwash scheme treat cleaning vehicle clean.
Further, before the clean level for detecting the bodywork surface of vehicle to be cleaned, further includes:
Vehicle parking to be cleaned is detected to position to be detected.
A kind of vehicle wash system based on image recognition, including,
First detection device, the clean level of the bodywork surface for detecting vehicle to be cleaned；
Processing unit, the clean level for the bodywork surface of vehicle to be cleaned according to detected by the first detection device
Match corresponding cleaning program；
Cleaning device, the corresponding cleaning program for being matched according to processing unit are treated cleaning vehicle and are cleaned.
Further, based on the vehicle wash system of image recognition further include:
Signal receiving/transmission device, for cleaning program is sent to car owner and receive car owner transmission operational order；
Mobile device, for receiving the cleaning program of signal receiving/transmission device transmission for car owner and operational order being sent to letter
Number R-T unit.
Further, based on the vehicle wash system of image recognition further include:
Second detection device, for detecting vehicle parking to be cleaned to position to be detected.
The invention has the beneficial effects that the vehicle cleaning method and system based on image recognition provided, can identify
The clean level of different vehicle has the progress being directed to so as to formulate corresponding cleaning program according to different clean levels
Vehicle cleaning, both can ensure that stolen car cleaned up, at the same can also be for not in contrast being that very dirty vehicle reduces cleaning when
Between and car washing liquid dosage, reduce the wasting of resources, while saving the car-cleaning time of car owner.
Detailed description of the invention
Fig. 1 is the schematic diagram of the vehicle cleaning method of the invention based on image recognition；
Fig. 2 is the schematic diagram of bilinear interpolation of the invention；
Fig. 3 is the schematic diagram of the vehicle wash system of the invention based on image recognition.
Specific embodiment
Specific introduce is made to the present invention below in conjunction with the drawings and specific embodiments.
As shown in Figure 1, a kind of vehicle cleaning method based on image recognition comprising the steps of: S2: detect vehicle to be cleaned
Bodywork surface clean level.S3: it is treated according to bodywork surface clean level detected using corresponding cleaning program
Cleaning vehicle is cleaned.
For S2: detecting the clean level of the bodywork surface of vehicle to be cleaned.
Specifically, the clean level of the bodywork surface of vehicle to be cleaned is obtained by image recognition technology, specific side
Method are as follows: acquire the bodywork surface image of vehicle to be cleaned first, then to the bodywork surface image of collected vehicle to be cleaned into
Row processing, finally to treated, the bodywork surface image of vehicle to be cleaned carries out the judgement of clean level again.
It should be understood that the bodywork surface image of vehicle to be cleaned can be acquired by camera, cleaning vehicle is waited to stop
When being put into predeterminated position, vehicle body surface image is acquired by camera.Generally, the surface image of bonnet of motor car can be acquired.
Preferably, the surface image of vehicle side car door can also be acquired, distance of the vehicle side car door away from ground is nearest, can most reflect
The clean level of vehicle.Meanwhile according to actual needs, the vehicle body image that can also acquire the multiple angles of vehicle carries out synthesis and sentences
It is disconnected.Optionally, the bodywork surface image of collected vehicle to be cleaned can be uploaded to server.
The step of collected original image noise is larger, needs to carry out image procossing, image procossing are as follows:
The first step carries out size normalization to the bodywork surface image of collected vehicle to be cleaned.
It can be by the methods of arest neighbors interpolation, bilinear interpolation, REGION INTERPOLATION, by Image Adjusting at onesize and mark
Object staff cun.In the present embodiment, use bilinear interpolation auxiliary with edge null filling, it is ensured that picture size is consistent.Two-wire
Property interpolation method: refer to that interpolating function is primary polynomial interpolation method, core concept is to carry out one respectively in both direction
Pixel value weighted sum under different coordinates is set up interpolating function by image local pixel, fitted by sublinear interpolation
The pixel value of corresponding coordinate position after scaling:
As illustrated in fig. 2, it is assumed that our known function f are in Q11=(x1, y1), Q12=(x1, y2), Q21=(x2, y1) with
And the value of Q22=(x2, y2) four points, expect function f in the value of point P=(x, y), the most common situation is: f is a picture
The pixel value of vegetarian refreshments.Linear interpolation is carried out in the direction x first, is obtained
Then linear interpolation is carried out in the direction y, obtained:
Integrate is exactly the last result of bilinear interpolation:
Second step carries out image enhancement to bodywork surface image after size normalization.
It is acquiring, often there is a degree of noise jamming, noise penalty during transmitting and handling image
The quality of image has flooded feature, has brought difficulty to picture analyzing, the clean information of surface of vehicle is one so that image is fuzzy
Kind texture information, using the texture information of canny operator and gaussian filtering enhancing image, so that the clean information of image is further
Significantly.Specific steps are as follows:
A, by Gaussian filter smoothed image, discretization is carried out to Gaussian function, with the Gaussian function numerical value on discrete point
For weight, the weighted average in a certain range neighborhood is done to each pixel of our collected gray matrixs, it can be effective
Eliminate Gaussian noise.
In actual operation, gaussian filtering is encapsulated in GaussianBlur () function: void GaussianBlur
(InputArray src, OutputArray dst, Size ksize, double sigmaX, double sigmaY=0, int
BorderType=BORDER_DEFAULT), image to be processed, the parameters such as the size and deviation of Gaussian kernel need to be only passed to
?.
B, first-order difference local derviation calculates gradient value and direction.
It C, is not that the place of maximum inhibits to gradient value, the gradient value calculated, the point for not being extreme value, all
0 is set, eliminates most of weak edge, image border can attenuate.
D, with the connection point in dual threshold connection figure: dual threshold t1, t2 (t1≤t2), the point greater than t2 is edge certainly,
Certainly not edge, the point between t1, t2 initiate the search in 8 field directions by fixed marginal point to point less than t1
(extensively searching), reachable in figure is edge, and inaccessible point is not edge, finally obtains canny edge graph.
Third step carries out pixel normalization to the bodywork surface image after image enhancement.
Assuming that original image is 8 gray level images, then the picture element matrix maximum value read in is 255, minimum value 0, definition
Matrix is I, J=I/256, is exactly normalized image array, that is all pixel values are all in [0,1] after normalization.
In, we can go each data in traversal vector matrix, by recording for Max and Min, and pass through Max-Min
The normalized of data is carried out as radix, the value after calculating is just between [0,1], as follows:
After handling through the above steps collected bodywork surface image, pass through CNN (Convolutional
Neural Networks) convolutional neural networks judge the clean level of bodywork surface image.For the identification of vehicle clean level
Some universals of vehicle are filtered off by convolutional neural networks, it is relevant to retain clean level by speech, depth learning technology
Feature, and these features are abstracted, to obtain unified feature, to judge whether vehicle is clean.The specific steps are that:
Image is sent into convolutional layer, convolutional layer will carry out the convolution operation of following formula to image,
Wherein, g is image after convolution, and f is input picture, and h is convolution kernel,
Image after convolution is sent into the pond layer having a size of 2, pond layer will carry out the Chi Huacao of following formula to image
Make,
Image size can become original half after pondization operation, and repeated multiple times execution convolution-pondization operation is until pond
Image size afterwards becomes the 1/32 of original image, which is sent into full articulamentum, full articulamentum also carries out convolution operation, full articulamentum
Input picture and convolution kernel it is in the same size, obtain a value after each convolution kernel and input picture convolution.There are three this layers
Convolution kernel, therefore three values are exported, these three values are corresponding extremely dirty, very dirty, general dirty, compare its size relation and judge vehicle
Clean level.Generally, clean level includes extremely dirty, very dirty and general dirty three ranks.It should be understood that according to practical need
It asks, the grade classification of clean level can be different.
Preferably, multiple images can be obtained in same position, then by averagely voting or the methods of Nearest Neighbor with Weighted Voting
Judge the clean level of vehicle.
For S3: treating cleaning vehicle using corresponding cleaning program according to bodywork surface clean level detected and carry out
Cleaning.
After finally obtaining the clean level of vehicle to be cleaned according to the method for above-mentioned S2, further according to the clean level, choosing
Suitable cleaning program is selected, there can be following methods:
First way: corresponding cleaning solution is calculated automatically according to clean level, and according to the cleaning solution to vehicle
It is cleaned.
The second way: the clean level for the vehicle that will test is sent to car owner, is generally sent on the mobile phone of car owner
Corresponding APP on, car owner can independently select different cleaning programs according to the clean level of the vehicle received, optional
, different cleaning programs can formulate different price plans according to the actual situation, and car owner is selecting different cleaning programs
Different expenses is paid simultaneously.
Cleaning program includes car washing liquid dosage and car-cleaning time, different cleaning programs, car washing liquid dosage in scheme and
Car-cleaning time is different.It should be understood that cleaning program can also include the hydraulic pressure intensity of car washing liquid concentration and carwash nozzle, it is different
Cleaning program can have the hydraulic pressure intensity of unused car washing liquid concentration and carwash nozzle.
Preferably, further include S1 before the clean level of bodywork surface that vehicle to be cleaned is detected in S2: detection is to be cleaned
Vehicle parking is to position to be detected.
Specifically, by one of photoelectric sensor, ultrasonic wave, distance measuring sensor or a variety of can detect car
It has been parked in correct position, for example, be respectively equipped with 2 ultrasonic waves in vehicle two sides, has been distributed in close to the position of headstock, the tailstock, when
After having detected that car enters, control system acquires the data of each ultrasonic wave, by logical process, final defeated place's voice and
LED prompt information: headstock please turn left lean on, headstock please turn right lean on, the tailstock please turn left lean on, the tailstock please turn right and lean on, instruct user vehicle
Stop in place, meanwhile, ultrasonic wave and TOF (Time of Flight) sensor are housed on the wall in tailstock dead astern,
After having detected that car enters, control system acquires the data of ultrasonic wave and TOF, by logical process, final defeated place's voice
With LED prompt information: continuing with forward, the prompt such as please retreat, vehicle is finally directed to position to be detected.
As shown in figure 3, the invention also discloses a kind of vehicle wash systems based on image recognition, including, the first detection
Device 1, processing unit 2 and cleaning device 3.Wherein, the first detection device 1 is used to detect the clean of the bodywork surface of vehicle to be cleaned
Net degree, clean level of the processing unit 2 for the bodywork surface of vehicle to be cleaned according to detected by the first detection device
Match corresponding cleaning program.Cleaning device 3 is used to treat cleaning vehicle according to the corresponding cleaning program that processing unit matches
It is cleaned.
Specifically, the first detection device 1 includes image collection module, image processing module and picture recognition module.Its
In, image collection module is used to obtain the bodywork surface image of vehicle to be cleaned, and generally camera, image processing module is used for
The image that image collection module is got is handled, picture recognition module is used for that image judges to be to be cleaned according to treated
The clean level of vehicle.
Preferably, based on the vehicle wash system of image recognition further include: signal receiving/transmission device 4 and mobile device 5.
Refer to specifically, signal receiving/transmission device 4 is used to cleaning program being sent to car owner and receives the operation that car owner sends
It enables.Mobile device 5 is used to receive for car owner the cleaning program of signal receiving/transmission device transmission and operational order is sent to signal to receive
Transmitting apparatus.Generally, which is mobile phone, it is possible to understand that is that other such as tablet computers, laptop are set
It is standby.
Further, based on the vehicle wash system of image recognition further include: second detection device 6, for detecting to clear
Vehicle parking is washed to position to be detected.Second detection device 6 generally comprises photoelectric sensor, ultrasonic wave, in distance measuring sensor
It is one or more.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the above embodiments do not limit the invention in any form, all obtained by the way of equivalent substitution or equivalent transformation
Technical solution is fallen within the scope of protection of the present invention.
Claims (10)
1. a kind of vehicle cleaning method based on image recognition, which is characterized in that comprise the steps of:
Detect the clean level of the bodywork surface of vehicle to be cleaned；
Cleaning vehicle is treated using corresponding cleaning program according to bodywork surface clean level detected to be cleaned.
2. the vehicle cleaning method according to claim 1 based on image recognition, which is characterized in that
The clean level of the bodywork surface of the detection vehicle to be cleaned method particularly includes:
Acquire the bodywork surface image of vehicle to be cleaned；
The bodywork surface image of collected vehicle to be cleaned is handled；
To treated, the bodywork surface image of vehicle to be cleaned carries out the judgement of the clean level.
3. the vehicle cleaning method according to claim 2 based on image recognition, which is characterized in that
What the bodywork surface image to collected vehicle to be cleaned was handled method particularly includes:
Size normalization is carried out to the bodywork surface image of collected vehicle to be cleaned；
Image enhancement is carried out to the bodywork surface image after size normalization；
Pixel normalization is carried out to the bodywork surface image after image enhancement.
4. the vehicle cleaning method according to claim 1 based on image recognition, which is characterized in that
The bodywork surface image of the vehicle to be cleaned to treated carries out clean level judgement method particularly includes:
The clean level of bodywork surface image is judged by convolutional neural networks.
5. the vehicle cleaning method according to claim 1 based on image recognition, which is characterized in that
The cleaning program includes the following contents: car washing liquid dosage and scavenging period；
The clean level includes extremely dirty, very dirty and general dirty three ranks；
For the different clean levels, when presetting the car washing liquid dosage and cleaning in the corresponding cleaning program
Between.
6. the vehicle cleaning method according to claim 1 based on image recognition, which is characterized in that
It is described to treat what cleaning vehicle was cleaned using corresponding cleaning program according to bodywork surface clean level detected
Method particularly includes:
Bodywork surface clean level detected is sent to car owner；
Car owner selects corresponding carwash scheme according to the clean level；
Further according to car owner selection carwash scheme treat cleaning vehicle clean.
7. the vehicle cleaning method according to claim 1 based on image recognition, which is characterized in that
Before the clean level of the bodywork surface of the detection vehicle to be cleaned, further includes:
Vehicle parking to be cleaned is detected to position to be detected.
8. a kind of vehicle wash system based on image recognition, which is characterized in that including,
First detection device, the clean level of the bodywork surface for detecting vehicle to be cleaned；
Processing unit, the clean level for the bodywork surface of vehicle to be cleaned according to detected by first detection device
Match corresponding cleaning program；
Cleaning device, the corresponding cleaning program for being matched according to the processing unit are treated cleaning vehicle and are cleaned.
9. according to claim 8 in the vehicle wash system of image recognition, which is characterized in that
The vehicle wash system of be set forth in image recognition further include:
Signal receiving/transmission device, for the cleaning program is sent to car owner and receive car owner transmission operational order；
Mobile device, for receiving the cleaning program of the signal receiving/transmission device transmission for car owner and sending the operational order
To the signal receiving/transmission device.
10. according to claim 8 in the vehicle wash system of image recognition, which is characterized in that
The vehicle wash system based on image recognition further include:
Second detection device, for detecting vehicle parking to be cleaned to position to be detected.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141444X | 2019-02-26 | ||
| CN201910141444 | 2019-02-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110217205A true CN110217205A (en) | 2019-09-10 |
Family
ID=67819460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910487171.4A Pending CN110217205A (en) | 2019-02-26 | 2019-06-05 | Vehicle cleaning method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110217205A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241953A (en) * | 2020-01-03 | 2020-06-05 | 秒针信息技术有限公司 | Decontamination verification method and device, storage medium and electronic device |
| CN111439238A (en) * | 2020-05-08 | 2020-07-24 | 济南睿达物联网有限公司 | Automatic car washing device based on internet of things information |
| CN112356808A (en) * | 2020-12-08 | 2021-02-12 | 西安建筑科技大学 | Non-contact car washer |
| CN112529093A (en) * | 2020-12-21 | 2021-03-19 | 上海英十信息科技有限公司 | Method for testing mold cleaning effect based on sample dimension weighting of pre-detection weight |
| CN112559858A (en) * | 2020-12-08 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Service information pushing method and device, computer readable medium and electronic equipment |
| CN112550235A (en) * | 2020-11-20 | 2021-03-26 | 北京中铁建建筑科技有限公司 | Automatic wheel washing system and wheel washing method thereof |
| CN112699940A (en) * | 2020-12-30 | 2021-04-23 | 腾讯科技（深圳）有限公司 | Vehicle cleaning associated resource recommendation method and device and storage medium |
| CN112977351A (en) * | 2021-02-26 | 2021-06-18 | 朱桂云 | Vehicle cleaning one-time quantitative system |
| CN113221727A (en) * | 2021-05-08 | 2021-08-06 | 杭州鸿泉物联网技术股份有限公司 | Method and system for judging cleaning state of engineering vehicle |
| CN114283370A (en) * | 2022-02-18 | 2022-04-05 | 城云科技（中国）有限公司 | Method and device for identifying uncleaned vehicle and application |
| CN114475529A (en) * | 2022-04-07 | 2022-05-13 | 湖南孚瑞锑格机械设备有限公司 | Intelligent unmanned vehicle washing system and method |
| CN116363349A (en) * | 2023-04-12 | 2023-06-30 | 广州市车聚乐信息科技有限公司 | Intelligent cleaning equipment control method and system based on Internet of things |
| CN118196743A (en) * | 2024-04-02 | 2024-06-14 | 济南智云数字科技有限公司 | Intelligent matching analysis method for car washing requirements of self-service car washing machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103909909A (en) * | 2013-11-29 | 2014-07-09 | 余姚市宏骏铜业有限公司 | Car washing system and car washing method |
| KR101421159B1 (en) * | 2013-04-17 | 2014-07-23 | 주식회사 대철이엔지 | System for washing underbody rail vehicle |
| CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
| CN107346591A (en) * | 2017-06-30 | 2017-11-14 | 成都科立达科技有限公司 | Automation vehicle washing system based on mobile phone terminal |
| CN107813796A (en) * | 2017-09-16 | 2018-03-20 | 深圳市赛亿科技开发有限公司 | A kind of automatic car washing system of automatic driving vehicle |
| CN108009520A (en) * | 2017-12-21 | 2018-05-08 | 东南大学 | A kind of finger vein identification method and system based on convolution variation self-encoding encoder neutral net |
-
2019
- 2019-06-05 CN CN201910487171.4A patent/CN110217205A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101421159B1 (en) * | 2013-04-17 | 2014-07-23 | 주식회사 대철이엔지 | System for washing underbody rail vehicle |
| CN103909909A (en) * | 2013-11-29 | 2014-07-09 | 余姚市宏骏铜业有限公司 | Car washing system and car washing method |
| CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
| CN107346591A (en) * | 2017-06-30 | 2017-11-14 | 成都科立达科技有限公司 | Automation vehicle washing system based on mobile phone terminal |
| CN107813796A (en) * | 2017-09-16 | 2018-03-20 | 深圳市赛亿科技开发有限公司 | A kind of automatic car washing system of automatic driving vehicle |
| CN108009520A (en) * | 2017-12-21 | 2018-05-08 | 东南大学 | A kind of finger vein identification method and system based on convolution variation self-encoding encoder neutral net |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241953B (en) * | 2020-01-03 | 2023-11-10 | 河北太行农牧供应链有限公司 | Decontamination verification method and device, storage medium and electronic device |
| CN111241953A (en) * | 2020-01-03 | 2020-06-05 | 秒针信息技术有限公司 | Decontamination verification method and device, storage medium and electronic device |
| CN111439238B (en) * | 2020-05-08 | 2021-11-02 | 济南睿达物联网有限公司 | Automatic car washing device based on internet of things information |
| CN111439238A (en) * | 2020-05-08 | 2020-07-24 | 济南睿达物联网有限公司 | Automatic car washing device based on internet of things information |
| CN112550235A (en) * | 2020-11-20 | 2021-03-26 | 北京中铁建建筑科技有限公司 | Automatic wheel washing system and wheel washing method thereof |
| CN112356808A (en) * | 2020-12-08 | 2021-02-12 | 西安建筑科技大学 | Non-contact car washer |
| CN112559858A (en) * | 2020-12-08 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Service information pushing method and device, computer readable medium and electronic equipment |
| CN112529093A (en) * | 2020-12-21 | 2021-03-19 | 上海英十信息科技有限公司 | Method for testing mold cleaning effect based on sample dimension weighting of pre-detection weight |
| CN112699940B (en) * | 2020-12-30 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Vehicle cleaning associated resource recommendation method and device and storage medium |
| CN112699940A (en) * | 2020-12-30 | 2021-04-23 | 腾讯科技（深圳）有限公司 | Vehicle cleaning associated resource recommendation method and device and storage medium |
| CN112977351A (en) * | 2021-02-26 | 2021-06-18 | 朱桂云 | Vehicle cleaning one-time quantitative system |
| CN112977351B (en) * | 2021-02-26 | 2023-12-22 | 三盈联合科技股份有限公司 | Vehicle cleaning once quantitative system |
| CN113221727A (en) * | 2021-05-08 | 2021-08-06 | 杭州鸿泉物联网技术股份有限公司 | Method and system for judging cleaning state of engineering vehicle |
| CN114283370A (en) * | 2022-02-18 | 2022-04-05 | 城云科技（中国）有限公司 | Method and device for identifying uncleaned vehicle and application |
| CN114475529A (en) * | 2022-04-07 | 2022-05-13 | 湖南孚瑞锑格机械设备有限公司 | Intelligent unmanned vehicle washing system and method |
| CN116363349A (en) * | 2023-04-12 | 2023-06-30 | 广州市车聚乐信息科技有限公司 | Intelligent cleaning equipment control method and system based on Internet of things |
| CN116363349B (en) * | 2023-04-12 | 2023-09-22 | 广州市车聚乐信息科技有限公司 | Intelligent cleaning equipment control method and system based on Internet of things |
| CN118196743A (en) * | 2024-04-02 | 2024-06-14 | 济南智云数字科技有限公司 | Intelligent matching analysis method for car washing requirements of self-service car washing machine |
| CN118196743B (en) * | 2024-04-02 | 2024-08-30 | 济南智云数字科技有限公司 | Intelligent matching analysis method for car washing requirements of self-service car washing machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110217205A (en) | Vehicle cleaning method and system based on image recognition | |
| CN106894481B (en) | One kind is detected automatically based on intelligent closestool and is cleaned dirt method and system | |
| CN104657735B (en) | Method for detecting lane lines, system, lane departure warning method and system | |
| Maini et al. | Study and comparison of various image edge detection techniques | |
| TWI737040B (en) | Fingerprint recognition method, chip and electronic device | |
| He et al. | Deep regression neural network for industrial surface defect detection | |
| CN104077773A (en) | Image edge detection method, and image target identification method and device | |
| CN103366601A (en) | Apparatus and method of setting parking position based on around-view image | |
| CN105891233A (en) | Intelligent detection system for surface defects of lens based on machine vision and implementation method of intelligent detection system | |
| CN116109637B (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
| CN110901597A (en) | Intelligent unmanned car washing method based on machine vision | |
| Kozamernik et al. | Visual inspection system for anomaly detection on KTL coatings using variational autoencoders | |
| CN111027534A (en) | Compact double-license-plate detection method and device | |
| CN111047598B (en) | Deep learning-based ultraviolet discharge light spot segmentation method and device for power transmission and transformation equipment | |
| CN112633086A (en) | Near-infrared pedestrian monitoring method, system, medium and equipment based on multitask EfficientDet | |
| CN116823819A (en) | Weld surface defect detection method, system, electronic equipment and storage medium | |
| CN105844265B (en) | A kind of fingerprint image treating method and apparatus | |
| CN113837029A (en) | Object identification method, system, terminal device and storage medium | |
| CN109299743B (en) | Gesture recognition method and device and terminal | |
| CN110826687A (en) | Data processing method, apparatus, medium, and system thereof | |
| CN115496984A (en) | Ceramic tile finished product defect automatic identification method and device, intelligent terminal and storage medium | |
| CN112977351B (en) | Vehicle cleaning once quantitative system | |
| CN109636744A (en) | A kind of adapting to image processing method of underground distance gated imaging | |
| CN112837307B (en) | Method, device, processor and system for determining weld bead profile | |
| CN114565841A (en) | Vehicle type recognition method based on image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |