CN113022496A - Intelligent windscreen wiper system based on images and control method - Google Patents
Intelligent windscreen wiper system based on images and control method Download PDFInfo
- Publication number
- CN113022496A CN113022496A CN202110380290.7A CN202110380290A CN113022496A CN 113022496 A CN113022496 A CN 113022496A CN 202110380290 A CN202110380290 A CN 202110380290A CN 113022496 A CN113022496 A CN 113022496A
- Authority
- CN
- China
- Prior art keywords
- wiper
- intelligent
- windscreen wiper
- image
- water wiping
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60S—SERVICING, CLEANING, REPAIRING, SUPPORTING, LIFTING, OR MANOEUVRING OF VEHICLES, NOT OTHERWISE PROVIDED FOR
- B60S1/00—Cleaning of vehicles
- B60S1/02—Cleaning windscreens, windows or optical devices
- B60S1/04—Wipers or the like, e.g. scrapers
- B60S1/06—Wipers or the like, e.g. scrapers characterised by the drive
- B60S1/08—Wipers or the like, e.g. scrapers characterised by the drive electrically driven
- B60S1/0818—Wipers or the like, e.g. scrapers characterised by the drive electrically driven including control systems responsive to external conditions, e.g. by detection of moisture, dirt or the like
- B60S1/0822—Wipers or the like, e.g. scrapers characterised by the drive electrically driven including control systems responsive to external conditions, e.g. by detection of moisture, dirt or the like characterized by the arrangement or type of detection means
- B60S1/0833—Optical rain sensor
- B60S1/0844—Optical rain sensor including a camera
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to the technical field of intelligent automobiles, and relates to an intelligent wiper system based on images and a control method. The intelligent windscreen wiper comprises an image acquisition module, a preprocessing module, an intelligent windscreen wiper model and a windscreen wiper motor driving module; the method comprises the steps of collecting a video in real time by using an image collection module, converting the video into an image by a preprocessing module according to frames, inputting the image converted in real time into an intelligent windscreen wiper model trained in advance, identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending an instruction to a windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval. The invention optimizes the prior wiper system based on images, solves the problems of few gears and manual operation of the traditional wiper, overcomes the defects of smaller measuring range and nonlinear rainfall signal of the automatic wiper based on the rainfall sensor, and enhances the driving safety and comfort.
Description
Technical Field
The invention belongs to the technical field of intelligent automobiles, and relates to an intelligent wiper system based on images and a control method.
Background
The automobile windscreen wiper is an important accessory arranged on a windscreen, and is a key for guaranteeing driving safety. The driving vision is poor in rainy weather, the traditional windscreen wiper needs to be manually operated by a driver, great potential safety hazards exist, the wiping speed of the windscreen wiper is fixed, and the wiping speed of the windscreen wiper does not change along with the change of rainfall. In contrast, an automatic wiper based on a rainfall sensor can enhance the safety of a part of scenes, but the rainfall sensor has some disadvantages at present, such as a small measurement range, a non-linear rainfall signal, a large influence of environmental factors on the effect, and the like, which make the effect of the wiper not ideal. In order to improve driving safety, an image-based intelligent wiper control system has become a research hotspot.
Patent document CN201710311805.1 discloses an intelligent wiper control device based on image recognition and cloud computing and a control method thereof, including an ARM processor, a satellite navigation module, an image acquisition module, a sensor data acquisition module, a wiper motor driving module, a memory, a data transmission module and a cloud server; the ARM processor is used for receiving information and sending instructions to the wiper motor driving module, the wiper motor driving module is used for driving the wiper to work, and the data transmission module is used for data transmission between the memory and the cloud server. The windscreen wiper controller is controlled by carrying out recognition processing and cloud computing on the image in real time, and the acquired rainfall picture data are consistent with the front view of a driver; the wiper controller is simple and convenient to upgrade; remote closing of the vehicle window can be achieved.
Patent document CN201811134183.0 discloses an automobile intelligence windscreen wiper system based on singlechip, including the windscreen wiper motor, the windscreen wiper motor is supplied power by the car power, still include the rainfall sensor module of being connected with car driving computer, AD conversion module, the singlechip, motor drive module, the singlechip passes through the serial ports and is connected with car driving computer, the output and the AD conversion module's of rainfall sensor module input are connected, AD conversion module's output and the input of singlechip are connected, motor drive module's input is connected to the output of singlechip, the control signal input of windscreen wiper motor is connected to motor drive module's output. Compared with the prior art, the rain sensor real-time monitoring system controls the windscreen wiper by the rain sensor real-time monitoring mode, according to the rainfall detected by the rain sensor and by controlling the working speed of the motor, avoids manually opening the windscreen wiper and adjusting the working speed of the windscreen wiper in a complicated road section, and is safer, more convenient and lower in cost and convenient to popularize and use.
Patent document CN201710269872.1 discloses an intelligent wiper for an automobile, which includes an infrared light detection raindrop circuit, a photoelectric conversion module, a controller and a motor driving circuit for driving a motor; the infrared ray raindrop detection circuit receives the optical signal, converts the optical signal into an electric signal and sends the electric signal into the controller, and the electric signal is processed and the size of raindrops is judged so as to control the motor driving circuit to drive the motor to work; the infrared ray raindrop detection circuit comprises an infrared emission circuit and an infrared receiving circuit, the infrared ray raindrop detection circuit detects raindrops by utilizing infrared rays, and the infrared emission circuit and the infrared receiving circuit are arranged in the automobile, so that the windscreen wiper is not interfered by the external environment, and the automatic work of the windscreen wiper is stably realized.
With the system disclosed in patent document 1, a wiper blade controller is controlled by performing recognition processing and cloud computing on an image, which is described as a hardware solution, and there is no solution of a specific algorithm for image recognition.
With the system disclosed in patent document 2, the method monitors the rainfall in real time by the rainfall sensor to control the operating speed of the wiper motor, but the measurement range of the rainfall sensor is small, the received rainfall signal is nonlinear, and the effect is greatly influenced by environmental factors.
With the system disclosed in patent document 3, the method of detecting the magnitude of rainfall by infrared light is susceptible to interference from background light, the photoelectric conversion signal is weak, and the rainfall signal is susceptible to noise flooding.
Disclosure of Invention
The invention aims to solve the technical problems that in the prior art, a rainfall sensor is small in measurement range, rainfall signals are nonlinear, and effects are greatly influenced by environmental factors, and provides an intelligent windscreen wiper system based on images and a control method.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme:
an image-based intelligent wiper system comprises an image acquisition module, a preprocessing module, an intelligent wiper model and a wiper motor driving module;
the image acquisition module is used for acquiring a video in real time during driving;
the preprocessing module is used for converting the video into images according to frames;
the intelligent windscreen wiper model is used for identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending instructions to the windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval.
Further, the intelligent wiper model is trained using a convolutional neural network.
A method of controlling an image-based intelligent wiper system, comprising:
the method comprises the steps of collecting a video in real time by using an image collection module, converting the video into an image by a preprocessing module according to frames, inputting the image converted in real time into an intelligent windscreen wiper model trained in advance, identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending an instruction to a windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval.
The control method of the intelligent wiper system based on the image further comprises the step of evaluating the accuracy of the intelligent wiper model obtained through training by using an evaluation standard.
In the technical scheme, the accuracy evaluation means that: and inputting the images in the test set into the trained intelligent wiper model, and evaluating the accuracy of model prediction by using the average precision mean value so as to judge the accuracy of the intelligent wiper model obtained after training.
Further, the intelligent wiper model is trained by using a convolutional neural network;
the training by using the convolutional neural network refers to adding a linear regression layer behind the convolutional network, outputting different rainfall intensity values, and dividing the rainfall intensity values into five intervals which respectively represent five label values; and obtaining the intelligent wiper model after training.
In the technical scheme, the convolutional network is a ResNet50 network, and the number of layers of the convolutional neural network is 50.
In the technical scheme, the image is as follows: and 3, dividing the ratio into a training set and a testing set, and setting five labels of light rain, medium rain, heavy rain and extra heavy rain.
In the technical scheme, the five kinds of labels respectively correspond to the speed of a wiper motor and the wiping time of a wiper.
Compared with the prior art, the invention has the beneficial effects that:
the invention optimizes the prior wiper system based on images, solves the problems of few gears and manual operation of the traditional wiper, overcomes the defects of smaller measuring range and nonlinear rainfall signal of the automatic wiper based on the rainfall sensor, and enhances the driving safety and comfort.
Drawings
The invention is further described with reference to the accompanying drawings in which:
fig. 1 is a block diagram of an image-based intelligent wiper system according to the present invention.
Fig. 2 is a schematic diagram of a training process of the intelligent wiper model.
Detailed Description
In order to make the implementation objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are only some, but not all embodiments of the invention. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience in describing the present invention and for simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore, should not be taken as limiting the scope of the present invention.
The invention is described in detail below with reference to the attached drawing figures:
referring to fig. 1, the image-based intelligent wiper system includes an image acquisition module, a preprocessing module, an intelligent wiper model, and a wiper motor driving module;
the image acquisition module is used for acquiring a video in real time during driving;
the preprocessing module is used for converting the video into images according to frames;
the intelligent windscreen wiper model is used for identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending instructions to the windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval.
A control method of an intelligent wiper system based on images comprises the following steps:
firstly, training an intelligent wiper model, referring to fig. 2, the training process is as follows:
the camera of the data acquisition module is used for acquiring the rainy-day videos with different rain intensities and the videos under other weather conditions
Sending the collected video to a preprocessing module, converting the video into pictures according to frames, and converting all the pictures into pictures according to the following steps of 7: and 3, dividing the proportion into a training set and a testing set, and setting five types of labels of light rain, medium rain, heavy rain and extra heavy rain, wherein each type of label corresponds to the speed of a wiper motor and the wiping time of the wiper respectively.
The images and corresponding labels in the training set are trained using a Convolutional Neural Network (CNN), such as a ResNet50 network, in which the number of layers of the convolutional neural network is 50, a linear regression layer is added after the convolutional network to output different rainfall intensity values, and the rainfall intensity values are divided into five intervals, each of which represents five label values. And obtaining the intelligent wiper model after training.
And evaluating the accuracy of the intelligent wiper model obtained by training by using an evaluation standard. And inputting the images in the test set into the trained intelligent wiper model, and evaluating the accuracy of model prediction by using an average precision average (mAP) so as to judge the accuracy of the intelligent wiper model obtained after training.
The working process of the intelligent windscreen wiper control system is that firstly, an image acquisition module is used for acquiring videos in real time during driving, a preprocessing module converts the videos into images according to frames, then the images converted in real time are input into an intelligent windscreen wiper model trained in advance, rainy days with different rainfall amounts are identified, corresponding windscreen wiper water wiping speeds and water wiping intervals are matched, and instructions are sent to a windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speeds and water wiping intervals.
According to the method, different rainfall capacities in rainy days can be recognized in real time by using the trained image intelligent windscreen wiper model, and the intelligent windscreen wiper control system automatically matches a proper wiping speed according to the different rainfall capacities to drive the windscreen wiper motor, so that the safety and the comfort of driving in rainy days are enhanced.
The method solves the problems that the traditional windscreen wiper has few gears and needs manual operation, and the defects that the automatic windscreen wiper based on the rainfall sensor has a small measuring range and a nonlinear rainfall signal, and enhances the driving safety and comfort.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims. And those not described in detail in this specification are well within the skill of those in the art.
Claims (9)
1. An intelligent windscreen wiper system based on image which characterized in that: the intelligent windscreen wiper comprises an image acquisition module, a preprocessing module, an intelligent windscreen wiper model and a windscreen wiper motor driving module;
the image acquisition module is used for acquiring a video in real time during driving;
the preprocessing module is used for converting the video into images according to frames;
the intelligent windscreen wiper model is used for identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending instructions to the windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval.
2. The image-based intelligent wiper system and control method according to claim 1, wherein:
the intelligent wiper model is trained using a convolutional neural network.
3. A method of controlling an image-based smart wiper system as defined in claim 1, comprising the steps of:
the method comprises the steps of collecting a video in real time by using an image collection module, converting the video into an image by a preprocessing module according to frames, inputting the image converted in real time into an intelligent windscreen wiper model trained in advance, identifying rainy days with different rainfall amounts, matching corresponding windscreen wiper water wiping speed and water wiping interval, and sending an instruction to a windscreen wiper motor driving module according to the calculated windscreen wiper water wiping speed and water wiping interval.
4. The method of claim 3 wherein the step of controlling the image-based smart wiper system further comprises the steps of:
and the method also comprises the step of evaluating the accuracy of the intelligent wiper model obtained by training by using an evaluation standard.
5. The method of claim 4 wherein the step of controlling the image-based smart wiper system further comprises the steps of:
the accuracy evaluation refers to: and inputting the images in the test set into the trained intelligent wiper model, and evaluating the accuracy of model prediction by using the average precision mean value so as to judge the accuracy of the intelligent wiper model obtained after training.
6. The method of claim 3 wherein the step of controlling the image-based smart wiper system further comprises the steps of:
the intelligent wiper model is trained by using a convolutional neural network;
the training by using the convolutional neural network refers to adding a linear regression layer behind the convolutional network, outputting different rainfall intensity values, and dividing the rainfall intensity values into five intervals which respectively represent five label values; and obtaining the intelligent wiper model after training.
7. The method of claim 6 wherein:
the convolutional network is a ResNet50 network with 50 layers of convolutional neural network.
8. The method of claim 6 wherein:
the image is as follows 7: and 3, dividing the ratio into a training set and a testing set, and setting five labels of light rain, medium rain, heavy rain and extra heavy rain.
9. The method of claim 8 wherein the step of controlling the image-based smart wiper system further comprises the steps of:
the five kinds of labels respectively correspond to the speed and the water scraping time of a wiper motor of the wiper.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110380290.7A CN113022496A (en) | 2021-04-09 | 2021-04-09 | Intelligent windscreen wiper system based on images and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110380290.7A CN113022496A (en) | 2021-04-09 | 2021-04-09 | Intelligent windscreen wiper system based on images and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113022496A true CN113022496A (en) | 2021-06-25 |
Family
ID=76456050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110380290.7A Pending CN113022496A (en) | 2021-04-09 | 2021-04-09 | Intelligent windscreen wiper system based on images and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113022496A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320625A (en) * | 2022-08-23 | 2022-11-11 | 一汽奔腾轿车有限公司 | Identification and judgment method for optimizing rainy scene of intelligent driving system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120064474A (en) * | 2010-12-09 | 2012-06-19 | 엘지이노텍 주식회사 | Apparatus and method for detecting raindrop using camera module |
| CN103543638A (en) * | 2013-10-10 | 2014-01-29 | 山东神戎电子股份有限公司 | Automatic windshield wiper control method |
| CN109927675A (en) * | 2019-04-09 | 2019-06-25 | 深圳创维汽车智能有限公司 | A kind of rain brush control method, device, equipment and storage medium |
| CN110562201A (en) * | 2019-09-19 | 2019-12-13 | 广州小鹏汽车科技有限公司 | Control method and control device for windscreen wiper and vehicle |
| CN110852274A (en) * | 2019-11-12 | 2020-02-28 | 上海智驾汽车科技有限公司 | Intelligent rainfall sensing method and device based on image recognition |
| CN112572356A (en) * | 2020-12-11 | 2021-03-30 | 江苏联成开拓集团有限公司 | Wiper control system based on automobile data recorder and method thereof |
-
2021
- 2021-04-09 CN CN202110380290.7A patent/CN113022496A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120064474A (en) * | 2010-12-09 | 2012-06-19 | 엘지이노텍 주식회사 | Apparatus and method for detecting raindrop using camera module |
| CN103543638A (en) * | 2013-10-10 | 2014-01-29 | 山东神戎电子股份有限公司 | Automatic windshield wiper control method |
| CN109927675A (en) * | 2019-04-09 | 2019-06-25 | 深圳创维汽车智能有限公司 | A kind of rain brush control method, device, equipment and storage medium |
| CN110562201A (en) * | 2019-09-19 | 2019-12-13 | 广州小鹏汽车科技有限公司 | Control method and control device for windscreen wiper and vehicle |
| CN110852274A (en) * | 2019-11-12 | 2020-02-28 | 上海智驾汽车科技有限公司 | Intelligent rainfall sensing method and device based on image recognition |
| CN112572356A (en) * | 2020-12-11 | 2021-03-30 | 江苏联成开拓集团有限公司 | Wiper control system based on automobile data recorder and method thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115320625A (en) * | 2022-08-23 | 2022-11-11 | 一汽奔腾轿车有限公司 | Identification and judgment method for optimizing rainy scene of intelligent driving system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107128287B (en) | Intelligent windscreen wiper control device and its control method based on image recognition and cloud computing | |
| CN101470900B (en) | Intelligent control method and device for vehicle | |
| CN109229062B (en) | Automatic wiper control system and method | |
| CN106945637B (en) | A kind of rain blowing controlled system and its method based on automobile data recorder | |
| CN109760635B (en) | Drive-by-wire windshield wiper control system based on GAN network | |
| CN111055811A (en) | Windscreen wiper control method and system based on vehicle-mounted intelligent camera | |
| CN111723849A (en) | Road adhesion coefficient online estimation method and system based on vehicle-mounted camera | |
| Cord et al. | Towards rain detection through use of in-vehicle multipurpose cameras | |
| CN112758046B (en) | Windshield definition control method and system based on intelligent identification | |
| CN113022496A (en) | Intelligent windscreen wiper system based on images and control method | |
| CN110481506A (en) | Motor vehicle rain brush automatic control system and method | |
| CN109466510B (en) | Wiper blade rubber strip fault detection method and system based on residual rainwater scratches | |
| JP2014024354A (en) | Wiper control device | |
| CN210822158U (en) | Automatic control system for motor vehicle windshield wiper | |
| CN111559344A (en) | Automatic windscreen wiper system based on image recognition | |
| CN113787987A (en) | Self-cleaning method and system for field of view area of front-view camera of windshield | |
| CN109552255B (en) | Wiper blade rubber strip fault detection method and system based on jitter state | |
| Lai et al. | Video-based windshield rain detection and wiper control using holistic-view deep learning | |
| CN116086547B (en) | Contact net icing detection method based on infrared imaging and meteorological monitoring | |
| JPH04303047A (en) | Image processing | |
| CN208027571U (en) | A kind of vehicle speed measuring equipment | |
| CN205292502U (en) | Weather identification system based on vehicle -mounted camera | |
| CN113301327A (en) | Performance determination method and device of image collector, medium and electronic equipment | |
| CN116547726A (en) | Correction of images of an imaging device during rain, incident light and dirt | |
| CN217181566U (en) | Self-adjusting lane line detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |
|
| RJ01 | Rejection of invention patent application after publication |