CN112297768B - Vehicle air conditioner control method and system based on visual identification - Google Patents
Vehicle air conditioner control method and system based on visual identification Download PDFInfo
- Publication number
- CN112297768B CN112297768B CN202011197498.7A CN202011197498A CN112297768B CN 112297768 B CN112297768 B CN 112297768B CN 202011197498 A CN202011197498 A CN 202011197498A CN 112297768 B CN112297768 B CN 112297768B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- air conditioner
- image
- air
- information
- 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.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
- B60H1/00742—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models by detection of the vehicle occupants' presence; by detection of conditions relating to the body of occupants, e.g. using radiant heat detectors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
- B60H1/008—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models the input being air quality
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00814—Control systems or circuits characterised by their output, for controlling particular components of the heating, cooling or ventilating installation
- B60H1/00821—Control systems or circuits characterised by their output, for controlling particular components of the heating, cooling or ventilating installation the components being ventilating, air admitting or air distributing devices
Landscapes
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Air-Conditioning For Vehicles (AREA)
Abstract
The invention provides a vehicle air conditioner control method and system based on visual identification, which comprises the steps of collecting visual information, collecting image information inside and outside a vehicle by a visual module, processing the image information into environmental information parameters and sending the environmental information parameters to an air conditioner control module; the method comprises the steps that temperature information in the vehicle is collected, a temperature sensing module detects the temperature information of each detection point in the vehicle and sends the temperature information to an air conditioner control module; and adjusting the working state of the air conditioner, judging and generating the working parameters of the air conditioner after the air conditioner control module receives the environmental information parameters and the temperature information, and adjusting the working state of the air conditioner according to the working parameters. The vehicle air conditioner control method and system based on visual recognition can automatically judge the characteristics of passengers in the vehicle and the condition of the environment outside the vehicle based on the image information inside and outside the vehicle, and further automatically adjust the working state of the air conditioner, so that the temperature in the vehicle is kept in a comfortable temperature range.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a vehicle air conditioner control method and system based on visual identification.
Background
Nowadays, a vehicle air conditioning system becomes an essential component of a vehicle, and the quality of the operation of the vehicle air conditioning system is an important index for vehicle selection. Vehicle air conditioners have not been changed as a component to passively accept the operator's controlled dormitory from manual, low-end, to touch-based, to medium-end, and to voice-based, high-end regulation controls. Therefore, in the driving process, the temperature and the air volume of the air conditioner are not appropriate for passengers, and the riding comfort of the passengers is reduced.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
Therefore, the technical problem to be solved by the present invention is to overcome the defect that the air conditioner of the vehicle in the prior art cannot automatically adjust the working state according to the conditions of the passengers and the external environment, so as to provide a vehicle air conditioner control method and system based on visual identification.
In order to solve the technical problems, the invention provides the following technical scheme: a vehicle air conditioner control method based on visual recognition comprises the following steps,
the method comprises the steps that visual information is collected, a visual module collects image information inside and outside a vehicle, the image information is processed into environmental information parameters, and the environmental information parameters are sent to an air conditioner control module;
the method comprises the steps that temperature information in the vehicle is collected, a temperature sensing module detects the temperature information of each detection point in the vehicle and sends the temperature information to an air conditioner control module;
and adjusting the working state of the air conditioner, wherein the air conditioner control module judges and generates the working parameters of the air conditioner after receiving the environmental information parameters and the temperature information, and the air conditioner adjusts the working state according to the working parameters.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the image information comprises an image of a passenger in the vehicle and an image of an environment outside the vehicle, and the image information is acquired by an image acquisition module in the vehicle and an image acquisition module outside the vehicle in the vision module respectively.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the image acquisition module in the vehicle acquires the image of the passenger in the vehicle, the image processing module processes the image information of the image processing machine of the passenger in the vehicle, and then the image processing module sends the image information to the image recognition module to extract the characteristic information of the passenger, and the characteristic information is sent to the air conditioner control module.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the environment image acquisition module in the vision module still gathers the outer environment image of car environment, and image processing module will outer environment image processing is the machine image information back, gives and draws the environment characteristic parameter by image identification module, the environment characteristic parameter send to air conditioner control module.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the air conditioner control module judges the air quality parameter in the environmental characteristic parameter and sets an airflow mode in the air conditioner; if the air quality parameter is lower than a preset air quality threshold value, setting the air flow mode of the air conditioner as an internal circulation mode; and if the air quality parameter is higher than a preset air quality threshold value, setting the air flow mode of the air conditioner as an external circulation mode.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the air conditioner control module matches with a preset action instruction set according to the received passenger characteristic information to obtain a control instruction, and controls the working state of the air conditioner according to the control instruction.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: the air conditioner control module compares the received temperature information with a preset temperature threshold, if the temperature is higher than the preset temperature threshold, the working temperature of the air conditioner is set as the preset temperature threshold, and the air output is adjusted to be large.
As a preferable aspect of the vision recognition-based vehicle air-conditioning control method of the present invention, wherein: and after the air conditioner control system adjusts the temperature in the vehicle to a set temperature threshold value, judging the air volume, reducing the air volume if the air volume is large, and finishing the adjustment of the working state of the air conditioner if the air volume is small.
The invention also provides a vehicle air conditioner control system based on visual identification, which comprises,
the vision module comprises an in-vehicle image acquisition module arranged in the vehicle and an environment image acquisition module arranged outside the vehicle, and is respectively used for acquiring an in-vehicle passenger image and an outside-vehicle environment image;
the temperature sensing module is arranged in the vehicle and used for detecting the temperature of a plurality of detection points in the vehicle;
and the air conditioner control module is connected with the visual module and the temperature sensing module and used for adjusting the working state of the air conditioner according to the image information and the temperature information of the visual module and the temperature sensing module.
The invention has the beneficial effects that: the vehicle air conditioner control method based on visual recognition can automatically judge the characteristics of passengers in the vehicle and the conditions of the environment outside the vehicle based on the image information inside and outside the vehicle, and further automatically adjust the working state of the air conditioner, so that the temperature in the vehicle is kept in a comfortable temperature range.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a structural diagram of a vehicle air conditioning control system based on visual recognition in embodiment 2 of the present invention;
fig. 2 is a structural diagram of an air conditioner control module in embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of a main control module in embodiment 2 of the present invention;
FIG. 4 is a flowchart of the operation in embodiment 3 of the present invention;
FIG. 5 is a schematic illustration of a set of standard images of the present invention with an air quality rating of "excellent";
fig. 6 is a schematic illustration of a set of standard images of the present invention with an air quality rating of "heavy pollution".
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
The embodiment provides a vehicle air conditioner control method based on visual identification, which comprises the steps of collecting visual information, collecting temperature information in a vehicle and adjusting the working state of an air conditioner, wherein the step of collecting the visual information comprises the steps of collecting image information inside and outside the vehicle by using a visual module 200, processing the image information into environmental information parameters and sending the environmental information parameters to an air conditioner control module 100; in the step of collecting the in-vehicle temperature information, the temperature sensing module 300 is used for detecting the temperature information of each detection point in the vehicle and sending the temperature information to the air conditioner control module 100. After receiving the environmental information parameter and the temperature information, the air conditioner control module 100 determines and generates a working parameter of the air conditioner 102, and the air conditioner 102 adjusts a working state according to the working parameter.
The vision module 200 is used for collecting the states of passengers in the vehicle, such as the sex, age, action, facial expression and the like of the passengers, and corresponding air conditioner working state parameters are set according to the states of the passengers, so that the working temperature, air volume and the like of the air conditioner are set to be the states which are most suitable for the passengers, and the comfort in the riding process is improved. The vision module 200 can also collect environmental information outside the vehicle to determine whether the air inside the vehicle is exchanged with the outside.
The image information collected by the vision module 200 in this embodiment is divided into an image of a passenger inside the vehicle and an image of an environment outside the vehicle, which are collected by an image collection module 201 inside the vehicle and an image collection module outside the vehicle in the vision module 200, respectively.
For the state collection of passengers in the vehicle, the in-vehicle image collection module 201 acquires images of the passengers in the vehicle, the image processing module 202 processes the images of the passengers into machine images suitable for machine identification, the machine images are sent to the identification module to extract key information in the machine images by using an image identification algorithm, so that corresponding passenger characteristic information is generated, and the characteristic information is sent to the air-conditioning control module 100.
The collection of the environmental information outside the vehicle is performed by the image collection module outside the vehicle, which acquires an environmental image outside the vehicle, processes the environmental image into a machine image in a manner similar to the image of the passenger inside the vehicle, identifies the environmental characteristic parameters in the environmental image, such as information about air quality, and the like, by the image identification module 203, and transmits the environmental characteristic parameters to the air conditioning control module 100.
The air conditioner control module 100 judges and sets an airflow mode in the air conditioner 102 according to the air quality parameter in the received environment characteristic parameters; if the air quality parameter is higher than the preset air quality threshold, setting the airflow mode of the air conditioner 102 as an internal circulation mode; if the air quality parameter is lower than the preset air quality threshold, the airflow mode of the air conditioner 102 is set to the external circulation mode. The air quality parameters in the present embodiment include, but are not limited to, information on inhalable particle concentration, visibility, harmful gas concentration, and the like. A higher air quality parameter indicates a poorer air quality, and a lower air quality parameter indicates a better air quality.
It should be noted here that, in order to realize the monitoring of the air quality outside the vehicle, the present embodiment may adopt an air sensor arranged outside the vehicle for real-time monitoring, so as to obtain the air quality data outside the vehicle in real time, for example, an air quality sensor with the model of FSM-A-002 is adopted, the control quality parameters outside the vehicle are output and input into the air conditioning control module 100, however, this method requires various sensors to collect data, calculate and integrate parameters, and finally outputs a unique parameter of air quality to determine the air quality grade, however, the present embodiment is directed to a method for detecting air quality based on visual recognition, which does not detect the magnitude of each parameter in the air for normalization and integration, but directly utilizes the air pollution to analyze and compare different distinguishing characteristic grades of the image and output the air quality grade.
Because different air pollution degrees are represented as different gray values on the acquired environment image, the environment image is subjected to gray value processing, and the pollution level of the current environment, namely the air quality level, can be identified by calculating the similarity of the gray values of the environment image and the standard image. Accordingly, the method specifically comprises the following steps: dividing the air quality area into different grades and correspondingly constructing a standard image database;
an environment image outside the vehicle is acquired by using a vehicle exterior image acquisition module and input into an image recognition module 203, and gray value characteristics are output after the image recognition module 203 recognizes;
the similarity matching module calculates and matches the gray value characteristics with the air quality grade corresponding to the current environment according to the similarity;
and determining the air flow circulation mode of the air conditioner according to the air quality grade.
It should be noted that in this embodiment, the air quality grades only need to be divided into six quality grades, i.e., excellent, good, light pollution, moderate pollution, heavy pollution and severe pollution, and according to the differentiated quality grades, a database of standard images is constructed, including environment images acquired under different pollutions in different environments, and a plurality of sets of environment images form a standard image database, for example, a set of standard images with the air quality grade "excellent" is shown in fig. 5, and a set of standard images with the air quality grade "heavy pollution" is shown in fig. 6, and the quality grade to which the current environment belongs can be determined through similarity calculation between the environment images of the vehicle-exterior image acquisition module and the standard images.
Furthermore, the gray value processing method of the image adopts image entropy statistics based on image gray, and the image entropy describes the average information content of the image information source and reflects the statistical information of the image gray, so that the image entropies of two similar images are similar. Based on this, the image entropy statistics can be calculated by:
x in the formulaiRepresents the ith pixel point, G (x)i) Expressing the gray value of the ith pixel point of the image; r (xi) is the ith imageThe red primary color value of the pixel point; g (x)i) Is the green primary color value of the ith pixel point; b (x)i) Is the blue-based chromatic value of the ith pixel point; equation (2) represents the average gray-scale value of the image.
By utilizing the calculation of the image gray entropy, calculating the gray value of each standard image, storing and constructing a database to be matched, and combining the calculation of similarity, the specific process is as follows:
defining a set of standard images with arbitrary pollution degree, wherein each image can be composed of a gray scale vector Si∈RdWhere d is 1024, the similarity is the learning mapping function H, and is used to compare the associated average gray-level values
The similarity between them, the similarity function H parameterized by W is given by:
HW＝G(i)SiWSjin the formula SiAnd Sj∈RdAny two gray vector values, W is a parameter. In order to minimize the distance between the gray level vectors (i.e. to maximize the similarity), similarity calculation is performed on the far positive matching pairs and the near non-matching pairs to minimize the error, so the present embodiment defines the similarity matching function LWIs of the formula:
in the formula (I), the compound is shown in the specification,
is SiOf (2) for each acquired image SiCalculate its similarity score, i.e. LWThe images are sorted according to the similarity scores, the similarity results are output according to the high-low sequence of the images, the air quality grade corresponding to the result with the highest similarity in the 6 standard image data groups is selected, and the air quality grade of the current environment is finally determined.
It should be noted that, in the present embodiment, an air quality image library is constructed based on image detection air quality levels, images in the library are obtained by crawling from a blog by using a web crawler, an air quality condition at the time of image capturing is recorded, 100 images with air quality level labels are obtained by the crawler, and the library formed by these images is referred to as the air quality image library.
The air quality levels of the respective images are classified according to the air pollution index, including,
"excellent" means that when the Air Pollution Index (API) is 0-50, the air quality is excellent and meets the air quality requirements of natural protection areas, scenic spots and other areas needing special protection, which means that the national air quality daily average value first-level standard is represented.
"good" means that when the Air Pollution Index (API) is 51-100, the standard is the national air quality daily average secondary standard, the air quality is good, and the air quality meets the requirements of air quality in residential areas, commercial areas, cultural areas, general industrial areas and rural areas.
The 'light pollution' means that when the Air Pollution Index (API) is 101-150, the standard is a three-level standard, and the air quality is light pollution. If the susceptible people contact the air for a long time, the symptoms of the susceptible people are mildly aggravated, and the healthy people have irritation symptoms. Meets the air quality requirements of specific industrial areas.
The term "moderate pollution" refers to moderate pollution when the Air Pollution Index (API) is 151-200, which is a four-level standard, and the air quality is moderate pollution. After the patient is exposed to the air for a certain time, the symptoms of the patient with heart disease and lung disease are remarkably aggravated, the exercise tolerance is reduced, and the symptoms generally appear in healthy people.
The term "severe pollution" refers to that when the Air Pollution Index (API) is 201-300, the standard is five-level standard, and the air quality is severe pollution. Healthy people have reduced exercise tolerance, obvious symptoms and certain diseases.
By "severe pollution" is meant that when the Air Pollution Index (API) is greater than 300, which is a six-level standard, the air quality is heavily polluted.
To verify that the modeling of the embodiment has higher identification precision in practice, the modeling is realized on Mat-labR2014a, the modeling is operated on a computer with a CPU (central processing unit) of i5-2450M, RAM of 4GB and Win 764 bit, and images in an air quality image library are used as a test set, images with air quality grade labels are crawled on a net through a crawler frame, and each label has 326 images in total and contains all air quality grades. During testing, images in a test set are randomly selected each time, the labels obtained through 1000 times of model input recognition are compared with the real labels, the accuracy of the error value in the acceptance range is 92.67-97.73%, and the real test result is shown in the following table 1.
Table 1: identification results on the test set.
As shown in table 1, in the present embodiment, when the levels "good" and "severe pollution" are provided, the image has a clear boundary and an obvious feature value, so that a high recognition rate is provided, but the gray-scale features of the images are relatively similar between the level labels "good", "light pollution" and "moderate pollution", so that a misalignment recognition error exists during recognition, but the recognition rate of the present embodiment may also reach more than 92.67%, and also has a high recognition rate, the error is within an acceptable range, and the overall recognition accuracy reaches 0.946%. The model can accurately estimate the air quality grade, has feasibility through similarity estimation, and obtains a high identification result.
The air quality in the driving environment can be effectively judged in real time by collecting the external environment information of the vehicle, and the air flow circulation mode of the air conditioner is optimized according to the detection result. The quality of air in the vehicle is maintained, and the damage of polluted air to the health of passengers is reduced.
In the present embodiment, a plurality of instruction sets are preset in the air conditioning control module 100 for adjusting the operation mode of the air conditioner 102, and one or more instructions correspond to the passenger characteristic information and the environmental characteristic parameter sent by the vision module 200. The air conditioner control module 100 matches the received information with a preset instruction set to call out a corresponding control instruction so as to control the working mode of the air conditioner. For example, the vision module 200 collects that the passenger has clasped both arms in the vehicle, the image recognition module 203 recognizes the clasping arm action of the passenger and sends the clasping arm action to the air-conditioning control module 100, and the air-conditioning control module 100 determines that the clasping arm action of the passenger corresponds to the fact that the passenger feels cold, and the temperature should be increased or the air volume should be reduced, so that the corresponding temperature adjustment instruction and the corresponding air volume adjustment instruction are matched, the working temperature of the air conditioner 102 is increased, and the air volume is reduced.
The temperature sensing module 300 in this embodiment can collect temperature information including, but not limited to, the air temperature in the vehicle, the temperature on the seat, and the temperature of different areas in the vehicle, such as the windward side or the leeward side, so as to accurately reflect the real-time temperature sensing of the passengers in the vehicle. The air conditioning control module 100 is preset with a plurality of temperature thresholds, and each threshold corresponds to a different passenger or driving condition. The air conditioner control module 100 compares the received temperature information with a preset temperature threshold, and if the temperature is outside the preset temperature threshold, the operating temperature of the air conditioner 102 is set as the preset temperature threshold, and the air output is adjusted to be a large air output, so that the temperature in the vehicle is adjusted to be the preset temperature as soon as possible. And if the temperature is within the preset temperature threshold value, reducing the air output.
The air conditioning control module 100 in this embodiment also determines the air volume after adjusting the temperature, and automatically turns to the small air volume if the air volume is large, and ends the adjustment of the working state of the air conditioner if the air volume is small, so that the air in the vehicle keeps the state that the passengers feel the most comfortable.
The vision module 200 in this embodiment detects whether there is a passenger in the vehicle before the air conditioner control module 100 receives information, continues to maintain the detection state if there is no passenger, and works according to the sequence of collecting the image and collecting the temperature and adjusting the working state of the air conditioner if the passenger enters the vehicle until the air in the vehicle is adjusted to a preset reasonable state.
Example 2
The present embodiment provides a vehicle air conditioning control system based on visual recognition, which comprises a visual module 200, a temperature sensing module 300 and an air conditioning control module 100 as shown in fig. 1. The vision module 200 comprises an in-vehicle image acquisition module 201 arranged in the vehicle and an environment image acquisition module 201 arranged outside the vehicle, and is used for acquiring an in-vehicle passenger image and an outside-vehicle environment image respectively; the temperature sensing module 300 is disposed in the vehicle and configured to detect temperatures of a plurality of detection points in the vehicle. And the air conditioner control module 100 is connected with the vision module 200 and the temperature sensing module 300, and adjusts the working state of the air conditioner 102 according to the image information and the temperature information of the vision module 200 and the temperature sensing module 300.
As shown in fig. 1, the vision module 200 in this embodiment includes a vision system including an image capturing module 201, an image processing module 202, an image recognizing module 203, and the image capturing module 201, which are used for detecting image information of the passengers inside the vehicle and the environment outside the vehicle for a motion capture device disposed inside the vehicle; the image processing module 202 is used for processing the passenger image information and the vehicle exterior environment image into machine image information; and the image recognition module 203 is used for extracting passenger characteristic information and environment characteristic information in the machine image information.
Specifically, the image capturing module 201 in this embodiment includes an in-vehicle image capturing device and an out-vehicle image capturing device. The in-vehicle image acquisition device is a CCD camera arranged in the vehicle, and takes pictures or videos of passengers in the vehicle, and sends the taken results to the image processing module 202 for processing in a data manner. The image processing module 202 and the image recognition module 203 are integrated on the same single chip, and the same processor is responsible for executing operation. The vehicle exterior image acquisition device is a CCD camera arranged outside the vehicle and used for acquiring environmental pictures or videos around the vehicle, and the vehicle exterior image acquisition device can comprise a plurality of CCD cameras and is used for acquiring environmental pictures in different directions.
As a preferred embodiment, the image capturing device outside the vehicle in this embodiment may further include an air quality sensor, for example, an FSM-a-002 type air quality detection module, which detects air pollution outside the vehicle according to the TGS2600 sensor, processes signals of the sensor, temperature, and the like and determines a pollution level through the single chip, generates a high level corresponding to the pollution level, and outputs the high level to the air conditioning control module 100, thereby implementing functions of detecting and controlling the air quality.
As shown in fig. 2, the air conditioner control module 100 in this embodiment includes a main control module 101 and an air conditioner 102, as shown in fig. 3, the main control module 101 includes a control system including a central processing unit 101a, a receiving end, a sending end, and a memory, the receiving end is connected to the sending end and the sending end, the vision module 200 and the temperature sensing module 300 are connected, and are further connected through an interface air conditioner 102, and a control instruction obtained after information sent by the vision module 200 and the temperature sensing module 300 reaches the central processing unit 101a for processing is used for adjusting the working state of the air conditioner 102. The main control module 101 is specifically located on the driving computer ECU, and is powered by a vehicle-mounted power supply. The storage 101b is a vehicle-mounted hard disk and a random access memory, and is used for storing driving control system data and temporary data respectively.
As shown in fig. 3, the air conditioner 102 in the present embodiment includes a cooling device, a heating device, and a ventilation device for controlling a flow mode of air-conditioning airflow and switching an internal/external circulation mode of the air conditioner. The airflow path in the air conditioner 102 includes an external circulation intake and an internal circulation intake, which are respectively communicated with the outside air and the inside air. The two air inlets are connected with an air conditioning airflow channel in the vehicle and communicated to the blower, and the blower is used for driving air in the airflow channel to flow. The joint of the two air inlets is provided with a baffle which can respectively block the external circulation air inlet or the internal circulation air inlet. The movement mode of the baffle is controlled by a motor, the motor is connected with the main control module 101, and the main control module 101 can adjust the internal and external circulation modes according to the information identified by the vision module 200.
The temperature sensing module 300 in this embodiment includes temperature sensors 301, specifically various thermistors, disposed inside and outside the vehicle for sensing the temperature inside and outside the vehicle. The positions of the air conditioner air outlet device include, but are not limited to, a fixed position in a vehicle, an air conditioner air outlet position, a position on a seat, a front windshield and a vehicle shell. The plurality of temperature sensors 301 can simulate the real feeling of passengers in the vehicle and the temperature distribution in the vehicle. The temperature sensor 301 transmits the temperature information to the air conditioner control module 100 so that the air conditioner control module 100 determines the operating temperature of the air conditioner and adjusts the operating state of the air conditioner.
Example 3
The present embodiment is based on the vehicle air-conditioning control method based on visual recognition and the vehicle air-conditioning control system based on visual recognition proposed in embodiments 1 and 2, and as shown in fig. 2, the work flow is as follows:
step 1: the air conditioner control module 100 determines whether there is a message in the vehicle sent by the visual recognition module.
Step 2: if yes, go to step 3. Otherwise, returning to the step 1 and continuing to wait for message judgment.
And step 3: the air conditioning control module 100 performs judgment according to the vehicle exterior pollution condition message sent by the visual identification module.
And 4, step 4: if the contamination is serious, go to step 5, otherwise go to step 6.
And 5: the air conditioner control module 100 sets the air conditioner to an internal circulation. And continuously jumping to the step 7 for execution.
Step 6: the air conditioner control module 100 sets the air conditioner to the external circulation. Proceed to step 7.
And 7: the air conditioner control module 100 matches the instruction for adjusting the working temperature range of the air conditioner 102 to the comfortable temperature range of 20 ℃ to 25 ℃ according to the characteristic information of the passengers in the vehicle sent by the vision module 200, and executes step 8.
And 8: the air conditioner control module 100 determines whether the current temperature information sent by the temperature sensing module 300 reaches a comfortable temperature range of 20-25 ℃.
And step 9: if not, proceed to step 10. Otherwise, jumping to step 11.
Step 10: the air conditioner control module 100 adjusts the air conditioner to adjust the temperature to the most recent value of 20 to 25 c, such as below 20 c, above 25 c, with the maximum air volume. Step 11 is continued.
Step 12: the air conditioner control module 100 determines whether the air conditioner is in a large air volume operation.
Step 13: if yes, step 14 is performed. Otherwise jump to step 15.
Step 14: the air conditioner control module 100 controls the air conditioner to reduce the air output and continues to execute the step 15.
Step 15: and ending the control flow once, and continuing the next flow control.
It is important to note that the construction and arrangement of the present application as shown in the various exemplary embodiments is illustrative only. Although only a few embodiments have been described in detail in this disclosure, those skilled in the art who review this disclosure will readily appreciate that many modifications are possible (e.g., variations in sizes, dimensions, structures, shapes and proportions of the various elements, values of parameters (e.g., temperatures, pressures, etc.), mounting arrangements, use of materials, colors, orientations, etc.) without materially departing from the novel teachings and advantages of the subject matter recited in this application. For example, elements shown as integrally formed may be constructed of multiple parts or elements, the position of elements may be reversed or otherwise varied, and the nature or number of discrete elements or positions may be altered or varied. Accordingly, all such modifications are intended to be included within the scope of this invention. The order or sequence of any process or method steps may be varied or re-sequenced according to alternative embodiments. In the claims, any means-plus-function clause is intended to cover the structures described herein as performing the recited function and not only structural equivalents but also equivalent structures. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present inventions. Therefore, the present invention is not limited to a particular embodiment, but extends to various modifications that nevertheless fall within the scope of the appended claims.
Moreover, in an effort to provide a concise description of the exemplary embodiments, all features of an actual implementation may not be described (i.e., those unrelated to the presently contemplated best mode of carrying out the invention, or those unrelated to enabling the invention).
It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure, without undue experimentation.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (4)
1. A vehicle air conditioner control method based on visual identification is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
visual information is collected, and a visual module (200) collects image information inside and outside the vehicle, processes the image information into environmental information parameters and sends the environmental information parameters to an air conditioner control module (100);
the method comprises the steps that temperature information in the vehicle is collected, a temperature sensing module (300) detects the temperature information of each detection point in the vehicle, and the temperature information is sent to an air conditioner control module (100);
adjusting the working state of an air conditioner, wherein the air conditioner control module (100) judges and generates the working parameters of the air conditioner (102) after receiving the environmental information parameters and the temperature information, and the air conditioner (102) adjusts the working state according to the working parameters;
the image information comprises an image of passengers in the vehicle and an image of the environment outside the vehicle, and is acquired by an image acquisition module (201) in the vehicle and an image acquisition module outside the vehicle in the vision module (200) respectively;
the in-vehicle image acquisition module (201) acquires in-vehicle passenger images of in-vehicle passengers, including the sex, age, action and facial expressions of the passengers, and the image processing module (202) processes image information of the in-vehicle passenger image processing machine, then sends the image information to the image recognition module (203) to extract passenger characteristic information and sends the characteristic information to the air-conditioning control module (100);
an environment image acquisition module in the vision module (200) also acquires an external environment image of an external environment, an image processing module (202) processes the external environment image into machine image information, and then an image recognition module (203) extracts environment characteristic parameters which are sent to the air conditioner control module (100);
the air conditioner control module (100) judges the air quality parameter in the environmental characteristic parameter and sets the airflow mode in the air conditioner (102); if the air quality parameter is higher than a preset air quality threshold value, setting the airflow mode of the air conditioner (102) as an internal circulation mode; setting the air flow mode of the air conditioner (102) as an external circulation mode if the air quality parameter is lower than a preset air quality threshold;
the method comprises the steps of performing gray value processing on an environment image, and identifying the current air quality level by calculating the similarity of the environment image and a gray value of a standard image;
based on this, the image entropy statistics can be calculated by:
x in the formulaiRepresents the ith pixel point, G (x)i) Expressing the gray value of the ith pixel point of the image; r (xi) is the red color value of the ith pixel point; g (x)i) Is the green primary color value of the ith pixel point; b (x)i) Is the blue-based chromatic value of the ith pixel point; expression (2) represents an imageAverage gray value of (a);
calculating the gray value of each standard image by utilizing the calculation of the image entropy, storing and constructing a database to be matched, and combining the calculation of similarity, the specific process is as follows:
defining a set of standard images with arbitrary pollution degree, wherein each image can be composed of a gray scale vector Si∈RdExpressing, where d =1024, the similarity is a learning mapping function H for comparing the associated mean gray values
Similarity between them, similarity function H parameterized by WWThe following formula:
HW=G(xi)SiWSjin the formula SiAnd Sj∈RdAny two gray scale vector values, W is a parameter;
in order to minimize the distance between the gray level vectors, similarity calculation is performed on the positive matching pairs with a longer distance and the mismatch pairs with a shorter distance, so as to reduce the error to the maximum extent, and therefore a similarity matching function L is definedWIs of the formula:
in the formula (I), the compound is shown in the specification,
is SiOf (2) for each acquired image SiCalculate its similarity score, i.e. LWThe images are sorted according to the similarity scores, the similarity results are output according to the high-low sequence of the images, the air quality grade corresponding to the result with the highest similarity in the 6 standard image data groups is selected, and the air quality grade of the current environment is finally determined.
2. The vision recognition-based vehicle air-conditioning control method of claim 1, characterized in that: the air conditioner control module (100) matches with a preset action instruction set according to the received passenger characteristic information to obtain a control instruction, and controls the working state of the air conditioner (102) according to the control instruction.
3. The vision recognition-based vehicle air conditioning control method of claim 2, wherein: the air conditioner control module (100) compares the received temperature information with a preset temperature threshold, if the temperature is higher than the preset temperature threshold, the working temperature of the air conditioner (102) is set as the preset temperature threshold, and the air output is adjusted to be large.
4. The vision recognition-based vehicle air conditioning control method of claim 3, wherein:
and after the air conditioner control module (100) adjusts the temperature in the vehicle to a set temperature threshold value, judging the air volume, reducing the air volume if the air volume is large, and finishing the adjustment of the working state of the air conditioner if the air volume is small.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011197498.7A CN112297768B (en) | 2020-10-31 | 2020-10-31 | Vehicle air conditioner control method and system based on visual identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011197498.7A CN112297768B (en) | 2020-10-31 | 2020-10-31 | Vehicle air conditioner control method and system based on visual identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112297768A CN112297768A (en) | 2021-02-02 |
| CN112297768B true CN112297768B (en) | 2022-03-25 |
Family
ID=74333555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011197498.7A Active CN112297768B (en) | 2020-10-31 | 2020-10-31 | Vehicle air conditioner control method and system based on visual identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112297768B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109249772B (en) * | 2017-07-13 | 2021-08-20 | 上海擎感智能科技有限公司 | Control method and system of vehicle air conditioner, cloud platform and storage medium |
| CN107972446A (en) * | 2017-11-22 | 2018-05-01 | 六六房车有限公司 | Temperature environment automates adjusting method in a kind of caravan |
| CN108052980B (en) * | 2017-12-21 | 2021-05-14 | 南京理工大学 | Image-based air quality grade detection method |
| CN108693087B (en) * | 2018-04-13 | 2020-09-01 | 中国科学院城市环境研究所 | Air quality monitoring method based on image understanding |
| EP3666564B1 (en) * | 2018-12-12 | 2023-10-11 | Ningbo Geely Automobile Research & Development Co., Ltd. | A system and method for estimating climate needs |
| CN109849614A (en) * | 2019-01-16 | 2019-06-07 | 北京百度网讯科技有限公司 | Air conditioning control method, device, system and the storage medium of unmanned vehicle |
| CN110576718A (en) * | 2019-08-16 | 2019-12-17 | 武汉格罗夫氢能汽车有限公司 | Automatic air conditioner adjusting system of hydrogen energy automobile |
| CN111152623A (en) * | 2020-01-19 | 2020-05-15 | 恒大新能源汽车科技(广东)有限公司 | Vehicle-mounted air conditioner control method, vehicle-mounted air conditioner control system and device |
| CN111860312A (en) * | 2020-07-20 | 2020-10-30 | 上海汽车集团股份有限公司 | Driving environment adjusting method and device |
-
2020
- 2020-10-31 CN CN202011197498.7A patent/CN112297768B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112297768A (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921100B (en) | Face recognition method and system based on visible light image and infrared image fusion | |
| CN101923645B (en) | Iris splitting method suitable for low-quality iris image in complex application context | |
| CN110263603B (en) | Face recognition method and device based on central loss and residual error visual simulation network | |
| CN102254183B (en) | Face detection method based on AdaBoost algorithm | |
| CN113177594B (en) | Air conditioner fault diagnosis method based on Bayesian optimization PCA-extreme random tree | |
| CN106934380A (en) | A kind of indoor pedestrian detection and tracking based on HOG and MeanShift algorithms | |
| JP2007257043A (en) | Occupant state estimating device and occupant state estimating method | |
| CN111353451A (en) | Battery car detection method and device, computer equipment and storage medium | |
| CN101320477B (en) | Human body tracing method and equipment thereof | |
| CN106569600A (en) | Gesture verification method and device for controlling air conditioners | |
| CN112528843A (en) | Motor vehicle driver fatigue detection method fusing facial features | |
| CN108846831A (en) | The steel strip surface defect classification method combined based on statistical nature and characteristics of image | |
| CN113516005A (en) | Dance action evaluation system based on deep learning and attitude estimation | |
| CN110427019B (en) | Industrial process fault classification method and control device based on multivariate discriminant analysis | |
| CN112297768B (en) | Vehicle air conditioner control method and system based on visual identification | |
| CN113963237B (en) | Model training method, mask wearing state detection method, electronic device and storage medium | |
| CN114882351A (en) | Multi-target detection and tracking method based on improved YOLO-V5s | |
| CN111104817A (en) | Fatigue detection method based on deep learning | |
| CN111339385A (en) | CART-based public opinion type identification method and system, storage medium and electronic equipment | |
| CN114663807A (en) | Smoking behavior detection method based on video analysis | |
| Zhang et al. | A novel face recognition system using hybrid neural and dual eigenspaces methods | |
| CN109376583A (en) | A kind of Driver Fatigue Detection that intelligent vehicle auxiliary drives | |
| CN116704609A (en) | Online hand hygiene assessment method and system based on time sequence attention | |
| CN113920573B (en) | Face change decoupling relativity relationship verification method based on counterstudy | |
| CN115129503A (en) | Equipment fault data cleaning method and system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210802 Address after: Floor 11, building A1, Huizhi science and Technology Park, 8 Hengtai Road, Nanjing Economic and Technological Development Zone, Jiangsu Province 210000 Applicant after: DILU TECHNOLOGY Co.,Ltd. Address before: 211106 block a, Mingjia science and technology building, 99 Shengli Road, Jiangning District, Nanjing City, Jiangsu Province Applicant before: Central Manpu Technology (Nanjing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |