Automobile control method and device based on detection of left-behind entity on automobile and medium

Abstract

This invention discloses a vehicle control method, computer device, and storage medium based on the detection of entities left behind in the vehicle. The invention includes steps such as obtaining a detection image of the vehicle's interior space while the driver is away from the vehicle, identifying entities left behind in the detection image, and controlling vehicle components to perform protective actions against the entities when the type information of the left-behind entities meets preset conditions. By analyzing the type information of entities left behind in the vehicle's interior space while the driver is away, and controlling vehicle components to perform protective actions against the entities when the type information meets preset conditions, this invention can automatically protect entities left behind even if the driver negligently fails to remove them from the vehicle. This protects the life or property of the left-behind entities without requiring the driver to return to the vehicle, providing convenience for the driver. This invention has wide applications in the field of automotive technology.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to an automotive control method, computer device, and storage medium based on the detection of entities left behind on the vehicle. Background Technology

[0002] During car use, it's common for drivers to drive to a destination, get out of the car to run errands, and due to time constraints or emergencies, become careless and leave items behind, sometimes even pets or infants. If pets or other living beings are left in the car, the cabin environment can easily become deteriorated due to prolonged periods of confinement, lack of ventilation, and exposure to sunlight, posing a potential danger to the animals. Even leaving behind personal items can attract unwanted attention if the owner is away from the car for an extended period, making it vulnerable to vandalism and theft. Summary of the Invention

[0003] In view of the technical problems that are easily caused by leaving objects or even biological entities on vehicles during current use, resulting in risks to life and property, the purpose of this invention is to provide a vehicle control method, computer device and storage medium based on the detection of entities left on the vehicle.

[0004] On one hand, embodiments of the present invention include a vehicle control method based on the detection of entities left behind on the vehicle, the vehicle control method based on the detection of entities left behind on the vehicle includes the following steps:

[0005] When the driver is detected to have left the vehicle, the interior of the car is photographed to obtain an image of the vehicle to be detected.

[0006] The image to be detected is inspected to determine the abandoned entities contained in the image to be detected;

[0007] Identify the type information of the abandoned entity;

[0008] Determine whether the type information meets the preset conditions;

[0009] When the type information meets the preset conditions, the control system will perform protective actions on the abandoned entity.

[0010] Further, the step of detecting the image to be detected and determining the abandoned entities contained in the image to be detected includes:

[0011] Run the target detection model;

[0012] Obtain a standard image; the standard image does not contain the legacy entity;

[0013] The image to be detected and the standard image are input into the target detection model for processing;

[0014] Based on the processing results of the target detection model, the location of the leftover entity in the image to be detected is determined.

[0015] Further, determining whether the type information meets preset conditions includes:

[0016] Based on the type information, determine the value information of the abandoned entity;

[0017] When the value information is greater than the value threshold, it is determined that the type information meets the preset conditions.

[0018] Further, determining whether the type information meets preset conditions includes:

[0019] The vehicle is located to obtain its current location information;

[0020] Detect the first correlation between the type information and the current location information;

[0021] When the first correlation degree is less than the correlation threshold, it is determined that the type information meets the preset conditions.

[0022] Further, determining whether the type information meets preset conditions includes:

[0023] Obtain the navigation information to be performed on the vehicle;

[0024] Based on the navigation information to be performed, determine the location information to be reached;

[0025] Detect the second correlation between the type information and the location information to be reached;

[0026] When the second correlation degree is greater than the correlation threshold, it is determined that the type information meets the preset conditions.

[0027] Further, determining whether the type information meets preset conditions includes:

[0028] Based on the type information, determine the environmental requirements information of the abandoned entity;

[0029] The interior space of the car is monitored to obtain current interior environmental information;

[0030] When the current cabin environment information does not match the environmental requirement information, it is determined that the type information meets the preset conditions.

[0031] Furthermore, the control vehicle component performs protective actions on the abandoned entity, including:

[0032] Using safety criteria as search criteria, the destination location information is obtained.

[0033] Based on the destination location information, generate autonomous driving instructions;

[0034] The aforementioned autonomous driving commands control the vehicle components to perform autonomous driving.

[0035] Furthermore, the control vehicle component performs protective actions on the abandoned entity, including:

[0036] When the type information indicates that the abandoned entity is a living being, an atmosphere adjustment command and / or a help warning command are generated.

[0037] When the type information indicates that the abandoned entity is an item, a window color-changing instruction is generated.

[0038] The aforementioned atmosphere adjustment command controls the vehicle components to perform cabin atmosphere adjustment.

[0039] The distress warning command is used to control the vehicle components to issue a distress warning.

[0040] The aforementioned window color-changing command controls the vehicle components to perform window color-changing.

[0041] On the other hand, embodiments of the present invention also include a computer device, including a memory and a processor, the memory for storing at least one program, and the processor for loading at least one program to execute a vehicle control method based on the detection of abandoned entities on a vehicle, as described in the embodiments.

[0042] On the other hand, embodiments of the present invention also include a storage medium storing a processor-executable program, which, when executed by a processor, is used to perform a vehicle control method based on the detection of abandoned entities on a vehicle, as described in the embodiments.

[0043] The beneficial effects of the present invention are as follows: The vehicle control method based on the detection of entities left behind in the vehicle in the embodiments analyzes the type information of entities left behind in the vehicle's cabin when the driver is away from the vehicle. When the type information meets preset conditions, the vehicle components are controlled to perform protective actions on the entities left behind. This can automatically protect entities left behind even if the driver neglects to take them out of the vehicle. Thus, the life or property safety of entities left behind can be protected without the need for the driver to return to the vehicle, providing convenience for the driver. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of an automotive system for which an automotive control method based on the detection of entities left behind on the vehicle can be applied in the embodiment.

[0045] Figure 2 This is a schematic diagram showing the installation location of the camera module in the embodiment;

[0046] Figure 3 This is a schematic diagram illustrating the steps of the vehicle control method based on the detection of entities left behind on the vehicle in the embodiment.

[0047] Figure 4 This is a flowchart illustrating the step of detecting and determining the abandoned entities contained in the image to be detected in this embodiment. Detailed Implementation

[0048] In this embodiment, the vehicle control method based on the detection of entities left behind on the vehicle can be applied to... Figure 1 The vehicle system shown. (Refer to...) Figure 1 The system comprises a control module, a camera module, a communication module, a navigation module, an atmosphere control module, an autonomous driving module, and a help module.

[0049] In this embodiment, components such as an Electronic Control Unit (ECU) can be used as the control module. The control module can be connected to other modules such as the camera module via a communication controller (EVCC).

[0050] The camera module includes several cameras, which can be installed... Figure 2 The circles in the image indicate locations such as the dashboard, steering wheel, center console, seats, doors, windows, and roof. Each camera's field of view is directed towards the driver's and passenger compartments, thus capturing images of areas where items may be placed or where people may be sitting, such as the center console, storage compartments, seats, and floor.

[0051] In this embodiment, a communication unit with Bluetooth, WiFi, or 5G communication protocols can be used as the communication module. The communication module connects to a mobile terminal such as a smartphone carried by the driver via a wireless communication protocol. The control module can send data to the communication module, which then sends the data directly or via a cloud server to the smartphone. Alternatively, the driver can edit control commands using the smartphone, sending them directly to the communication module via Bluetooth or WiFi, or uploading them to a cloud server via a 5G communication protocol. The cloud server then sends the control commands to the communication module, which in turn sends them to the control module. The control module can then control the vehicle components based on the control commands sent from the smartphone.

[0052] In this embodiment, the navigation module can locate the vehicle based on satellite positioning technology or indoor positioning technology to obtain the vehicle's location information. The driver can operate the navigation module to set navigation tasks and thus perform navigation. The in-vehicle navigation module can integrate the complete hardware and software required for car navigation, or it can use a communication module as a navigation module. The communication module establishes a data connection with the driver's mobile phone, and the navigation software is run on the mobile phone for positioning and navigation. The communication module requests the mobile phone to send location information and navigation tasks, thereby obtaining the vehicle's location information, as well as navigation-related information such as the departure point and destination.

[0053] In this embodiment, the atmosphere control module includes ambient lighting, air conditioning, an air filtration unit, an air purification unit, a ventilation unit, and an audio-visual entertainment unit. The atmosphere control module can display ambient lighting with specific color combinations through the ambient lighting, thereby creating a specific atmosphere visually. For example, displaying soft, changing green ambient lighting can create a relaxing atmosphere. The atmosphere control module can use the air conditioning to cool or heat the cabin space, thereby adjusting the cabin temperature to a comfortable level. The air filtration unit, air purification unit, and ventilation unit can filter, purify, and circulate the air inside the cabin, thereby reducing the concentration of PM2.5 pollutants, volatile organic compounds, odor substances, and carbon dioxide in the cabin air, improving cabin air quality. The audio-visual entertainment unit can play music or videos, thereby creating a specific atmosphere visually and aurally. For example, playing lighthearted and humorous videos helps create a relaxing atmosphere.

[0054] In this embodiment, the autonomous driving module can be a combination of sensors, power system, transmission system and steering system installed in the vehicle, thereby realizing L3 or higher level of autonomous driving.

[0055] In this embodiment, the distress signal module includes components such as an indicator light and a speaker. The indicator light can display a flashing red light as a distress signal, and the speaker can play a loud sound as a distress signal. The communication module can send a message containing distress information to a mobile phone by invoking the communication module, thereby enabling the communication module to function as a distress signal module.

[0056] In this embodiment, the control module can execute the various steps of the vehicle control method based on the detection of entities left behind on the vehicle. When the control module needs to acquire certain data, send processed data or control commands, or control other modules when executing certain steps of the vehicle control method based on the detection of entities left behind on the vehicle, the control module can call... Figure 1 Each module in, or Figure 1 Other devices not shown.

[0057] In this embodiment, refer to Figure 3 The vehicle control method based on the detection of entities left on the vehicle includes the following steps:

[0058] S1. When the driver is detected to have left the vehicle, an image of the interior space of the car is captured to obtain the image to be detected;

[0059] S2. Detect the image to be detected and identify the leftover entities contained in the image;

[0060] S3. Identify the type information of the legacy entity;

[0061] S4. Determine whether the type information meets the preset conditions;

[0062] S5. When the type information meets the preset conditions, control the automotive components to perform protective actions on the abandoned entity.

[0063] Before executing step S1, the control module can call the car's sensors to determine whether the driver is off the vehicle. For example, if the sensors detect that no one is in the driver's seat, the car is off (not started), and the brakes are in the parking brake state, the control module can determine that the driver is off the vehicle and begin executing steps S1-S5.

[0064] In step S1, the control module calls the camera module to take pictures of the interior space of the car, and the camera module sends the captured images to be detected to the control module.

[0065] The control module executes step S2 to perform image analysis on the image to be detected obtained in step S1, and determines whether there is a left-behind entity in the image. Specifically, the left-behind entity can be items such as luggage, wallets, mobile phones and documents, or living beings such as pets and babies.

[0066] In this embodiment, when the control module executes step S2, which is to detect the image to be detected and determine the abandoned entities contained in the image to be detected, it can specifically perform the following steps:

[0067] S201. Run the target detection model;

[0068] S202. Obtain a standard image;

[0069] S203. Input the image to be detected and the standard image into the target detection model for processing;

[0070] S204. Based on the processing results of the target detection model, determine the location of the remaining entities in the image to be detected.

[0071] In this embodiment, the process of steps S201-S204 is as follows: Figure 4 As shown.

[0072] In step S201, the target detection model used to detect the location of the abandoned entity can specifically include a ResNet model and a Siamese neural network model. If the control module has sufficient computing power, the ResNet model and Siamese neural network model can be run locally on the control module. If the control module lacks sufficient computing power, the ResNet model and Siamese neural network model can be run on a cloud server, with the control module requesting the cloud server to invoke the ResNet model and Siamese neural network model via the communication module.

[0073] In step S202, the standard image obtained is an image that does not contain the leftover entities. Specifically, the car owner can clean the interior space beforehand, ensuring that it only contains the car's functional components and excludes leftover items such as mobile phones, wallets, and documents, before calling... Figure 2 Each camera in the system captures images to obtain a standard image. This standard image can be stored in the storage unit of the control module and retrieved when the control module executes step S202.

[0074] In step S203, the image to be detected and a standard image captured by the same camera (or from the same viewpoint) are input into the object detection model for processing. Before input, preprocessing such as resizing, normalization, and cropping can be performed on the standard image and the image to be detected to adapt to the input requirements of the object detection model. The standard image can be used by object detection models such as ResNet and Siamese neural network models to compare image similarity with the image to be detected. The output of the object detection model marks the locations in the image to be detected that are dissimilar to the standard image; these locations are the positions of the remaining entities.

[0075] In this embodiment, the working principle of the Siamese model is as follows: The Siamese model is used to perform anomaly detection on the image to be detected. Specifically, the Siamese model uses the feature maps of the second and third intermediate layers of ResNet as features, and uses local neighborhood feature aggregation to extract features from the standard image. The output of the third intermediate layer is bilinearly interpolated to match with the second intermediate layer to obtain a preliminary feature map. By performing adaptive average pooling feature aggregation on the feature map, a feature vector of a pre-defined dimension is obtained. Downsampling is used to reduce the model size and generate the detection model. For the image to be detected, the features of the image to be detected are obtained in the same way. Nearest neighbor retrieval and distance calculation of the feature vector are used to determine whether the features of the image to be detected are similar to the features of the standard image. If the features are not similar, the features of the image to be detected are considered to be abnormal features, and there are leftover entities in the image to be detected.

[0076] In this embodiment, the working principle of the Siamese neural network model is as follows: The Siamese neural network model is used to perform anomaly detection on the image to be detected. Specifically, the Siamese neural network model obtains the abandoned entities from the previous frame of the image to be detected from the system, uses a matrix to extract the position of the abandoned entities in the previous frame of the image to be detected [the data format of the position is (x,y,width,height)], and then compares the abandoned entity (occupying region B) identified in the current frame of the image to be detected with the abandoned entity (occupying region A) identified in the previous frame of the image to be detected to determine whether they are the same abandoned entity. If they are the same abandoned entity, the IOU overlap between region A and region B is calculated. If the IOU overlap is greater than a threshold (e.g., 90%), then the position of the overlapping area between region A and region B can be marked as the position of the abandoned entity in the previous frame.

[0077] In this embodiment, by executing steps S201-S204, a neural network model can be used to quickly detect whether there is a leftover entity in the image to be detected, whether the leftover entity is the same as the previous leftover entity, and the location of the leftover entity if it exists.

[0078] In this embodiment, when performing step S3, the YOLO model, Fast R-CNN model, or Transform model can be used to identify the type of the abandoned entity detected in step S2, thereby determining the type information of the abandoned entity, that is, whether the abandoned entity belongs to items such as mobile phones, wallets, glasses, or documents, or to living beings such as pets or babies.

[0079] In this embodiment, when the control module executes step S4, which is to determine whether the type information meets the preset conditions, it can specifically perform the following steps:

[0080] S401A. Determine the value information of the legacy entity based on the type information;

[0081] S402A. When the value information is greater than the value threshold, determine that the type information meets the preset conditions.

[0082] Steps S401A-S402A are the first execution method of step S4.

[0083] In step S401A, a data table can be pre-established in the control module to record the correspondence between the type information and value information of the legacy entities. The format of this data table can be as shown in Table 1.

[0084] Table 1

[0085]

[0086]

[0087] In Table 1, when the abandoned entity is a human, its value information can be set to a very large value that will not cause hardware or software overflow in the control module. By querying the data table shown in Table 1, the value information of the abandoned entity can be obtained according to its type information. The value information of the abandoned entity represents its economic or emotional value.

[0088] In step S402A, a value threshold (e.g., 3000 yuan) can be set. When the value information detected in step S3 is greater than the value threshold, the control module determines that the type information meets the preset conditions and can execute step S5, thereby controlling the car parts to perform protective actions on the abandoned entity.

[0089] In this embodiment, the principle of executing steps S401A-S402A is as follows: when the value information is determined to be greater than the value threshold, it indicates that the value of the abandoned entity in the car is high, such as being a valuable item, a precious pet, or a human being such as an infant. When the driver has left the car, the control module generates a control command to control the car components to perform protective actions on the abandoned entity, thereby protecting the abandoned entity from harm, damage, or theft, and ensuring the safety of life and property.

[0090] In this embodiment, when the control module executes step S4, which is to determine whether the type information meets the preset conditions, it can specifically perform the following steps:

[0091] S401B. Locate the vehicle and obtain its current location information;

[0092] S402B. Detect the first correlation between the detection type information and the current location information;

[0093] S403B. When the first degree of association is less than the association threshold, the type information is determined to meet the preset conditions.

[0094] Steps S401B-S403B are the second execution method of step S4.

[0095] In step S401B, the control module calls the navigation module to locate the vehicle and obtain the current location information. The current location information represents the latitude and longitude coordinates of the vehicle's current location.

[0096] In step S402B, the control module can determine the correlation between the type information and the current location information, i.e., the first correlation, by looking up a table. Specifically, the control module can determine the type of location where the car is parked based on the current location information, such as office buildings, schools, hospitals, shopping malls, government offices, amusement parks, etc.; the control module can determine the scenarios in which the abandoned entity might be used or disposed of based on the type of item represented by the type information, and sort and assign values ​​according to the probability of being used or disposed of, recording them in the data table shown in Table 2.

[0097] Table 2

[0098]

[0099]

[0100] In step S402B, the control module queries the corresponding item type in Table 2 based on the type information identified in step S3, queries the corresponding possible application scenarios in Table 2 based on the current location information obtained in step S401B, and determines the first correlation degree based on the determined assignment.

[0101] In step S403B, the control module can set an association threshold (e.g., 50). When the first association degree detected in step S402B is less than the association threshold, the control module determines that the type information meets the preset conditions and can execute step S5, thereby controlling the automotive components to perform protective actions on the abandoned entity.

[0102] In this embodiment, the principle of executing steps S401B-S403B is as follows: the first correlation recorded in Table 2 is positively correlated with the probability that the abandoned entity is applied to the corresponding scene location; for example, when the item type of the abandoned entity is a document, it is most likely to be used by the driver to work or hold a meeting in an office building. Therefore, the scenario of "office building" corresponds to the highest assignment, that is, the abandoned entity "document" is very likely to be indispensable for the things that the driver needs to do at the location indicated by the current location information. Therefore, if the driver forgets to take the abandoned entity "document" when leaving the car, there is still a high probability that he or someone else will need to return to the car to retrieve the document. At this time, the first correlation detected by the control module is large, so step S403B will not determine that the type information meets the preset conditions. Therefore, the control module will not execute step S5, and will not control the car parts to perform protective actions on the abandoned entity. In other cases, such as if the current location information is detected as "amusement park", the likelihood of the "document" being used in the "amusement park" scenario is low. It is not essential for the driver's business at the location indicated by the current location information. Therefore, if the driver forgets to take the "document" when leaving the car, the likelihood of returning to the car to retrieve the document is low (or returning to the car to retrieve the document would cause significant trouble for the driver). In this case, the first correlation detected by the control module is low. Then, in step S403B, it will be determined that the type information meets the preset conditions. The control module executes step S5 to control the car components to perform protective actions on the left-behind entity.

[0103] In this embodiment, the principle of executing steps S401B-S403B is as follows: When the first correlation degree is determined to be greater than the correlation threshold, it indicates that the driver or his / her agent is more likely to return to the car to retrieve the abandoned entity. At this time, the control module does not need to control the car components to perform protective actions on the abandoned entity, thereby saving the resources required to perform protective actions. When the first correlation degree is determined to be less than the correlation threshold, it indicates that the driver or his / her agent is less likely to return to the car to retrieve the abandoned entity, or returning to the car to retrieve the document would cause the driver a lot of trouble. At this time, the control module can control the car components to perform protective actions on the abandoned entity. Without the driver returning to the car to retrieve the abandoned entity, the abandoned entity can still be protected, preventing it from being harmed, damaged, or stolen, and ensuring property safety.

[0104] In this embodiment, when the control module executes step S4, which is to determine whether the type information meets the preset conditions, it can specifically perform the following steps:

[0105] S401C. Obtain the navigation information to be performed for the vehicle;

[0106] S402C. Determine the destination location based on the navigation information to be performed;

[0107] S403C. The second degree of correlation between detection type information and the location information to be reached;

[0108] S404C. When the second correlation degree is greater than the correlation threshold, it is determined that the type information meets the preset conditions.

[0109] Steps S401C-S404C are the third execution method of step S4.

[0110] In step S401C, the control module obtains the navigation information to be performed by calling the navigation module. The navigation information to be performed indicates the navigation task that the driver will perform while driving the car.

[0111] In step S402C, the control module obtains the destination information from the navigation information to be performed. The destination information indicates the destination that the navigation module will reach by navigating according to the navigation information to be performed.

[0112] In step S403C, the correlation degree between type information and location information to be reached can be pre-established in the control module, i.e., the second correlation degree, by referring to the form of Table 2. The second correlation degree between the type information obtained in step S3 and the location information to be reached obtained in step S402C is determined by looking up the table.

[0113] In step S404C, the control module can set an association threshold (e.g., 50). When the second association degree detected in step S402C is greater than the association threshold, the control module determines that the type information meets the preset conditions and can execute step S5, thereby controlling the automotive components to perform protective actions on the abandoned entity.

[0114] In this embodiment, similar to the principle of steps S401B-S403B, the principle of executing steps S401C-S403C is as follows: when the second correlation degree is determined to be greater than the correlation threshold, it indicates that the driver is more likely to use the abandoned entity at the destination to be reached in the next navigation, that is, the abandoned entity is important to the driver. At this time, the control module can control the car components to perform protective actions on the abandoned entity, without the driver having to return to the car to retrieve the abandoned entity, and can also provide protection for the abandoned entity to prevent it from being injured, damaged or stolen, thus ensuring property safety; when the second correlation degree is determined to be less than the correlation threshold, it indicates that the abandoned entity is not important to the driver. At this time, the control module does not need to control the car components to perform protective actions on the abandoned entity, thereby saving the resources required to perform protective actions.

[0115] The system provides suggestions for protecting abandoned items based on preset thresholds and prompts the vehicle owner to respond and take appropriate action via the vehicle's app. In some cases, if the vehicle owner does not respond, the default response strategy is executed.

[0116] In this embodiment, when the control module executes step S4, which is to determine whether the type information meets the preset conditions, it can specifically perform the following steps:

[0117] S401D. Determine the environmental requirements information of the legacy entity based on the type information;

[0118] S402D. Detects the interior space of a vehicle and obtains information about the current interior environment;

[0119] S403D. When the current cabin environment information does not match the environmental requirements information, determine if the type information meets the preset conditions.

[0120] Steps S401D-S403D are the fourth execution method of step S4.

[0121] The correspondence between type information and environmental requirement information can be pre-recorded in the control module. When executing step S401D, the control module obtains the environmental requirement information by looking up a table. The environmental requirement information indicates the optimal storage environment required for the type of the legacy entity. For example, when the type information is "file", the environmental requirement information could be "temperature below 30°C, humidity below 50%, illuminance below 500 lux", etc.

[0122] In step S402D, the control module calls the environmental parameter sensors inside the car cabin to detect the temperature, humidity, illuminance, etc. of the cabin space and obtain the current cabin environment information.

[0123] In step S403D, the control module checks whether the current cabin environment information obtained in step S402D meets the conditions of the environmental requirement information obtained in step S401D. For example, it determines whether the current cabin environment information such as temperature, humidity, and illuminance measured in step S402D meets the requirements of environmental requirement information such as "temperature below 30℃, humidity below 50%, and illuminance below 500 lux". If the requirements of such environmental requirement information are not met, the control module determines that the current cabin environment information does not match the environmental requirement information and determines that the type information meets the preset conditions.

[0124] In this embodiment, the principle of executing steps S401D-S403D is as follows: when the current cabin environment information does not match the environmental requirements information, it indicates that the current cabin environment deviates from the preservation environment (or survival environment for organisms) required by the abandoned entity. At this time, the control module can control the vehicle components to perform protective actions on the abandoned entity, thereby protecting the abandoned entity from damage or harm and ensuring the safety of life and property. Conversely, the control module does not need to control the vehicle components to perform protective actions on the abandoned entity, thereby saving the resources required to perform protective actions.

[0125] In this embodiment, when the control module executes step S5, which is the step of controlling the automotive components to perform a protective action on the abandoned entity, it can specifically perform the following steps:

[0126] S501A. Using safety indicators as search criteria, the destination location information is obtained;

[0127] S502A. Generates autonomous driving instructions based on destination location information;

[0128] S503A. Controls vehicle components to perform autonomous driving using autonomous driving commands.

[0129] Steps S501A-S503A are the first execution method of step S5.

[0130] In step S501A, the control module can pre-store destination location information that meets the conditions and directly call it to obtain the destination location information; the control module can also set safety indicator conditions such as "located within the shooting range of the surveillance camera and the flow of people is greater than the threshold" and call the navigation module to search for destination location information that meets such safety indicator conditions. For example, the destination location information can be another parking space in the same parking lot as the current parking space of the car, and the parking space is closer to the location of the security booth of the parking lot. Or, if the current parking space of the car is not a standard parking space (such as an empty space on the shoulder), then a standard parking lot can be searched within a certain distance (such as 10km) to obtain the destination location information.

[0131] In step S502A, the control module generates an autonomous driving command based on the destination location information and sends the command to the autonomous driving module. In step S503A, the autonomous driving module executes Level 3 or higher autonomous driving, thereby automatically driving the car to the destination.

[0132] In this embodiment, the principle of executing steps S501A-S503A is as follows: the control module can automatically move the car by calling the autonomous driving module to perform autonomous driving operation, thereby helping to protect the abandoned entity from damage or injury and ensuring the safety of life and property.

[0133] When automotive components perform protective actions against abandoned objects, the following steps can be executed:

[0134] In this embodiment, when the control module executes step S5, which is the step of controlling the automotive components to perform a protective action on the abandoned entity, it can specifically perform the following steps:

[0135] S501B. When the type information indicates that the abandoned entity is a living being, generate an atmosphere adjustment command and / or a help / warning command.

[0136] S502B. When the type information indicates that the abandoned entity is an item, generate a window color-changing instruction;

[0137] S503B. Controls automotive components to perform cabin atmosphere adjustment using atmosphere adjustment commands;

[0138] S504B. Uses a distress warning command to control automotive components to execute a distress warning;

[0139] S505B. Controls automotive components to change the color of the windows using a window color-changing command.

[0140] Steps S501B-S505B are the second execution method of step S5.

[0141] In step S501B, when the type information indicates that the abandoned entity is an infant, elderly person, or pet, the control module generates an atmosphere adjustment command and / or a distress warning command. When the control module executes step S503B, it sends the atmosphere adjustment command to the atmosphere adjustment module, which can control the atmosphere adjustment module to create a soothing atmosphere in the vehicle's cabin space, thereby calming the emotions of the infant, elderly person, or pet and helping to prevent greater harm caused by emotional instability while waiting for the driver or other personnel to arrive for rescue. When the control module executes step S504B, it sends the distress warning command to the distress module, which can control the distress module to emit distress signals through lights, sounds, or electronic information, thereby notifying the outside world to provide assistance or rescue to the infant, elderly person, or pet left in the vehicle, thus helping to ensure life safety.

[0142] Figure 1The color-changing window module in this vehicle uses electrochromic elements installed in the windows, sunroof, and front and rear windshields. When these elements receive a color-changing command, they adjust the light transmittance of the windows, sunroof, and windshields through the electrochromic effect. When the light transmittance is high, it allows visibility into the vehicle from the outside; conversely, when the light transmittance is low, it prevents visibility into the vehicle from the outside.

[0143] In step S502B, when the type information indicates that the abandoned entity is an item, the control module generates a window color-changing instruction. When the control module executes step S505B, it sends the window color-changing instruction to the color-changing window module. The color-changing window module controls the light transmittance of the windows, sunroof, and front and rear windshields, making them opaque. This prevents people outside the vehicle from entering and thus prevents them from seeing the abandoned entity inside. This avoids the possibility of unauthorized personnel seeing valuables or important documents, thereby reducing the risk of theft and damage to the vehicle and ensuring property security.

[0144] If no abandoned entity is present in the vehicle cabin, or if the type information of the abandoned entity does not meet preset conditions, the control module will not generate a window tinting command. Therefore, it will not control the light transmittance of the tinted window module, maintaining the light transmittance of the windows, sunroof, and front and rear windshields at a high level (e.g., greater than 70%). The tinted window module is not powered on, reducing the consumption of the vehicle's stored energy. When the vehicle is being driven, the control module may also refrain from generating a window tinting command, thus not controlling the light transmittance of the tinted window module to meet safety requirements.

[0145] A computer program for executing the vehicle control method based on the detection of left-behind entities in the vehicle as described in this embodiment can be written into a computer device or storage medium. When the computer program is read out and run, the vehicle control method based on the detection of left-behind entities in the vehicle as described in this embodiment is executed, thereby achieving the same technical effect as the vehicle control method based on the detection of left-behind entities in the vehicle as described in the embodiment.

[0146] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. Furthermore, the descriptions of "upper," "lower," "left," and "right" used in this disclosure are only relative to the relative positional relationships of the components of this disclosure in the accompanying drawings. The singular forms "a," "an," and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. Moreover, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this embodiment specification is only for describing particular embodiments and is not intended to limit the invention. The term "and / or" as used in this embodiment includes any combination of one or more of the associated listed items.

[0147] It should be understood that although the terms first, second, third, etc., may be used to describe various elements in this disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element without departing from the scope of this disclosure, and similarly, a second element may also be referred to as a first element. The use of any and all instances or exemplary language (“e.g.,” “such as,” etc.) provided in this embodiment is intended only to better illustrate embodiments of the invention and, unless otherwise required, does not impose a limitation on the scope of the invention.

[0148] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).

[0149] Furthermore, the procedures described in this embodiment can be performed in any suitable order unless otherwise indicated by this embodiment or clearly contradicted by the context. The procedures (or variations and / or combinations thereof) described in this embodiment can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. A computer program includes multiple instructions executable by one or more processors.

[0150] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices, etc. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention of this embodiment includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps above in conjunction with a microprocessor or other data processor. When programmed according to the methods and techniques of the invention, the invention also includes the computer itself.

[0151] A computer program can be applied to input data to perform the functions of this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

[0152] The above are merely preferred embodiments of the present invention. The present invention is not limited to the above-described embodiments. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention, as long as they achieve the technical effects of the present invention by the same means, should be included within the scope of protection of the present invention. Within the scope of protection of the present invention, the technical solutions and / or implementation methods can have various modifications and variations.

Claims

1. A vehicle control method based on the detection of entities left behind on the vehicle, characterized in that, The vehicle control method based on the detection of entities left behind on the vehicle includes: When the driver is detected to have left the vehicle, the interior of the car is photographed to obtain an image of the vehicle to be detected. The image to be detected is inspected to determine the abandoned entities contained in the image to be detected; Identify the type information of the abandoned entity; Determine whether the type information meets the preset conditions; When the type information meets the preset conditions, the vehicle components are controlled to perform protective actions on the abandoned entity. The step of determining whether the type information meets the preset conditions includes: The vehicle is located to obtain its current location information; Detect the first correlation between the type information and the current location information; When the first correlation degree is less than the correlation threshold, it is determined that the type information meets the preset conditions.

2. The vehicle control method based on the detection of entities left behind on the vehicle according to claim 1, characterized in that, The step of detecting the image to be detected and determining the abandoned entities contained in the image to be detected includes: Run the target detection model; Obtain a standard image; the standard image does not contain the legacy entity; The image to be detected and the standard image are input into the target detection model for processing; Based on the processing results of the target detection model, the location of the leftover entity in the image to be detected is determined.

3. The vehicle control method based on the detection of entities left behind on the vehicle according to claim 1, characterized in that, The step of determining whether the type information meets the preset conditions includes: Based on the type information, determine the value information of the abandoned entity; When the value information is greater than the value threshold, it is determined that the type information meets the preset conditions.

4. The vehicle control method based on the detection of entities left behind on the vehicle according to claim 1, characterized in that, The step of determining whether the type information meets the preset conditions includes: Obtain the navigation information to be performed on the vehicle; Based on the navigation information to be performed, determine the location information to be reached; Detect the second correlation between the type information and the location information to be reached; When the second correlation degree is greater than the correlation threshold, it is determined that the type information meets the preset conditions.

5. The vehicle control method based on the detection of entities left behind on the vehicle according to claim 1, characterized in that, The step of determining whether the type information meets the preset conditions includes: Based on the type information, determine the environmental requirements information of the abandoned entity; The interior space of the car is monitored to obtain current interior environmental information; When the current cabin environment information does not match the environmental requirement information, it is determined that the type information meets the preset conditions.

6. The vehicle control method based on the detection of entities left behind on the vehicle according to any one of claims 1-5, characterized in that, The control vehicle component performs protective actions on the abandoned entity, including: Using safety criteria as search criteria, the destination location information is obtained. Based on the destination location information, generate autonomous driving instructions; The aforementioned autonomous driving commands control the vehicle components to perform autonomous driving.

7. The vehicle control method based on the detection of entities left behind on the vehicle according to any one of claims 1-5, characterized in that, The control vehicle components perform protective actions on the abandoned entity, including: When the type information indicates that the abandoned entity is a living being, an atmosphere adjustment command and / or a help warning command are generated. When the type information indicates that the abandoned entity is an item, a window color-changing instruction is generated. The aforementioned atmosphere adjustment command controls the vehicle components to perform cabin atmosphere adjustment. The distress warning command is used to control the vehicle components to issue a distress warning. The aforementioned window color-changing command controls the vehicle components to perform window color-changing.

8. A computer device, characterized in that, It includes a memory and a processor, the memory being used to store at least one program, and the processor being used to load at least one program to execute the vehicle control method based on the detection of abandoned entities on the vehicle as described in any one of claims 1-7.

9. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform the vehicle control method based on the detection of abandoned entities on the vehicle as described in any one of claims 1-7.

Images