Vehicle assisted driving control method and control system

Abstract

The application provides a vehicle auxiliary driving control method and a control system, and belongs to the technical field of vehicle auxiliary driving. The vehicle auxiliary driving control method comprises the following steps: collecting image information and sound information around a vehicle; determining a scene where the vehicle is located according to the image information and the sound information; determining a corresponding preset opening degree according to the scene where the vehicle is located, wherein the preset opening degree corresponds to a safe opening degree under the current scene; and starting a brake of the vehicle to replace an accelerator when an opening degree of the accelerator of the vehicle exceeds the preset opening degree corresponding to the scene where the vehicle is located. The application further provides a vehicle auxiliary driving control system for executing the vehicle auxiliary driving control method. The vehicle auxiliary driving control method and the control system can improve driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle assisted driving, and in particular to a vehicle assisted driving control method and control system. Background Art

[0002] Intelligent driving vehicles add advanced sensors (radar, camera), controllers, actuators and other devices to ordinary vehicles. Through on-board sensing systems and information terminals, they realize intelligent information exchange with people, vehicles, roads, etc., so that vehicles have intelligent environmental perception capabilities, can automatically analyze the safety and danger status of vehicle driving, and make the vehicle reach the destination according to the wishes of the people, ultimately achieving the purpose of replacing human operation to reduce the burden of human driving.

[0003] Existing technologies generally use system driving to replace human driving. However, when performing human driving operations, the system will give priority to human operation. This mode is more convenient and safer for experienced drivers, but for novices, human driving operations are sometimes unsafe. Existing systems lack the ability to identify and respond to such unsafe operations. Summary of the Invention

[0004] An object of the first aspect of the present invention is to provide a vehicle assisted driving control method that can improve driving safety.

[0005] A further object of the present invention is to improve the accuracy of auxiliary control.

[0006] A further object of the present invention is to reduce the amount of calculation.

[0007] An object of the second aspect of the present invention is to provide a vehicle assisted driving control system for executing the above-mentioned vehicle assisted driving control method.

[0008] In particular, the present invention provides a vehicle assisted driving control method, comprising:

[0009] Collect image and sound information around the vehicle;

[0010] determining a scene in which the vehicle is located based on the image information and the sound information;

[0011] Determining a corresponding preset opening according to the scene in which the vehicle is located, the preset opening corresponding to a safe opening in the current scene;

[0012] When the current throttle opening of the vehicle exceeds the preset opening corresponding to the scenario described by the vehicle, the brake of the vehicle is activated instead of the throttle.

[0013] Optionally, the step of determining the scene in which the vehicle is located according to the image information and the sound information includes:

[0014] determining the scale of people, buildings, and plants based on the image information;

[0015] determining the noise level of the current environment according to the sound information;

[0016] The scene in which the vehicle is located is determined according to the scale of the person, the scale of the building, the scale of the plant, and the noise level of the current environment.

[0017] Optionally, the step of determining the scene in which the vehicle is located according to the size of the person, the size of the building, the size of the plant, and the noise level of the current environment includes:

[0018] When the size of the people in unit time is greater than or equal to the first threshold, or the size of the building in unit time is greater than or equal to the second threshold and the size of the plants in unit time is less than the third threshold, or the noise level in unit time is greater than or equal to the fourth threshold, it is determined that the vehicle is in an urban scene.

[0019] Optionally, the step of determining the scene in which the vehicle is located according to the size of the person, the size of the building, the size of the plant, and the noise level of the current environment includes:

[0020] When the scale of the building per unit time is smaller than the second threshold or the scale of the plant per unit time is greater than or equal to the third threshold, and the scale of the people per unit time is smaller than the first threshold, and the noise level per unit time is smaller than the fourth threshold, it is determined that the vehicle is in a suburban scene.

[0021] Optionally, the step of determining the scene in which the vehicle is located according to the size of the person, the size of the building, the size of the plant, and the noise level of the current environment includes:

[0022] When the size of the people, the size of the buildings, and the size of the plants within a unit time are all smaller than a fifth threshold, it is determined that the vehicle is in a high-speed scene.

[0023] Optionally, the step of determining the scale of a person, a building, and a plant according to the image information includes:

[0024] The scale value of a person, Sc(Pp), is calculated according to the following formula:

[0025]

[0026] Among them, v car is the average speed of the vehicle during the time period t0, np is the number of people detected in the time period t0, where t0 is the measurement time;

[0027] The scale value of the building Sc(Bd) is calculated according to the following formula:

[0028]

[0029] Among them, n B is the number of buildings detected during the time period t0, d i Represents the width of the i-th building in the image;

[0030] The scale value of the plant Sc(Tr) is calculated according to the following formula:

[0031]

[0032] Among them, S all is the sum of the areas of plants in the image detected by the image analysis unit during the time period t0.

[0033] Optionally, the sound information includes sound information inside the vehicle and mixed sound information inside and outside the vehicle, and before the step of determining the noise level of the current environment according to the sound information, the step further includes:

[0034] The sound information inside the vehicle and the mixed sound information are processed to obtain audio data containing only the sound information outside the vehicle.

[0035] Optionally, the step of determining the noise level of the current environment according to the sound information includes:

[0036] intercepting m continuous audio segments within a time period t0 of the audio data, wherein the audio data is represented by amplitude;

[0037] Each of the audio segments is divided into n monotonically increasing or monotonically decreasing son sub-fragments;

[0038] The noisiness index Vn of the i-th audio segment is calculated according to the following formula: i :

[0039] Vn i =(log2n son )*(σt+1)*(σA+1);

[0040] Where σt is the standard deviation of the dataset {t(j)}, t(j) represents the duration of the jth sub-segment, σA is the standard deviation of the dataset {ΔA(j)}, ΔA(j) represents the amplitude change of the i-th sub-segment

[0041] The noisiness Vc of the audio data is calculated according to the following formula:

[0042]

[0043] Optionally, the step of determining a corresponding preset opening according to the scene in which the vehicle is located includes:

[0044] The preset opening A is determined according to the following formula:

[0045] A=k·(v max -v)·t;

[0046] Wherein, t is the time taken to step on the accelerator to the current throttle opening, v is the real-time speed of the vehicle, and k is the conversion coefficient, which is calibrated through experiments.

[0047] In particular, the present invention also provides a vehicle assisted driving control system, comprising a memory and a processor, wherein the memory stores a control program, and when the control program is executed by the processor, it is used to implement the vehicle assisted driving control method according to any one of the above items.

[0048] According to one embodiment of the present invention, by analyzing the vehicle's current scenario and setting corresponding preset throttle openings for different scenarios, if the current throttle opening exceeds the preset opening for the current scenario, the vehicle's brakes are controlled instead of the accelerator. This prevents the driver from mistakenly pressing the accelerator instead of the brake in an emergency and causing a car accident, thereby assisting the vehicle in safe driving and improving driving safety. This assisted driving control method is particularly suitable for novice drivers, and can promptly identify dangerous operations and replace them with safe operations.

[0049] Furthermore, since the current scene is determined by combining image and audio information, the identified scene is more accurate, thereby being able to provide a more accurate preset opening, making the auxiliary control more accurate.

[0050] According to one embodiment of the present invention, the scene is judged by the conditions of people, buildings and plants and the noise level of the current environment, and three different scenes are accurately matched according to different combinations, thereby improving the accuracy of scene determination.

[0051] According to one embodiment of the present invention, audio data is processed and a specific method for calculating noisiness is provided. The noisiness parameter is used to measure the noise level of the current environment. The data processing method using standard deviation is used to improve the reliability of the calculated value and make the noisiness more accurate.

[0052] Furthermore, in this embodiment, the audio data is processed by using a segment analysis method, which can greatly reduce the amount of calculation.

[0053] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Hereinafter, some specific embodiments of the present invention will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0055] Figure 1 is a schematic structural diagram of a vehicle assisted driving control method according to an embodiment of the present invention;

[0056] Figure 2 It is a structural diagram of a vehicle assisted driving control method according to another embodiment of the present invention. DETAILED DESCRIPTION

[0057] Figure 1 FIG. 1 is a schematic diagram of a vehicle assisted driving control method according to an embodiment of the present invention. Figure 1 As shown, in one embodiment, the vehicle assisted driving control method includes:

[0058] Step S100 , collecting image information and sound information around the vehicle, for example, by using multiple cameras of the vehicle to collect images on both sides and in front of the vehicle, and by using an audio collection unit to collect sound information around the vehicle.

[0059] Step S200: Determine the scene the vehicle is in based on the image information and the sound information, for example, whether the vehicle is in an urban area, a highway, or a suburban area.

[0060] Step S300 determines a preset opening according to the vehicle's current scene. The preset opening corresponds to a safe opening for the current scene. Different scenes correspond to different safety openings. For example, the safety opening for a highway scene may be larger than that for an urban scene or a suburban scene, and the safety opening for an urban scene may be larger than that for a suburban scene.

[0061] Step S400: When the current throttle opening of the vehicle exceeds the preset opening corresponding to the vehicle scenario, the vehicle's brake is activated instead of the throttle.

[0062] This embodiment analyzes the vehicle's current scenario and sets corresponding preset throttle openings for different scenarios. If the current throttle opening exceeds the preset opening for the current scenario, the vehicle's brakes are activated instead of the accelerator. This prevents the driver from mistaking the accelerator for the brake in an emergency and causing a crash, thereby assisting the vehicle in safe driving and improving driving safety. This assisted driving control method is particularly suitable for novice drivers, as it can promptly identify dangerous maneuvers and replace them with safer ones.

[0063] Furthermore, since the present embodiment uses a combination of image and audio information to determine the current scene, the identified scene is more accurate, thereby being able to provide a more accurate preset opening, making the auxiliary control more accurate.

[0064] Figure 2 FIG. 1 is a schematic diagram of a vehicle assisted driving control method according to another embodiment of the present invention. Figure 2 As shown, in one embodiment, step S200 includes:

[0065] Step S210 determines the scale of people, buildings, and plants based on the image information. That is, the image information includes at least image information of people, buildings, and plants. The image analysis unit analyzes the captured image to obtain the aforementioned image information. It should be noted that the image analysis unit only analyzes data on people, buildings, and plants in the near distance of the image, while ignoring those in the distant distance.

[0066] Step S220: determining the noise level of the current environment based on the sound information.

[0067] Step S230 , determining the scene in which the vehicle is located based on the scale of people, the scale of buildings, the scale of plants, and the noise level of the current environment.

[0068] In a further embodiment, step S230 includes:

[0069] When the scale of people in unit time is greater than or equal to the first threshold, or the scale of buildings in unit time is greater than or equal to the second threshold and the scale of plants in unit time is less than the third threshold, or the noise level in unit time is greater than or equal to the fourth threshold, the vehicle is determined to be in an urban scene.

[0070] When the scale of the building per unit time is less than the second threshold or the scale of the plant per unit time is greater than or equal to the third threshold, and the scale of the people per unit time is less than the first threshold, and the noise level per unit time is less than the fourth threshold, the vehicle is determined to be in a suburban scene.

[0071] When the scale of people, buildings, and plants per unit time are all smaller than a fifth threshold (the fifth threshold may be 0), it is determined that the vehicle is in a high-speed scene.

[0072] In this embodiment, the scene is judged by the conditions of people, buildings and plants and the noise level of the current environment, and three different scenes are accurately matched according to different combinations, thereby improving the accuracy of scene determination.

[0073] In one embodiment, in step S210 , the scale values ​​Sc(Pp) of people, Sc(Bd) of buildings, and Sc(Tr) of plants are used to measure the scales of people, buildings, and plants.

[0074] The scale value of a person, Sc(Pp), is calculated according to the following formula (1):

[0075]

[0076] Among them, v car is the average speed of the vehicle during the time period t0, n p is the number of people detected in the time period t0, where t0 is the measurement time;

[0077] The scale value of the building Sc(Bd) is calculated according to the following formula (2):

[0078]

[0079] Among them, n B is the number of buildings detected during the time period t0, d i Represents the width of the i-th building in the image;

[0080] The scale value of the plant Sc(Tr) is calculated according to the following formula:

[0081]

[0082] Among them, S all is the sum of the areas of plants in the image detected by the image analysis unit during the time period t0.

[0083] In a further embodiment, the sound information includes the sound information inside the vehicle and the mixed sound information inside and outside the vehicle, such as Figure 2 As shown, before step S220, the following steps are also included:

[0084] Step S212: Process the sound information inside the vehicle and the mixed sound information to obtain audio data containing only the sound information outside the vehicle.

[0085] In this embodiment, the audio acquisition unit may include two audio collectors and an audio processor, one audio collector is used to collect sound information inside the vehicle, and the other audio collector is used to collect mixed sound information outside the vehicle. The audio processor processes the two sound information to obtain audio data containing sound information outside the vehicle.

[0086] The aforementioned audio information and the aforementioned image information may both be stored in a data storage unit of the vehicle.

[0087] In one embodiment, step S220 includes:

[0088] During the t0 period of the audio data, m consecutive audio segments are captured, and the audio data is represented by amplitude.

[0089] Each audio segment is divided into monotonically increasing or monotonically decreasing n son sub-segments. That is, the amplitude of each sub-segment either increases or decreases over time.

[0090] The noisiness index Vn of the i-th audio segment is calculated according to the following formula (4): i :

[0091] Vn i =(log2n son )*(σt+1)*(σA+1) (4)

[0092] Where σt is the standard deviation of the dataset {t(j)}, t(j) represents the duration of the j-th sub-segment, σA is the standard deviation of the dataset {ΔA(j)}, ΔA(j) represents the amplitude change of the i-th sub-segment.

[0093] The noisiness Vc of the audio data is calculated according to the following formula (5):

[0094]

[0095] This embodiment processes audio data and provides a specific method for calculating noisiness, using the noisiness parameter to measure the noisiness of the current environment. The standard deviation data processing method is used to improve the reliability of the calculated value and make the noisiness more accurate.

[0096] Furthermore, in this embodiment, the audio data is processed by using a segment analysis method, which can greatly reduce the amount of calculation.

[0097] Accordingly, step S230 includes:

[0098] When one of the following three conditions is met, the vehicle is determined to be in an urban area;

[0099] Condition 1: Sc(Pp) ≥ P1, Condition 2: Sc(Bd) ≥ B1 and Sc(Tr) < T1, Condition 3: vc ≥ V1;

[0100] Among them, P1 is the scale threshold of people, B1 is the scale threshold of buildings, T1 is the scale threshold of trees, and V1 is the noise threshold.

[0101] When the following three conditions are met at the same time, the vehicle is determined to be in a suburban scene;

[0102] Condition 1: Sc(Pp)<P1, Condition 2: 0<Sc(Bd)<B1 or Sc(Tr)≥T1, Condition 3: v c <V1.

[0103] When Sc(Pp)=0, Sc(Bd)=0, and Sc(Tr)=0, it is determined that the vehicle is in a high-speed scene. In this embodiment, relatively stringent conditions are set. In other embodiments, other thresholds can also be set to indicate that the scale of people, buildings, and plants is extremely small.

[0104] Among them, P1 is the scale threshold of people, B1 is the scale threshold of buildings, T1 is the scale threshold of trees, and V1 is the noise threshold.

[0105] In one embodiment, step S300 includes:

[0106] The preset opening A is determined according to the following formula (6):

[0107] A=k·(v max -v)·t (6)

[0108] Wherein, t is the time taken to step on the accelerator to the current throttle opening, v is the real-time speed of the vehicle, and k is the conversion coefficient, which is calibrated through experiments.

[0109] Accordingly, step S400 can be determined using the following formula (7):

[0110]

[0111] Among them, α is the current throttle opening, and its value range is [0, 1]. When it is 0, it is considered that the throttle is not depressed, and 1 is that the throttle is fully depressed.

[0112] The present invention also provides a vehicle assisted driving control system, comprising a memory and a processor, wherein a control program is stored in the memory, and when the control program is executed by the processor, it is used to implement the vehicle assisted driving control method according to any one of the above embodiments or combinations of embodiments. The processor can be a central processing unit (CPU), or a digital processing unit, etc. The processor sends and receives data through a communication interface. The memory is used to store the program executed by the processor. The memory is any medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, or it can be a combination of multiple memories. The above-mentioned computing program can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or downloaded to a computer or external storage device via a network (such as the Internet, a local area network, a wide area network and / or a wireless network).

[0113] The vehicle assisted driving control system may also include an image acquisition unit, an image analysis unit, an audio acquisition unit (the audio acquisition unit may include two audio collectors and an audio processor) and a data storage unit. The image acquisition unit is used to collect image information around the vehicle, and the image analysis unit is used to analyze data on people, buildings and plants in the close-up of the image. One audio collector is used to collect sound information inside the vehicle, and the other audio collector is used to collect mixed sound information outside the vehicle. The audio processor processes the two sound information to obtain audio data containing sound information outside the vehicle. The above-mentioned audio information and the aforementioned image information can both be stored in the vehicle's data storage unit.

[0114] The control unit of the vehicle assisted driving control system (including the above-mentioned memory and processor) can collect image information and audio information in the above-mentioned data storage unit, as well as the current throttle opening of the vehicle, and some preset thresholds, and then perform operations according to the program corresponding to the above-mentioned method.

[0115] The vehicle-assisted driving control system of this embodiment analyzes the vehicle's current scenario and sets corresponding preset throttle openings for different scenarios. If the current throttle opening exceeds the preset opening for the current scenario, the vehicle's brakes are activated instead of the accelerator. This prevents the driver from mistaking the accelerator for the brake in an emergency and causing a traffic accident, thereby assisting the vehicle in safe driving and improving driving safety. This assisted driving control method is particularly suitable for novice drivers, as it can promptly identify dangerous maneuvers and replace them with safer ones.

[0116] Furthermore, since the present embodiment uses a combination of image and audio information to determine the current scene, the identified scene is more accurate, thereby being able to provide a more accurate preset opening, making the auxiliary control more accurate.

[0117] At this point, those skilled in the art will recognize that, although a number of exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications consistent with the principles of the present invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and deemed to cover all such other variations or modifications.

Claims

1. A vehicle assisted driving control method, characterized in that: include: Collect image and sound information around the vehicle; determining a scene in which the vehicle is located based on the image information and the sound information; Determining a corresponding preset opening according to the scene in which the vehicle is located, the preset opening corresponding to a safe opening in the current scene; When the current throttle opening of the vehicle exceeds the preset opening corresponding to the scene in which the vehicle is located, activating the brake of the vehicle instead of the throttle; The step of determining the scene in which the vehicle is located according to the image information and the sound information includes: determining the scale of people, buildings, and plants based on the image information; determining the noise level of the current environment according to the sound information; determining the scene in which the vehicle is located based on the size of the person, the size of the building, the size of the plant, and the noise level of the current environment; The step of determining the scale of a person, a building, and a plant according to the image information includes: The scale value of a person, Sc(Pp), is calculated according to the following formula: Among them, v car is the average speed of the vehicle during the time period t0, n p is the number of people detected in the time period t0, where t0 is the measurement time; The scale value of the building Sc(Bd) is calculated according to the following formula: Among them, n B is the number of buildings detected during the time period t0, d i Represents the width of the i-th building in the image; The scale value of the plant Sc(Tr) is calculated according to the following formula: Among them, S all is the sum of the areas of plants in the image detected by the image analysis unit during the time period t0.

2. The vehicle assisted driving control method according to claim 1, characterized in that: The step of determining the scene in which the vehicle is located according to the scale of the person, the scale of the building, the scale of the plant, and the noise level of the current environment includes: When the size of the people in unit time is greater than or equal to the first threshold, or the size of the building in unit time is greater than or equal to the second threshold and the size of the plants in unit time is less than the third threshold, or the noise level in unit time is greater than or equal to the fourth threshold, it is determined that the vehicle is in an urban scene.

3. The vehicle assisted driving control method according to claim 2, characterized in that: The step of determining the scene in which the vehicle is located according to the scale of the person, the scale of the building, the scale of the plant, and the noise level of the current environment includes: When the scale of the building per unit time is smaller than the second threshold or the scale of the plant per unit time is greater than or equal to the third threshold, and the scale of the people per unit time is smaller than the first threshold, and the noise level per unit time is smaller than the fourth threshold, it is determined that the vehicle is in a suburban scene.

4. The vehicle assisted driving control method according to claim 1, characterized in that: The step of determining the scene in which the vehicle is located according to the scale of the person, the scale of the building, the scale of the plant, and the noise level of the current environment includes: When the size of the people, the size of the buildings, and the size of the plants within a unit time are all smaller than a fifth threshold, it is determined that the vehicle is in a high-speed scene.

5. The vehicle assisted driving control method according to claim 1, characterized in that: The sound information includes sound information inside the vehicle and mixed sound information inside and outside the vehicle. Before the step of determining the noise level of the current environment based on the sound information, the method further includes: The sound information inside the vehicle and the mixed sound information are processed to obtain audio data containing only the sound information outside the vehicle.

6. The vehicle assisted driving control method according to claim 5, characterized in that: The step of determining the noise level of the current environment according to the sound information includes: intercepting m continuous audio segments within a time period t0 of the audio data, wherein the audio data is represented by amplitude; Each of the audio segments is divided into n monotonically increasing or monotonically decreasing son sub-fragments; The noisiness index Vn of the i-th audio segment is calculated according to the following formula: i : Vn i =(log2n son )*(σt+1)*(σA+1); Where σt is the standard deviation of the dataset {t(j)}, t(j) represents the duration of the jth sub-segment, σA is the standard deviation of the dataset {ΔA(j)}, ΔA(j) represents the amplitude change of the i-th sub-segment The noisiness Vc of the audio data is calculated according to the following formula:

7. The vehicle assisted driving control method according to claim 1, characterized in that: The step of determining a corresponding preset opening according to the scene in which the vehicle is located includes: The preset opening A is determined according to the following formula: A=k·(v max -v)·t; Wherein, t is the time taken to step on the accelerator to the current throttle opening, v is the real-time speed of the vehicle, and k is the conversion coefficient, which is calibrated through experiments.

8. A vehicle assisted driving control system, comprising a memory and a processor, wherein the memory stores a control program, and when the control program is executed by the processor, it is used to implement the vehicle assisted driving control method according to any one of claims 1 to 7.

Images