CN115891981A - Driving assistance system and method based on visual recognition - Google Patents

Abstract

The invention relates to the technical field of driving assistance, and specifically discloses a driving assistance system and method based on visual recognition, wherein the system includes a first image acquisition module for collecting image data outside the vehicle; a driving control module for acquiring vehicle driving data and accelerator pedal strength data, the auxiliary module is used to determine the environment outside the vehicle according to the image data outside the vehicle; judge the current state of the vehicle according to the driving data, if the state of the vehicle is maneuvering or parking, according to the driving trajectory of the vehicle and the The external environment judges whether there is an obstacle on the driving track, and if there is an obstacle, calculates the distance between the vehicle and the obstacle; it is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judges Whether the throttle strength data exceeds the estimated strength, and if so, an alarm message is generated. Adopting the technical solution of the invention can ensure the safety of the vehicle and the driver in the scene of parking or moving the car, and reduce the probability of accidents.

Description

Driving assistance system and method based on visual recognition

technical field

The invention relates to the technical field of driving assistance, in particular to a driving assistance system and method based on visual recognition.

Background technique

With the development of modern society, the number of cars is also increasing, which requires drivers to be vigilant at all times during driving, not only to avoid collisions with other vehicles, pedestrians, and obstacles, but also to try to Avoid the influence of other vehicles, etc. on yourself. However, due to the limited attention and observation range of the driver during driving, sometimes the situation in front of the road cannot be discovered in time, and the influence of other vehicles can be avoided, resulting in traffic accidents.

For this reason, a driving assistance system has appeared, which uses various sensors installed on the car to sense the surrounding environment at any time during the driving process of the car, collect data, identify, detect and track static and dynamic objects, and Combined with navigation map data, system calculation and analysis are carried out, so that drivers can be aware of possible dangers in advance, and the comfort and safety of car driving can be increased.

However, such driving assistance systems are usually used on roads and require the driver to actively activate them; for parking or maneuvering scenarios, if the driver chooses to operate manually, they often only provide images or radar warnings outside the vehicle. When an operation error occurs, it cannot intervene immediately.

Therefore, there is a need for a visual recognition-based driving assistance system and method that can ensure the safety of vehicles and drivers in parking or maneuvering scenarios.

Contents of the invention

One of the objectives of the present invention is to provide a driving assistance system based on visual recognition, which can ensure the safety of vehicles and drivers in parking or maneuvering scenarios, and reduce the probability of accidents.

In order to solve the above technical problems, the application provides the following technical solutions:

Driver assistance systems based on visual recognition, including:

The first image collection module is used to collect image data outside the vehicle;

The driving control module is used to obtain the current driving data and accelerator pedal strength data of the vehicle. The driving data includes steering angle data, gear position data and vehicle speed data;

The auxiliary module is used to determine the environment outside the vehicle according to the image data outside the vehicle; it is also used to judge the current state of the vehicle according to the driving data, and if the state of the vehicle is moving or parking, estimate the driving trajectory of the vehicle according to the driving data; It is also used to judge whether there is an obstacle on the driving track according to the driving track of the vehicle and the environment outside the car, and if there is an obstacle, calculate the distance between the vehicle and the obstacle;

It is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator strength data exceeds the estimated strength. If not, execute the instruction of the accelerator pedal; if it exceeds, generate an alarm message , does not execute the command of the accelerator pedal.

The principles and beneficial effects of the basic scheme are as follows:

In this solution, the image data of the parking space is collected after the vehicle is started, and the environment outside the vehicle can be determined through analysis related to visual recognition; and then according to the current driving data, it can be known whether the vehicle is in the state of moving or parking; if Yes, estimate the vehicle's driving trajectory and judge whether there are obstacles on the driving trajectory; in the case of obstacles, if the driver has problems controlling the accelerator pedal, it is easy to cause an accident. For example, the force of the accelerator pedal is controlled to be too large, causing the vehicle to accelerate rapidly, and another example is to use the accelerator pedal as a brake pedal. This program pre-sets the warning value, which is the value of the reaction time; calculates the estimated strength of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, so as to ensure that the driver has time to react before the vehicle touches the obstacle; if Judging that the accelerator force data exceeds the estimated force, an alarm message is generated, and the instruction of the accelerator pedal is not executed, so as to avoid the collision between the vehicle and the obstacle caused by the driver's untimely response.

In summary, this solution can ensure the safety of vehicles and drivers in parking or moving scenarios, and reduce the probability of accidents. In this solution, before the driver controls the accelerator pedal, pre-analysis has been carried out. When the driver controls the accelerator pedal, the accelerator force data is compared with the estimated force. The amount of calculation is small, the system delay is low, and the driving experience is better. Well, at the same time, this solution does not modify the calibration of the accelerator pedal to avoid affecting the driver's muscle memory.

Further, the auxiliary module is used to identify whether the vehicle’s external environment includes a driving area and a non-driving area according to the image data outside the vehicle, and judge whether the vehicle’s driving track passes through the non-driving area, and if it passes through the non-driving area, determine whether there is a vehicle on the driving track. obstacle.

In this priority plan, the definition of obstacles is broader, such as non-driving areas with height drops, such non-driving areas are also regarded as obstacles, which can prevent vehicles from entering non-driving areas with height drops, and are safe Sex is higher.

Further, the auxiliary module is also used to obtain historical driving data and accelerator pedal strength data, classify the driver's driving style according to the historical driving data and accelerator pedal strength data, and select different warning values according to the classification.

For example, a driver with an aggressive acceleration style adopts a shorter warning value to realize personalized settings for different drivers and different driving styles.

Further, it also includes a second image acquisition module, which is used to acquire image data in the vehicle;

The auxiliary module is also used to identify the driver according to the image data in the car, and determine the driver's viewing direction; it is also used to determine the direction of the obstacle outside the car, and judge whether the driver's viewing direction is consistent with the direction of the obstacle outside the car. Consistent, if inconsistent, maintain the current warning value, if consistent, increase the current warning value.

When the driver's observation direction is consistent with the direction of the obstacle outside the vehicle, the driver is more likely to know that there is an obstacle, and the current warning value is increased, so that the control of the vehicle is more in the hands of the driver. Reduces potential for driver disturbance.

Further, the auxiliary module is also used to estimate the driving direction of the vehicle according to the driving area and the non-driving area, judge whether the gear position is consistent with the driving direction according to the driving direction and the gear position data, and generate a reminder message if not.

It can remind the driver when the driver is in the wrong gear.

Further, it also includes a positioning module for obtaining satellite positioning data of the vehicle;

The auxiliary module is also used to record the satellite positioning data of the vehicle, judge whether the current position is a common parking position according to the historical satellite positioning data of the vehicle and the current satellite positioning data, and increase the current warning value if it is a common parking position.

In the usual parking position of the driver, he usually has a better understanding of the surrounding situation, and is more familiar with the entry and exit routes of the vehicle, increasing the current warning value and reducing the possibility of interfering with the driver.

Further, the driving data also includes vehicle inclination data;

The auxiliary module is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value, the distance between the vehicle and the obstacle, the vehicle speed data and the vehicle inclination data.

Avoid the situation where the vehicle does not move when the accelerator pedal is pressed in scenarios such as slopes.

The second object of the present invention is to provide a driving assistance method based on visual recognition, including the following:

S1. Collect image data outside the vehicle;

S2. Obtain the current driving data and accelerator pedal strength data of the vehicle, the driving data includes steering angle data, gear position data, and vehicle speed data;

S3. Determine the environment outside the vehicle according to the image data outside the vehicle; the recognized environment outside the vehicle includes a driving area and a non-driving area;

S4. Judging the current state of the vehicle according to the driving data; judging whether the state of the vehicle is moving or parking; if not, go to S4; if yes, go to S5;

S5. Estimate the driving trajectory of the vehicle according to the driving data; judge whether there is an obstacle on the driving trajectory according to the driving trajectory of the vehicle and the environment outside the vehicle, if there is an obstacle, go to S6, if there is no obstacle, go to S5;

S6. Calculate the distance between the vehicle and the obstacle; calculate the estimated force of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator force data exceeds the estimated force. If not, go to step S7. If exceeded, skip to step S8;

S7. Execute the instruction of the accelerator pedal;

S8. Generate alarm information, and not execute the instruction of the accelerator pedal.

Description of drawings

Fig. 1 is a logical block diagram of a driving assistance system based on visual recognition in Embodiment 1.

Detailed ways

The following is further described in detail through specific implementation methods:

Embodiment one

As shown in FIG. 1 , the driving assistance system based on visual recognition in this embodiment includes a first image acquisition module, a driving control module and an auxiliary module.

The first image acquisition module is used to acquire image data outside the vehicle; in this embodiment, the first image acquisition module adopts a camera arranged outside the vehicle.

The driving control module is used to obtain the current driving data and accelerator pedal strength data of the vehicle. The driving data includes steering angle data, gear position data, and vehicle speed data. Specifically, the driving control module acquires vehicle speed data from the vehicle speed sensor, gear position data from the gearbox, steering angle data from the steering mechanism, and inclination data from the gyroscope.

Auxiliary modules include image analysis unit, path planning unit, and data analysis unit;

The image analysis unit is used to determine the environment outside the vehicle according to the image data outside the vehicle; in this embodiment, the image analysis unit uses a pre-trained neural network model to identify the image data outside the vehicle. The recognized environment outside the vehicle includes a driving area and a non-driving area. In this embodiment, road surfaces with depressions, protrusions, objects, other vehicles and pedestrians are regarded as non-driving areas.

The data analysis unit is used to judge the current state of the vehicle according to the driving data; if the state of the vehicle is maneuvering or parking, the path planning unit is used to estimate the driving trajectory of the vehicle according to the driving data; The trajectory and the environment outside the vehicle determine whether there is an obstacle on the driving trajectory, and if there is an obstacle, calculate the distance between the vehicle and the obstacle. In this embodiment, the data analysis unit judges whether the driving track of the vehicle passes the non-driving area, and if it passes the non-driving area, it determines that there is an obstacle on the driving track. In this embodiment, when the vehicle speed is lower than the threshold and the gear is in reverse gear, it is regarded as parking; when the vehicle is started, the vehicle speed is 0, and the vehicle is engaged in forward gear or reverse gear, it is regarded as maneuvering.

The data analysis unit is also used to calculate the estimated force of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator force data exceeds the estimated force. If not, execute the instruction of the accelerator pedal; if it exceeds, A warning message is generated, and the instruction of the accelerator pedal is not executed. In this embodiment, the preset warning value is time, and when the distance and time are known, the average speed can be calculated, and the speed increase that requires accelerator pedal force is lower than the average speed.

Based on the above system, this embodiment also provides a driving assistance method based on visual recognition, including the following:

S1. Collect image data outside the vehicle;

S2. Obtain the current driving data and accelerator pedal strength data of the vehicle, the driving data including steering angle data, gear position data, and vehicle speed data. Specifically, the driving control module acquires vehicle speed data from the vehicle speed sensor, gear position data from the gearbox, steering angle data from the steering mechanism, and inclination data from the gyroscope.

S3. Determine the environment outside the vehicle according to the image data outside the vehicle; the recognized environment outside the vehicle includes a driving area and a non-driving area. In this embodiment, road surfaces with depressions, protrusions, objects, other vehicles and pedestrians are regarded as non-driving areas.

S4. Judging the current state of the vehicle according to the driving data; judging whether the state of the vehicle is moving or parking; if not, go to S4; if yes, go to S5;

S5. Estimate the driving trajectory of the vehicle according to the driving data; judge whether there is an obstacle on the driving trajectory according to the driving trajectory of the vehicle and the environment outside the vehicle, if there is an obstacle, go to S6, if there is no obstacle, go to S5; In this embodiment, it is judged whether the driving track of the vehicle passes through the non-driving area, and if it passes through the non-driving area, it is judged that there is an obstacle on the driving track.

S6. Calculate the distance between the vehicle and the obstacle. Calculate the estimated force of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator force data exceeds the estimated force. If not, go to step S7; if it exceeds, go to step S8;

S7. Execute the instruction of the accelerator pedal;

S8. Generate alarm information, and not execute the instruction of the accelerator pedal.

Embodiment two

The difference between this embodiment and the first real-time example is that the system of this embodiment further includes a second image acquisition module.

The second image acquisition module is used to acquire image data in the vehicle. In this embodiment, the second image acquisition module adopts a camera installed inside the vehicle.

The data analysis unit is also used to obtain historical driving data and accelerator pedal strength data, classify the driver's driving style according to the historical driving data and accelerator pedal strength data, and select different warning values according to the classification. In this embodiment, the driver's driving style is divided into cautious, normal and aggressive, and the corresponding warning value decreases gradually. In other words, the time of the warning corresponding to cautious is the longest.

The image analysis unit is also used to identify the driver according to the image data in the car, and determine the driver's viewing direction; the data analysis unit is also used to determine the direction of the obstacle outside the car, and judge the driver's viewing direction and the obstacle outside the car. Whether the directions are the same, if not, keep the current warning value, if they are consistent, increase the current warning value.

The path planning unit is also used to estimate the driving direction of the vehicle according to the driving area and the non-driving area, judge whether the gear position is consistent with the driving direction according to the driving direction and gear position data, and generate a reminder message if not.

Embodiment Three

The difference between this embodiment and Embodiment 2 is that the system of this embodiment further includes a positioning module, and the positioning module is used to acquire satellite positioning data of the vehicle.

The data analysis unit is also used to record the satellite positioning data of the vehicle, judge whether the current position is a common parking position according to the historical satellite positioning data of the vehicle and the current satellite positioning data, and increase the current warning value if it is a common parking position. In this embodiment, the commonly used parking location refers to the car being moved or parked more than 5 times at the same location.

The travel data also includes inclination data. The data analysis unit is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value, the distance between the vehicle and the obstacle, the vehicle speed data and the vehicle inclination data.

The above is only an embodiment of the present invention, and the invention is not limited to the field involved in this implementation case. The common knowledge such as the specific structure and characteristics known in the scheme is not described here, and those of ordinary skill in the art know the filing date or priority All ordinary technical knowledge in the technical field to which the invention belongs before the date, can know all the prior art in this field, and have the ability to apply the conventional experimental methods before the date, those of ordinary skill in the art can, under the inspiration given by this application, To perfect and implement this solution in combination with one's own ability, some typical known structures or known methods should not become obstacles for those of ordinary skill in the art to implement this application. It should be pointed out that for those skilled in the art, under the premise of not departing from the structure of the present invention, several modifications and improvements can also be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation of the present invention. Effects and utility of patents. The scope of protection required by this application shall be based on the content of the claims, and the specific implementation methods and other records in the specification may be used to interpret the content of the claims.

Claims (8)

1. A driving assistance system based on visual recognition, characterized in that it includes: The first image collection module is used to collect image data outside the vehicle; The driving control module is used to obtain the current driving data and accelerator pedal strength data of the vehicle. The driving data includes steering angle data, gear position data and vehicle speed data; The auxiliary module is used to determine the environment outside the vehicle according to the image data outside the vehicle; it is also used to judge the current state of the vehicle according to the driving data, and if the state of the vehicle is moving or parking, estimate the driving trajectory of the vehicle according to the driving data; It is also used to judge whether there is an obstacle on the driving track according to the driving track of the vehicle and the environment outside the car, and if there is an obstacle, calculate the distance between the vehicle and the obstacle; It is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator strength data exceeds the estimated strength. If not, execute the instruction of the accelerator pedal; if it exceeds, generate an alarm message , does not execute the command of the accelerator pedal. 2. The driving assistance system based on visual recognition according to claim 1, characterized in that: the auxiliary module is used to judge the driving of the vehicle based on the external environment of the vehicle recognized by the image data outside the vehicle, including driving areas and non-driving areas. Whether the track passes through a non-driving area, and if it passes through a non-driving area, it is judged that there is an obstacle on the driving track. 3. The driving assistance system based on visual recognition according to claim 2, characterized in that: the auxiliary module is also used to obtain historical driving data and accelerator pedal strength data, and to provide information to the driver according to the historical driving data and accelerator pedal strength data. Different driving styles are classified according to the classification, and different warning values are selected. 4. The driving assistance system based on visual recognition according to claim 3, characterized in that: it also includes a second image acquisition module for collecting image data in the car; The auxiliary module is also used to identify the driver according to the image data in the car, and determine the driver's viewing direction; it is also used to determine the direction of the obstacle outside the car, and judge whether the driver's viewing direction is consistent with the direction of the obstacle outside the car. Consistent, if inconsistent, maintain the current warning value, if consistent, increase the current warning value. 5. The driving assistance system based on visual recognition according to claim 4, characterized in that: the auxiliary module is also used to estimate the driving direction of the vehicle according to the driving area and the non-driving area, and judge according to the driving direction and gear position data Whether the gear position is consistent with the driving direction, if not, a reminder message is generated. 6. The driving assistance system based on visual recognition according to claim 5, further comprising a positioning module for obtaining satellite positioning data of the vehicle; The auxiliary module is also used to record the satellite positioning data of the vehicle, judge whether the current position is a common parking position according to the historical satellite positioning data of the vehicle and the current satellite positioning data, and increase the current warning value if it is a common parking position. 7. The driving assistance system based on visual recognition according to claim 6, characterized in that: the driving data also includes vehicle inclination data; The auxiliary module is also used to calculate the estimated strength of the accelerator pedal according to the preset warning value, the distance between the vehicle and the obstacle, the vehicle speed data and the vehicle inclination data. 8. A driving assistance method based on visual recognition, comprising the following content: S1. Collect image data outside the vehicle; S2. Obtain the current driving data and accelerator pedal strength data of the vehicle, the driving data includes steering angle data, gear position data, and vehicle speed data; S3. Determine the environment outside the vehicle according to the image data outside the vehicle; the recognized environment outside the vehicle includes a driving area and a non-driving area; S4. Judging the current state of the vehicle according to the driving data; judging whether the state of the vehicle is moving or parking; if not, go to S4; if yes, go to S5; S5. Estimate the driving trajectory of the vehicle according to the driving data; judge whether there is an obstacle on the driving trajectory according to the driving trajectory of the vehicle and the environment outside the vehicle, if there is an obstacle, go to S6, if there is no obstacle, go to S5; S6. Calculate the distance between the vehicle and the obstacle; calculate the estimated force of the accelerator pedal according to the preset warning value and the distance between the vehicle and the obstacle, and judge whether the accelerator force data exceeds the estimated force. If not, go to step S7. If exceeded, jump to step S8; S7. Execute the instruction of the accelerator pedal; S8. Generate alarm information, and not execute the instruction of the accelerator pedal.

Images