Active intelligent pedestrian protection system
By integrating intelligent systems with cameras, collision sensors and deep learning algorithms on vehicles, we can judge and reduce false explosions, and solve the problem of misjudgment of existing pedestrian protection systems, reduce the maintenance cost and maintenance cycle of vehicle parts, and improve pedestrian protection Effect.
Patent Information
- Application Number
- CN202411453946.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-01-07
AI Technical Summary
The existing pedestrian protection system is difficult to distinguish the characteristics of the collision, resulting in an increase in the chance of misjudgment and false explosion, which in turn increases the maintenance cycle and cost of vehicle-related components.
Adopt an active intelligent pedestrian protection system, including pedestrian protection airbags, cap hoisting device, camera, collision sensor, vehicle speed sensor and controller ECU, and determine whether the obstacle in front is a pedestrian through deep learning algorithms, and use the deep learning algorithm to determine whether the obstacle in front is a pedestrian, and based on the vehicle speed and obstacle information Determine whether to slow down or detonate.
Improve the pre-position of collision sensors, identify and reduce false explosions in advance, reduce maintenance costs and repair cycles of vehicle components, and maximize pedestrian protection.
Smart Images
Figure CN119261804A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of pedestrian safety protection, and in particular to an active intelligent pedestrian protection system. Background Art
[0002] As the market demand for automobiles increases, the safety requirements for automobiles are getting higher and higher. Not only the safety of passengers in the cabin is considered in the event of a collision, but pedestrian protection is also receiving more and more attention from OEMs and consumers. The latest versions of E-NCAP and C-NCAP have upgraded the requirements for pedestrian head injury values.
[0003] For pedestrian safety protection, a buffer device is usually installed between the pedestrian's head and the engine hood or front windshield, which can effectively reduce the risk of injury to personnel. The traditional solution mainly adds sensors to the crossbar behind the bumper. When a collision occurs, the sensor transmits the collected pressure or acceleration change information to the controller, which evaluates whether to detonate the hood lifter or windshield airbag based on the calibration results.
[0004] Since the existing collision information is collected through changes in vehicle acceleration or pressure changes in pressure sensors, the system is prone to miscalibration of a variety of non-human conditions, which will cause the lifters and airbags to be detonated according to the design definition, increasing the probability of misjudgment and misexplosion, making it extremely easy for the bonnet lifters and airbags to detonate once a collision occurs, and the maintenance of the bonnet lifters and airbags is also relatively expensive, thereby increasing the maintenance cycle and cost of vehicle-related components. Summary of the invention
[0005] In view of this, the purpose of the present invention is to propose an active intelligent pedestrian protection system to solve the problem that the existing pedestrian protection system is difficult to distinguish the characteristics of the collision object, resulting in an increased probability of misjudgment, thereby increasing the maintenance cycle and cost of vehicle-related components.
[0006] Based on the above purpose, the present invention provides an active intelligent pedestrian protection system, including a pedestrian protection airbag arranged at the front windshield of the vehicle, and a hood lifter arranged at the engine hood hinge, and also includes a camera, a collision sensor, a vehicle speed sensor, an MCU and a controller ECU; the camera is used to collect obstacle information in front of the vehicle, the collision sensor is used to collect pressure change information on the front bumper beam, and the vehicle speed sensor is used to collect vehicle speed information during driving; the MCU processes the obstacle information collected by the camera, and the controller ECU determines whether to slow down the vehicle according to the processed obstacle information and the collected vehicle speed information, and at the same time, The controller ECU will also determine whether a collision occurs based on the collected pressure change information on the front bumper beam and the processed obstacle information. If a collision occurs, the controller ECU will determine whether the obstacle in front of the vehicle is a pedestrian based on the obstacle information collected by the camera and combined with the deep learning algorithm. If the controller ECU determines that the vehicle has collided and the obstacle in front of the vehicle is a pedestrian, it will control one or more of the pedestrian protection airbags or the bonnet lifters to detonate. If the controller ECU determines that the vehicle has collided and the obstacle in front of the vehicle is not a pedestrian, it will control neither the pedestrian protection airbag nor the bonnet lifter to detonate, so as to protect the vehicle.
[0007] Preferably, the MCU can obtain the distance information between the vehicle and the obstacle by processing the obstacle information collected by the camera, and set the distance as S.
[0008] Preferably, the process of the controller determining whether to decelerate the vehicle is as follows: first, when the vehicle speed is higher than V1, the safe distance of the vehicle during driving is greater than S1 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; and when the vehicle speed is lower than V1, the safe distance of the vehicle during driving is greater than S2 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; then the controller ECU compares the current vehicle speed V detected by the speed sensor with V1.
[0009] Preferably, if the current vehicle speed V is higher than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S1. If S is greater than S1, the controller ECU does not react. If S is less than S1, the controller ECU controls the vehicle to actively decelerate. If the current vehicle speed V is lower than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S2. If S is greater than S2, the controller ECU does not react. If S is less than S2, the controller ECU controls the vehicle to actively decelerate.
[0010] Preferably, the controller ECU can identify whether the vehicle has collided in combination with the pressure change information collected by the collision sensor, and the controller ECU can also identify whether the vehicle has collided in combination with the obstacle information collected by the camera.
[0011] Preferably, if the controller ECU identifies that the vehicle has collided through pressure change information, the controller ECU will not react directly, but will first determine whether the colliding obstacle is a pedestrian. If the colliding object is determined to be a pedestrian, the controller ECU will control the pedestrian protection airbag or the hood lifter to react.
[0012] Preferably, if the controller detects a collision through a camera, and the collision object is a pedestrian, the controller ECU can directly control the pedestrian protection airbag or the hood lifter to respond.
[0013] The beneficial effects of the present invention are as follows: 1. The proactiveness of passive sensors (collision sensors) in receiving signals is improved. The camera can identify non-collision information at a distance, prompt the vehicle to slow down and avoid in advance, or detonate components such as jacks and airbags in advance compared to traditional solutions, which can provide more effective pedestrian protection.
[0014] 2. Combined with the video pedestrian assessment, it will first determine whether the colliding obstacle is a pedestrian. If it is determined that the colliding object is a pedestrian, the controller ECU will control the pedestrian protection airbag or the bonnet lifter to respond, thereby protecting the pedestrian. If it is determined that the obstacle in front of the vehicle is not a pedestrian, the pedestrian protection airbag and the bonnet lifter will not be detonated, thereby protecting the vehicle and minimizing the maintenance cost. For example, if the vehicle hits a columnar obstacle such as a tree, the system determines that the bonnet lifter and the front windshield pedestrian protection airbag will not be detonated, thereby reducing the maintenance cycle and cost of related components of the entire vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 is a system block diagram of an embodiment of the present invention; Figure 2 is a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION
[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connecting" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0019] like Figure 1 , Figure 2 As shown, the active intelligent pedestrian protection system includes a pedestrian protection airbag arranged at the front windshield of the vehicle, and a hood lifter arranged at the hinge of the engine hood, and also includes a camera, a collision sensor, a vehicle speed sensor, an MCU and a controller ECU; the camera is arranged on the front bumper of the vehicle, and the camera is used to collect obstacle information in front of the vehicle; the collision sensor is a pressure sensor arranged on the rear crossbeam of the front bumper of the vehicle, and the collision sensor can be a pressure sensor, which is used to collect pressure change information on the front bumper crossbeam; the vehicle speed sensor is used to collect vehicle speed information during driving; the MCU processes the obstacle information collected by the camera, and the MCU (microcontroller unit) can realize multiple functions and applications when connected to the camera. The camera can capture image information, and the MCU can process this information and perform specific tasks. The controller ECU determines whether to decelerate the vehicle based on the processed obstacle information and the collected vehicle speed information. At the same time, the controller ECU will also determine whether a collision occurs based on the collected pressure change information on the front bumper crossbeam and the processed obstacle information. If a collision occurs, the controller ECU determines whether the obstacle in front of the vehicle is a pedestrian based on the obstacle information collected by the camera and combined with the deep learning algorithm.
[0020] If the controller ECU determines that the vehicle has collided and that the obstacle in front of the vehicle is a pedestrian, it controls one or more of the pedestrian protection airbags or the hood lifters to detonate.
[0021] ECUs (Electronic Control Units) play an increasingly important role in modern cars, controlling multiple functions of the vehicle. As technology advances, ECUs can now incorporate deep learning algorithms to improve the performance of vehicle systems, including pedestrian detection. Deep learning algorithms are trained on large data sets to recognize and understand the content in images, including the shape, size, and behavior patterns of pedestrians.
[0022] If the controller ECU analyzes the shape of the pedestrian as a child (shorter in stature), the controller ECU only controls the bonnet lifter for single-point detonation. Children are short in stature and are likely to fall on the bonnet during a collision, so a single-point detonation is sufficient. If the controller ECU analyzes the shape of the pedestrian as an adult (taller in stature), the controller ECU controls the pedestrian protection airbag and the bonnet lifter to detonate at the same time. Children are likely to fall on the bonnet and the front windshield at the same time during a collision, so dual-point detonation is required to better protect pedestrians.
[0023] If the controller ECU determines that the vehicle has collided and that the obstacle in front of the vehicle is not a pedestrian, the pedestrian protection airbag and the hood lifter will not be detonated to protect the vehicle.
[0024] In a preferred embodiment of the present invention, the MCU can obtain the distance information between the vehicle and the obstacle by processing the obstacle information collected by the camera, and set the distance as S.
[0025] When used with a camera, an MCU (microcontroller unit) can use image processing techniques to estimate the distance of objects in the image. This typically involves computer vision and image processing algorithms, such as using focal length, the size of the object in the image, and known object dimensions to calculate the distance.
[0026] Specifically, the MCU can process the image captured by the camera and estimate the distance through the following steps: Image acquisition: The camera captures images of the scene, and these images are transmitted to the MCU through the MCU's interface (such as the DCMI interface).
[0027] Image processing: The MCU runs image processing algorithms, such as edge detection and feature extraction, to identify specific objects in the image.
[0028] Distance calculation: Using geometric relationships and the camera's internal parameters (such as focal length, sensor size) and pixel information in the image, the MCU can calculate the distance of the object. For example, if the actual size of the object and the number of pixels it occupies in the image are known, the distance can be estimated through simple triangulation.
[0029] Deep learning: In more advanced applications, the MCU can run deep learning algorithms, such as convolutional neural networks (CNNs), which can identify objects in an image and predict their relative distances from the camera.
[0030] Output: The calculated distance can be used in various applications such as collision avoidance in autonomous driving systems, robot navigation, etc.
[0031] In another preferred embodiment of the present invention, the process by which the controller determines whether to decelerate the vehicle is as follows: first, when the vehicle speed is higher than V1, the safe distance of the vehicle during driving is greater than S1 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; and when the vehicle speed is lower than V1, the safe distance of the vehicle during driving is greater than S2 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; then the controller ECU compares the current vehicle speed V detected by the speed sensor with V1.
[0032] The safety distance S1 when the vehicle speed is higher than V1, and the safety distance S2 when the vehicle speed is lower than V1 can be set according to the specific usage conditions. For example, the safety distance can be appropriately increased in bad weather conditions. For example, when a motor vehicle is driving on a highway, when the speed exceeds 100 kilometers per hour, it should maintain a distance of more than 100 meters from the vehicle in front of it in the same lane; when the speed is lower than 100 kilometers per hour, the distance from the vehicle in front of it in the same lane can be appropriately shortened, but the minimum distance shall not be less than 50 meters. In addition, when encountering meteorological conditions with low visibility, such as fog, rain, snow, dust, hail, etc., the safety distance should be further increased.
[0033] In another preferred embodiment of the present invention, if the current vehicle speed V is higher than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S1. If S is greater than S1, the controller ECU does not react. If S is less than S1, the controller ECU controls the vehicle to actively decelerate. If the current vehicle speed V is lower than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S2. If S is greater than S2, the controller ECU does not react. If S is less than S2, the controller ECU controls the vehicle to actively decelerate.
[0034] It should be noted that the controller ECU can identify whether the vehicle has collided by combining the pressure change information collected by the collision sensor, and the controller ECU can also identify whether the vehicle has collided by combining the obstacle information collected by the camera.
[0035] The controller ECU (Electronic Control Unit) combined with the camera can effectively determine whether the vehicle has collided. This system is usually implemented by real-time monitoring and analysis of the images captured by the camera.
[0036] Image acquisition: The camera captures images of the vehicle's surroundings, and the controller ECU receives and processes these image data.
[0037] Collision detection algorithms: The controller ECU can run specific algorithms (such as deep learning-based object detection algorithms) to identify objects in the image (such as other vehicles, pedestrians, etc.). These algorithms can analyze the size, shape, and relative position of objects to determine whether there is a risk of collision.
[0038] Distance calculation: Through image processing technology, the controller ECU can estimate the distance between the object and the vehicle. If the detected distance is lower than the safety threshold, the system can determine that a collision may occur.
[0039] Real-time reaction: Once the risk of collision is determined, the controller ECU can take immediate action, such as sounding an alarm, automatically braking, or adjusting the vehicle's driving path to avoid the collision.
[0040] If the controller ECU identifies that the vehicle has collided through pressure change information, the controller ECU will not respond directly, but will first determine whether the colliding obstacle is a pedestrian. If it is determined that the collision object is a pedestrian, the controller ECU will control the pedestrian protection airbag or the hood lifter to respond.
[0041] If the controller detects a collision through the camera and the collision object is a pedestrian, the controller ECU can directly control the pedestrian protection airbag or the hood lifter to respond.
[0042] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
[0043] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. Active intelligent pedestrian protection system, including a pedestrian protection airbag arranged at the front windshield of the vehicle, and a hood lifter arranged at the hinge of the engine hood, characterized in that: It also includes a camera, a collision sensor, a vehicle speed sensor, an MCU and a controller ECU; the camera is used to collect obstacle information in front of the vehicle, the collision sensor is used to collect pressure change information on the front bumper beam, and the vehicle speed sensor is used to collect vehicle speed information during driving; the MCU processes the obstacle information collected by the camera, and the controller ECU determines whether to slow down the vehicle based on the processed obstacle information and the collected vehicle speed information. At the same time, the controller ECU also determines whether a collision occurs based on the collected pressure change information on the front bumper beam and the processed obstacle information. If a collision occurs, the controller ECU determines whether the obstacle in front of the vehicle is a pedestrian based on the obstacle information collected by the camera and in combination with a deep learning algorithm; If the controller ECU determines that the vehicle has collided and the obstacle in front of the vehicle is a pedestrian, it controls one or more of the pedestrian protection airbags or the bonnet lifters to detonate. If the controller ECU determines that the vehicle has collided and the obstacle in front of the vehicle is not a pedestrian, it controls neither the pedestrian protection airbag nor the bonnet lifter to detonate, so as to protect the vehicle.
2. The active intelligent pedestrian protection system according to claim 1, characterized in that: The MCU processes the obstacle information collected by the camera to obtain the distance information between the vehicle and the obstacle, and sets the distance as S.
3. The active intelligent pedestrian protection system according to claim 2, characterized in that: The process of the controller determining whether to decelerate the vehicle is as follows: first, when the vehicle speed is higher than V1, the safe distance of the vehicle during driving is greater than S1 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; and when the vehicle speed is lower than V1, the safe distance of the vehicle during driving is greater than S2 in the controller ECU, otherwise, the controller ECU will control the vehicle to actively decelerate; then the controller ECU compares the current vehicle speed V detected by the speed sensor with V1.
4. The active intelligent pedestrian protection system according to claim 3, characterized in that: If the current vehicle speed V is higher than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S1. If S is greater than S1, the controller ECU does not react. If S is less than S1, the controller ECU controls the vehicle to actively decelerate. If the current vehicle speed V is lower than the set vehicle speed V1, the controller ECU compares the distance S between the vehicle and the obstacle with the safety distance S2. If S is greater than S2, the controller ECU does not react. If S is less than S2, the controller ECU controls the vehicle to actively decelerate.
5. The active intelligent pedestrian protection system according to claim 1, characterized in that: The controller ECU can identify whether the vehicle has collided in combination with the pressure change information collected by the collision sensor, and the controller ECU can also identify whether the vehicle has collided in combination with the obstacle information collected by the camera.
6. The active intelligent pedestrian protection system according to claim 5, characterized in that: If the controller ECU identifies that the vehicle has collided through pressure change information, the controller ECU will not react directly, but will first determine whether the colliding obstacle is a pedestrian. If it is determined that the colliding obstacle is a pedestrian, the controller ECU will control the pedestrian protection airbag or the hood lifter to react.
7. The active intelligent pedestrian protection system according to claim 5, characterized in that: If the controller detects a collision through a camera and the collision object is a pedestrian, the controller ECU can directly control the pedestrian protection airbag or the hood lifter to respond.