Pedestrian protection system and method integrating active and passive perception

Abstract

This application relates to the field of automotive safety technology, and in particular to a pedestrian protection system and method that integrates active and passive perception. The system includes: a signal acquisition module for acquiring road scene and vehicle speed data, and identifying pedestrian targets in the road scene; an active algorithm control module for determining whether to trigger an emergency automatic braking function based on the pedestrian target and vehicle speed; an impact intensity acquisition module for acquiring and identifying the impact intensity when the emergency automatic braking function is triggered; a passive algorithm control module for determining whether the impact intensity reaches a preset impact threshold; and an actuator for triggering the active detonation system if the impact intensity does not meet the preset impact threshold. This solves the problems of false detonation in existing passive perception methods, where the system cannot accurately identify a person when the impact energy is comparable to that of other objects, and false triggering leads to significant maintenance costs.

Description

Technical Field

[0001] This application relates to the field of automotive safety technology, and in particular to a pedestrian protection system and method that integrates active and passive perception. Background Technology

[0002] With the increasing number of motor vehicles, pedestrian accidents have become a prominent social problem. Developed countries in Europe and America have taken the lead in initiating research on pedestrian protection and promulgating relevant regulations and evaluation procedures to guide vehicle manufacturers to pay more attention to pedestrian safety and fully consider the severity of pedestrian accidents in their designs. Domestic safety agencies have also successively promulgated relevant evaluation procedures (such as the China New Car Assessment Program (C-NCAP), the China Insurance Automotive Safety Index (C-IASI), and GB 24550 (effective from January 1, 2025). Research on pedestrian accident injuries shows that disabling and fatal injuries are mainly caused by vehicles hitting pedestrians' heads and legs, especially the head, which can lead to serious injury or death if it hits the vehicle's hard structure. To improve the protection of pedestrian heads, active hood systems have been developed. These systems sense the occurrence of pedestrian accidents and, through ECU control, issue a trigger command to ignite a lifting system hidden under the hood system, raising the space in a designated area to achieve better cushioning and reduce pedestrian head injuries.

[0003] Traditional active hood systems primarily rely on passive methods to detect pedestrians, issuing commands based on the intensity of contact with the pedestrian. However, this approach has several weaknesses: passive detection can lead to false triggering. When the impact energy of a person is comparable to that of other objects, the system may fail to accurately identify the person, resulting in significant repair costs. Furthermore, in situations where a collision with a small animal like a dog or cat, or a basketball or soccer ball, can cause the system to malfunction and trigger an unexpected hood, requiring replacement of the hood, lift, and front exterior trim, incurring repair costs of several thousand yuan. This creates an unpleasant experience for drivers and passengers, leading to customer complaints. Summary of the Invention

[0004] This application provides a pedestrian protection system and method that integrates active and passive sensing to solve the problems of false detection in existing passive sensing methods, namely, when the impact energy of a person is comparable to that of other objects, the system cannot accurately identify the person, and false triggering of the system will lead to large maintenance costs.

[0005] The first aspect of this application provides a pedestrian protection system that integrates active and passive sensing, comprising: The signal acquisition module is used to acquire road scene and vehicle speed, and to identify pedestrian targets in the road scene; An active algorithm control module is used to determine whether to trigger the emergency automatic braking function based on the pedestrian target and the vehicle speed. The impact intensity acquisition module is used to acquire and identify the impact intensity when the emergency automatic braking function is triggered. A passive algorithm control module is used to determine whether the impact intensity reaches a preset impact threshold. An actuator is used to trigger an active shielding system if the impact intensity is not a preset impact threshold.

[0006] Optionally, the signal acquisition module includes: Radar and / or cameras are used to capture road scenes; and A speed sensor is used to collect vehicle speed data. An advanced driver assistance system is used to identify whether there are pedestrian targets in the road scene.

[0007] Optionally, the advanced driver assistance system includes: The background modeling unit is used to extract target features from the foreground motion in the road scene to obtain the background modeling result; A reference background unit is used to compare the background modeling results with a standard reference background based on a pre-built classifier to identify whether there are pedestrian targets in the road scene.

[0008] Optionally, the active algorithm control module includes: The collision risk value is calculated based on the pedestrian target and the vehicle speed, and the collision risk value is compared with a preset collision risk threshold. If the collision risk value is greater than or equal to the preset collision risk threshold, the emergency automatic braking function is triggered to reduce the vehicle speed until it comes to a stop.

[0009] Optionally, the impact intensity acquisition module includes: The pressure sensor tube is used to distinguish the human body from other objects by the pressure waveform and intensity when the emergency automatic braking function is triggered. An acceleration sensor is used to distinguish pedestrians from other impacts by impact acceleration when the emergency automatic braking function is triggered. Elastic wave sensors are used to distinguish the human body from other objects by measuring the changes in the waveform and intensity of elastic waves.

[0010] Optionally, the pressure sensor tube is a long, narrow, sealed tube, with a pressure sensor at each end.

[0011] A second aspect of this application provides a pedestrian protection method that integrates active and passive sensing, comprising the following steps: Collect road scene data and vehicle speed data, and identify pedestrian targets in the road scene; Determine whether to trigger the emergency automatic braking function based on the pedestrian target and the vehicle speed; When the emergency automatic braking function is triggered, the impact intensity is collected and identified, and it is determined whether the impact intensity reaches the preset impact threshold. If the impact intensity is not at the preset impact threshold, the active shielding system is triggered.

[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the pedestrian protection method of active and passive perception fusion as described in the above embodiments.

[0013] A fourth aspect of the present invention provides a computer program product, which, when executed by a processor, implements the pedestrian protection method of active and passive perception fusion as described above.

[0014] A fifth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described pedestrian protection method integrating active and passive perception.

[0015] The pedestrian protection system and method based on active and passive perception fusion proposed in this application, on the basis of traditional active shielding systems, intervenes in pedestrian perception in advance before a collision by fusing signals from cameras and radar to reduce the probability of false triggering. It uses an active and passive fusion algorithm to determine the process of pedestrian collision accidents and links it with AEB braking to reduce vehicle speed, avoid accidents or reduce the impact speed, so as to minimize pedestrian injury. When a collision is unavoidable, the active shielding system is triggered to achieve good buffering and reduce pedestrian head injury.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a block diagram of a pedestrian protection system that integrates active and passive sensing according to an embodiment of this application. Figure 2 This is a schematic diagram of a pedestrian protection system that integrates active and passive sensing according to an embodiment of this application. Figure 3 This is a flowchart of an active and passive sensing process provided according to an embodiment of this application; Figure 4 This is a vehicle layout diagram of a pedestrian protection system that integrates active and passive perception according to an embodiment of this application. Figure 5 This is a schematic diagram illustrating the development requirements of an active pop-up airbag / pedestrian airbag system according to an embodiment of this application; Figure 6 This is a flowchart illustrating the discrimination process of a pedestrian / bicycle collision event by an active sensing system according to an embodiment of this application. Figure 7 This is a schematic diagram illustrating the working principle of an active sensing system according to an embodiment of this application; Figure 8 This is an example diagram of a visual image processing method provided according to an embodiment of this application; Figure 9 This is an example diagram of a passive pressure sensing tube structure provided according to an embodiment of this application; Figure 10 This is a diagram illustrating the arrangement and development of a passive sensing sensor according to an embodiment of this application. Figure 11 This is an example diagram of a development logic diagram for passive sensing according to an embodiment of this application; Figure 12 This is an example diagram of a passive sensing development matrix provided according to an embodiment of this application; Figure 13 This is an example diagram of a passively sensed pressure curve provided according to an embodiment of this application; Figure 14 This is a flowchart of a passive sensing signal processing method according to an embodiment of this application; Figure 15 This is a schematic diagram illustrating the development of a passive sensing system algorithm according to an embodiment of this application; Figure 16 This is a schematic diagram illustrating the collaborative principle of a sensing system and an execution system according to an embodiment of this application. Figure 17 This is a flowchart of a pedestrian protection method that integrates active and passive sensing according to an embodiment of this application; Figure 18 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0018] Explanation of reference numerals in the attached figures: 100 - Pedestrian protection system integrating active and passive perception; 101 - Signal acquisition module; 102 - Active algorithm control module; 103 - Impact intensity acquisition module; 104 - Passive algorithm control module; 105 - Actuator; 901 - Pressure tube; 902 - Sensor; 1001 - Pressure tube cross-section; 1002 - Front bumper beam foam; 1003 - Front bumper beam; 1004 - Vehicle front exterior trim; 1005 - Vehicle lower support; 1006 - Engine hood outer panel; 1007 - Engine hood inner panel; 1008 - Engine hood latch; 3001 - Reference ground line; 3002 - Centerline of PDI-2 collider; 3003 - Height of pressure tube sensor; 4001 - First contact point between PDI-2 collider and vehicle front exterior trim; 1801 - Memory; 1802 - Processor; 1803 - Communication interface. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0020] The pedestrian protection system and method integrating active and passive perception according to embodiments of this application are described below with reference to the accompanying drawings.

[0021] Figure 1 This is a block diagram of a pedestrian protection device that integrates active and passive sensing, provided as an embodiment of this application.

[0022] like Figure 1 As shown, the pedestrian protection device 100, which integrates active and passive perception, includes: a signal acquisition module 101, an active algorithm control module 102, an impact intensity acquisition module 103, a passive algorithm control module 104, and an actuator 105.

[0023] The system includes a signal acquisition module 101 for acquiring road scene and vehicle speed data, and for identifying pedestrian targets within the road scene. An active algorithm control module 102 determines whether to trigger the emergency automatic braking function based on the pedestrian target and vehicle speed. An impact intensity acquisition module 103 acquires and identifies the impact intensity when the emergency automatic braking function is triggered. A passive algorithm control module 104 determines whether the impact intensity reaches a preset impact threshold. An actuator 105 triggers the active braking system based on whether the impact intensity meets the preset impact threshold.

[0024] In actual implementation, such as Figure 2As shown, in this embodiment of the application, radar and / or cameras in the Advanced Driver Assistance System (ADAS) are used for scene recognition, and speed is recognized using a speed sensor. Collision prediction can then be performed based on the scene recognition results and speed recognition, i.e., active algorithm threshold judgment is performed to determine whether to trigger the Automatic Emergency Braking (AEB) function. If the AEB function is triggered, the speed is reduced or stopped to reduce the probability of collision or the collision energy, thereby mitigating the damage from the collision accident. If a non-pedestrian is identified, the active airbag system is turned off, and the impact intensity is identified using pressure / acceleration / elastic wave sensors. Then, passive algorithm threshold judgment is performed to determine whether a preset impact threshold has been reached. If it has been reached, the pedestrian airbag lifting system is triggered.

[0025] In some embodiments, the signal acquisition module 101 includes: Radar and / or cameras are used to capture road scenes; and A speed sensor is used to collect vehicle speed data. Advanced driver assistance systems are used to identify whether pedestrian targets are present in a road scene.

[0026] In some embodiments, the advanced driver assistance system includes: The background modeling unit is used to extract target features from the foreground motion in the road scene to obtain the background modeling result; A reference background unit is used to compare the background modeling results with a standard reference background based on a pre-built classifier to identify whether there are pedestrian targets in the road scene.

[0027] In actual implementation, such as Figure 3 As shown, in this embodiment of the application, road scene images are acquired through visual acquisition hardware, such as radar and cameras, to input image sequences into subsequent stages; target features are extracted (i.e. scene recognition) of foreground motion in the road scene to obtain background modeling results; based on a classifier, the acquired background modeling results are compared with a standard reference background to determine the attributes of the target object, i.e., whether it contains pedestrians.

[0028] It should be noted that during the target feature extraction process, it is necessary to adapt to changes in the environment (such as changes in image color caused by changes in lighting), camera shake causing image shake (such as movement when taking a handheld photo), densely appearing objects in the image (such as densely appearing objects like leaves or tree trunks, which must be detected correctly), and changes in background objects (such as newly parked cars must be classified as background objects in a timely manner, and objects that have started to move from a stationary position also need to be detected in a timely manner), as well as the ghost regions that often appear in object detection.

[0029] A classifier extracts the most discriminative information from an image for judgment and classification. The purpose of classification is to confirm whether a pedestrian target exists in the candidate window, which is generally accomplished by designing a pedestrian template. The construction and implementation of a classifier generally involves the following steps: (1) Select samples (including positive and negative samples) and divide all samples into training samples and test samples. (2) Execute the classifier algorithm on the training samples to generate a classification model. (3) Execute the classification model on the test samples to generate prediction results. (4) Calculate the necessary evaluation indicators based on the prediction results to evaluate the performance of the classification model. The classifier is trained using deep learning to improve detection efficiency. It is also updated online based on the results of image discrimination and machine learning.

[0030] Furthermore, wheel speed sensors are generally placed on the wheels and partially on the transmission to identify and record vehicle speed. These speeds, along with pedestrian target results, are input into the active algorithm control module 102 for active algorithm threshold discrimination.

[0031] In some embodiments, the impact intensity acquisition module 103 includes: The pressure sensor tube is used to distinguish the human body from other objects by the pressure waveform and intensity when the emergency automatic braking function is triggered. An acceleration sensor is used to distinguish pedestrians from other impacts by impact acceleration when the emergency automatic braking function is triggered. Elastic wave sensors are used to distinguish the human body from other objects by measuring the changes in the waveform and intensity of elastic waves.

[0032] In some embodiments, the pressure sensor tube is a long, narrow, sealed tube, with a pressure-sensing sensor 902 at each end.

[0033] In practical applications, three types of sensors, or combinations thereof, are currently used for pedestrian collision intensity detection. These sensors include pressure tube sensors, accelerometers, and elastic wave sensors, as well as combinations thereof. Accelerometers distinguish pedestrians from other impacts based on impact acceleration. Pressure tube sensors differentiate between humans and other objects by measuring the pressure waveform and intensity through a squeezed stress tube. Elastic wave sensors differentiate between humans and other objects by measuring the changes in elastic wave waveform and intensity. By setting certain thresholds and algorithms, the system identifies whether a pedestrian impact occurred and whether the impact intensity reached the set threshold, thereby determining whether the system was functioning correctly.

[0034] Specifically, such as Figure 4As shown, the accelerometer is positioned on the inner plane of the front bumper skin and fastened to it. Its main purpose is to detect the acceleration signal of an impact. The pressure tube sensor consists of a slender elastic tube connected to sensors at both ends; the pressure tube sensor is positioned between the front bumper foam and the front section of the anti-collision beam. The pressure tube is generally embedded in a slot in the front bumper foam. When an impact occurs, the pressure tube deforms with the foam, generating a pressure signal. The strength of the pressure signal can be used as a judgment input for the system's operation. The elastic wave sensor is a new type of sensor that can be placed on the vehicle's exterior trim, giving the vehicle body tactile sensing capabilities similar to human skin. When an impact is received, it identifies pedestrians by analyzing the elastic wave waveform and intensity.

[0035] After a collision event is detected, the signals acquired by the aforementioned sensing hardware are input to the vehicle computing platform to determine whether the active pop-up hood system should be detonated.

[0036] In some embodiments, the active algorithm control module 102 includes: The collision risk value is calculated based on the pedestrian target and the vehicle speed, and then compared with the preset collision risk threshold. If the collision risk value is greater than or equal to the preset collision risk threshold, the emergency automatic braking function is triggered to reduce the vehicle speed until it comes to a stop.

[0037] In actual execution, both the active algorithm control module 102 and the passive algorithm control module 104 are integrated on the vehicle computing platform. They compare the collected signals with the judged algorithm thresholds. If the threshold is exceeded, the relevant functions are activated; if the threshold is not reached, the system does not function.

[0038] Specifically, the active algorithm threshold judgment process of the active algorithm control module 102 is as follows: it mainly compares the scene with radar and cameras, comprehensively considering whether the target object is a pedestrian or a two-wheeled vehicle rider, the relative distance, and the relative speed to determine the probability of an accident. If a collision risk is found, the AEB system is activated to reduce the vehicle speed; the same signal is output to the AEB deceleration judgment module to determine whether braking can be stopped. If braking can be stopped, the active algorithm is turned off and the event is closed.

[0039] Furthermore, the passive algorithm threshold discrimination process of the passive algorithm control module 104 is as follows: the pressure tube 901, acceleration, and elastic wave sensor are all based on contact measurement of collision intensity. When the intensity reaches a certain threshold, the on-board computing platform determines whether the system action threshold has been reached. If it is reached, the hood is raised / the airbag is deployed to provide buffer protection for the pedestrian. If the system does not reach the collision intensity threshold, the system does not act (at this time, either the target object is not a human body, or the collision intensity is insufficient to cause death or injury).

[0040] Furthermore, in this embodiment of the invention, the actuator 105 acts as a device that can cushion the human body through actions such as lifting or detonating vehicle components. The actuator 105 includes a front pedestrian airbag, a rear edge pedestrian airbag, an active pop-up airbag, or one or more combinations thereof.

[0041] like Figure 5 As shown, the development of actuator 105 must meet the following technical requirements: HIT <TRT,TRT=ST+DT。

[0042] In the formula, HIT stands for Head Impact Time, which is the time required for a pedestrian / bicycle rider's head to collide with the vehicle; TRT stands for Total Responsibility Time, which refers to the action time of the pedestrian protection system, including perception time and execution time; ST stands for Sensor Time, which refers to the system's perception time, i.e., the time it takes for passive perception to distinguish between human and non-human bodies; DT stands for Deployment Time, which refers to the time it takes for the system to act at the designed position after receiving the detonation / action command from the onboard computing platform; for pedestrian airbags, it is the deployment time.

[0043] The following is a detailed description of the pedestrian protection system based on the fusion of active and passive perception proposed in this application, through a specific embodiment.

[0044] (1) The acquisition process of active signal sensing is as follows: like Figure 6 As shown, when the vehicle is driving on the road, the scene recognition hardware reuses the radar and camera in the advanced driver assistance system (ADAS) to collect road scene data in real time, obtain the risk of pedestrians / two-wheeled cyclists crossing the road, and input the relevant collected data into the intelligent driving computing platform for the system to judge the risk of collision accidents. The collected signals are transmitted by the sensors to the pedestrian detection module (i.e., the active algorithm control module 102) in the intelligent driving computing platform. The probability of collision events is judged according to the set threshold algorithm. When a pedestrian collision event is detected, the signal is input to the converter, which converts the signal into an ignition electrical signal and outputs it to the actuator 105.

[0045] The active sensing signal triggers the AEB-controlled braking system to reduce speed. At this time, the intelligent driving computing platform determines the collision time TTC based on distance and executes braking action; if the distance allows for stopping, the pedestrian protection system is deactivated; if braking fails to bring the vehicle to a stop, the passive pedestrian sensing system is activated.

[0046] like Figure 7As shown, this system recommends using a multi-sensor fusion algorithm to fuse visual signals, radar, wheel speed signals, and traffic control signals. The fused signals are then input to the intelligent driving computing platform to determine the relative positions of pedestrians and vehicles, vehicle speed, and other fusion control parameters. The results are then output to the intelligent driving computing platform for decision-making.

[0047] It should be noted that LVDS lines are used to transmit low-voltage differential signals, short for Low-Voltage Differential Signaling. This technology is a low-power, low-error-rate, low-crosstalk, and low-radiation differential signaling technology that can transmit data at extremely high speeds. Its core lies in using extremely low voltage swings for high-speed differential transmission.

[0048] CAN, short for Controller Area Network, is a serial communication network used to achieve distributed real-time control. Developed by Bosch in Germany, CAN primarily addresses the data exchange issues between numerous control and testing instruments in modern automobiles.

[0049] (2) The process of active perception, recognition, and decision-making is as follows: like Figure 8 As shown, the image recognition-based deep learning approach is divided into two modules: online pedestrian detection and online detector training and updating. The online pedestrian detection module identifies pedestrians through acquired image sequences; pedestrian detection can be defined as determining whether an input image or video frame contains pedestrians, and if so, detecting them and outputting the result.

[0050] (3) The passive sensing signal acquisition process is as follows: like Figure 9 As shown, the passive sensing signal is mainly used to detect contact energy online when it is determined that AEB intervention is still unable to avoid a collision. Acceleration signals are generally placed on the vehicle exterior, such as the front bumper cover. It is important to ensure that their orientation is aligned with the vehicle coordinate system plane to guarantee that their output signal is in the standard vehicle coordinate system direction. Currently used pedestrian protection systems typically recommend 2-3 acceleration sensors, generally used as auxiliary signals to the pressure signal. That is, the pressure signal is the primary signal, and when the pressure signal is insufficient to distinguish pedestrians, acceleration is added as an auxiliary discrimination signal.

[0051] like Figure 9 As shown, the pressure tube sensor structure is a long, thin, sealed tube with a sensor 902 at each end for sensing pressure.

[0052] like Figure 10As shown, the pressure tube sensor is generally positioned between the anti-collision beam foam and the anti-collision crossbeam. To protect the pressure tube 901, the tubular object is typically embedded in a groove at the rear of the anti-collision beam foam. Its working principle is as follows: when a human leg (the figure uses a PDI-2 impactor designated by the testing and evaluation agency to represent a human body) collides with the vehicle, the front exterior trim 1004 of the vehicle is impacted and shifts backward, directly compressing the anti-collision beam foam 1002. The foam then compresses the pressure tube cross-section 1001 embedded at the rear of the foam. Due to the pressure on the gas within the pressure tube cross-section 1001, a pressure change occurs within the sensor at the corresponding location. The pressure sensor then identifies the pressure change and determines whether the impact was on a pedestrian or another object by obtaining the intensity in the time domain from the pressure curve. (4) The passive perception, recognition, and decision-making process is as follows: To differentiate between pedestrians and cyclists, the development process requires extracting scenarios from road accidents and establishing a system action / non-action decision-making strategy. For example... Figure 11 As shown, the identified targets include non-explosive targets such as basketballs, small stones, branches, birds, soccer balls, and small animals; high-intensity collision targets such as pillars, vehicles, and walls; and roadside warning signs, poles, and trash cans. The detonation range uses PDI-2 as the low detonation threshold and PLI collider as the high detonation threshold. By collecting the pressure and acceleration signals from the aforementioned colliders, a development strategy matrix based on mass-impact intensity is established. Finally, the above strategy is implemented through algorithm development.

[0053] A general development strategy should take the following information into account: The collider categories, as shown above, distinguish between human and non-human entities; For collision speeds, 4-5 interval speeds are typically set between 25km / h and 55km / h to obtain pressure signals at different speeds. The ambient temperature should generally be set within the range of -40℃ to 40℃, including at least several temperature intervals such as low temperature, room temperature, and high temperature. Vehicle status is generally set to two states: moving and stationary.

[0054] like Figure 12 As shown, the algorithm development matrix covers different speeds, positions, colliders, temperatures, vehicle states, etc.

[0055] The development matrix must meet the requirements of evaluation procedures such as GB24550, C-NCAP, and C-IASI on the one hand, and take into account the actual use scenarios of actual action / false action to minimize the risk of false explosion of the system.

[0056] like Figure 13As shown, taking the distinction between the two most difficult-to-distinguish signals, PDI-2 and small animal signals, as an example, the peak position and peak value of the human pressure signal represented by PDI-2 are both higher than those of small animals to satisfy the distinction between ignition and non-ignition. For example... Figure 14 As shown, the collected pressure curves need to be processed as follows: Data filtering / sampling: The raw data collected cannot be used directly and the curve needs to be smoothed and filtered. It is recommended to use the SAE method to filter and remove spikes and interference signals. Data transformation: In order to improve the efficiency of the algorithm threshold discrimination, the data is transformed by integration and logarithm to convert the curve performance into a value representing the collision intensity, which is updated online as time changes. Numerical classification: The converted data is classified according to velocity, intensity level, etc., to generate impact energy value points; Boundary solution: refers to the comprehensive value determined by taking into account factors such as velocity and collision intensity. This value is used for comparison with the detonation threshold. Decision-making: Generally, algorithms set dynamic threshold channels, such as... Figure 15 As shown, the generated pressure signal is converted and compared with a threshold value. Once the detonation condition is met, an execution signal is issued to activate the passive safety system (airbags, lifters) to protect pedestrians. Figure 16 As shown. The threshold of this system is dynamically adjusted, and it is determined based on the relative speed (vehicle speed) at the time of collision. If the speed is low, the detonation threshold is dynamically increased; if the relative speed is high, the detonation threshold is decreased to achieve the best system protection effect.

[0057] (5) The execution process under active perception conditions is as follows: Under active perception conditions, the recognition triggers the execution system to brake and reduce speed; under certain conditions, steering control can be integrated to reduce vehicle speed and avoid collisions, thereby preventing accidents or reducing the severity of accidents.

[0058] The deceleration is achieved by AEB, which uses wheel speed sensors to predict the degree of deceleration until the vehicle comes to a complete stop. If the vehicle cannot stop, the predicted impact speed is input into the intelligent driving computing platform to assist the passive safety system in taking action.

[0059] Specifically, when a pedestrian / two-wheeled vehicle collision event is detected, the AEB system slows down the vehicle; this can be extended to the intelligent driving system intervening in the steering wheel to achieve directional avoidance.

[0060] (6) The execution process under passive perception conditions is as follows: Execution under passive perception means that when avoidance and braking cannot prevent the accident, the pressure tube / accelerometer is used to identify whether it is a pedestrian collision and whether the impact intensity has reached the detonation threshold. Specifically, for pedestrian collision accidents, 20-25 km / h is set as the minimum detonation speed of the system.

[0061] The passive sensing system adaptively activates the pedestrian airbag and active pop-up shield system based on the impact intensity. The pedestrian airbag enables soft contact between the pedestrian and the vehicle, while the active pop-up shield system increases the space between the pedestrian's head and the hard points under the vehicle (engine, transmission, battery, vehicle rigid structure, etc.), providing sufficient space for buffering and reducing the risk of pedestrian death or injury.

[0062] Specifically, pedestrian airbags include vehicle front airbags and windshield front airbags, etc. Their working principle is the same as that of passenger airbags, using a rapidly inflated bag structure to cushion pedestrians; the active pop-up hood main actuator 105 consists of a lifter and an active hinge. When it receives an ignition command, the lifter pops up and forces the active hinge to open in the opposite direction, releasing the buffer space in the designated area; generally speaking, the existing lifting positions mainly include several structural forms such as rear lifting of the hood, front lifting of the hood, and simultaneous front and rear lifting, and the specific needs to be determined in combination with the protection strategy.

[0063] In summary, the pedestrian protection system based on the active and passive perception fusion proposed in this application, on the basis of the traditional active shielding system, intervenes in pedestrian perception in advance before a collision by fusing signals from cameras and radar to reduce the probability of false triggering. It uses an active and passive fusion algorithm to determine the process of a pedestrian collision accident and links it with AEB braking to reduce vehicle speed, avoid the accident or reduce the impact speed, so as to minimize pedestrian injury. When a collision is unavoidable, the active shielding system is triggered to achieve good buffering and reduce pedestrian head injury.

[0064] Next, referring to the accompanying drawings, a pedestrian protection method integrating active and passive perception proposed according to an embodiment of this application is described.

[0065] Figure 17 This is a flowchart illustrating a pedestrian protection method that integrates active and passive sensing, as provided in an embodiment of this application.

[0066] like Figure 17 As shown, the pedestrian protection method that integrates active and passive perception includes the following steps: In step S1701, the road scene and vehicle speed are collected, and pedestrian targets in the road scene are identified.

[0067] In step S1702, it is determined whether to trigger the emergency automatic braking function based on the pedestrian target and the vehicle speed.

[0068] In step S1703, when the emergency automatic braking function is triggered, the impact intensity is collected and identified, and it is determined whether the impact intensity reaches the preset impact threshold.

[0069] In step S1704, the active shielding system is triggered, depending on whether the impact intensity has a preset impact threshold.

[0070] It should be noted that the foregoing explanation of the pedestrian protection device embodiment with active and passive perception fusion also applies to the pedestrian protection method with active and passive perception fusion in this embodiment, and will not be repeated here.

[0071] According to the pedestrian protection method based on active and passive perception fusion proposed in the embodiments of this application, on the basis of the traditional active shielding system, pedestrian perception is intervened in advance before the collision by fusing signals from cameras and radar to reduce the probability of false triggering. The active and passive fusion algorithm is used to determine the process of pedestrian collision accident and is linked with AEB braking to reduce vehicle speed, avoid the occurrence of accident or reduce the impact speed, so as to minimize pedestrian injury. When the collision is unavoidable, the active shielding system is triggered to achieve good buffering and reduce pedestrian head injury.

[0072] Figure 18 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0073] The electronic device may include: a memory 1801, a processor 1802, and a computer program stored on the memory 1801 and executable on the processor 1802.

[0074] When the processor 1802 executes the program, it implements the pedestrian protection method of active and passive perception fusion provided in the above embodiments.

[0075] Furthermore, electronic devices also include: Communication interface 1803 is used for communication between memory 1801 and processor 1802.

[0076] Memory 1801 is used to store computer programs that can run on processor 1802.

[0077] The memory 1801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0078] If the memory 1801, processor 1802, and communication interface 1803 are implemented independently, then the communication interface 1803, memory 1801, and processor 1802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 18 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0079] Optionally, in a specific implementation, if the memory 1801, processor 1802, and communication interface 1803 are integrated on a single chip, then the memory 1801, processor 1802, and communication interface 1803 can communicate with each other through an internal interface.

[0080] The processor 1802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0081] This invention also provides a computer program product, which, when executed by a processor, implements the above-described pedestrian protection method that integrates active and passive perception.

[0082] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described pedestrian protection method that integrates active and passive perception.

[0083] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0084] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0085] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0087] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0088] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0089] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0090] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A pedestrian protection system integrating active and passive sensing, characterized in that, include: The signal acquisition module is used to acquire road scene and vehicle speed, and to identify pedestrian targets in the road scene; An active algorithm control module is used to determine whether to trigger the emergency automatic braking function based on the pedestrian target and the vehicle speed. The impact intensity acquisition module is used to acquire and identify the impact intensity when the emergency automatic braking function is triggered. A passive algorithm control module is used to determine whether the impact intensity reaches a preset impact threshold. An actuator is used to trigger an active shielding system if the impact intensity is not a preset impact threshold.

2. The pedestrian protection system integrating active and passive sensing according to claim 1, characterized in that, The signal acquisition module includes: Radar and / or cameras are used to capture road scenes; and A speed sensor is used to collect vehicle speed data. An advanced driver assistance system is used to identify whether there are pedestrian targets in the road scene.

3. The pedestrian protection system integrating active and passive sensing according to claim 2, characterized in that, The advanced driver assistance system includes: The background modeling unit is used to extract target features from the foreground motion in the road scene to obtain the background modeling result; A reference background unit is used to compare the background modeling results with a standard reference background based on a pre-built classifier to identify whether there are pedestrian targets in the road scene.

4. The pedestrian protection system integrating active and passive sensing according to claim 1, characterized in that, The active algorithm control module includes: The collision risk value is calculated based on the pedestrian target and the vehicle speed, and the collision risk value is compared with a preset collision risk threshold. If the collision risk value is greater than or equal to the preset collision risk threshold, the emergency automatic braking function is triggered to reduce the vehicle speed until it comes to a stop.

5. The pedestrian protection system integrating active and passive sensing according to claim 1, characterized in that, The impact intensity acquisition module includes: The pressure sensor tube is used to distinguish the human body from other objects by the pressure waveform and intensity when the emergency automatic braking function is triggered. An acceleration sensor is used to distinguish pedestrians from other impacts by impact acceleration when the emergency automatic braking function is triggered. Elastic wave sensors are used to distinguish the human body from other objects by measuring the changes in the waveform and intensity of elastic waves.

6. The pedestrian protection system integrating active and passive sensing according to claim 5, characterized in that, The pressure sensor tube is a long, thin, sealed tube with a pressure sensor at each end.

7. A pedestrian protection method integrating active and passive sensing, characterized in that, The pedestrian protection system employing the active and passive sensing fusion as described in any one of claims 1-6 includes the following steps: Collect road scene data and vehicle speed data, and identify pedestrian targets in the road scene; Determine whether to trigger the emergency automatic braking function based on the pedestrian target and the vehicle speed; When the emergency automatic braking function is triggered, the impact intensity is collected and identified, and it is determined whether the impact intensity reaches the preset impact threshold. If the impact intensity is not at the preset impact threshold, the active shielding system is triggered.

8. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the pedestrian protection method of active and passive perception fusion as described in claim 7.

9. A computer program product, characterized in that, When the computer program / instruction is executed by the processor, it implements the pedestrian protection method of active and passive perception fusion as described in claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the pedestrian protection method of active and passive perception fusion as described in claim 7.

Images