Collision detection method and apparatus

Abstract

The present application relates to the technical field of autonomous driving. Provided are a collision detection method and apparatus, which are used for improving the accuracy of contact collision detection. The method comprises: acquiring first environmental data collected by a first sensor in a terminal device; receiving a first signal from a signal amplification module; and on the basis of the first signal and a first threshold value, determining whether a collision has occurred for the terminal device, wherein when the first environmental data meets a first condition, an amplification factor of the signal amplification module and / or the first threshold value are adjusted values / is an adjusted value. In this solution, current environment information is determined on the basis of the first environmental data collected by the first sensor, such that when the first condition is met, the amplification factor or the first threshold value can be adjusted, thereby enhancing the signal detection capability, improving the detection capability for a weak collision signal, and reducing the false detection rate.

Description

A collision detection method and apparatus Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a collision detection method and apparatus. Background Technology

[0002] Collision detection can be categorized into two types based on whether a collision has occurred: non-contact collision detection and contact collision detection. Non-contact collision detection aims to prevent collisions from happening, while contact collision detection detects collisions and initiates emergency actions upon detection. Contact collision detection is used during vehicle operation to make a rapid and accurate judgment when a vehicle hits a pedestrian, enabling emergency braking to avoid secondary injuries and significantly reduce the injury rate. Currently, contact collision detection primarily utilizes piezoelectric sensors to achieve passive defense, quickly detecting a collision after it occurs and preventing secondary injuries through emergency braking.

[0003] However, contact collision detection is susceptible to scene interference. Piezoelectric sensors (such as elastic wave sensors) have an internal structure of piezoelectric ceramics. When going over speed bumps, the vehicle body vibrates and deforms, generating a signal. Additionally, audio can cause resonance in the vehicle's casing, also triggering a signal from piezoelectric sensors. However, these deformations and resonances are not caused by a collision, but they are very similar in characteristics from a sensor perspective, making them difficult to distinguish.

[0004] Summary of the Invention

[0005] This application provides a collision detection method and apparatus to improve the accuracy of contact collision detection.

[0006] Firstly, a collision detection method is provided. The method includes acquiring first environmental data collected by a first sensor in a terminal device, the first environmental data representing the environmental information of the terminal device. A first signal is received from a signal amplification module in the terminal device, the first signal being amplified by a second sensor in the terminal device. Based on the first signal and a first threshold, it is determined whether a collision has occurred in the terminal device. Wherein, when the first environmental data satisfies a first condition, the amplification factor of the signal amplification module and / or the first threshold are adjusted values.

[0007] Based on the above scheme, the current environmental information is determined based on the first environmental data collected by the first sensor. Thus, when the first condition is met, the amplification factor and / or the first threshold can be adjusted to enhance the signal detection capability, improve the detection capability of small collision signals, and reduce the false detection rate.

[0008] In one possible implementation, the first sensor includes a camera and / or a pyroelectric sensor. When a living being is detected from the first environmental data, the magnification is increased to the desired value. And / or, when a living being is detected from the first environmental data, the first threshold is decreased to the desired value. Based on the above scheme, when a living being is detected in the environment, the magnification can be increased and / or the first threshold can be decreased, thereby improving collision detection sensitivity.

[0009] In one possible implementation, when the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the magnification is the increased value. And / or, when the first environmental data indicates that the speed of the terminal device is less than or equal to the first value, the first threshold is the decreased value. Based on the above scheme, increasing the magnification and / or decreasing the first threshold at low vehicle speeds can improve the perception sensitivity during minor collisions and increase the detection success rate.

[0010] In one possible implementation, when the first environmental data indicates that the speed of the terminal device is greater than or equal to a second value, the amplification factor is reduced. And / or, when the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the first threshold is increased. Based on the above scheme, reducing the amplification factor and / or increasing the first threshold when the vehicle speed is high reduces the probability of false alarms.

[0011] In one possible implementation, the camera on the terminal device is activated when a living being is detected from the initial environmental data. Based on this solution, the camera can be activated when a living being approaches, which can improve the detection success rate in scenarios such as a living being bumping into a vehicle (e.g., scratching it).

[0012] In one possible implementation, the first sensor includes a pyroelectric sensor. Based on the above scheme, by adding a pyroelectric sensor, it is possible to detect whether a living being is approaching, and activate the camera in advance for sentinel detection.

[0013] In one possible implementation, second environmental data is acquired from a pyroelectric sensor in the terminal device. When a living being is detected from the second environmental data, the camera of the terminal device is activated. Based on the above solution, by adding a pyroelectric sensor, it is possible to sense whether a living being is approaching, activate the camera in advance, and perform sentinel detection, which can improve the detection success rate in scenarios such as a living being bumping into a vehicle (e.g., scratching a car).

[0014] In one possible implementation, the first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

[0015] In one possible implementation, the second sensor includes a piezoelectric sensor.

[0016] In one possible implementation, the first and second sensors are deployed together. Based on the above scheme, the first and second sensors can be deployed together, thereby reducing cable and material costs, jointly collecting data, and achieving hard synchronization.

[0017] Secondly, a collision detection device is provided, comprising: a processing unit and a transceiver unit.

[0018] The processing unit is used to acquire first environmental data collected by a first sensor in the terminal device, the first environmental data representing the environmental information of the terminal device. The transceiver unit is used to receive a first signal from a signal amplification module in the terminal device, the first signal being amplified by a second sensor in the terminal device. The processing unit is also used to determine whether a collision has occurred in the terminal device based on the first signal and a first threshold. Wherein, when the first environmental data meets a first condition, the amplification factor of the signal amplification module and / or the first threshold are adjusted values.

[0019] In one possible implementation, the first sensor includes a camera and / or a pyroelectric sensor, and when a living being is detected from the first environmental data, the magnification is the enhanced value. And / or, when a living being is detected from the first environmental data, the first threshold is the reduced value.

[0020] In one possible implementation, when the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the amplification factor is the increased value. And / or, when the first environmental data indicates that the speed of the terminal device is less than or equal to the first value, the first threshold is the decreased value.

[0021] In one possible implementation, when the first environmental data indicates that the speed of the terminal device is greater than or equal to a second value, the amplification factor is the reduced value. And / or, when the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the first threshold is the increased value.

[0022] In one possible implementation, the processing unit is also used to: activate the camera of the terminal device when a living being is detected from the first environmental data.

[0023] In one possible implementation, the first sensor includes a pyroelectric sensor.

[0024] In one possible implementation, the processing unit is further configured to: acquire second environmental data collected by a pyroelectric sensor in the terminal device; and activate the camera of the terminal device when a living being is detected from the second environmental data.

[0025] In one possible implementation, the first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

[0026] In one possible implementation, the second sensor includes a piezoelectric sensor.

[0027] In one possible implementation, the first and second sensors are deployed together.

[0028] Thirdly, embodiments of this application provide a vehicle including a collision detection device, a first sensor, a second sensor, and a signal amplification module as provided in any of the second aspects above. The first sensor is used to collect first environmental data, which characterizes the environmental information of the vehicle's location. The second sensor is used to transmit a second signal. The signal amplification module is used to amplify the signal transmitted by the second sensor.

[0029] In one possible implementation, the first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

[0030] In one possible implementation, the second sensor includes a piezoelectric sensor.

[0031] In one possible implementation, the first and second sensors are deployed together.

[0032] Fourthly, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed by a processor, cause a collision detection device to perform the method described in the first aspect or any possible implementation thereof.

[0033] Fifthly, this application provides a computer program product comprising a computer program or instructions that, when executed by a processor, cause a collision detection device to perform the method described in the first aspect or any possible implementation thereof.

[0034] In a sixth aspect, this application provides a chip including a processor coupled to a memory for executing a computer program or instructions stored in the memory, such that the chip implements the methods of the first aspect and any possible implementation thereof.

[0035] In a seventh aspect, this application provides a collision detection apparatus, including at least one processor and an interface. The at least one processor is configured to read instructions via the interface to execute methods as described in the first aspect and any possible implementation thereof. Attached Figure Description

[0036] Figure 1 is a schematic diagram of a vehicle provided in an embodiment of this application;

[0037] Figure 2 is a schematic diagram of a radar provided in an embodiment of this application;

[0038] Figure 3 is an exemplary flowchart of a collision detection method provided in an embodiment of this application;

[0039] Figure 4A is a schematic diagram of a scenario for a collision detection method provided in an embodiment of this application;

[0040] Figure 4B is a schematic diagram of a scenario for another collision detection method provided in an embodiment of this application;

[0041] Figure 5A is a schematic diagram of the transmission process of a first signal provided in an embodiment of this application;

[0042] Figure 5B is a schematic diagram of a neural network model provided in an embodiment of this application;

[0043] Figure 6 is a schematic diagram of a scenario for another collision detection method provided in an embodiment of this application;

[0044] Figure 7A is a schematic diagram of a deployment method of a first sensor and a second sensor provided in an embodiment of this application;

[0045] Figure 7B is a schematic diagram of another deployment method of the first sensor and the second sensor provided in the embodiments of this application;

[0046] Figure 8 is a schematic diagram of a scenario provided by an embodiment of this application;

[0047] Figure 9 is a schematic diagram of a collision detection device provided in an embodiment of this application;

[0048] Figure 10 is a schematic diagram of another collision detection device provided in an embodiment of this application. Detailed Implementation

[0049] The technical solutions provided in this application can be applied to vehicles with collision detection functions, or other devices with collision detection functions in vehicles. These other devices include, but are not limited to, vehicle-mounted terminals, vehicle-mounted controllers, vehicle-mounted modules, vehicle-mounted components, vehicle-mounted chips, vehicle-mounted units, vehicle-mounted radar, or vehicle-mounted cameras, and other sensors. Vehicles can implement the collision detection method provided in this application through these vehicle-mounted terminals, vehicle-mounted controllers, vehicle-mounted modules, vehicle-mounted components, vehicle-mounted chips, vehicle-mounted units, vehicle-mounted radar, or vehicle-mounted cameras. Of course, the collision detection method in this application can also be used in other intelligent terminals with collision detection functions besides vehicles, or installed in other intelligent terminals with collision detection functions besides vehicles, or installed in components of such intelligent terminals. These intelligent terminals can be intelligent transportation equipment, smart home devices, robots, etc. Examples include, but are not limited to, intelligent terminals or controllers, chips, radar, cameras, and other sensors and components within intelligent terminals.

[0050] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0051] Collision detection can be categorized into two types based on whether a collision has occurred: non-contact collision detection and contact collision detection. Non-contact collision detection aims to prevent collisions from happening, while contact collision detection detects collisions and initiates emergency actions upon detection. Contact collision detection is used during vehicle operation to make a rapid and accurate judgment when a vehicle hits a pedestrian, enabling emergency braking to avoid secondary injuries and significantly reduce the injury rate. Currently, contact collision detection primarily utilizes piezoelectric sensors to achieve passive defense, quickly detecting a collision after it occurs and preventing secondary injuries through emergency braking.

[0052] However, contact-based collision detection is susceptible to scene interference. Piezoelectric sensors (such as elastic wave sensors) have an internal structure of piezoelectric ceramics. When going over speed bumps, the vehicle body vibrates and deforms, generating a signal. Additionally, audio can cause resonance in the vehicle's casing, also triggering a signal from piezoelectric sensors. However, these deformations and resonances are not caused by a collision, but they are very similar in characteristics from a sensor perspective, making them difficult to distinguish. Furthermore, when a vehicle collides with obstacles such as tree branches in a parking lot, or when raindrops or hail hit the vehicle body, the vehicle will detect the collision through signals generated by piezoelectric sensors, triggering emergency braking. However, in these non-pedestrian-hit scenarios, emergency braking is not necessary.

[0053] In view of this, embodiments of this application provide a collision detection method. This method utilizes first environmental data collected by a first sensor. When the first environmental data meets a first condition, the amplification factor of the signal amplification module is adjusted, or a first threshold for determining whether a collision has occurred is adjusted. Then, a first signal amplified by the signal amplification module is compared with the first threshold to determine whether a collision has occurred.

[0054] The present application will now be described in further detail with reference to the accompanying drawings. It should be understood that the specific operational methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that in the description of this application, "at least one" refers to one or more, where "multiple" refers to two or more. Therefore, in the embodiments of this application, "multiple" can also be understood as "at least two". "And / or" describes the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / ", unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0055] Referring to Figure 1, a schematic diagram of the hardware architecture of a vehicle provided in an embodiment of this application is shown. As shown in Figure 1, the vehicle can be equipped with a vehicle detection system, and the vehicle includes, but is not limited to, unmanned vehicles, intelligent vehicles, electric vehicles, or digital vehicles. The vehicle detection system can acquire measurement information such as the vehicle's latitude and longitude, speed, orientation, and distance to surrounding objects in real time or periodically. Based on this measurement information and in conjunction with an advanced driving assistance system (ADAS), assisted driving or autonomous driving of the vehicle can be achieved. For example, latitude and longitude can be used to determine the vehicle's position, speed and orientation can be used to determine the vehicle's driving direction and destination over a future period, or the distance to surrounding objects can be used to determine the number and density of obstacles around the vehicle. Further, optionally, the vehicle detection system may include an onboard perception module and an onboard fusion module. The onboard perception module can be sensors installed around the vehicle body (e.g., the front left, front right, left, right, rear left, rear right, etc. of the vehicle) (the functions of the sensors are described below). This application does not limit the installation location of the onboard perception module on the vehicle. An in-vehicle fusion module can be, for example, a processor, a domain controller, an electronic control unit (ECU), or other chips installed in the vehicle. The ECU, also known as a "vehicle computer," "on-board computer," "vehicle-specific microcomputer controller," or "lower-level machine," is one of the core components of a vehicle. The in-vehicle fusion module can fuse signals from various sensors in the vehicle to detect whether a collision has occurred.

[0056] The following section introduces the sensors suitable for vehicle-mounted sensing modules.

[0057] Sensors can be broadly categorized into two types based on their sensing method: passive sensors and active sensors. Passive sensors primarily rely on radiation information from the external environment. Active sensors, on the other hand, sense the environment by actively emitting energy waves. The following sections will detail passive and active sensors respectively.

[0058] Passive sensing sensors may include, for example, cameras (or video cameras), piezoelectric sensors, pyroelectric sensors, humidity sensors, and temperature sensors.

[0059] The accuracy of camera perception results primarily depends on image processing and classification algorithms. The camera includes any camera used to acquire images of the vehicle's environment (e.g., still cameras, video cameras, etc.). In some examples, the camera can be configured to detect visible light, referred to as a visible light camera. Visible light cameras use charge-coupled devices (CCDs) or standard complementary metal-oxide semiconductors (CMOS) to obtain images corresponding to visible light. In other examples, the camera can also be configured to detect light from other parts of the spectrum (such as infrared light), referred to as an infrared camera. Infrared cameras can use CCDs or CMOS, filtered by a filter to allow only light of the color wavelength range and a set infrared wavelength range to pass through.

[0060] Piezoelectric sensors, including elastic wave sensors and structured acoustic sensors, are sensors based on the piezoelectric effect and are both power-generating and electromechanical conversion sensors. Their sensing element is made of a piezoelectric material, which generates a charge on its surface upon receiving an object. This charge is amplified by a charge amplifier and measurement circuitry, and after impedance transformation, becomes an electrical output proportional to the applied external force. For example, piezoelectric sensors can be mounted on the housing of a vehicle.

[0061] Pyroelectric sensors, also known as human infrared sensors, work by sensing temperature changes. Temperature differences cause changes in the potential of the object's surface, which are then converted into voltage output.

[0062] A temperature sensor is a sensor that can sense temperature and convert it into a usable output signal.

[0063] A humidity sensor is a sensor that can sense humidity and convert it into a usable output signal.

[0064] Among these, active sensing sensors can be radar. As shown in Figure 2, taking a radar deployed at the front of a vehicle as an example, this radar can sense a fan-shaped area as indicated by the solid line box. This fan-shaped area can be considered the radar's sensing area (or detection area). The radar transmits electromagnetic wave signals outward through its antenna and receives the echo signals reflected by the target. It then amplifies and down-converts the echo signals to obtain information such as the relative distance, relative speed, and angle between the vehicle and the target. For example, radar can include lidar, millimeter-wave radar, and ultrasonic radar.

[0065] Based on the above, the collision detection method proposed in the embodiments of this application will be described in detail below with reference to Figure 3.

[0066] Referring to Figure 3, an exemplary flowchart of a collision detection method provided in an embodiment of this application is shown, which may include the following steps. In one example, the embodiment shown in Figure 3 can be executed by an in-vehicle fusion module. Unless otherwise specified, the term "terminal device" in this application can refer to a terminal device, a component within a terminal device (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of a terminal device. Exemplarily, the terminal device can be a vehicle or the aforementioned intelligent terminal. In the following description, a vehicle is used as an example of the terminal device.

[0067] S301: Acquire the first environmental data collected by the first sensor in the vehicle.

[0068] The first environmental data represents the environmental information of the vehicle. For example, the first sensor can be a sensor from an onboard perception module. For instance, the first sensor can include one or more of a camera, radar, or pyroelectric sensor. For example, if the first sensor includes a camera, then the first environmental data can include video data captured by the camera. As another example, if the first sensor includes a pyroelectric sensor, then the first environmental data can include data captured by the pyroelectric sensor. As yet another example, if the first sensor includes radar, then the first environmental data can include data captured by the radar.

[0069] S302: When the first environmental data meets the first condition, adjust the amplification factor of the signal amplification module in the vehicle or adjust the first threshold.

[0070] The signal amplification module can be used to amplify the signal sent by the second sensor. For example, the second sensor can be a sensor used to detect whether a vehicle collision has occurred. For instance, the second sensor can be a piezoelectric sensor, such as an elastic wave sensor or a structured sound sensor. In some embodiments, the piezoelectric sensor can be mounted on the housing of the terminal device. When the housing deforms, the piezoelectric sensor generates and sends a second signal. This second signal is amplified by the signal amplification module to obtain the first signal.

[0071] In S302, when the first environmental data meets the first condition, the amplification factor of the signal amplification module and / or the first threshold can be adjusted. For example, when the first environmental data meets the first condition, the amplification factor and the first threshold can be adjusted. For another example, when the first environmental data meets the first condition, the amplification factor can be adjusted. For another example, when the first environmental data meets the first condition, the first threshold can be adjusted. In this embodiment, the first threshold can be used to determine whether a collision has occurred. Exemplarily, the first threshold can be a confidence level representing whether a collision has occurred or a probability representing whether a collision has occurred. Exemplarily, a higher confidence level or a higher probability indicates a greater likelihood of a collision. Optionally, the first threshold can also be a signal strength characteristic indicating whether a collision has occurred. Exemplarily, a higher signal strength indicates a greater likelihood of a collision. In one example, if the confidence level / probability determined by the first signal is greater than or equal to the first threshold, it can be considered that a collision has occurred.

[0072] In one possible implementation, the first environmental data satisfying the first condition may include one or more of the following:

[0073] Scenario 1: A living organism was detected from the first environmental data.

[0074] In scenario 1, the first sensor may include a camera and / or a pyroelectric sensor. For example, the first sensor may include a camera, and the first environmental data collected from the camera can detect the presence of living beings, such as humans or animals. Exemplarily, the presence of living beings in the first environmental data can be detected through methods such as image processing. As another example, the first sensor may include a pyroelectric sensor, and the presence of living beings can be detected from the first environmental data collected by the pyroelectric sensor. Exemplarily, there is a temperature difference between living beings (such as humans or animals) and non-living beings (such as trees), and the temperature of the object can be collected by the pyroelectric sensor, thereby determining whether there are living beings in the first environmental data based on the object's temperature.

[0075] In one example, if a living being is detected from the first environmental data, the amplification factor of the signal amplification module can be increased, and / or the first threshold can be decreased. Optionally, if no living being is detected from the first environmental data, the amplification factor and the first threshold are not adjusted.

[0076] It should be noted that the adjustment values ​​for the magnification factor and the first threshold can be predefined, preconfigured, indicated by received instructions, such as being updated via over-the-air technology (OTA), calculated automatically, or determined by other means, and will not be described again below.

[0077] For example, Figure 4A is a schematic diagram of a collision detection method provided in an embodiment of this application.

[0078] As shown in Figure 4A, the first sensor may include a pyroelectric sensor. The vehicle-mounted fusion module can acquire the first environmental data collected by the pyroelectric sensor and detect whether there is a living organism in the first environmental data. When a living organism is detected from the first environmental data, the vehicle-mounted fusion module can increase the amplification factor of the signal amplification module and / or decrease the first threshold.

[0079] For example, a pyroelectric sensor can collect first environmental data. In the embodiment shown in Figure 4A, the first environmental data is collected using a data acquisition frequency of 20Hz as an example. The pyroelectric sensor sends the collected first environmental data to a pyroelectric signal accumulation module, which can store the first environmental data collected by the pyroelectric sensor. For example, the pyroelectric signal accumulation module can store the first environmental data collected by the pyroelectric sensor within a first time period, which can be predefined, preconfigured, indicated by a received instruction, or determined in other ways. The pyroelectric signal accumulation module can send the first environmental data within the stored first time period to a pyroelectric signal detection module. The pyroelectric signal detection module can detect the first environmental data within the first time period, and when a living organism is detected, it increases the amplification factor of the signal amplification module and / or decreases a first threshold.

[0080] It should be noted that in the embodiment shown in Figure 4A, the pyroelectric signal accumulation module and the pyroelectric signal detection module can be separate modules or integrated into the vehicle fusion module.

[0081] Optionally, ambient temperature may affect the data collected by the pyroelectric sensor. For example, when the vehicle fusion module detects the presence of living beings using data collected by the pyroelectric sensor, it can determine the presence of living beings based on the difference between the temperature of the object indicated in the data collected by the pyroelectric sensor and the ambient temperature. Therefore, including a temperature sensor as the first sensor can improve the accuracy of the vehicle fusion module in determining whether there are living beings around the vehicle.

[0082] For example, a temperature sensor can send the collected ambient temperature to the vehicle fusion module. Exemplarily, the temperature sensor can collect the ambient temperature within a first time period and send it to the vehicle fusion module, which can be implemented by referring to the method of data collection by the pyroelectric sensor in the embodiment shown in Figure 4A, and will not be repeated here. The method of environmental data collection by the pyroelectric sensor can also be implemented by referring to the embodiment shown in Figure 4A, and will not be repeated here. In this case, the first environmental data may include the ambient temperature collected by the temperature sensor and the environmental data collected by the pyroelectric sensor. The vehicle fusion module can detect the presence of living beings based on the ambient temperature collected by the temperature sensor and the environmental data collected by the pyroelectric sensor. When the vehicle fusion module detects a living being based on the ambient temperature collected by the temperature sensor and the environmental data collected by the pyroelectric sensor, it can increase the amplification factor of the signal amplification module and / or decrease the first threshold.

[0083] In another example, ambient temperature also affects the response strength of the piezoelectric sensor's output signal. For instance, the response strength of the piezoelectric sensor's output signal is greater at higher temperatures than at lower temperatures. Therefore, the vehicle fusion module can also combine the ambient temperature data collected by the temperature sensor when determining whether a collision has occurred.

[0084] Optionally, radar may influence the detection results of the vehicle-mounted fusion module. For example, the first sensor may also include radar (not shown in the figure), such as one or more of millimeter-wave radar, ultrasonic radar, or lidar. Radar can determine the presence of an object through echo signals. Therefore, the vehicle-mounted fusion module can receive data sensed by the radar, improving the accuracy of detecting the presence of living beings. For instance, if the data received by the vehicle-mounted fusion module from the radar indicates the presence of an object around the vehicle, and the data received from the pyroelectric sensor detects the presence of a living being, then the object around the vehicle can be considered a living being. Optionally, if the data received by the vehicle-mounted fusion module from the radar indicates no object around the vehicle, but the data received from the pyroelectric sensor detects the presence of a living being, then the vehicle-mounted fusion module can continue to acquire data from both the radar and the pyroelectric sensor to further detect the presence of living beings around the vehicle, thereby reducing the false detection rate.

[0085] Based on the solution in scenario 1 above, when a living being is detected around the vehicle, increasing the magnification and / or lowering the first threshold can improve the collision detection rate and reduce the overall false detection rate.

[0086] Case 2: The vehicle's speed is less than or equal to the first value.

[0087] In scenario 2, the first sensor may include a wheel speed sensor, and the first environmental data may include the vehicle's speed. Optionally, the vehicle speed may also be obtained from vehicle information, which may be stored in the vehicle's domain controller or ECU. In one example, when the vehicle speed is less than or equal to a first value, the amplification factor of the signal amplification module can be increased, and / or the first threshold can be decreased. Optionally, if the vehicle speed is greater than the first value, the amplification factor and the first threshold are not adjusted. In another example, when the vehicle speed is within a first range, the amplification factor of the signal amplification module can be increased, and / or the first threshold can be decreased. Optionally, if the vehicle speed is not within the first range, the amplification factor and the first threshold are not adjusted.

[0088] For example, as shown in Figure 4B, the vehicle fusion module can receive the vehicle speed collected by the wheel speed sensor from the wheel speed sensor. Optionally, the vehicle fusion module can receive the vehicle speed collected by the wheel speed sensor from the wheel speed sensor within a first time period. As another example, the vehicle fusion module can obtain the vehicle speed (such as the vehicle speed within the first time period) from vehicle information. The vehicle fusion module can compare the vehicle speed within the first time period with a first value (or a first range). When the vehicle speed within the first time period is less than or equal to the first value (or falls within the first range), the amplification factor of the signal amplification module can be increased, and / or the first threshold can be decreased.

[0089] It should be noted that the vehicle speed within the first time period can be understood as the average, peak, or squared difference of the vehicle speed within the first time period.

[0090] Optionally, in scenario 2, the vehicle fusion module can acquire the speed change trend of the vehicle within a first time period. If the speed change trend is less than or equal to a first value (or falls within a first range), the amplification factor of the signal amplification module can be increased, and / or the first threshold can be decreased. It should be understood that the aforementioned speed change trend can be interpreted as the speed value increasing or decreasing per second.

[0091] Optionally, ambient temperature can affect the response intensity of the piezoelectric sensor's output signal. For example, the first sensor may include a temperature sensor. For instance, the response intensity of the piezoelectric sensor's output signal is greater at higher temperatures than at lower temperatures. The vehicle-mounted fusion module can also combine the ambient temperature data collected by the temperature sensor when determining whether a collision has occurred.

[0092] Based on the solution in scenario 2 above, increasing the magnification and / or lowering the first threshold when the vehicle speed is low can improve the perception sensitivity during minor collisions, as well as the perception sensitivity when the vehicle is stopped or parked (such as in automatic parking), thereby increasing the detection success rate and reducing the false detection rate.

[0093] It should be noted that the aforementioned first value (or first range) may be predefined, preconfigured, indicated by received instructions, or determined in other ways.

[0094] Case 3: The vehicle's speed is greater than or equal to the second value.

[0095] In scenario 3, the first sensor may include a wheel speed sensor, and the first environmental data may include the vehicle's speed. Optionally, the vehicle speed may also be obtained from vehicle information, which may be stored in the vehicle's domain controller or ECU. In one example, when the vehicle speed is greater than or equal to a first value, the amplification factor of the signal amplification module can be reduced, and / or the first threshold can be increased. Optionally, if the vehicle speed is less than a second value, the amplification factor and the first threshold are not adjusted. In another example, when the vehicle speed is within a second range, the amplification factor of the signal amplification module can be reduced, and / or the first threshold can be increased. Optionally, if the vehicle speed is not within the second range, the amplification factor and the first threshold are not adjusted.

[0096] Optionally, in scenario 3, the vehicle fusion module can acquire the speed change trend of the vehicle within a first time period. If the change trend is greater than or equal to a first value (or falls within a second range), the amplification factor of the signal amplification module can be reduced, and / or the first threshold can be increased. It should be understood that the aforementioned change trend can be interpreted as the speed value increasing or decreasing per second.

[0097] In scenario 3, the method by which the vehicle fusion module acquires the vehicle's speed can be referred to the relevant description in scenario 2, and will not be repeated here. Optionally, the first sensor may also include a temperature sensor, which can be referred to the relevant description in scenario 2, and will not be repeated here.

[0098] Based on the solution in scenario 3 above, reducing the amplification factor and / or increasing the first threshold when the vehicle speed is high can reduce the probability of false alarms.

[0099] It should be noted that situations 1 to 3 described above in this application embodiment can be implemented individually or in combination. For example, the vehicle fusion module can increase the magnification and / or decrease the first threshold when a living being is detected and the vehicle speed is low. Alternatively, when the vehicle speed is high and no living being is detected, the vehicle fusion module can optionally decrease the magnification and / or increase the first threshold.

[0100] S303: Receives the first signal from the signal amplification module.

[0101] The first signal can be a signal sent by the second sensor and amplified by the signal amplification module.

[0102] In some embodiments, the amplification factor of the signal amplification module may be adjusted or not. For example, if the first environmental data meets a first condition, the amplification factor of the signal amplification module is adjusted.

[0103] S304: Based on the first signal and the first threshold, determine whether a collision has occurred.

[0104] In some embodiments, the first threshold in S304 may be adjusted or unadjusted. For example, the first threshold is adjusted if the first environmental data meets a first condition. Exemplarily, the vehicular fusion module can extract features of the first signal and determine the confidence / probability corresponding to the first signal based on these features. If the confidence / probability is greater than or equal to the first threshold, a vehicle collision can be considered to have occurred.

[0105] For example, referring to Figure 5A, when a piezoelectric sensor detects deformation (such as a change in the shape of the vehicle shell due to a collision between the vehicle and a living or non-living object, such as a dent), it sends a second signal to a signal amplification module. The signal amplification module amplifies the second signal and sends the amplified first signal to a signal accumulation module. The signal accumulation module can store the first signal sent by the signal amplification module. For example, the signal accumulation module can store the first signal within a second time period, which can be predefined, preconfigured, or indicated by a received command. Optionally, the signal accumulation module can send the first signal within the second time period to a feature extraction module, which extracts features of the first signal (such as time-domain features and frequency-domain features). The signal accumulation module can then send the features of the first signal to an onboard fusion module, which determines whether a collision has occurred.

[0106] It should be noted that in the embodiment shown in Figure 5A, the signal accumulation module and the feature extraction module can be separate modules, or they can be integrated into the vehicle fusion module.

[0107] In one possible implementation, the in-vehicle fusion module can determine whether a collision has occurred using a neural network model. For example, a first signal can be input into the neural network model. One or more layers in the neural network model can extract features of the first signal (such as time-domain and frequency-domain features) to output a confidence score / probability. Optionally, the input to the neural network model can be features of the first signal (such as time-domain and frequency-domain features), and each layer of the neural network model can output a confidence score / probability based on the features of the first signal. When the confidence score / probability output by the neural network model is greater than or equal to a first threshold, a collision can be considered to have occurred.

[0108] For example, as shown in Figure 5B, the in-vehicle fusion module can store a neural network model (a lightweight neural network model as shown in Figure 5B). In the embodiment shown in Figure 5B, the neural network model can consist of 5 layers, with the leftmost layer being the first layer and the rightmost layer being the fifth layer for illustration. The first layer may include 80 neurons (or processing units), the second layer may include 64 neurons, the third layer may include 20 neurons, the fourth layer may include 10 neurons, and the fifth layer may include 2 neurons. The input to this neural network model can be a first signal or features of the first signal. The output of this neural network model can be a confidence level indicating whether a collision has occurred.

[0109] It should be noted that the number of layers and the number of neurons in each layer of the neural network model shown in Figure 5B are merely illustrative examples. Those skilled in the art can design neural network models to perform collision detection by incorporating the characteristics of the first signal.

[0110] Optionally, if a collision is determined, the vehicle can be controlled to apply emergency braking to avoid secondary injuries, and / or the vehicle can be controlled to issue warnings, such as audible alarms, so that the driver is aware of the collision. For example, the in-vehicle fusion module can send collision information to the vehicle control module (such as a multi-domain controller (MDC) and a chassis dynamics domain controller (VDC)), which then controls the vehicle (as shown in Figures 4A, 4B, and 6).

[0111] Based on the above, a technical solution for the vehicle fusion module to determine whether a collision has occurred using a first signal and a first threshold has been introduced. In this embodiment, the vehicle fusion module can also combine first environmental data to make the judgment when determining whether a vehicle collision has occurred. That is, the vehicle fusion module can make the judgment using the first signal and the first environmental data when determining whether a vehicle collision has occurred.

[0112] In one example, the first sensor may include a pyroelectric sensor. Optionally, the first sensor may also include a temperature sensor. The first environmental data may then include environmental data collected by the pyroelectric sensor, and optionally, the ambient temperature collected by the temperature sensor. The vehicle-mounted fusion module detects whether there is a living organism in the first environmental data. When a living organism is detected from the first environmental data, the vehicle-mounted fusion module may increase the amplification factor of the signal amplification module and / or decrease the first threshold. Furthermore, the vehicle-mounted fusion module can acquire features of the first environmental data, such as the rate of change of the time-domain signal, the peak value of the pyroelectric intensity in the first environmental data, and frequency domain features. The vehicle-mounted fusion module can input the first environmental data and a first signal, or the features of the first environmental data and the features of the first signal, into a neural network model to obtain the confidence level of whether a collision has occurred, as output by the neural network model. When the confidence level output by the neural network model is greater than or equal to the first threshold, a collision can be considered to have occurred.

[0113] It should be noted that when designing a neural network model, those skilled in the art can combine the characteristics of the first environmental data and the characteristics of the first signal to design the number of layers and the number of neurons in each layer of the neural network model.

[0114] In another example, the first sensor may include a wheel speed sensor. Optionally, the first sensor may also include a temperature sensor. The first environmental data may then include the vehicle speed collected by the wheel speed sensor, and optionally, the ambient temperature collected by the temperature sensor. Optionally, the vehicle fusion module may also obtain the vehicle speed from vehicle information without using the wheel speed sensor. When the vehicle speed is greater than or equal to a first value, the vehicle fusion module may increase the amplification factor of the signal amplification module and / or decrease the first threshold. The vehicle fusion module may input the first environmental data and the first signal, or the features of the first environmental data and the features of the first signal, into a neural network model to obtain the confidence level of whether a collision has occurred, as output by the neural network model. When the confidence level output by the neural network model is greater than or equal to the first threshold, a collision can be considered to have occurred.

[0115] In another example, referring to Figure 6, the first sensor (the environmental information detection module shown in Figure 6) may include a pyroelectric sensor, ultrasonic radar, millimeter-wave radar, camera, wheel speed sensor, humidity sensor, temperature sensor, and lidar. The ultrasonic radar, millimeter-wave radar, and lidar can determine whether there are objects around the vehicle or whether objects have passed by using echo signals. That is, the vehicle fusion module can determine whether an object has been detected from the radar data of ultrasonic radar, millimeter-wave radar, and lidar in the first environmental data. The humidity sensor and temperature sensor affect the data collected by the pyroelectric sensor. Therefore, when detecting data collected by the pyroelectric sensor, the data collected by the humidity sensor and temperature sensor can be referenced. The vehicle fusion module can increase the amplification factor of the signal amplification module and / or decrease the first threshold when a living being is detected from the first environmental data and / or the vehicle speed is less than or equal to a first value. The vehicle fusion module can input the first environmental data and a first signal, or the features of the first environmental data and the features of the first signal, into a neural network model to obtain the confidence level of whether a collision has occurred, as output by the neural network model. When the confidence level output by the neural network model is greater than or equal to the first threshold, a collision can be considered to have occurred.

[0116] Optionally, the embodiment shown in Figure 6 may further include an environmental information extraction module. This module can be used to extract features from the first environmental data, and the environmental information acquisition module can send the acquired first environmental data to the environmental information extraction module. It should be understood that the environmental information extraction module can be a separate module or it can be integrated into the vehicle-mounted fusion module.

[0117] In one possible implementation, the first and second sensors can be deployed together. Referring to Figure 7A, the first and second sensors can be deployed together to reduce cable and material costs, jointly collect data, and achieve hard synchronization. For example, the first sensor may include a pyroelectric sensor, and the second sensor may include a piezoelectric sensor. The vehicle may be equipped with a front pyroelectric sensor and a front piezoelectric sensor located at the front end of the vehicle, a rear pyroelectric sensor and a rear piezoelectric sensor located at the rear end of the vehicle, and four-door pyroelectric sensors and four-door piezoelectric sensors located at the four doors of the vehicle. Specifically, the front pyroelectric sensor and the front piezoelectric sensor can be deployed together, the rear pyroelectric sensor and the rear piezoelectric sensor can be deployed together, and the four-door pyroelectric sensor and the four-door piezoelectric sensor can be deployed together. In the embodiment shown in Figure 7A, the on-board fusion module can be an ECU, and the vehicle control module can include an MDC and a VDC.

[0118] In another possible implementation, the first and second sensors can be deployed separately. Referring to Figure 7B, the first and second sensors can be deployed separately, sharing an ECU to reduce material costs, and jointly collect data to achieve hard synchronization. For example, the first sensor may include a pyroelectric sensor, and the second sensor may include a piezoelectric sensor. The vehicle may be equipped with a front pyroelectric sensor and a front piezoelectric sensor located at the front end of the vehicle, a rear pyroelectric sensor and a rear piezoelectric sensor located at the rear end of the vehicle, and four-door pyroelectric sensors and four-door piezoelectric sensors located at the four doors of the vehicle. In the embodiment shown in Figure 7B, the on-board fusion module can be an ECU, and the vehicle control module can include an MDC and a VDC.

[0119] In some embodiments, if a living being is detected in the first environmental data, the vehicle's camera can be activated. For example, if a living being is detected in the first environmental data, the camera can be activated and video recording can begin. The recording duration can be predefined, preconfigured, or indicated by a received instruction. The vehicle can store the recorded video. For instance, if a living being is detected in the first environmental data, the vehicle's sentry mode can be activated, and the vehicle will activate its camera and begin recording video.

[0120] In other embodiments, referring to FIG8, the vehicle-mounted fusion module can acquire second environmental data collected by the pyroelectric sensor. If a living being is detected in the second environmental data, the camera can be activated and video recording can begin. For example, the method by which the pyroelectric sensor collects the second environmental data can be implemented with reference to the embodiment shown in FIG4A, and will not be repeated here. The video recording duration can be predefined, preconfigured, or indicated by a received instruction. The vehicle can store the recorded video. For example, if a living being is detected in the second environmental data, the vehicle's sentry mode can be activated, and the vehicle will activate the camera and begin recording video.

[0121] Based on the above solution, the detection success rate of life-bearing collisions (such as scratching the car) in sentry mode can be improved when a living being approaches. For example, when the vehicle is stationary, by adding a pyroelectric sensor, it is possible to detect whether a living being is approaching, and activate the camera in advance to perform sentry detection.

[0122] Based on the above content and the same concept, Figure 9 is a schematic diagram of the possible collision detection device provided in this application. These collision detection devices can be used to implement the functions of the vehicle fusion module in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0123] As shown in Figure 9, the collision detection device 900 includes a processing unit 901 and a transceiver unit 902. The collision detection device 900 is used to implement the function of the vehicle fusion module in the method embodiment shown in Figure 3 above.

[0124] For example, processing unit 901 is configured to: acquire first environmental data collected by a first sensor in the terminal device, the first environmental data representing the environmental information of the terminal device. Transceiver unit 902 is configured to: receive a first signal from a signal amplification module in the terminal device, the first signal being amplified by a second sensor in the terminal device. Processing unit 901 is further configured to determine whether a collision has occurred in the terminal device based on the first signal and a first threshold. Wherein, when the first environmental data meets a first condition, the amplification factor of the signal amplification module or the first threshold is an adjusted value.

[0125] A more detailed description of the above-mentioned processing unit 901 and transceiver unit 902 can be obtained directly from the relevant description in the method embodiment shown in Figure 3, and will not be repeated here.

[0126] It should be understood that the processing unit 901 in the embodiments of this application can be implemented by a processor or processor-related circuit components, and the transceiver unit 902 can be implemented by a transceiver or transceiver-related circuit components.

[0127] Based on the above content and the same concept, as shown in FIG10, this application also provides a collision detection device 1000. The collision detection device 1000 may include at least one processor 1001 and a transceiver 1002. The processor 1001 and the transceiver 1002 are coupled to each other. It is understood that the transceiver 1002 may be an interface circuit or an input / output interface. Optionally, the collision detection device 1000 may further include a memory 1003 for storing instructions executed by the processor 1001, or storing input data required by the processor 1001 to execute instructions, or storing data generated after the processor 1001 executes instructions.

[0128] When the collision detection device 1000 is used to implement the method shown in FIG3, the processor 1001 is used to execute the function of the processing unit 901, and the transceiver 1002 is used to execute the function of the transceiver unit 902.

[0129] Based on the foregoing content and the same concept, this application provides a vehicle. The vehicle includes the aforementioned collision detection device, a first sensor, a second sensor, and a signal amplification module. The collision detection device can execute the method performed by the onboard fusion module. Possible implementations of the first sensor, the second sensor, and the signal amplification module are described above and will not be repeated here. Further, optionally, the vehicle may also include other devices, such as a processor, a memory, and a wireless communication device.

[0130] In one possible implementation, the vehicle could be, for example, an autonomous vehicle, an intelligent vehicle, an electric vehicle, or a digital vehicle.

[0131] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0132] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a probing system. Of course, the processor and storage medium can also exist as discrete components in the probing system.

[0133] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer programs or instructions. When a computer program or instruction is loaded and executed on a computer, all or part of the processes or functions of the embodiments of this application are performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a detection system, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); or it can be a semiconductor medium, such as a solid-state drive (SSD).

[0134] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0135] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates an "or" relationship between the preceding and following related objects; in the formulas of this application, the character " / " indicates a "division" relationship between the preceding and following related objects. Additionally, in this application, the term "exemplary" is used to indicate an example, illustration, or explanation. Any embodiment or design described as "example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Alternatively, it can be understood that the use of the term "example" is intended to present concepts in a specific manner and does not constitute a limitation of this application.

[0136] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and inherent logic. Terms such as "first," "second," and similar expressions are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or modules. A method, system, product, or device is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices.

[0137] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of protection of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A collision detection method, characterized in that, include: Acquire first environmental data collected by a first sensor in a terminal device, wherein the first environmental data characterizes the environmental information in which the terminal device is located; The first signal is received from the signal amplification module in the terminal device. The first signal is sent by the second sensor in the terminal device and is amplified by the signal amplification module. Based on the first signal and the first threshold, it is determined whether the terminal device has experienced a collision; Wherein, when the first environmental data meets the first condition, the amplification factor of the signal amplification module and / or the first threshold are adjusted values.

2. The method according to claim 1, characterized in that, The first sensor includes a camera and / or a pyroelectric sensor. The step of setting the amplification factor of the signal amplification module or the first threshold to an adjusted value when the first environmental data meets the first condition includes: When a living organism is detected from the first environmental data, the magnification factor is the enhanced value; and / or, When a living organism is detected from the first environmental data, the first threshold is the reduced value.

3. The method according to claim 1 or 2, characterized in that, When the first environmental data meets the first condition, the amplification factor of the signal amplification module or the first threshold is an adjusted value, including: When the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the magnification factor is the enhanced value; and / or, When the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the first threshold is the reduced value.

4. The method according to claim 1, characterized in that, When the first environmental data meets the first condition, the amplification factor of the signal amplification module or the first threshold is an adjusted value, including: When the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the magnification factor is the reduced value; and / or, When the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the first threshold is the enhanced value.

5. The method according to any one of claims 1 to 4, characterized in that, Also includes: When a living being is detected from the first environmental data, the camera of the terminal device is turned on.

6. The method according to claim 5, characterized in that, The first sensor includes a pyroelectric sensor.

7. The method according to any one of claims 1 to 4, characterized in that, Also includes: Acquire the second environmental data collected by the pyroelectric sensor in the terminal device; When a living being is detected from the second environmental data, the camera of the terminal device is turned on.

8. The method according to any one of claims 1 to 7, characterized in that, The first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

9. The method according to any one of claims 1 to 8, characterized in that, The second sensor includes a piezoelectric sensor.

10. The method according to any one of claims 1 to 9, characterized in that, The first sensor and the second sensor are deployed together.

11. A collision detection device, characterized in that, include: Processing unit and transceiver unit The processing unit is used to acquire first environmental data collected by the first sensor in the terminal device, wherein the first environmental data characterizes the environmental information of the terminal device. The transceiver unit is used to receive a first signal from the signal amplification module in the terminal device. The first signal is sent by the second sensor in the terminal device and is amplified by the signal amplification module. The processing unit is further configured to determine whether the terminal device has experienced a collision based on the first signal and the first threshold. Wherein, when the first environmental data meets the first condition, the amplification factor of the signal amplification module and / or the first threshold are adjusted values.

12. The apparatus according to claim 11, characterized in that, The first sensor includes a camera and / or a pyroelectric sensor. The step of setting the amplification factor of the signal amplification module or the first threshold to an adjusted value when the first environmental data meets the first condition includes: When a living organism is detected from the first environmental data, the magnification factor is the enhanced value; and / or, When a living organism is detected from the first environmental data, the first threshold is the reduced value.

13. The apparatus according to claim 11 or 12, characterized in that, When the first environmental data meets the first condition, the amplification factor of the signal amplification module or the first threshold is an adjusted value, including: When the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the magnification factor is the enhanced value; and / or, When the first environmental data indicates that the speed of the terminal device is less than or equal to a first value, the first threshold is the reduced value.

14. The apparatus according to claim 11, characterized in that, When the first environmental data meets the first condition, the amplification factor of the signal amplification module or the first threshold is an adjusted value, including: When the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the magnification factor is the reduced value; and / or, When the first environmental data indicates that the speed of the terminal device is greater than or equal to the second value, the first threshold is the enhanced value.

15. The apparatus according to any one of claims 11 to 14, characterized in that, The processing unit is also used for: When a living being is detected from the first environmental data, the camera of the terminal device is turned on.

16. The apparatus according to claim 15, characterized in that, The first sensor includes a pyroelectric sensor.

17. The apparatus according to any one of claims 11 to 14, characterized in that, The processing unit is also used for: Acquire the second environmental data collected by the pyroelectric sensor in the terminal device; When a living being is detected from the second environmental data, the camera of the terminal device is turned on.

18. The apparatus according to any one of claims 11 to 17, characterized in that, The first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

19. The apparatus according to any one of claims 11 to 18, characterized in that, The second sensor includes a piezoelectric sensor.

20. The apparatus according to any one of claims 11 to 19, characterized in that, The first sensor and the second sensor are deployed together.

21. A vehicle, characterized in that, Includes the collision detection device, first sensor, second sensor, and signal amplification module as described in any one of claims 11 to 20; The first sensor is used to collect first environmental data, which represents the environmental information of the vehicle. The second sensor is used to send a second signal; The signal amplification module is used to amplify the signal sent by the second sensor.

22. The vehicle according to claim 21, characterized in that, The first sensor includes one or more of a camera, a pyroelectric sensor, or radar.

23. The vehicle according to claim 21 or 22, characterized in that, The second sensor includes a piezoelectric sensor.

24. The vehicle according to any one of claims 21 to 23, characterized in that, The first sensor and the second sensor are deployed together.

25. A computer-readable storage medium, characterized in that, Includes computer instructions that, when executed on a processor, cause the detection system to perform the method as described in any one of claims 1 to 10.

26. A computer program product, characterized in that, When the computer program product is run on the processor, it causes the detection system to perform the method as described in any one of claims 1 to 10.

27. A collision detection device, characterized in that, It includes at least one processor and an interface, wherein the at least one processor is configured to read instructions through the interface to execute the method as described in any one of claims 1 to 10.

Images