Vehicle-mounted lens control method and device, readable storage medium and program product

Abstract

The invention provides a vehicle-mounted lens control method and device, a readable storage medium and a program product, and the method comprises the steps: obtaining the vehicle driving data of a target vehicle, and enabling the target vehicle to be provided with a plurality of liquid lenses corresponding to different view fields; selecting a corresponding target lens from the plurality of liquid lenses according to the driving data; and switching the current lens of the plurality of liquid lenses to the target lens.

Description

Technical Field

[0001] The present invention relates to the field of automobiles, and particularly to a control method, device, readable storage medium and program product based on an in-vehicle lens. Background Art

[0002] The in-vehicle surround view system is a core perception technology for intelligent driving, aiming to construct a 360° panoramic view around the vehicle in real time through the collaborative work of multiple cameras, so as to eliminate the visual blind area and improve driving safety and reliability. Its principle usually relies on wide-angle lenses such as fisheye cameras deployed around the vehicle body. Through image stitching, distortion correction and coordinate mapping algorithms, multiple video streams are fused into a unified panoramic image and transmitted to the in-vehicle computing unit for environmental perception. This technology can help the vehicle accurately identify close-range obstacles, pedestrians and complex road conditions, and provide key environmental information for scenarios such as parking and low-speed driving. It is the core support for the basic environmental interaction of the autonomous driving system.

[0003] In related technologies, lenses with a fixed field of view (FOV, also known as the viewing angle) are usually used for environmental monitoring, resulting in insufficient adaptability of the above system in dynamic scenarios. Specifically, the fixed FOV design faces the contradiction between detection distance and field of view width: the wide-angle lens has a wide field of view but a short detection distance and is difficult to capture distant targets; the telephoto lens can identify distant objects but sacrifices peripheral environmental information and is prone to missing sudden obstacles nearby. In addition, even if the device realizes the switching use of the wide-angle lens and the telephoto lens at the cost of high latency, this also means that the traditional system requires additional hardware support, increasing power consumption and space occupancy. Especially in variable scenarios of high-level autonomous driving such as L3 and L4, problems such as response lag, incomplete scene coverage and high computing power requirements of such systems are prominent, seriously restricting the real-time decision-making ability in complex road conditions. Summary of the Invention

[0004] In view of this, the present invention provides a control method, device, readable storage medium and program product based on an in-vehicle lens to solve the deficiencies in related technologies.

[0005] Specifically, the present specification is implemented through the following technical solutions: According to a first aspect of the present specification, there is provided a control method for an in-vehicle lens, the method comprising: Obtaining vehicle driving data of a target vehicle, the target vehicle being configured with a plurality of liquid lenses corresponding to different fields of view; Selecting a corresponding target lens from the plurality of liquid lenses according to the driving data; Switching the current lens of the plurality of liquid lenses to the target lens.

[0006] According to a second aspect of the present specification, there is provided a control device for an in-vehicle lens, the device comprising: a vehicle driving data acquisition unit configured to acquire vehicle driving data of a target vehicle, the target vehicle being configured with a plurality of liquid lenses respectively corresponding to different field of view ranges; a target lens selection unit configured to select a corresponding target lens from the plurality of liquid lenses according to the driving data; a lens switching unit configured to switch a current lens of the plurality of liquid lenses to the target lens.

[0007] According to a third aspect of the present specification, there is provided a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method according to the first aspect.

[0008] According to a fourth aspect of the present specification, a computer program product includes a computer program / instructions, which when executed by a processor, implements the steps of the method according to the first aspect.

[0009] In the present application, by dynamically switching the field of view range of the liquid lens, the contradiction problem between the detection distance and the field of view width of the traditional fixed FOV lens is solved. Based on the vehicle driving data, the corresponding liquid lens is selected in real time. Also, since the liquid lens can adjust the focal length without a mechanical structure, the hardware redundancy and delay of switching between traditional wide-angle or telephoto lenses are avoided. At the same time, by covering multi-scenario requirements with a single lens, the space occupancy, power consumption and computing power load are significantly reduced, thereby realizing more efficient environmental perception and real-time decision-making in scenarios such as high-level autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings according to these drawings without creative efforts.

[0011] Figure 1 is a schematic diagram of the architecture of a control system based on an in-vehicle lens shown in an open embodiment of the present invention; Figure 2 is a flowchart of a control method based on an in-vehicle lens shown in an open embodiment of the present invention; Figure 3 is a schematic diagram of the architecture of another control system based on an in-vehicle lens shown in an open embodiment of the present invention; Figure 4 is a flowchart of another control method based on an in-vehicle lens shown in an open embodiment of the present invention; Figure 5 It is a schematic structural diagram of an electronic device shown in an embodiment of the present invention; Figure 6 It is a block diagram of a control device based on a vehicle-mounted lens shown in an embodiment of the present invention. Specific embodiments

[0012] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention.

[0013] The terms used in the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0014] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0015] The following describes in detail an embodiment of the control method based on a vehicle-mounted lens of the present invention with reference to the drawings.

[0016] Figure 1 It is a schematic architecture diagram of a vehicle-mounted lens control system shown in an embodiment disclosed in this specification. As Figure 1 shown, the system may include a lens controller 12 in the target vehicle 10 and a liquid lens group 14 including a plurality of liquid lenses.

[0017] The lens controller 12 is the core control unit of the vehicle-mounted system. It can be used to parse the driving data of the target vehicle in real time and select a liquid lens corresponding to the driving data based on a preset decision logic. It can communicate with other sensors and computing units of the target vehicle 10 through, for example, a Controller Area Network (CAN) or an in-vehicle Ethernet bus, generate corresponding control information according to the driving data, and control the FOV adjustment of the liquid lens group 14. Compared with the traditional mechanical switching or fixed lens solutions, this controller directly drives the curvature change of the liquid lens through an electrical signal, achieving a millisecond-level response, avoiding the delay and reliability problems of physical lens switching, and at the same time reducing the computing power burden caused by multi-module redundancy, ensuring real-time performance and stability in high-order autonomous driving scenarios.

[0018] The liquid lens group 14 is composed of multiple electronically controllable focus liquid lenses. Those skilled in the art can understand that the so-called multiple liquid lenses can actually only represent multiple logically, and from a physical form perspective, there is still only one lens. In other words, the same liquid lens can dynamically adjust its own field of view (FOV) by changing the curvature of the internal liquid medium, covering the continuous zoom requirements from wide angle to telephoto. For example, a set of lenses can be preset to 120° wide angle (covering the near-field blind area), 60° standard focal length (medium-distance monitoring), and 30° telephoto (long-distance target recognition) respectively. Compared with traditional fixed-FOV lenses, the liquid lens group does not need to configure multiple independent optical modules, and a single lens can achieve multi-scene adaptive switching, significantly reducing the number of hardware and space occupancy. Specifically, the core structure of the above liquid lens includes a liquid cavity, a driving unit, and a transparent window. The driving unit integrates a piezoelectric ceramic driving layer, an electromagnetic compensation coil (activated at low temperature), and a ring-shaped capacitive sensing film, and triggers the piezoelectric ceramic deformation through a Pulse Width Modulation (PWM) control signal to precisely adjust the curvature of the liquid cavity, achieving millisecond-level dynamic zoom. In addition, it works in cooperation with the lens controller 12, supports seamless switching between different FOV modes through instantaneous electronic control adjustment of the focal length, avoiding the delay and power consumption problems of multi-lens switching in traditional solutions, and being able to take into account panoramic coverage at close range and high-precision detection at long range, meeting the multi-dimensional perception requirements of L3+ autonomous driving for complex environments.

[0019] Figure 2 It is a flowchart of a control method based on a vehicle-mounted lens shown in an exemplary embodiment disclosed by the present invention. The method can specifically include the following steps: Step S202, obtain the vehicle driving data of the target vehicle, and the target vehicle is equipped with multiple liquid lenses corresponding to different fields of view.

[0020] In this specification, the target vehicle can first collect its own driving data in real time through in-vehicle sensors such as speed sensors, steering angle sensors, inertial sensors (Inertial Measurement Unit, IMU), radars, cameras, etc., including but not limited to vehicle motion data mainly composed of vehicle speed, acceleration, angular velocity, and steering angle, as well as vehicle position data determined based on navigation positioning and electronic maps. The above vehicle driving data is transmitted to the processing unit through the in-vehicle bus, providing a dynamic environment perception basis for subsequent lens switching decisions and ensuring the real-time and multi-dimensional nature of the data source.

[0021] Each of the above-mentioned multiple liquid lenses can be independently configured with a corresponding Image Signal Processor (ISP), and the ISP of at least one liquid lens can be different from that of other lenses in terms of hardware architecture or functional modules, so as to achieve the differentiation of ISPs. For example, for a wide-angle lens, its ISP integrates a real-time fisheye distortion correction algorithm and a multi-frame noise reduction module, which preferentially optimizes the geometric accuracy of the near-field large-field-of-view image and the noise suppression in low-light environments; for a telephoto lens, its ISP incorporates a super-resolution reconstruction algorithm and a motion blur compensation module to enhance the detail restoration of distant targets and the stability of dynamic tracking.

[0022] In addition, the different image signal processors configured for the above-mentioned multiple liquid lenses can maintain the dedicated data of their respective lenses based on the same memory, such as memory and video memory, including lens calibration parameters, such as the fisheye correction coefficient of the wide-angle lens, the super-resolution weight parameter of the telephoto lens, etc. This method can also ensure data isolation between partitions through a hardware-level memory protection mechanism to avoid cross-region access conflicts. Of course, a common storage area can also be planned in the above-mentioned memory to store global shared data, such as vehicle attitude information and environmental light models, for all ISPs to read as needed.

[0023] Step S204, select a corresponding target lens from the multiple liquid lenses according to the driving data.

[0024] Based on the real-time driving data, the above system can select a target lens suitable for the current scene from multiple liquid lenses through the above driving data and a preset decision logic.

[0025] When selecting a target lens according to the driving data, the current driving scene of the target vehicle can first be determined. Among them, when determining the current driving scene according to the driving data, two types of inputs, namely vehicle motion data and vehicle position data, can be distinguished, and scene classification logics can be designed respectively: In the first aspect, scenario determination based on vehicle motion data, that is, when the driving data contains motion parameters such as vehicle speed, acceleration, and steering angle, the system can classify driving scenarios in real time through threshold determination or machine learning models such as decision trees and neural networks. For example: when the vehicle motion data indicates that the target vehicle is at a speed less than or equal to low speed (for example, 20km / h) and the steering angle fluctuates frequently, then it is determined to be a near-field monitoring scenario when parking or following a vehicle in congestion, or a low-speed scenario. When the vehicle motion data indicates that the target vehicle is at a medium speed (for example, between 20-60km / h), then it is determined to be a medium-distance balancing scenario when driving on urban roads, or a medium-speed scenario. When the vehicle motion data indicates that the target vehicle is at a speed greater than or equal to high speed (for example, 60km / h), then it can be determined to be a long-distance tracking scenario when cruising or driving on an expressway, or a high-speed scenario.

[0026] Secondly, when driving data includes vehicle location data such as Global Positioning System (GPS) coordinates, high-precision map information, or navigation routes, the system can combine geofencing technology with map semantic information such as road type and traffic regulations to determine the scene. For example, if the vehicle is within the coordinate range of a parking lot, it will be forced to switch to parking mode; if the navigation route indicates that it is about to enter a highway, it will predict a highway scene and preemptively activate the telephoto lens; if a school area is identified on urban roads, it will switch to the wide-angle lens to enhance pedestrian detection. In short, this location data provides global environmental information and supports long-term, forward-looking scene adaptation, compensating for the limitations of motion data. Furthermore, when motion data and location data indicate different scenarios, such as suddenly entering a parking lot while driving at high speed, the system can prioritize the more real-time motion data to trigger scene switching, while simultaneously verifying and correcting the scene classification using location data to ensure robust scene classification. This design, through multi-source data fusion, solves the problem of scene misjudgment in complex road conditions caused by traditional fixed-FOV lenses, improving the assisted driving system's adaptability to dynamic environments.

[0027] In summary, based on the scene classification results, the above system can select an appropriate target lens from multiple liquid lenses based on a preset scene-lens mapping rule. The rule defines that the field of view of the target lens is negatively correlated with the vehicle speed, for example: 1. Low-speed scenarios: A wide-angle lens (FOV = 120°) can be selected to prioritize coverage of the near-range blind spots around the vehicle body, ensuring panoramic perception when parking or avoiding obstacles. At the same time, a fisheye correction algorithm can be simultaneously activated to eliminate wide-angle lens distortion and improve the accuracy of parking assist lines and obstacle positioning.

[0028] 2. Medium-speed scenario: A standard lens (FOV = 60°) can be selected to balance the recognition of medium-distance lane lines and the detection of nearby pedestrians. Specifically, if there are only two liquid lenses, the wide-angle and telephoto lenses, in the liquid lens group, then both the wide-angle and telephoto liquid lenses can be activated simultaneously, and the FOV can be linearly interpolated according to the real-time vehicle speed. For example, when the vehicle speed is 15 km / h, FOV = 120° (wide-angle), and when v = 30 km / h, FOV = 30° (telephoto), and the intermediate speeds are dynamically adjusted proportionally.

[0029] 3. High-speed scenario: A telephoto lens (FOV = 30°) can be selected to focus on long-distance lanes, traffic signs, and the dynamics of the vehicle ahead, and to ensure the tracking stability of long-distance targets through high-frequency closed-loop regulation of algorithms such as the Proportional-Integral-Derivative (PID) controller, while avoiding interference from redundant information in the wide-angle field of view.

[0030] This design solves the contradiction between the field of view and detection distance of traditional fixed lenses in variable vehicle speed scenarios through speed-driven dynamic adjustment of the FOV. For example, reducing the FOV at high speeds can improve the resolution of long-distance targets, while avoiding the risk of false detection caused by blurred long-distance imaging of wide-angle lenses; expanding the FOV at low speeds enhances the ability to capture sudden near-field obstacles. In addition, the system supports optimizing the scene classification and lens switching strategy through a machine learning model to further improve the adaptive performance in complex road conditions.

[0031] Of course, when in-vehicle signals such as GPS and CAN bus used to receive vehicle position data are interrupted or the data reliability is lower than the threshold, motion data such as angular velocity and acceleration provided by the inertial measurement unit can also be additionally used, combined with the historical trajectory prediction algorithm, to maintain the driving scene determination and lens control functions.

[0032] Step S206: Switch the current lens of the multiple liquid lenses to the target lens.

[0033] After selecting the target lens, the above system can send an electric control signal through the operation controller to drive the piezoelectric ceramic layer of the corresponding liquid lens, adjust the curvature of the liquid cavity, and achieve millisecond-level switching of the focal length. For example, it can switch from the wide-angle mode R = 15 mm to the telephoto mode R = 3 mm within 0.5 ms. The switching process does not require physical movement of the lens module and is only completed through the deformation of the liquid medium. Combined with the closed-loop feedback of the capacitive sensing film and PID regulation, the focal length stability is ensured. Compared with the mechanical switching of traditional lens groups, this method can not only eliminate delays but also reduce the hardware redundancy of multiple lenses, significantly optimizing the system response efficiency and integration.

[0034] As described above, when the image signal processor (ISP) corresponding to any one of the multiple liquid lenses, this specification introduces an automatic trigger mechanism for redundant processing, that is, the image signals of the abnormal lens are taken over and processed by other normally operating ISPs, thereby improving the system's fault tolerance.

[0035] In one embodiment, when the image signal processor corresponding to any one of the multiple liquid lenses malfunctions, the image signals of the any one liquid lens can be processed by other image signal processors, thereby ensuring the availability of basic functions. Among them, the so-called abnormality can be obtained by real-time monitoring the operating status of each ISP through heartbeat detection and integrity checks such as CRC checks and hash value comparison data. Once an ISP fails to respond or outputs abnormal data for a preset number of consecutive cycles, it can be determined to be in a faulty state, and the corresponding image signal processor is marked as unavailable, otherwise it is judged to be normal.

[0036] It is worth mentioning that the above liquid lens and the above image signal processor can be respectively connected with independent temperature sensors. Once any temperature sensor meets the heat dissipation conditions of the corresponding device, the temperature control unit corresponding to the temperature sensor can control the radiator of the corresponding device to perform heat dissipation processing. Specifically, for the temperature sensor of the liquid lens, the temperature of the liquid cavity and the driving unit can be monitored, such as the piezoelectric ceramic layer, the electromagnetic compensation coil, etc.; for the temperature sensor of the ISP, the temperature of the processor chip and the memory module can be tracked; when any sensor detects that the temperature exceeds the grading threshold (such as T1 = 60 °C warning, T2 = 80 °C critical), it is determined that heat dissipation needs to be started. Of course, if the lens temperature is greater than or equal to T1, a micro thermoelectric cooler (TEC), such as a thermoelectric cooler, can be started as a radiator to reduce the viscosity of the liquid medium by active cooling and avoid focal length drift caused by high temperature; if the lens temperature is greater than or equal to T2, frequency reduction protection can be synchronously triggered to limit the amplitude of the driving voltage to reduce heat generation. At the same time, if the processor temperature is greater than or equal to T1, a fan or a liquid cooling system can be enabled to improve the heat dissipation efficiency; if the temperature is greater than or equal to T2, the computing task can be dynamically downloaded to give priority to ensuring the basic image processing function.

[0037] In short, each of the above radiators can be adjusted in real time according to temperature changes during operation, and the temperature is maintained in a safe range, such as 55 ± 5 °C, through the PID algorithm; and the temperature-heat dissipation correlation data can be recorded to optimize the heat dissipation strategy and avoid problems such as response lag or overcooling in a fixed heat dissipation scenario.

[0038] The following combines Figure 3 to illustrate the schematic diagram of the architecture of another vehicle-mounted lens-based control system, as Figure 3As described, in one embodiment, the temperature control module 302 in the figure can be an integrated micro thermoelectric cooler and a high-precision temperature sensor, which maintains the working temperature of the liquid lens group 304 stable through active heat dissipation to avoid focal length drift caused by high temperature. The vehicle-mounted sensors 306 can include a vehicle speed sensor, an IMU, a GPS, etc., and can collect data such as the speed, steering angle, and position of the vehicle in real time as vehicle driving data, providing a decision-making basis for lens switching. The liquid lens group 304: consists of an electronically controlled adjustable liquid lens, supports the switching between a wide-angle (130° FOV) and a telephoto (12° FOV) mode, and realizes a millisecond-level deformation response through a piezoelectric ceramic drive layer and a capacitive sensing film. The lens controller 308: receives the driving data based on a Controller Area Network with Flexible Data – Rate (CAN-FD) or in-vehicle Ethernet, executes dynamic mode decision-making, and generates a PWM signal to drive the FOV adjustment of the liquid lens group 304. The main ISP 310 and the auxiliary ISP 312 are heterogeneous computing units that cooperate with each other, hereinafter referred to as the main ISP and the auxiliary ISP for short. Among them, the main ISP is responsible for processing the telephoto data stream, such as super-resolution reconstruction and target tracking of images, and the auxiliary ISP can process the wide-angle data to achieve effects such as fisheye correction and image stitching. The two realize data interaction through a shared memory pool 314, and the memory is divided into areas dedicated to the telephoto raw image in YUV422 format and the wide-angle corrected data in RGB888 format to ensure processing efficiency. The output module 316 integrates the processed image data and outputs it to the in-vehicle display screen or the autonomous driving decision-making unit through dynamic blanking control to complete the environmental perception closed-loop. It can be seen that Figure 3 The architecture shown ensures the hardware stability through the temperature control module 302, and through the collaborative design of the heterogeneous ISP 310 / 312 and the shared memory pool 314, it realizes the efficient processing of multi-modal data, meeting the stringent requirements of high-level autonomous driving for real-time performance and reliability.

[0039] Next, based on Figure 3 , for Figure 4 , the flowchart of another control method based on an in-vehicle lens will be introduced. This method includes the following steps: Step S402: The vehicle-mounted sensors collect vehicle driving data.

[0040] In one embodiment, the vehicle-mounted sensors 306 can collect the vehicle speed, GPS coordinates, steering angle, and IMU data of the target vehicle in real time. For example, when the vehicle speed is 65 km / h and the vehicle is on a highway section, the sensor transmits the above data to the lens controller 308. At the same time, the temperature control module 302 monitors that the temperature of the liquid lens group 304 is 58 °C, and then activates the thermoelectric cooler TEC for pre-cooling to ensure that the lens group maintains a stable working state in subsequent operations.

[0041] Step S404: Data verification and scene classification.

[0042] In one embodiment, the lens controller 308 performs a CRC32 check on the received sensor data to eliminate outliers caused by vehicle speed fluctuations exceeding 20 km / s². Combining GPS coordinates with navigation path information, the system predicts that the vehicle is about to enter the parking lot coordinate fence. When the vehicle speed drops to 10 km / h and the steering angle fluctuation exceeds ±30° / s, the lens controller determines that the current situation is low-speed parking and selects wide-angle lens mode (130° FOV) based on preset rules. If the GPS signal is lost, the system switches to IMU fusion mode, inferring the vehicle's position by integrating angular velocity.

[0043] Step S406: The lens controller switches the current lens to a wide-angle lens.

[0044] In one embodiment, the lens controller 308 generates a 120V PWM drive signal, triggering the deformation of the liquid lens assembly 304 through the piezoelectric ceramic layer. The curvature radius of the liquid cavity switches from 15mm in wide-angle mode to 3mm in telephoto mode within 0.5ms. The capacitive sensing film provides real-time feedback on deformation errors, approximately ±0.1mm. The lens controller 3 also stabilizes the drive voltage to 118V using a PID closed-loop control system to ensure focal length accuracy.

[0045] Step S408: The auxiliary ISP performs wide-angle image processing.

[0046] In one embodiment, the secondary ISP 312 reads wide-angle raw data in YUV422 format from a specified address in the shared memory pool 314, such as 0x4000-0x7FFF, loads fisheye correction parameters (distortion coefficients k1 = -0.28, k2 = 0.06), and performs multi-frame noise reduction and geometric correction. The corrected RGB888 format image is then transferred to the output module 316 via direct memory access (DMA), with near-field obstacle feature points marked.

[0047] Step S410: The primary ISP takes over the target detection task.

[0048] In one embodiment, the primary ISP 310 launches a lightweight YOLOv5-Tiny model to perform inference on images processed by the secondary ISP 312, identifying nearby obstacles such as pedestrians and pillars. The model outputs target coordinates and confidence levels, and a CRC32+ECC check is performed on the hardware safety island 301 to ensure data integrity. If the primary ISP 310 temperature exceeds 80°C, the temperature control module 302 triggers the liquid cooling system and reduces the load on non-critical tasks.

[0049] Step S412: The output module completes the environmental perception closed-loop.

[0050] In one embodiment, the output module 316 performs quality verification on the panoramic image (PSNR≥32dB), and eliminates frames that are blurred or have excessive distortion. After passing the verification, the obstacle coordinates and the panoramic view are transmitted to the automatic parking system of the target vehicle via the CAN bus, and the sound and light alarms are triggered synchronously. At the same time, the temperature control module 302 dynamically adjusts the TEC power according to the lens deformation frequency, and controls the temperature gradient within ≤3°C / s to ensure the long-term stability of the system.

[0051] Figure 5 is a schematic structural diagram of an electronic device in an exemplary embodiment. Please refer to Figure 5 , at the hardware level, the electronic device includes a processor 502, an internal bus 510, a network interface 504, a memory 506, and a non-volatile memory 508. Of course, other required hardware may also be included. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a detection device for risk codes at the logical level. Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logical devices or a combination of software and hardware. That is to say, the execution subject of the following processing flow is not limited to each logical unit, and can also be hardware or a logical device.

[0052] Figure 6 A block diagram of a control device based on an in-vehicle lens shown in an embodiment of the present invention. Please refer to Figure 6 , this device can be applied to a device such as Figure 5 shown to implement the technical solution described in the present invention. The device includes: A vehicle driving data acquisition unit 602, configured to acquire vehicle driving data of a target vehicle, where the target vehicle is configured with a plurality of liquid lenses corresponding to different field of view ranges; A target lens selection unit 604, configured to select a corresponding target lens from the plurality of liquid lenses according to the driving data; A lens switching unit 606, configured to switch the current lens of the plurality of liquid lenses to the target lens.

[0053] Optionally, the target lens selection unit 604 is specifically configured to: Determine the current driving scenario of the target vehicle according to the driving data; Select a corresponding target lens from the plurality of liquid lenses according to the current driving scenario, and the field of view range of the target lens is negatively correlated with the vehicle speed corresponding to the current driving scenario.

[0054] Optionally, the apparatus for determining the current driving scenario of the target vehicle according to the driving data is specifically configured to: When the vehicle driving data includes the vehicle motion data of the target vehicle, determine the current driving scenario according to the vehicle motion data; When the vehicle driving data includes the vehicle position data of the target vehicle, determine the current driving scenario according to the vehicle position data.

[0055] Optionally, each of the plurality of liquid lenses is respectively configured with an image signal processor, and the image signal processor configured for at least one of the plurality of liquid lenses is different from that of other liquid lenses.

[0056] Optionally, different image signal processors maintain the lens data corresponding to the respective liquid lenses based on the same memory.

[0057] Optionally, the apparatus further includes: An image signal processor redundancy unit, configured to, when an image signal processor corresponding to any one of the plurality of liquid lenses has an exception, process the image signal of the any one liquid lens by other image signal processors.

[0058] Optionally, temperature sensors are respectively connected to the liquid lens and the image signal processor; the apparatus further includes: A device heat dissipation unit, configured to, when any one temperature sensor meets the heat dissipation condition of the corresponding device, control the radiator of the corresponding device to perform heat dissipation processing.

[0059] For the implementation processes of the functions and roles of each unit in the above apparatus, please refer to the implementation processes of the corresponding steps in the above method for details, which will not be elaborated here.

[0060] For the apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial descriptions of the method embodiments. The apparatus embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0061] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor realizes the steps of the method as described in any of the above embodiments by running the executable instructions.

[0062] Based on the same concept as the above method, this specification also provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method as described in any of the above embodiments are realized.

[0063] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the method as described in any of the above embodiments are realized.

[0064] Embodiments of the subject matter and functional operations described in this specification can be implemented in the following: digital electronic circuits, tangible computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules in computer program instructions encoded on a tangible non-transitory program carrier to be executed by a data processing apparatus or to control the operation of the data processing apparatus. Alternatively or additionally, the program instructions can be encoded on a manually generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by the data processing apparatus. A computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0065] The processes and logical flows described in this specification can be executed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logical flows can also be executed by dedicated logic circuits - such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits), and the apparatus can also be implemented as dedicated logic circuits.

[0066] Computers suitable for executing computer programs include, for example, general and / or special purpose microprocessors, or any other type of central processing unit. Generally, the central processing unit will receive instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing the instructions and data. Generally, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, etc., or the computer will be operatively coupled to such mass storage devices to receive data therefrom or transfer data thereto, or both. However, a computer is not necessarily required to have such devices. In addition, a computer may be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a GPS receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name just a few.

[0067] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as including semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0068] Although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of what is claimed, but rather as mainly being used to describe the features of specific embodiments of a particular invention. Certain features that are described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may act in certain combinations as described above and even be initially claimed as such, one or more features from a claimed combination may in some cases be removed from that combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination.

[0069] Similarly, although operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or sequentially, or that all illustrated operations be performed, to achieve a desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0070] Accordingly, specific embodiments of the subject matter have been described. Additionally, the processes depicted in the figures are not necessarily in the particular order or sequential order shown to achieve the desired results. In certain implementations, multitasking and parallel processing may be advantageous.

[0071] The above are only the preferred embodiments of this specification and are not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification shall be included within the scope of protection of this specification.

Claims

1. A control method for a vehicle-mounted lens, characterized in that, The method includes: Obtaining vehicle driving data of a target vehicle, where the target vehicle is configured with a plurality of liquid lenses corresponding to different field of views; Selecting a corresponding target lens from the plurality of liquid lenses according to the driving data; Switching the current lens of the plurality of liquid lenses to the target lens.

2. The method according to claim 1, characterized in that, The selecting a corresponding target lens from the plurality of liquid lenses according to the driving data includes: Determining the current driving scenario of the target vehicle according to the driving data; Selecting a corresponding target lens from the plurality of liquid lenses according to the current driving scenario, where the field of view of the target lens is negatively correlated with the vehicle speed corresponding to the current driving scenario.

3. The method according to claim 2, wherein The determining the current driving scenario of the target vehicle according to the driving data includes: When the vehicle driving data includes the vehicle motion data of the target vehicle, determining the current driving scenario according to the vehicle motion data; When the vehicle driving data includes the vehicle position data of the target vehicle, determining the current driving scenario according to the vehicle position data.

4. The method according to claim 1, wherein Each of the plurality of liquid lenses is respectively configured with an image signal processor, and at least one of the plurality of liquid lenses is configured with an image signal processor different from other liquid lenses.

5. The method according to claim 4, characterized in that The different image signal processors maintain the lens data corresponding to the corresponding liquid lenses based on the same memory.

6. The method according to claim 4, characterized in that The method further includes: When an abnormality occurs in the image signal processor corresponding to any one of the plurality of liquid lenses, processing the image signal of the any one liquid lens by other image signal processors.

7. The method according to claim 4, wherein Temperature sensors are respectively connected to the liquid lens and the image signal processor; the method further includes: When any temperature sensor meets the heat dissipation condition of the corresponding device, controlling the radiator of the corresponding device to perform heat dissipation processing.

8. A control device for a vehicle-mounted lens, characterized in that, The device includes: A vehicle driving data acquisition unit, configured to acquire vehicle driving data of a target vehicle, where the target vehicle is configured with a plurality of liquid lenses corresponding to different field of views; A target lens selection unit, configured to select a corresponding target lens from the plurality of liquid lenses according to the driving data; A lens switching unit, configured to switch the current lens of the plurality of liquid lenses to the target lens.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, Including a computer program / instructions, when the computer program / instructions are executed by a processor, it implements the steps of the method according to any one of claims 1 - 7.

Images