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

Abstract

The application provides a vehicle-mounted lens control method and device, a readable storage medium and a program product. The method comprises the following steps: obtaining vehicle driving data of a target vehicle, wherein the target vehicle is provided with a plurality of liquid lenses corresponding to different field of view ranges respectively; selecting a corresponding target lens from the plurality of liquid lenses according to the driving data; and switching a current lens of the plurality of liquid lenses to the target lens.

Description

Technical Field

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

[0002] The on-board surround view system is a core perception technology for intelligent driving. It aims to create a 360-degree panoramic view of the vehicle's surroundings in real time through the collaborative work of multiple cameras, eliminating blind spots and improving driving safety and reliability. Its principle generally 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 merged into a unified panoramic image and transmitted to the on-board computing unit for environmental perception. This technology can help vehicles accurately identify close-range obstacles, pedestrians, and complex road conditions, providing critical environmental information for scenarios such as parking and low-speed driving. It is the core support for autonomous driving systems to achieve basic environmental interaction.

[0003] In related technologies, lenses with a fixed field of view (FOV, also known as field of view angle) are usually used for environmental monitoring, resulting in insufficient adaptability of the above-mentioned systems in dynamic scenes. Specifically, the fixed FOV design faces a contradiction between detection distance and field of view width: wide-angle lenses have a wide field of view but a short detection distance, making it difficult to capture distant targets; telephoto lenses can recognize distant objects but sacrifice information about the surrounding environment, making it easy to miss sudden obstacles nearby. In addition, even if the device achieves switching between wide-angle and telephoto lenses at the cost of high latency, this means that traditional systems still require additional hardware support, increasing power consumption and space occupation. Especially in the changing scenarios of high-level autonomous driving such as L3 and L4, the problems of response lag, incomplete scene coverage, and high computing power requirements of such systems are prominent, seriously restricting the ability to make real-time decisions under 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 a vehicle-mounted lens to address the deficiencies in the related art.

[0005] Specifically, this specification is implemented through the following technical solutions:

[0006] According to a first aspect of this specification, a method for controlling a vehicle-mounted lens is provided, the method comprising:

[0007] Acquiring vehicle driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different field of view ranges;

[0008] Selecting a corresponding target lens from the plurality of liquid lenses according to the driving data;

[0009] Switching a current lens of the plurality of liquid lenses to the target lens.

[0010] According to a second aspect of this specification, a control device for a vehicle-mounted lens is provided, the device comprising:

[0011] A vehicle driving data acquisition unit, configured to acquire vehicle driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different field of view ranges;

[0012] a target lens selection unit, configured to select a corresponding target lens from the plurality of liquid lenses according to the driving data;

[0013] A lens switching unit is used to switch a current lens of the plurality of liquid lenses to the target lens.

[0014] According to a third aspect of this specification, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0015] According to a fourth aspect of this specification, a computer program product includes a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.

[0016] This application addresses the conflict between detection range and field of view width in traditional fixed-FOV lenses by dynamically switching the field of view of a liquid lens. The corresponding liquid lens is selected in real time based on vehicle driving data. Because the liquid lens can adjust its focal length without requiring a mechanical structure, it avoids the hardware redundancy and latency associated with switching between traditional wide-angle and telephoto lenses. By covering multiple scenarios with a single lens, it significantly reduces space usage, power consumption, and computing load, enabling more efficient environmental perception and real-time decision-making in scenarios such as advanced autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present invention, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0018] Figure 1 1 is a schematic diagram of the architecture of a control system based on a vehicle-mounted lens according to an embodiment disclosed in the present invention;

[0019] Figure 2 This is a flow chart of a control method based on a vehicle-mounted lens shown in an embodiment disclosed in the present invention;

[0020] Figure 3 This is a schematic diagram of the architecture of another control system based on a vehicle-mounted camera according to an embodiment disclosed in the present invention;

[0021] Figure 4 is a flow chart of another control method based on a vehicle-mounted lens according to an embodiment disclosed in the present invention;

[0022] Figure 5 is a schematic structural diagram of an electronic device shown in an embodiment of the present invention;

[0023] Figure 6 This is a block diagram of a control device based on a vehicle-mounted lens shown in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present invention.

[0025] The terms used in this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The singular forms "a," "the," and "the" used in this invention and the appended claims are also intended to include 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.

[0026] 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 merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0027] The following describes in detail an embodiment of the control method based on the vehicle-mounted lens of the present invention with reference to the accompanying drawings.

[0028] Figure 1 This is a schematic diagram of the architecture of a vehicle-mounted lens control system shown in the embodiment disclosed in this specification. Figure 1 As shown, the system may include a lens controller 12 in a target vehicle 10 and a liquid lens assembly 14 including a plurality of liquid lenses.

[0029] The lens controller 12 is the core control unit of the vehicle-mounted system, capable of analyzing the target vehicle's driving data in real time and selecting the appropriate liquid lens based on pre-set decision logic. It communicates with other sensors and computing units in the target vehicle 10 via, for example, a Controller Area Network (CAN) or Ethernet vehicle bus. Based on the driving data, it generates control information to adjust the field of view (FOV) of the liquid lens assembly 14. Compared to traditional mechanical switching or fixed lens solutions, this controller directly drives the curvature of the liquid lens through electrical signals, achieving millisecond-level response, avoiding the latency and reliability issues associated with physical lens switching. It also reduces the computing power burden associated with multi-module redundancy, ensuring real-time performance and stability in advanced autonomous driving scenarios.

[0030] The liquid lens assembly 14 is composed of multiple electrically controlled, focus-adjustable liquid lenses. Those skilled in the art will appreciate that the term "multiple" liquid lenses may simply represent a logical plurality; physically, there remains only one lens. In other words, the field of view (FOV) of the same liquid lens can be dynamically adjusted simply by changing the curvature of the liquid medium within it, enabling continuous zoom from wide angle to telephoto. For example, a set of lenses can be preset for a 120° wide angle (covering near-field blind spots), a 60° standard focal length (for mid-range monitoring), and a 30° telephoto (for long-range object recognition). Compared to traditional fixed-FOV lenses, liquid lens systems eliminate the need for multiple independent optical modules. A single lens can achieve adaptive switching across multiple scenes, significantly reducing hardware requirements and space usage. Specifically, the core structure of the liquid lens comprises a liquid cavity, a drive unit, and a transparent window. The drive unit integrates a piezoelectric ceramic drive layer, an electromagnetic compensation coil (activated at low temperatures), and a ring-shaped capacitive sensing film. Pulse Width Modulation (PWM) control signals trigger the deformation of the piezoelectric ceramic, precisely adjusting the curvature of the liquid cavity and achieving millisecond-level dynamic zoom. Furthermore, the liquid lens works in conjunction with the lens controller 12 to enable seamless switching between different FOV modes through instantaneous electronic adjustment of the focal length. This avoids the latency and power consumption associated with multi-lens switching in traditional solutions while balancing close-range panoramic coverage with long-range high-precision detection, meeting the multi-dimensional perception requirements of complex environments for Level 3+ autonomous driving.

[0031] Figure 2 This is a flowchart of a control method based on a vehicle-mounted lens shown in an exemplary embodiment disclosed in the present invention. The method may specifically include the following steps:

[0032] Step S202 : Acquire vehicle driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different field of view ranges.

[0033] In this specification, the target vehicle first collects real-time driving data using onboard sensors such as speed sensors, steering angle sensors, inertial measurement units (IMUs), radars, and cameras. This data includes, but is not limited to, vehicle motion data primarily based on speed, acceleration, angular velocity, and steering angle, as well as vehicle position data determined by navigation and electronic maps. This driving data is transmitted to the processing unit via an onboard bus, providing a dynamic environmental perception foundation for subsequent camera switching decisions, ensuring the real-time and multi-dimensional nature of the data source.

[0034] Each of the above-mentioned 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, thereby achieving ISP differentiation. For example, the ISP of a wide-angle lens integrates a real-time fisheye distortion correction algorithm and a multi-frame noise reduction module, giving priority to optimizing the geometric accuracy of near-field large-field images and noise suppression in low-light environments; for a telephoto lens, its ISP has a built-in super-resolution reconstruction algorithm and a motion blur compensation module to enhance the detail restoration and dynamic tracking stability of distant targets.

[0035] Furthermore, the different image signal processors in the aforementioned multiple liquid lens configurations can maintain their respective lens-specific data based on the same memory, such as internal memory or video memory. This includes lens calibration parameters, such as the fisheye correction coefficient for wide-angle lenses and the super-resolution weight parameters for telephoto lenses. This approach can also ensure data isolation between partitions through hardware-level memory protection mechanisms to avoid cross-partition access conflicts. Of course, a public storage area can also be planned in the aforementioned memory to store globally shared data, such as vehicle posture information and ambient lighting models, for on-demand reading by all ISPs.

[0036] Step S204 : selecting a corresponding target lens from the plurality of liquid lenses according to the driving data.

[0037] Based on real-time driving data, the system can select a target lens suitable for the current scene from multiple liquid lenses using the driving data and preset decision logic.

[0038] When selecting target shots based on driving data, the current driving scene of the target vehicle can be determined first. When determining the current driving scene based on driving data, two types of inputs can be distinguished: vehicle motion data and vehicle position data, and scene classification logic is designed for each:

[0039] 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.

[0040] 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.

[0041] 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:

[0042] 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.

[0043] 2. Medium-speed scenario: You can choose a standard lens (FOV = 60°) to balance mid-range lane recognition and close-up pedestrian detection. In particular, if the liquid lens group only has wide-angle and telephoto liquid lenses, then the wide-angle and telephoto liquid lenses can be activated simultaneously, and the FOV is linearly interpolated according to the real-time vehicle speed. For example, at a speed of 15 km / h, FOV = 120° (wide-angle), and at v = 30 km / h, FOV = 30° (telephoto). Intermediate speeds are dynamically adjusted proportionally.

[0044] 3. High-speed scenarios: A telephoto lens (FOV = 30°) can be selected to focus on distant lanes, traffic signs, and the dynamics of the vehicle ahead. High-frequency closed-loop adjustment, such as the Proportional-Integral-Derivative Controller (PID) algorithm, ensures tracking stability of distant targets while avoiding interference from redundant information in the wide-angle field of view.

[0045] This design resolves the conflict between field of view and detection range in variable speed scenarios with traditional fixed lenses through speed-driven dynamic adjustment of the FOV. For example, reducing the FOV at high speeds improves resolution of distant targets while minimizing the risk of false detections caused by blurring at long distances with wide-angle lenses. Expanding the FOV at low speeds enhances the ability to detect sudden obstacles in the near field. Furthermore, the system uses machine learning models to optimize scene classification and lens switching strategies, further enhancing adaptive performance in complex road conditions.

[0046] Of course, when the on-board signals used to receive vehicle position data, such as GPS and CAN bus, are interrupted or the data reliability is lower than the threshold, the angular velocity, acceleration and other motion data provided by the inertial measurement unit can be combined with the historical trajectory prediction algorithm to maintain the driving scene judgment and lens control functions.

[0047] Step S206 : Switching the current lens of the plurality of liquid lenses to the target lens.

[0048] After selecting the target lens, the system can send an electrical control signal through the operating controller to drive the piezoelectric ceramic layer of the corresponding liquid lens, adjust the curvature of the liquid cavity, and achieve millisecond-level focal length switching, for example, switching from wide-angle mode R = 15mm to telephoto mode R = 3mm in 0.5ms. The switching process does not require physical movement of the lens module, but is completed solely through the deformation of the liquid medium. Combined with closed-loop feedback and PID control of the capacitive sensing film, focal length stability is ensured. Compared with the mechanical switching of traditional lens groups, this method can not only eliminate delays, but also reduce multi-lens hardware redundancy, significantly optimizing system response efficiency and integration.

[0049] As mentioned above, when the image signal processor ISP corresponding to any of the multiple liquid lenses is abnormal, this specification introduces an automatic triggering mechanism for redundant processing, that is, other normally operating ISPs take over and process the image signal of the abnormal lens, thereby improving the system's fault tolerance.

[0050] In one embodiment, if an image signal processor corresponding to any of the multiple liquid lenses experiences an abnormality, another image signal processor can process the image signal of that liquid lens, thereby ensuring the availability of basic functions. The abnormality can be detected by real-time monitoring of the operating status of each ISP through heartbeat detection and integrity checks such as CRC checks and hash value comparisons. If an ISP fails to respond for a predetermined number of consecutive cycles or outputs abnormal data, it can be determined to be in a fault state and the corresponding image signal processor can be marked as unavailable. Otherwise, it is considered normal.

[0051] It's worth noting that the liquid lens and image signal processor can each be connected to an independent temperature sensor. Once either temperature sensor meets the corresponding device's heat dissipation requirements, the temperature control unit associated with the corresponding temperature sensor can control the corresponding device's heat sink for heat dissipation. Specifically, the liquid lens's temperature sensor can monitor the temperature of the liquid cavity and driver unit, such as the piezoelectric ceramic layer and electromagnetic compensation coil. The ISP's temperature sensor can track the temperature of the processor chip and memory module. When either sensor detects a temperature exceeding a threshold (e.g., T1 = 60°C for warning, T2 = 80°C for critical), heat dissipation is initiated. If the lens temperature is greater than or equal to T1, a micro-thermoelectric cooler (TEC), such as a semiconductor refrigeration chip, can be activated as a heat sink. This active cooling reduces the viscosity of the liquid medium, preventing focal length drift caused by high temperatures. If the lens temperature is greater than or equal to T2, frequency reduction protection can be triggered to limit the drive voltage amplitude to reduce heat generation. At the same time, if the processor temperature is greater than or equal to T1, the fan or liquid cooling system can be enabled to improve heat dissipation efficiency; if the temperature is greater than or equal to T2, the computing tasks can be dynamically reduced to prioritize basic image processing functions.

[0052] In short, each of the above-mentioned radiators can be adjusted in real time according to temperature changes during operation, and the temperature can be 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 response lag or overcooling problems in fixed heat dissipation scenarios.

[0053] The following combination Figure 3 Another schematic diagram of the control system based on the vehicle-mounted lens is described as follows: Figure 3In one embodiment, the temperature control module 302 in the figure can be an integrated micro-thermoelectric cooler and a high-precision temperature sensor. Active heat dissipation maintains a stable operating temperature for the liquid lens assembly 304, preventing focal length drift caused by high temperatures. Vehicle sensors 306 can include a speed sensor, IMU, GPS, and other sensors, collecting real-time data such as vehicle speed, steering angle, and position as driving data to inform lens switching decisions. The liquid lens assembly 304 consists of an electrically controlled, focus-adjustable liquid lens that supports wide-angle (130° FOV) and telephoto (12° FOV) mode switching. It achieves millisecond-level deformation response through a piezoelectric ceramic drive layer and capacitive sensing film. The lens controller 308 receives driving data via a Controller Area Network with Flexible Data Rate (CAN-FD) or in-vehicle Ethernet, performs dynamic mode decisions, and generates PWM signals to drive FOV adjustment for the liquid lens assembly 304. The primary ISP 310 and the secondary ISP 312 are heterogeneous computing units that collaborate and divide responsibilities. They are hereinafter referred to as the primary and secondary ISPs. Among them, the main ISP is responsible for telephoto data stream processing, such as super-resolution reconstruction of images and target tracking, and the auxiliary ISP can process wide-angle data to achieve effects such as fisheye correction and image stitching. The two realize data interaction through the shared memory pool 314. The memory is divided into dedicated areas for telephoto original images in YUV422 format and wide-angle correction data in RGB888 format to ensure processing efficiency. The output module 316 integrates the processed image data and outputs it to the vehicle display or autonomous driving decision unit through dynamic blanking control to complete the environmental perception closed loop. It can be seen that Figure 3 The illustrated architecture ensures hardware stability through a temperature control module 302 and, combined with the collaborative design of heterogeneous ISPs 310 / 312 and a shared memory pool 314, enables efficient processing of multimodal data, meeting the stringent real-time and reliability requirements of advanced autonomous driving.

[0054] The following is based on Figure 3 ,right Figure 4 Another control method based on a vehicle-mounted lens is described in the flowchart, which includes the following steps:

[0055] Step S402: The vehicle-mounted sensor collects vehicle driving data.

[0056] In one embodiment, the onboard sensor 306 can collect the target vehicle's speed, GPS coordinates, steering angle, and IMU data in real time. For example, when the vehicle's speed is 65 km / h and it is located on a highway, the sensor transmits this data to the lens controller 308. Simultaneously, the temperature control module 302 detects that the temperature of the liquid lens assembly 304 is 58°C and immediately activates the semiconductor cooling element (TEC) to pre-cool the liquid lens assembly, ensuring that the lens assembly maintains a stable operating state during subsequent operations.

[0057] Step S404: Data verification and scene classification.

[0058] 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.

[0059] Step S406: The lens controller switches the current lens to a wide-angle lens.

[0060] 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.

[0061] Step S408: The auxiliary ISP performs wide-angle image processing.

[0062] 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.

[0063] Step S410: The primary ISP takes over the target detection task.

[0064] 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.

[0065] Step S412: The output module completes the environment perception closed loop.

[0066] In one embodiment, the output module 316 performs a quality check on the panoramic image (PSNR ≥ 32dB) and removes frames with excessive blur or distortion. Once the check passes, the obstacle coordinates and the panoramic view are transmitted via the CAN bus to the target vehicle's automatic parking system, triggering an audible and visual alarm. Simultaneously, the temperature control module 302 dynamically adjusts the TEC power based on the lens deformation frequency, controlling the temperature gradient to ≤ 3°C / s to ensure long-term system stability.

[0067] Figure 5 This is a schematic structural diagram of an electronic device in an exemplary embodiment. 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, and may also include other necessary hardware. The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a risk code detection device at the logical level. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware. In other words, the execution of the following processing flow is not limited to individual logic units and can also be hardware or logic devices.

[0068] Figure 6 The block diagram of a control device based on a vehicle-mounted lens is shown in the embodiment of the present invention. Figure 6 , the device can be used for Figure 5 In the device shown, to implement the technical solution of the present invention, the device includes:

[0069] A vehicle driving data acquisition unit 602 is used to acquire vehicle driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different field of view ranges;

[0070] a target lens selection unit 604, configured to select a corresponding target lens from the plurality of liquid lenses according to the driving data;

[0071] The lens switching unit 606 is configured to switch the current lens of the plurality of liquid lenses to the target lens.

[0072] Optionally, the target shot selection unit 604 is specifically configured to:

[0073] determining a current driving scene of the target vehicle based on the driving data;

[0074] A target lens corresponding to the current driving scene is selected from the plurality of liquid lenses, wherein a field of view of the target lens is negatively correlated with a vehicle speed corresponding to the current driving scene.

[0075] Optionally, the device for determining the current driving scene of the target vehicle based on the driving data is specifically configured to:

[0076] In a case where the vehicle driving data includes vehicle motion data of the target vehicle, determining the current driving scene according to the vehicle motion data;

[0077] In a case where the vehicle travel data includes vehicle position data of the target vehicle, the current driving scene is determined according to the vehicle position data.

[0078] 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 the other liquid lenses.

[0079] Optionally, different image signal processors maintain lens data corresponding to the liquid lens based on the same memory.

[0080] Optionally, the device further includes:

[0081] The image signal processor redundancy unit is configured to, when an image signal processor corresponding to any one of the plurality of liquid lenses fails, process the image signal of the liquid lens by another image signal processor.

[0082] Optionally, the liquid lens and the image signal processor are respectively connected to a temperature sensor; the device further includes:

[0083] The device heat dissipation unit is used to control the radiator of the corresponding device to perform heat dissipation processing when any temperature sensor meets the heat dissipation conditions of the corresponding device.

[0084] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0085] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0086] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0087] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0088] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

[0089] Embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied 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 may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation 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 device. The computer storage medium may 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.

[0090] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can be implemented as, special-purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0091] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a 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 instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to such mass storage devices to receive data from them or to transmit data to them, or both. However, a computer does not necessarily have such devices. In addition, a computer can 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 a few.

[0092] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, 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 memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0093] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of specific embodiments of specific inventions. Certain features described in multiple embodiments within 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 work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of the sub-combination.

[0094] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood 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.

[0095] Thus, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the particular order shown or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0096] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A method for controlling a vehicle-mounted lens, characterized in that: The method comprises: Acquiring vehicle driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different fields of view, each of the plurality of liquid lenses is equipped with an image signal processor, and at least one of the plurality of liquid lenses is equipped with an image signal processor different from that of the other liquid lenses; and the liquid lenses and the image signal processor are respectively connected to independent temperature sensors; Selecting a corresponding target lens from the plurality of liquid lenses according to the driving data; Switching a current lens of the plurality of liquid lenses to the target lens; The method further comprises: When any temperature sensor meets the heat dissipation condition of the corresponding device, the radiator of the corresponding device is controlled to perform heat dissipation processing, and the liquid lens and the image signal processor respectively perform different heat dissipation processing based on the corresponding heat dissipation conditions.

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 comprises: determining a current driving scene of the target vehicle based on the driving data; A target lens corresponding to the current driving scene is selected from the plurality of liquid lenses, wherein a field of view of the target lens is negatively correlated with a vehicle speed corresponding to the current driving scene.

3. The method according to claim 2, characterized in that The determining the current driving scene of the target vehicle according to the driving data includes: In a case where the vehicle driving data includes vehicle motion data of the target vehicle, determining the current driving scene according to the vehicle motion data; In a case where the vehicle travel data includes vehicle position data of the target vehicle, the current driving scene is determined according to the vehicle position data.

4. The method according to claim 1, wherein Different image signal processors maintain lens data of corresponding liquid lenses based on the same memory.

5. The method according to claim 1, wherein The method further comprises: When an image signal processor corresponding to any one of the plurality of liquid lenses fails, the image signal of the liquid lens is processed by another image signal processor.

6. A control device for a vehicle-mounted lens, characterized in that: The device comprises: A vehicle driving data acquisition unit, configured to acquire driving data of a target vehicle, wherein the target vehicle is equipped with a plurality of liquid lenses corresponding to different fields of view; each of the plurality of liquid lenses is equipped with an image signal processor, and at least one of the plurality of liquid lenses is equipped with an image signal processor different from that of the other liquid lenses; and the liquid lenses and the image signal processor are respectively connected to independent temperature sensors; 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; The device further comprises: The device heat dissipation unit is used to control the radiator of the corresponding device to perform heat dissipation processing when any temperature sensor meets the heat dissipation conditions of the corresponding device. The liquid lens and the image signal processor respectively perform different heat dissipation processing based on the corresponding heat dissipation conditions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer program product, characterized in that The method comprises a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 5 when executed by a processor.

Images