Data acquisition method and device of hovercar, electronic equipment and storage medium

Abstract

The invention discloses a data acquisition method and device for a hovercar, electronic equipment and a storage medium. The method comprises the following steps: acquiring flight state data and environment data of a target hovercar; environment data is collected through a browser; performing target identification and scene identification on the environment data based on a preset identification model operated by the browser to obtain a target identification result and a scene identification result; under the condition that the target recognition result, the scene recognition result and the flight state data meet preset conditions, a data acquisition request is sent to the target hovercar through the browser; the data acquisition request is used for requesting the target hovercar to acquire original sensing data of the target hovercar and the surrounding environment. According to the embodiment of the invention, the data acquisition efficiency and acquisition quality can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data acquisition method, device, electronic device, and storage medium for a flying car. Background Technology

[0002] In recent years, artificial intelligence has developed rapidly, and flying cars, as an important component of strategic emerging industries, have attracted increasing attention. During flight, flying cars can improve driving safety and achieve more precise and intelligent control through autonomous driving technology, leading to a continuous increase in the demand for autonomous driving data. However, in related technologies, manual identification is prone to omissions and inaccuracies, and the large volume of data collection results in unstable data acquisition, leading to low data quality, accuracy, and stability. Summary of the Invention

[0003] To address the aforementioned problems in the prior art, this invention discloses a data acquisition method, device, electronic equipment, and storage medium for flying cars, which can improve data acquisition efficiency and quality. The technical solution disclosed in this invention is as follows: According to one aspect of the disclosed embodiments of the present invention, a data acquisition method for a flying car is provided, comprising: Acquire flight status data and environmental data of the target flying car; the environmental data is collected via a browser; Based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the environmental data to obtain target recognition results and scene recognition results; When the target recognition result, the scene recognition result, and the flight status data meet preset conditions, a data acquisition request is sent to the target flying car through the browser; the data acquisition request is used to request the target flying car to collect the raw perception data of the target flying car and its surrounding environment.

[0004] Optionally, when the target recognition result, the scene recognition result, and the flight status data meet preset conditions, sending a data collection request to the target flying car through the browser includes: If the target recognition result includes a preset target and the scene recognition result includes a preset scene, the flight status data is matched with the preset conditions corresponding to the preset scene to obtain a matching result; If the matching result indicates that the current scene is the preset scene, the data collection request is sent to the target flying car through the browser.

[0005] Optionally, the scene recognition result includes a first scene recognition result and a second scene recognition result, and the method further includes: The target scene recognition result is determined from the first scene recognition result and the second scene recognition result; The browser sends the data acquisition request to the target flying car, so that the target flying car can acquire the current environmental data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, based on the data acquisition frequency corresponding to the target scene recognition result. The current environment data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, are labeled and stored.

[0006] Optionally, the data acquisition request includes a data acquisition frequency, and the method further includes: The data acquisition frequency corresponding to the scene recognition result is determined according to the preset mapping relationship; the preset mapping relationship is used to characterize the correspondence between the scene recognition result and the data acquisition frequency.

[0007] Optionally, the step of performing target recognition and scene recognition on the environmental data based on the preset recognition model running in the browser to obtain target recognition results and scene recognition results includes: The environmental data is input into the preset recognition model to obtain at least one target recognition result and at least one scene recognition result, as well as their respective confidence levels; When any confidence level is greater than or equal to a preset confidence threshold, the corresponding target recognition result and scene recognition result are obtained.

[0008] Optionally, the environmental data includes 3D point cloud data and environmental image data. The target recognition and scene recognition of the environmental data based on the preset recognition model running in the browser, to obtain target recognition results and scene recognition results, includes: The 3D point cloud data and the environmental image data are fused to obtain fused environmental data. Based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the fused environment data to obtain the target recognition result and the scene recognition result.

[0009] Optionally, the method is applied to a preset terminal including a control module and a subordinate execution module, the method is executed by the control module and the subordinate execution module, and the method further includes: The control module acquires the performance parameters corresponding to the subordinate execution module; Based on the performance parameters and a preset parameter range, the control module adjusts the execution task volume corresponding to each of the control module and the subordinate execution module, and based on the adjusted execution task volume, repeats the iterative steps of the control module obtaining the performance parameters corresponding to the subordinate execution module and adjusting the execution task volume corresponding to each of the control module and the subordinate execution module based on the performance parameters and the preset parameter range, until the performance parameters are within the preset parameter range.

[0010] According to another aspect of the disclosed embodiments of the present invention, a data acquisition device for a flying car is provided, comprising: The acquisition module is used to acquire flight status data and environmental data of the target flying car; the environmental data is collected through a browser. The recognition module is used to perform target recognition and scene recognition on the environmental data based on the preset recognition model running in the browser, and obtain target recognition results and scene recognition results; The data acquisition request sending module is used to send a data acquisition request to the target flying car through the browser when the target recognition result, the scene recognition result, and the flight status data meet preset conditions; the data acquisition request is used to request the target flying car to collect the original perception data of the target flying car and its surrounding environment.

[0011] According to another aspect of the disclosed embodiments of the present invention, an electronic device for data acquisition of a flying car is provided, including a processor and a memory, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the data acquisition method of the flying car described in any of the preceding claims.

[0012] According to another aspect of the disclosed embodiments of the present invention, a computer-readable storage medium is provided, wherein at least one instruction is stored in the computer storage medium, the at least one instruction being loaded and executed by a processor to implement the data acquisition method for a flying car as described in any of the preceding claims.

[0013] According to another aspect of the disclosed embodiments of the present invention, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to execute the data acquisition method for a flying car as described in any of the above-described embodiments of the present invention.

[0014] The data acquisition method for flying cars provided by this invention has the following technical effects: The data acquisition method for flying cars provided by this invention first acquires the flight status data and environmental data of the target flying car; the environmental data is collected through a browser; based on a preset recognition model running in the browser, target recognition and scene recognition are performed on the environmental data to obtain target recognition results and scene recognition results; when the target recognition results, scene recognition results, and flight status data meet preset conditions, a data acquisition request is sent to the target flying car through the browser; the data acquisition request is used to request the target flying car to collect the original perception data of the target flying car and its surrounding environment, thereby improving data acquisition efficiency and quality, as well as the accuracy and stability of data acquisition.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a data acquisition method for a flying car according to an exemplary embodiment; Figure 2 This is a flowchart illustrating another data acquisition method for a flying car according to an exemplary embodiment; Figure 3 This is a block diagram illustrating a data acquisition device for a flying car according to an exemplary embodiment; Figure 4 This is a block diagram illustrating a terminal electronic device for data acquisition in a flying car according to an exemplary embodiment; Figure 5 This is a block diagram illustrating a server electronic device for data acquisition in a flying car, according to an exemplary embodiment. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solutions disclosed in this invention, the technical solutions in the disclosed embodiments will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention disclosed herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0020] Please see Figure 1 , Figure 1 This is a flowchart illustrating a data acquisition method for a flying car according to an exemplary embodiment. This specification provides the operational steps of the method as described in the embodiments or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server products, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment). Specifically, as... Figure 1 As shown, the above method may include: S101: Acquire flight status data and environmental data of the target flying car.

[0021] In one specific embodiment, the target flying car can be any flying car that requires data collection. The flying car can be driven by intelligent devices and can completely replace human driving in special circumstances. During flight, the driving safety of the flying car can be improved through autonomous driving technology, and more precise and intelligent control can be achieved. The flying car technology is mainly based on supervised deep learning, and the algorithm model training has extremely high requirements for data.

[0022] In one specific embodiment, environmental data can be obtained through a browser, while flight status data can be obtained through sensor sensing or vehicle signal data, which can be CAN signals. Flight status data may include the flying car's flight speed, acceleration, flight angle, flight altitude, position, and motor power. Environmental data may include environmental image data, which can be collected by the flying car's front-facing camera. For the browser, the browser can obtain image data from the flying car's front-facing camera to obtain environmental image data. This image data can be obtained from the vehicle itself, which may have network communication capabilities (i.e., the flying car integrates a network communication module). Alternatively, the vehicle itself may refer to an onboard terminal that can act as an intermediary for network communication.

[0023] Optionally, the image data from the flying car's forward-facing camera can be obtained from a server, with a corresponding communication connection established between the browser and the vehicle. To facilitate data transmission when acquiring the vehicle's forward-facing images, Kafka can be used to transmit the collected image data. Kafka is a publish-subscribe system consisting of a producer and a consumer. The producer pushes messages to the Kafka cluster, and the consumer pulls messages from the cluster. Kafka categorizes messages by topic; each topic represents a type of message, and different topics are independent of each other. Correspondingly, the vehicle's ROS (Robot Operating System) service can subscribe to forward-facing camera image data and CAN (Controller Area Network bus) information (which may include geolocation, steering information, etc.), and the subscribed data is uploaded to the Kafka server. The browser or backend server can consume image data from the Kafka server to obtain image data from the flying car's forward-facing camera.

[0024] Specifically, the forward-facing camera of a flying car can be a camera capable of capturing images of a certain area in front of the flying car, and it can be located on the left, right, top, or other positions of the flying car; CANBUS information refers to data transmitted between different control systems and devices inside the vehicle via the CANBUS protocol, and may include, but is not limited to, at least one of the following: engine information (engine speed, engine temperature, engine load, etc.), vehicle speed information (vehicle speed, acceleration, deceleration, etc.), safety information (seatbelt status, door open / close status, airbag status, etc.), lighting information (light status, brightness adjustment, etc.), instrument information (fuel level, driving range, oil pressure, etc.), and location information (i.e., geolocation); the Kafka server is a distributed stream processing platform whose high throughput ensures real-time and efficient data transmission, while low latency ensures data real-time performance.

[0025] Optionally, the browser can be located on the aforementioned terminal device, and the backend server can be a backend server that communicates with the browser. The matching here can be based on the browser's own identification information or on the browser's user (observer or other relevant users), as long as it can be ensured that the relevant users can obtain the image data from the front-view camera of the vehicle through the browser.

[0026] Optionally, the browser's acquisition of image data from the flying car's front-view camera can be a continuous process. For example, it can periodically acquire image data from the flying car's front-view camera, with an acquisition period of 5 seconds, 10 seconds, or other periods. The environmental image data is the image data acquired at a particular time. Alternatively, the browser's acquisition of image data from the flying car's front-view camera can be an event-triggered process, with the environmental image data being the image data acquired after a particular event is triggered. In this embodiment, the format of the image data acquired by the browser from the flying car's front-view camera is not limited.

[0027] S103: Based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the environmental data to obtain target recognition results and scene recognition results.

[0028] In one specific embodiment, the preset recognition model can be obtained by training an initial recognition model using training environment data labeled with preset targets and preset scenes. The preset recognition model can be run by a browser, which can load and run the preset recognition model. Specifically, the preset recognition model can be a multi-task target scene recognition model, or it can include multiple recognition models that recognize different preset targets and preset scenes respectively. Target recognition results can include targets such as drones, cars, trees, mountains, and buildings, while scene recognition results can include scenes such as rainy days, sunny days, crowds below, mountains below, and flocks of birds in front.

[0029] In an optional embodiment, the above-mentioned browser-based preset recognition model performs target recognition and scene recognition on environmental data, and the target recognition results and scene recognition results may include: By inputting environmental data into a preset recognition model, at least one target recognition result and at least one scene recognition result are obtained, along with their respective confidence levels. When any confidence level is greater than or equal to a preset confidence threshold, the corresponding target recognition result and scene recognition result are obtained.

[0030] In one specific embodiment, there may be more than one identified target and scene. Based on the identified target and scene, the preset recognition model can also output the confidence score for each target and scene. If the confidence score is greater than a preset confidence threshold, the corresponding target and scene will be output for further judgment. Targets and scenes with insufficient confidence scores will be filtered out and not included in the subsequent judgment. The preset confidence threshold can be set according to actual application requirements.

[0031] In the above embodiments, by pre-setting a confidence threshold, the confidence level corresponding to each identified target and scene is filtered, which can ensure the reliability of the final output target recognition results and scene recognition results, reduce invalid data processing, and thus improve the accuracy and efficiency of data collection.

[0032] Optionally, the aforementioned browser-based preset recognition model performs target and scene recognition on environmental data to obtain target and scene recognition results, which may include: The 3D point cloud data and environmental image data are fused to obtain fused environmental data. A preset recognition model running in the browser is used to perform target recognition and scene recognition on the fused environment data, and the target recognition results and scene recognition results are obtained.

[0033] In one specific embodiment, environmental data may include 3D point cloud data and environmental image data. By fusing the collected multidimensional data, more and richer environmental features can be included. Then, target recognition and scene recognition can be performed on the fused environmental data, which can more accurately identify targets and scenes, making the trigger judgment for data collection more accurate, thereby correctly collecting the required data.

[0034] S105: If the target recognition result, scene recognition result, and flight status data meet the preset conditions, send a data collection request to the target flying car through the browser.

[0035] In one specific embodiment, the data acquisition request may include the data acquisition frequency and the data to be acquired. The data acquisition request may be used to request the target flying car to acquire raw perception data of the target flying car and its surrounding environment. This raw perception data can be acquired by multiple sensors installed on the flying car, specifically including various sensors such as lidar, cameras, and millimeter-wave radar.

[0036] In one specific embodiment, the browser can send a data collection request to the flying car, requesting the flying car to collect and save its own flight status data and surrounding environment data. Upon receiving the data collection request, the flying car can perform data collection, and the collected data can be saved to a pre-defined storage location, such as a specified database or storage system. The collection time for each data collection session can be preset, for example, 1 minute, 2 minutes, or other values. Preset conditions can be set according to actual application requirements.

[0037] In one specific embodiment, a data collection request can be sent to the target flying car via a browser when the target recognition result includes a preset target, the scene recognition result includes a preset scene, and the flight status data meets a preset condition. This allows for the capture of specific and complex scenes by combining multiple conditions, significantly reducing false triggers. For example, a pedestrian is identified, the weather is rainy, and the vehicle speed is >30km / h. Optionally, a data collection request can also be sent to trigger data collection when a single piece of data (target, scene, or flight status) meets its corresponding condition.

[0038] In this embodiment of the specification, a preset recognition model running on the browser is used to perform target recognition and scene recognition on the environmental image data of the flying car. When a specified scene is detected (a scene that requires scene data collection, such as the aforementioned special scene), the collection vehicle is controlled to collect scene data. This can achieve the purpose of remotely and automatically collecting driving data of the collection vehicle. Since it is not necessary to configure a collector for each collection vehicle, it can reduce labor costs and improve data collection efficiency.

[0039] Optional, such as Figure 2 As shown, when the target recognition results, scene recognition results, and flight status data meet preset conditions, sending a data collection request to the target flying car via a browser may include: S201: When the target recognition result includes a preset target and the scene recognition result includes a preset scene, the flight status data is matched with the preset conditions corresponding to the preset scene to obtain the matching result.

[0040] S203: If the matching result indicates that the current scene is a preset scene, send a data collection request to the target flying car through the browser.

[0041] In one specific embodiment, the matching result can be used to indicate whether the current flight status data matches the preset conditions corresponding to the preset scenario, that is, it can be used to determine that the current scenario includes the preset scenario, thereby improving the confidence of scenario recognition through dual matching, reducing the risk brought by single matching, and thus improving the effectiveness of the collected data.

[0042] Optionally, the above method may also include: Based on the preset mapping relationship, determine the data collection frequency corresponding to the scene recognition results.

[0043] In one specific embodiment, the preset mapping relationship can be used to characterize the correspondence between scene recognition results and data collection frequency. The data collection frequency can be different for different scenes. For example, a higher collection frequency can be set for scenes that are more urgent or have a higher priority.

[0044] Optionally, the above method may also include: The target scene recognition result is determined from the first scene recognition result and the second scene recognition result; The browser sends a data collection request to the target flying car, so that the target flying car can collect the current environmental data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, based on the data collection frequency corresponding to the target scene recognition result. The current environmental data and current flight status data corresponding to the first scene recognition result and the second scene recognition result are labeled and stored.

[0045] In one specific embodiment, the scene recognition result may include a first scene recognition result and a second scene recognition result. Different urgency levels or priority levels can be preset for different scenes, thereby setting different collection frequencies. A higher collection frequency is set for scenes with higher urgency or priority levels. The target scene recognition result may be the scene recognition result with higher urgency or priority level between the first scene recognition result and the second scene recognition result. Flight status data and surrounding environment data can be collected according to the data collection frequency corresponding to the scene recognition result with higher urgency or priority level. The collected data is then mapped to the first scene recognition result and the second scene recognition result respectively, and scene annotations are performed and stored separately.

[0046] In one specific embodiment, data acquisition can continuously collect data for a certain period of time at a collection frequency. After a certain period of time following a scene change, the data corresponding to the previous scene is no longer collected. The decision to trigger data acquisition is based on the changed scene.

[0047] Optionally, the above method may also include: The control module obtains the performance parameters corresponding to the subordinate execution module; Based on performance parameters and a preset parameter range, the control module adjusts the execution task volume of each of the control module and the subordinate execution module. Based on the adjusted execution task volume, the control module repeatedly obtains the performance parameters of the subordinate execution module and iterates the execution task volume of each of the control module and the subordinate execution module based on the performance parameters and the preset parameter range until the performance parameters are within the preset parameter range.

[0048] In one specific embodiment, the above method can be applied to a preset terminal including a control module and a slave execution module, and the method is executed by the control module and the slave execution module. In one specific embodiment, both the control module and the slave execution module can be a motherboard, and the control module can be used to control the amount of tasks executed by the control module and the slave execution module. Performance parameters may include CPU (Central Processing Unit) utilization, memory usage, etc.

[0049] In a specific embodiment, the preset parameter range can be a reference range of the performance parameters corresponding to the subordinate execution module. Specifically, taking a preset parameter range of CPU utilization of (50%, 80%) as an example, when the CPU utilization of the subordinate execution module is lower than 50%, the control module can assign data acquisition tasks to the subordinate execution module. Optionally, when the CPU utilization of the subordinate execution module is higher than 80%, the control module suspends the assignment of data acquisition tasks to the subordinate execution module and shares the data acquisition tasks being executed by the subordinate execution module. Accordingly, based on the adjusted execution task volume, the control module repeatedly obtains the CPU utilization of the subordinate execution module. Based on the CPU utilization of the subordinate execution module and the preset parameter range of CPU utilization of (50%, 80%), the control module adjusts the cyclic iteration steps of the execution task volume of the control module and the subordinate execution module respectively until the CPU utilization of the subordinate execution module is at (50%, 80%).

[0050] In the above embodiments, by setting up simultaneous acquisition on both motherboards, the problem of motherboard overheating and crashing caused by acquisition on a single motherboard is avoided. Furthermore, by controlling the execution workload of the subordinate execution module in real time through the control module, dynamic load balancing is achieved, which effectively reduces the risk of motherboard overheating, improves the stability and reliability of motherboard operation, and ensures efficient data acquisition.

[0051] In practical applications, front view image data and vehicle CAN data can be acquired and sent to a websocket. Then, a listening program can be created to obtain real-time image data from the websocket, and target recognition and scene detection can be performed through the model. The CAN data from the websocket can be acquired to monitor vehicle signals, and the recognition results and CAN signals can be transmitted to the websocket. Furthermore, a listening program can be created to obtain the recognition results and CAN signals from the websocket. When a matching condition is identified, the data acquisition process begins.

[0052] As can be seen from the technical solutions provided in the embodiments of this specification above, this specification first acquires the flight status data and environmental data of the target flying car; the environmental data is collected through a browser; based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the environmental data to obtain target recognition results and scene recognition results; when the target recognition results, scene recognition results and flight status data meet preset conditions, a data acquisition request is sent to the target flying car through the browser; the data acquisition request is used to request the target flying car to collect the original perception data of the target flying car and its surrounding environment, thereby improving data acquisition efficiency and quality, as well as improving the accuracy and stability of data acquisition.

[0053] This invention also provides a data acquisition device for a flying car, such as... Figure 3 As shown, the device includes: The acquisition module 310 is used to acquire the flight status data and environmental data of the target flying car; the environmental data is collected through a browser. The recognition module 320 is used to perform target recognition and scene recognition on the environmental data based on the preset recognition model running in the browser, and obtain target recognition results and scene recognition results; The data acquisition request sending module 330 is used to send a data acquisition request to the target flying car through the browser when the target recognition result, the scene recognition result, and the flight status data meet preset conditions; the data acquisition request is used to request the target flying car to collect the original perception data of the target flying car and its surrounding environment.

[0054] Optionally, the data acquisition request sending module includes: A matching unit is configured to match the flight status data with preset conditions corresponding to the preset scene when the target recognition result includes a preset target and the scene recognition result includes a preset scene, and obtain a matching result. The data acquisition request sending unit is used to send the data acquisition request to the target flying car through the browser when the matching result indicates that the current scene is the preset scene.

[0055] Optionally, the scene recognition result includes a first scene recognition result and a second scene recognition result, and the device further includes: The target scene recognition result determination module is used to determine the target scene recognition result from the first scene recognition result and the second scene recognition result; The data acquisition module is used to send the data acquisition request to the target flying car through the browser, so that the target flying car can acquire the current environmental data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, based on the data acquisition frequency corresponding to the target scene recognition result. The annotation module is used to annotate and store the current environmental data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data.

[0056] Optionally, the data acquisition request includes a data acquisition frequency, and the device further includes: The data acquisition frequency determination module is used to determine the data acquisition frequency corresponding to the scene recognition result according to a preset mapping relationship; the preset mapping relationship is used to characterize the correspondence between the scene recognition result and the data acquisition frequency.

[0057] Optionally, the identification module includes: The first identification unit is used to input the environmental data into the preset identification model to obtain at least one target identification result and at least one scene identification result, as well as their respective confidence levels; The recognition result determination unit is used to obtain the corresponding target recognition result and scene recognition result when any confidence level is greater than or equal to a preset confidence threshold.

[0058] Optionally, the environmental data includes 3D point cloud data and environmental image data, and the recognition module includes: The fusion unit is used to fuse the three-dimensional point cloud data and the environmental image data to obtain fused environmental data; The second recognition unit is used to perform target recognition and scene recognition on the fused environment data based on the preset recognition model running in the browser, and obtain the target recognition result and the scene recognition result.

[0059] Optionally, the method is applied to a preset terminal including a control module and a subordinate execution module, the method is executed by the control module and the subordinate execution module, and the device further includes: A performance parameter acquisition module is used by the control module to acquire the performance parameters corresponding to the subordinate execution module. The repeat module is used by the control module to adjust the execution task volume of the control module and the subordinate execution module respectively based on the performance parameters and the preset parameter range, and repeat the cyclic iteration steps of the control module obtaining the performance parameters corresponding to the subordinate execution module and the control module adjusting the execution task volume of the control module and the subordinate execution module respectively based on the performance parameters and the preset parameter range until the performance parameters are within the preset parameter range.

[0060] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0061] Figure 4 This is a block diagram illustrating an electronic device for data acquisition from a flying car, according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the electronic device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a data acquisition method for a flying car. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0062] Figure 5 This is a block diagram illustrating an electronic device for data acquisition from a flying car, according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the electronic device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a data acquisition method for a flying car.

[0063] Those skilled in the art will understand that Figure 4 or Figure 5 The structures shown are merely block diagrams of some structures related to the disclosed solutions of this invention, and do not constitute a limitation on the electronic devices to which the disclosed solutions of this invention are applied. Specific electronic devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0064] In an exemplary embodiment, an electronic device for data acquisition of a flying car is also provided, including a processor and a memory, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the data acquisition method of the flying car in the disclosed embodiment of the present invention.

[0065] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one instruction, which is loaded and executed by a processor to implement the data acquisition method for a flying car in the disclosed embodiments of the present invention.

[0066] In an exemplary embodiment, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the data acquisition method for a flying car in the disclosed embodiments of the present invention.

[0067] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0068] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles disclosed herein and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0069] It should be understood that the present invention is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims

1. A data acquisition method for a flying car, characterized in that, include: Acquire flight status data and environmental data of the target flying car; the environmental data is collected via a browser; Based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the environmental data to obtain target recognition results and scene recognition results; When the target recognition result, the scene recognition result, and the flight status data meet preset conditions, a data acquisition request is sent to the target flying car through the browser; the data acquisition request is used to request the target flying car to collect the raw perception data of the target flying car and its surrounding environment.

2. The method according to claim 1, characterized in that, When the target recognition result, the scene recognition result, and the flight status data meet preset conditions, sending a data collection request to the target flying car through the browser includes: If the target recognition result includes a preset target and the scene recognition result includes a preset scene, the flight status data is matched with the preset conditions corresponding to the preset scene to obtain a matching result; If the matching result indicates that the current scene is the preset scene, the data collection request is sent to the target flying car through the browser.

3. The method according to claim 1, characterized in that, The scene recognition result includes a first scene recognition result and a second scene recognition result; the method further includes: The target scene recognition result is determined from the first scene recognition result and the second scene recognition result; The browser sends the data acquisition request to the target flying car, so that the target flying car can acquire the current environmental data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, based on the data acquisition frequency corresponding to the target scene recognition result. The current environment data corresponding to the first scene recognition result and the second scene recognition result, as well as the current flight status data, are labeled and stored.

4. The method according to claim 1, characterized in that, The data acquisition request includes the data acquisition frequency, and the method further includes: The data acquisition frequency corresponding to the scene recognition result is determined according to the preset mapping relationship; the preset mapping relationship is used to characterize the correspondence between the scene recognition result and the data acquisition frequency.

5. The method according to claim 1, characterized in that, The preset recognition model running based on the browser performs target recognition and scene recognition on the environmental data, and the target recognition results and scene recognition results are as follows: The environmental data is input into the preset recognition model to obtain at least one target recognition result and at least one scene recognition result, as well as their respective confidence levels; When any confidence level is greater than or equal to a preset confidence threshold, the corresponding target recognition result and scene recognition result are obtained.

6. The method according to claim 1, characterized in that, The environmental data includes 3D point cloud data and environmental image data. The target recognition and scene recognition results obtained by the preset recognition model running in the browser on the environmental data include: The 3D point cloud data and the environmental image data are fused to obtain fused environmental data. Based on the preset recognition model running in the browser, target recognition and scene recognition are performed on the fused environment data to obtain the target recognition result and the scene recognition result.

7. The method according to claim 1, characterized in that, The method is applied to a preset terminal including a control module and a subordinate execution module, the method is executed by the control module and the subordinate execution module, and the method further includes: The control module acquires the performance parameters corresponding to the subordinate execution module; Based on the performance parameters and a preset parameter range, the control module adjusts the execution task volume corresponding to each of the control module and the subordinate execution module, and based on the adjusted execution task volume, repeats the iterative steps of the control module obtaining the performance parameters corresponding to the subordinate execution module and adjusting the execution task volume corresponding to each of the control module and the subordinate execution module based on the performance parameters and the preset parameter range, until the performance parameters are within the preset parameter range.

8. A data acquisition device for a flying car, characterized in that, The device includes: The acquisition module is used to acquire flight status data and environmental data of the target flying car; the environmental data is collected through a browser. The recognition module is used to perform target recognition and scene recognition on the environmental data based on the preset recognition model running in the browser, and obtain target recognition results and scene recognition results; The data acquisition request sending module is used to send a data acquisition request to the target flying car through the browser when the target recognition result, the scene recognition result, and the flight status data meet preset conditions; the data acquisition request is used to request the target flying car to collect the original perception data of the target flying car and its surrounding environment.

9. An electronic device for data acquisition in flying cars, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to implement the data acquisition method for a flying car as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction, which is loaded and executed by a processor to implement the data acquisition method for a flying car as described in any one of claims 1 to 7.

Images