Vehicle control method, system and device and vehicle

Abstract

The embodiment of the invention provides a vehicle control method, system and device and a vehicle, and relates to the technical field of vehicle control. The method comprises the steps that vehicle motion data of a target vehicle and visual perception data collected by a vehicle-mounted camera are obtained, and display content corresponding to the visual perception data comprises a target object; object marking is carried out on the visual perception data to obtain a marking result, and the marking result is used for representing the category of the target object; determining relative motion data between the target vehicle and the target object by using the vehicle motion data and the marking result; based on the relative motion data and a prediction condition, an automobile data recorder of the target vehicle is controlled to be switched to an emergency recording state, the prediction condition is used for predicting whether the target vehicle has a driving risk or not, and the emergency recording state is used for locking and storing recorded information of the automobile data recorder. The technical problem of poor timeliness of a vehicle control method in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle control method, system, device and vehicle. Background Technology

[0002] In the field of in-vehicle video recording, dashcams not only offer daily loop recording functions but also possess the ability to record emergency videos. This is designed to ensure that relevant videos can be locked and saved promptly in emergency situations for later analysis or as evidence. However, the emergency recording function typically relies on manual triggering by the user within the dashcam app. How to automatically trigger the emergency recording function has become a pressing issue in the relevant technical field.

[0003] In related technologies, the emergency recording function is activated by using the signal generated by a vehicle collision. However, this vehicle control method can only trigger the emergency recording function after a vehicle collision. It is easy for the signal to be lost due to a strong impact, resulting in the inability to activate the emergency recording function. This vehicle control method has obvious lag and poor timeliness.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a vehicle control method, system, device, and vehicle, aiming to improve the technical problem of poor timeliness in related vehicle control methods.

[0006] According to one aspect of the embodiments of this application, a vehicle control method is provided, comprising: acquiring vehicle motion data of a target vehicle and visual perception data collected by an on-board camera, wherein the display content corresponding to the visual perception data includes a target object; marking the visual perception data to obtain a marking result, wherein the marking result is used to characterize the category of the target object; determining the relative motion data between the target vehicle and the target object using the vehicle motion data and the marking result; and controlling the dashcam of the target vehicle to switch to an emergency recording state based on the relative motion data and prediction conditions, wherein the prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording state is used to lock and retain the recording information of the dashcam.

[0007] The vehicle control method provided in this application achieves the following technical effects: By acquiring the vehicle's motion data and the visual perception data collected by the vehicle-mounted camera, the visual perception data is marked to obtain the marking results, enabling real-time identification of targets around the vehicle; furthermore, by utilizing the vehicle's motion data and the marking results, the relative motion data between the target vehicle and the target object is determined. Combined with this relative motion data and prediction conditions, it is possible to predict in advance whether there is a driving risk to the target vehicle (e.g., whether a collision will occur between the target vehicle and the target object), thereby promptly controlling the dashcam to switch to emergency recording mode and locking and storing the recorded information. Thus, this application achieves the goal of quickly controlling the dashcam to switch to emergency recording mode using the relative motion data between the target vehicle and the target object, enhancing the timeliness of the vehicle control method. It overcomes the lag inherent in related technologies that utilize signals generated by vehicle collisions to activate the emergency recording function, thereby solving the problem of poor timeliness in related vehicle control methods.

[0008] Optionally, the visual perception data includes feature data corresponding to multiple candidate objects. The object labeling of the visual perception data to obtain the labeling result includes: using a visual recognition algorithm to identify the feature data corresponding to multiple candidate objects to obtain the recognition result; and labeling the feature data corresponding to multiple candidate objects based on the recognition result to obtain the labeling result.

[0009] The above-mentioned optional embodiments of this application can achieve the following technical effects: by using a visual recognition algorithm, features can be extracted from images captured by an in-vehicle camera and specific objects can be identified to obtain recognition results. Compared with motion detection or shape matching methods, the accuracy of recognition results can be improved by using a visual recognition algorithm. Furthermore, based on the recognition results, the feature data corresponding to multiple candidate objects are marked to obtain more accurate marking results.

[0010] Optionally, determining the relative motion data between the target vehicle and the target object using the vehicle motion data and the marking results includes: extracting the feature data corresponding to the target object from the visual perception data based on the marking results and the target object selection criteria, wherein the target object selection criteria are used to determine whether the category of the candidate object belongs to the expected category; and determining the relative motion data using the vehicle motion data and the feature data corresponding to the target object.

[0011] The above-mentioned optional embodiments of this application can achieve the following technical effects: based on the marking results and target selection criteria, the target object belonging to the expected category can be accurately selected from multiple candidate objects according to the classification results of multiple candidate objects, thereby extracting the feature data corresponding to the target object in the visual perception data, laying the foundation for obtaining accurate relative motion data in the future.

[0012] Optionally, the relative motion data includes relative displacement and relative displacement change index. The relative motion data is determined by using the vehicle motion data and the feature data corresponding to the target object, including: determining the warning distance threshold according to the category of the target object; determining the relative displacement using the vehicle motion data and the feature data corresponding to the target object; and determining the relative displacement change index based on the warning distance threshold, relative displacement, and exponential curvature function.

[0013] The above optional embodiments of this application can achieve the following technical effects: In this application, the warning distance is determined according to the selected target object category, thereby determining the relative motion data (e.g., relative displacement, relative displacement change index). In other words, this application can determine the warning distance more specifically according to different types of target objects, thereby improving the accuracy of the relative displacement change index.

[0014] Optionally, controlling the dashcam to switch to emergency recording state based on relative motion data and prediction conditions includes: judging the relative motion data according to the prediction conditions and obtaining a judgment result, wherein the judgment result is used to characterize whether the relative motion data meets the prediction conditions; and in response to the judgment result characterizing that the relative motion data meets the prediction conditions, controlling the dashcam to switch from normal recording state to emergency recording state.

[0015] The above-mentioned optional embodiments of this application can achieve the following technical effects: through real-time analysis and intelligent judgment, it can ensure that the emergency recording function can be automatically and quickly triggered when there is a driving risk in the target vehicle, that is, control the dashcam to switch from normal recording state to emergency recording state, so as to ensure that the video recorded by the dashcam can be effectively preserved and provide evidence for subsequent accident analysis and liability determination.

[0016] Optionally, the prediction conditions include vehicle status judgment conditions and a third judgment condition. The relative motion data also includes the relative displacement change index, relative distance, and relative speed. The relative motion data is judged based on the prediction conditions to obtain the judgment result, which includes: determining the status result of the target vehicle based on the vehicle status judgment conditions, the relative displacement change index, and the relative speed, wherein the vehicle status judgment conditions are used to determine whether the target vehicle is in an emergency movement state; in response to the status result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning distance threshold based on the third judgment condition to determine the judgment result, wherein the third judgment condition is used to determine whether the target vehicle is within the warning range.

[0017] The above-mentioned optional embodiments of this application can achieve the following technical effects: based on the vehicle status judgment conditions, the relative displacement change index and the relative speed, it is judged whether the target vehicle is in an emergency movement state, and the status result of the target vehicle is determined; further, in response to the status result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning distance threshold according to the third judgment condition to determine the judgment result, which can ensure that the vehicle is controlled when it is in motion, and avoids the emergency recording function being accidentally triggered when the vehicle is parked.

[0018] Optionally, the vehicle state judgment conditions include a first judgment condition and a second judgment condition. Determining the dynamic characteristics of the target vehicle based on the relative displacement change index and the relative speed includes: comparing the relative speed with a preset speed threshold based on the first judgment condition to determine the speed judgment result; comparing the relative displacement change index with a preset index threshold based on the second judgment condition to determine the displacement judgment result; and determining the state result based on the speed judgment result and the displacement judgment result.

[0019] The above-mentioned optional embodiments of this application can achieve the following technical effects: This application uses multiple types of parameters to determine the state result of the target vehicle, which can more comprehensively evaluate the driving state of the vehicle, improve the accuracy of the state result, and thus ensure the accuracy of the system's warning in dynamic driving environment.

[0020] According to another aspect of the embodiments of this application, a vehicle control system is also provided, including: a target vehicle, configured to send the target vehicle's own motion data and visual perception data collected by an onboard camera, wherein the display content corresponding to the visual perception data includes a target object; a cloud computing module, connected to the target vehicle, configured to use a visual recognition algorithm to mark objects in the visual perception data to obtain a marking result, wherein the marking result is used to characterize the category of the target object; the target vehicle is further configured to use the own motion data and the marking result to determine the relative motion data between the target vehicle and the target object; the target vehicle is further configured to control the target vehicle's dashcam to switch to an emergency recording state based on the relative motion data and prediction conditions, wherein the prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording state is used to lock and retain the recorded information of the dashcam.

[0021] The vehicle control system provided in this application embodiment achieves the following technical effects: by using the target vehicle, the vehicle's own motion data and the visual perception data collected by the vehicle-mounted camera are sent to the cloud computing module connected to the target vehicle; further, by using the cloud computing module to call the visual recognition algorithm to mark the visual perception data, the cloud computing resources can be used for data processing, improving the speed of obtaining the marking results and enhancing the timeliness of the vehicle control method; further, the relative motion data between the target vehicle and the target object can be determined more promptly, and the driving risk of the target vehicle can be predicted in advance, thereby quickly controlling the dashcam to switch to emergency recording mode and locking and retaining the recorded information of the dashcam.

[0022] According to another aspect of the embodiments of this application, a vehicle control device is also provided, comprising: an acquisition module, configured to acquire vehicle motion data of a target vehicle and visual perception data collected by an onboard camera, wherein the display content corresponding to the visual perception data includes a target object; a marking module, configured to mark the visual perception data to obtain a marking result, wherein the marking result is used to characterize the category of the target object; a determination module, configured to determine the relative motion data between the target vehicle and the target object using the vehicle motion data and the marking result; and a control module, configured to control the dashcam of the target vehicle to switch to an emergency recording state based on the relative motion data and prediction conditions, wherein the prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording state is used to lock and retain the recording information of the dashcam.

[0023] The vehicle control device provided in this application achieves the following technical effects: Using an acquisition module, it acquires the vehicle's motion data and visual perception data collected by the vehicle-mounted camera. Using a marking module, it marks the visual perception data to obtain marking results, enabling real-time identification of objects around the vehicle. Furthermore, using a determination module, it determines the relative motion data between the target vehicle and the target object based on the vehicle's motion data and the marking results. Using a control module, combining this relative motion data and prediction conditions, it can predict in advance whether there is a driving risk to the target vehicle (e.g., whether a collision will occur between the target vehicle and the target object), thereby promptly controlling the dashcam to switch to emergency recording mode and locking and storing the recorded information. Therefore, this application embodiment, by utilizing the relative motion data between the target vehicle and the target object, can quickly control the dashcam to switch to emergency recording mode, enhancing the performance of the vehicle control device.

[0024] According to another aspect of the embodiments of this application, a vehicle is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the method of any one of the above when it runs.

[0025] The vehicle provided in this application embodiment achieves the following technical effects: by acquiring the vehicle's own motion data and the visual perception data collected by the vehicle-mounted camera, the visual perception data is marked to obtain the marking results, enabling real-time identification of target objects around the vehicle; furthermore, by utilizing the vehicle's own motion data and the marking results, the relative motion data between the target vehicle and the target object is determined, and by combining the relative motion data and prediction conditions, it is possible to predict in advance whether there is a driving risk to the target vehicle (e.g., whether the target vehicle will collide with the target object), thereby timely controlling the dashcam to switch to emergency recording mode, locking and storing the recorded information of the dashcam, and enhancing the vehicle's intelligence. Attached Figure Description

[0026] Figure 1 This is a flowchart of a vehicle control method provided in an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a vehicle control method provided in an embodiment of this application;

[0028] Figure 3 This is a structural block diagram of a vehicle control device provided in an embodiment of this application;

[0029] Figure 4 This is a structural block diagram of a vehicle provided in one embodiment of this application;

[0030] Figure 5 This is a hardware structure block diagram of a computing terminal provided in an embodiment of this application;

[0031] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0032] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the following detailed description is provided in conjunction with embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application described 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 apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] This application provides a vehicle control method; please refer to the embodiments provided. Figure 1 This includes the following steps.

[0035] S10: Acquire the vehicle's motion data and the visual perception data collected by the vehicle's camera, wherein the display content corresponding to the visual perception data includes the target object.

[0036] The aforementioned vehicle motion data may include vehicle driving status data and driving operation data. The driving operation data can be used to characterize the driver's actions. This driving operation data may include, but is not limited to: steering wheel angle information, accelerator pedal angle information, and vehicle braking information.

[0037] The aforementioned vehicle driving status data can be used to characterize the vehicle's current operating state. This data may include, but is not limited to: vehicle gear information, pulse signals corresponding to each of the four wheels, wheel speed signals corresponding to each of the four wheels, inertial measurement unit (IMU) information, drive torque corresponding to each of the four tires, vehicle body vibration information, and noise information corresponding to each of the four tires. The IMU information may include: three-axis (X-axis, Y-axis, Z-axis) acceleration information and three-axis angular velocity information in the vehicle body coordinate system. This vehicle driving status data can be collected by onboard sensors. These onboard sensors may include, but are not limited to: radar sensors, laser sensors, inertial sensors, rotation sensors (e.g., Hall effect sensors), speed sensors, acceleration sensors, angular velocity sensors, temperature sensors, humidity sensors, tire pressure sensors, wheel speed sensors, vibration sensors, and acoustic sensors.

[0038] The aforementioned target objects can include both static and dynamic objects. Static objects may include, but are not limited to, roadblocks, signs, and roadside fences. Dynamic objects may include, but are not limited to, pedestrians, other vehicles around the target vehicle, and animals. The aforementioned visual perception data can refer to environmental information captured and processed by the vehicle-mounted camera. This visual perception data may include, but is not limited to, the target object's position, size, shape, color data, direction of movement, speed, and environmental climate information data of the target vehicle (e.g., temperature, humidity, light intensity). The aforementioned vehicle-mounted camera can be installed on the outer surface of the target vehicle.

[0039] It is easy to understand that in this embodiment of the application, the vehicle motion data of the target vehicle is obtained in real time by utilizing the on-board sensors of the target vehicle, and visual images are collected in real time by the on-board camera. The visual images are processed by computer vision technology to obtain visual perception data from the real-time images, thereby obtaining the visual perception data collected by the on-board camera. This enhances the timeliness of the vehicle motion data and visual perception data, which helps to control the vehicle more promptly and switch the dashcam to emergency recording mode.

[0040] S20: Label the visual perception data to obtain the labeling results, whereby the labeling results are used to characterize the category of the target object.

[0041] The labeling results described above may include, but are not limited to: category labels for the target objects and confidence scores for the target objects. Category labels for the target objects may include static objects (e.g., roadblocks, signs, roadside fences, etc.) and dynamic objects (e.g., pedestrians, other vehicles around the target vehicle, animals, etc.). These category labels can be used to characterize the type of the target object. The confidence scores for the target objects can be used to indicate the accuracy of the labeling results.

[0042] The process of object labeling of visual perception data described above can be achieved in several ways. For example, the labeling result can be obtained using a visual recognition algorithm. Alternatively, the labeling result can be obtained manually; specifically, the passenger can label objects in the visual perception data to determine the category of the target object in the displayed content. Another example is using feature matching methods to extract image feature points from the visual perception data, and then identifying and labeling objects by matching the feature points. Yet another example is using the Hough transform method to label objects in the visual perception data, identifying object boundaries and shapes, and thus determining the object category. It is easy to understand that by labeling objects in visual perception data, objects in images captured by the vehicle's camera can be automatically and quickly identified.

[0043] S30: Using the vehicle's motion data and the marking results, determine the relative motion data between the target vehicle and the target object.

[0044] The aforementioned relative motion data is used to characterize the changes in the dynamic relationship between the target vehicle and the target object. This relative motion data may include, but is not limited to: relative displacement, relative distance, relative velocity, relative acceleration, relative displacement change exponent, and relative steering angle. The aforementioned relative motion data can be determined using (but is not limited to) the following methods: mathematical calculation methods based on vehicle motion relationships, data fusion-based methods, motion trend prediction methods, and Kalman filter algorithms.

[0045] For example, the process of determining the relative motion data can be as follows: real-time acquisition of vehicle motion data through onboard sensors, and object labeling of visual perception data to obtain labeling results; further, based on the labeling results, analysis of the changes of the target object in multiple consecutive image frames, for example, prediction of the speed and direction of the target object through optical flow algorithms, feature point tracking, or deep learning models; then, through coordinate system transformation methods, the motion information of the target object in the world coordinate system is transformed into the motion information in the vehicle's own coordinate system, and the vehicle motion data is combined with the motion estimation results of the target object to determine the relative speed, relative acceleration, and relative direction between the target vehicle and the target object, and the relative distance and relative position between the target object and the vehicle are calculated by the position change of the target object in the image and the vehicle motion data.

[0046] It is easy to understand that by using the vehicle's motion data and the marking results, the relative motion data between the target vehicle and the target object can be determined. The relative motion data can be used to predict the motion status of the target object in advance, providing the necessary data support for timely control of the vehicle, ensuring that the system can react in a timely manner (e.g., triggering the emergency recording function), enhancing the timeliness of the vehicle control method, and improving the vehicle's performance.

[0047] S40: Based on relative motion data and prediction conditions, control the dashcam of the target vehicle to switch to emergency recording mode. The prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording mode is used to lock and retain the recorded information of the dashcam.

[0048] The aforementioned prediction conditions can include multiple judgment criteria, such as judgment criteria for the target object's movement trend, environmental factors, target object behavior, and relative distance. These prediction conditions can be set according to the triggering requirements of emergency recording. By real-time monitoring and analysis of relative motion data and comparing it with the set prediction conditions, the driving risk level faced by the target vehicle can be determined.

[0049] For example, based on prediction conditions, the relative motion data is judged. When the relative motion data meets the prediction conditions (e.g., the movement trend of the target object indicates a collision risk between the target vehicle and the target object), the dashcam can be controlled to switch to emergency recording mode. Alternatively, the relative motion data can also be judged based on prediction conditions. When the relative motion data does not meet the prediction conditions (e.g., the relative distance is not greater than a preset distance value), the dashcam can be controlled to switch to emergency recording mode. In particular, when there are multiple judgment conditions for the prediction, the dashcam can be controlled to switch to emergency recording mode if the relative motion data does not meet any one of the multiple judgment conditions.

[0050] The aforementioned emergency recording state refers to a special recording mode that the dashcam system automatically enters based on identified potential driving risks. The recorded information may include, but is not limited to, video, image, and audio data. In emergency recording state, the dashcam's recordings are locked and retained. Specifically, this recording information can be video data; that is, the system locks the dashcam's recordings to prevent them from being repeatedly overwritten or manually deleted, ensuring that video information of critical events is preserved.

[0051] In some application scenarios, the recorded information mentioned above can also be information collected by the vehicle camera. By using the dashcam as a storage device and the vehicle camera as a collection device, the dashcam can lock and retain the information collected by the vehicle camera.

[0052] It should be noted that during the process of switching the dashcam to emergency recording mode, the initial state of the dashcam may include, but is not limited to, standby mode, normal recording mode, and sleep mode. In particular, when the dashcam is initially in sleep mode, an activation command can be sent to the dashcam to wake it up and control it to switch to emergency recording mode.

[0053] The vehicle control method provided in this application achieves the following technical effects: By acquiring the vehicle's motion data and the visual perception data collected by the vehicle-mounted camera, the visual perception data is marked to obtain the marking results, enabling real-time identification of targets around the vehicle; furthermore, by utilizing the vehicle's motion data and the marking results, the relative motion data between the target vehicle and the target object is determined. Combined with this relative motion data and prediction conditions, it is possible to predict in advance whether there is a driving risk to the target vehicle (e.g., whether a collision will occur between the target vehicle and the target object), thereby promptly controlling the dashcam to switch to emergency recording mode and locking and storing the recorded information. Thus, this application achieves the goal of quickly controlling the dashcam to switch to emergency recording mode using the relative motion data between the target vehicle and the target object, enhancing the timeliness of the vehicle control method. It overcomes the lag inherent in related technologies that utilize signals generated by vehicle collisions to activate the emergency recording function, thereby solving the problem of poor timeliness in related vehicle control methods.

[0054] The vehicle control method provided in this application uses the relative motion data between the target vehicle and the target object to control the dashcam to switch to emergency recording mode in a timely manner, and can be widely used in multiple application scenarios.

[0055] For example, in emergency automatic recording scenarios, when there is a potential collision risk between the target vehicle and the target object, the system can automatically identify and record changes in the environment around the vehicle (such as sudden deceleration of the vehicle in front, or the unexpected intrusion of pedestrians or animals). It can make judgments in advance using the relative motion data between the target vehicle and the target object, so as to ensure that the dashcam can be switched to emergency recording mode in advance when there is a potential collision risk, thereby enhancing the timeliness of vehicle control methods and providing key video evidence for event analysis.

[0056] For example, in intelligent driving assistance applications, by combining visual perception data and vehicle motion data, the system can determine the relative motion data between the target vehicle and the target object, and can predict potential dangers in advance, such as the vehicle deviating from the lane or the vehicle in front braking suddenly, thereby triggering recording in time, providing auxiliary information to the driver, and enhancing driving safety.

[0057] For example, in the application scenario of traffic violation evidence collection, this application utilizes the relative motion data between the target vehicle and the target object. When violations such as running red lights or speeding are detected, the system can promptly control the dashcam to switch to emergency recording mode and automatically lock the relevant video, which facilitates subsequent traffic violation review and processing.

[0058] The vehicle control method provided in this application embodiment can be applied to, but is not limited to, the application scenarios listed above. With the continuous evolution of technology, the above method can also be applied to a wider range of scenarios. By timely controlling the dashcam to switch to emergency recording mode, it supports a variety of advanced functions and applications, which can enhance the timeliness of the control method.

[0059] Optionally, the visual perception data includes feature data corresponding to multiple candidate objects. In step S20 above, the object labeling of the visual perception data to obtain the labeling result includes the following steps:

[0060] S21: Using a visual recognition algorithm, identify the feature data corresponding to multiple candidate objects to obtain the recognition result;

[0061] S22: Based on the recognition results, the feature data corresponding to multiple candidate objects are labeled to obtain the labeling results.

[0062] The aforementioned visual recognition algorithms may include, but are not limited to: convolutional neural network algorithms, recurrent convolutional neural network algorithms, recognition methods based on support vector machines, and object detection networks. The recognition results can be used to characterize the attributes and states corresponding to multiple candidate objects. These results may include, but are not limited to: the position, size, and motion state of the target object.

[0063] In an exemplary application scenario, such as Figure 2 As shown, the visual perception data (i.e., image acquisition) is obtained by the vehicle-mounted camera. The display content corresponding to the visual perception data can include multiple candidate objects, and the target object may be present among the multiple candidate objects. In particular, for the visual perception data of a certain image frame, the target object may not be present among the multiple candidate objects. In this case, the visual perception data of the next image frame of the image frame can be identified using a visual recognition algorithm (i.e., visual recognition).

[0064] The aforementioned labeling results may include, but are not limited to: classification labels (e.g., adding text labels near multiple candidate objects in the display content corresponding to the visual perception data to indicate the categories of the multiple candidate objects, especially the category of the target object), motion state annotation (e.g., for moving targets, marking their direction and speed, which can be represented by arrows or numbers), assigning identifiers to multiple candidate objects (e.g., assigning a unique identifier to each candidate object to facilitate tracking the continuous movement and identification of the candidate objects), and target object confidence scores. For example, a visual recognition algorithm is used to identify features in an image, and based on the recognition results, multiple objects in the display content corresponding to the visual perception data are labeled to generate labeling results containing category information.

[0065] The above-mentioned optional embodiments of this application can achieve the following technical effects: by using a visual recognition algorithm, features can be extracted from images captured by an in-vehicle camera and specific objects can be identified to obtain recognition results. Compared with motion detection or shape matching methods, the accuracy of recognition results can be improved by using a visual recognition algorithm. Furthermore, based on the recognition results, the feature data corresponding to multiple candidate objects are marked to obtain more accurate marking results.

[0066] Optionally, in step S30 above, determining the relative motion data between the target vehicle and the target object using the vehicle's motion data and the marking results includes the following steps:

[0067] S31: Based on the marking results and the target selection criteria, extract the feature data corresponding to the target from the visual perception data. The target selection criteria are used to determine whether the category of the candidate object belongs to the expected category.

[0068] S32: Determine relative motion data by using the vehicle's motion data and the feature data corresponding to the target object.

[0069] The target object selection criteria mentioned above can include target object level selection criteria and confidence level selection criteria. The categories of the candidate objects mentioned above can include static object categories, dynamic object categories, and unknown object categories. The expected category mentioned above can be set according to selection needs; in particular, the static object category can be selected as the expected category. Using the above target object selection criteria, candidate objects belonging to the expected category can be filtered out. Furthermore, the target object is determined from this portion of candidate objects belonging to the expected category. It can be understood that the above expected category can be considered as the category of candidate objects that are easier to calculate relative motion data. Selecting target objects belonging to the expected category from multiple candidate objects helps to more accurately determine the relative motion data subsequently.

[0070] The process of extracting feature data corresponding to the target object from the visual perception data described above can be as follows: After determining the target object from multiple candidate objects based on the labeling results and target object selection criteria, the feature data corresponding to the target object can be extracted from the visual perception data using deep learning network algorithms; or, feature extraction algorithms (such as feature point matching algorithms, semantic segmentation algorithms, etc.) can be used to further extract features from the detected target object's location area, thereby extracting the feature data corresponding to the target object.

[0071] In one exemplary application scenario, it is still as follows Figure 2As shown, assuming the categories of the candidate objects can include static objects (set as first-level target objects), dynamic objects (set as second-level target objects), and unknown objects, and the expected categories can include first-level target objects and second-level target objects, the system determines whether target objects (including first-level and second-level target objects) exist in the displayed content corresponding to the visual perception data. Based on the labeling results, the categories of multiple candidate objects in the displayed content corresponding to the visual perception data can be determined. According to the target object selection criteria, when multiple candidate objects simultaneously include both first-level and second-level target objects, the candidate object belonging to the first-level target object is selected first. Further, when multiple candidate objects simultaneously include multiple first-level target objects, the target object confidence score in the labeling results is used to rank the multiple candidate objects belonging to the first-level target object, and the candidate object with the highest target object confidence score is selected as the target object. Correspondingly, when only second-level target objects exist among multiple candidate objects, the candidate object belonging to the second-level target object is selected. Specifically, if the target object does not exist in the displayed content corresponding to the visual perception data, the image is re-acquired (or the visual perception data of the next frame image is marked with an object).

[0072] The above-mentioned optional embodiments of this application can achieve the following technical effects: based on the marking results and target selection criteria, the target object belonging to the expected category can be accurately selected from multiple candidate objects according to the classification results of multiple candidate objects, thereby extracting the feature data corresponding to the target object in the visual perception data, and preparing for obtaining accurate relative motion data in the future.

[0073] Optionally, in step S32 above, the relative motion data includes relative displacement and relative displacement change index. Determining the relative motion data using the vehicle's motion data and the feature data corresponding to the target object includes the following steps:

[0074] S321: Determine the warning distance threshold based on the type of the target object;

[0075] S322: Determine the relative displacement using the vehicle's motion data and the characteristic data corresponding to the target object;

[0076] S323: Determine the relative displacement change index based on the warning distance threshold, relative displacement, and exponential curvature function.

[0077] The aforementioned warning distance threshold is primarily used to characterize the safe distance range within which a target vehicle poses no potential risk. This warning distance threshold can be determined using a mapping table between object categories and warning distances. In the system, a safe distance limit (i.e., a warning distance threshold) is set for each category of target object. This threshold can be used to assist in assessing the proximity between the target object and the target vehicle. For example, when the target object is a roadblock, the warning distance threshold can be a first distance threshold (e.g., 10 meters); when the target object is a vehicle ahead, the warning distance threshold can be a second distance threshold (e.g., 50 meters).

[0078] In some application scenarios, the warning distance threshold can also be predicted and determined using a machine learning model. By training the model with historical data, it learns the relationship between the target category and the warning distance threshold, thus determining the threshold based on the target category. The machine learning model can further subdivide the target category. For example, after identifying a pedestrian, the pedestrian's movement speed can be assessed, classifying them as fast-approaching or slow-approaching pedestrians. A lower warning distance threshold can be assigned to fast-approaching pedestrians, while a higher threshold can be assigned to slow-approaching pedestrians, resulting in a more accurate determination of the warning distance threshold.

[0079] The aforementioned exponential curvature function can be used to quantify the rate of change of relative displacement over time. The aforementioned relative displacement change exponent can be used to measure the changing trend of the approaching speed of a target. The aforementioned relative displacement can be used to characterize the vector information (including distance and direction information) of the target's position change relative to the vehicle. This relative displacement can include changes in the straight-line distance between the target and the vehicle, and lateral offset. This relative displacement can be used to characterize the speed and path of the target approaching or moving away from the vehicle.

[0080] The relative displacement can be determined by position analysis of multiple consecutive image frames. Specifically, for any image frame, the visual recognition algorithm obtains the position coordinates of the target object in that image frame, transforms the position coordinates of the target object to the vehicle coordinate system, compares the position coordinates of the target object with the coordinates of the target vehicle, and uses time series analysis to calculate the position change of the target object relative to the vehicle, thereby determining the relative displacement.

[0081] It should be noted that, by using the aforementioned vehicle motion data and the feature data corresponding to the target object, in addition to determining the relative displacement between the target vehicle and the target object, the relative speed and relative distance can also be determined using the aforementioned vehicle motion data and the feature data corresponding to the target object.

[0082] In an exemplary application scenario, the warning distance threshold is denoted as X1. The relative displacement (denoted as x) is determined using the vehicle motion data and the feature data corresponding to the target object. Furthermore, based on the warning distance threshold X1, the relative displacement x, and the exponential curvature function, the relative displacement change index (denoted as ΔX) is determined, as shown in Equation (1).

[0083] △X=X1×e x Equation (1)

[0084] Still in the above application scenario, the above vehicle motion data may include the vehicle speed (denoted as v2), and the feature data corresponding to the above target object includes the target object speed (denoted as v1). In particular, when the above target object is a static object, the target object speed v1 can be 0. Then, the relative speed (denoted as Δv) can be obtained by using the vehicle speed and the target object speed, as shown in equation (2).

[0085] △v=v1-v2 Equation (2)

[0086] In the same application scenario, the feature data corresponding to the target object is analyzed to determine the position coordinates of the target object in the image frame. The position coordinates of the target object are then transformed to the vehicle coordinate system, and the position coordinates of the target object are compared with the coordinates of the target vehicle to determine the relative distance between the target vehicle and the target object.

[0087] The above optional embodiments of this application can achieve the following technical effects: In this application, the warning distance is determined according to the selected target object category, thereby determining the relative motion data (e.g., relative displacement, relative displacement change index). In other words, this application can determine the warning distance more specifically according to different types of target objects, thereby improving the accuracy of the relative displacement change index.

[0088] Optionally, in step S40 above, controlling the dashcam to switch to emergency recording mode based on relative motion data and prediction conditions includes the following steps:

[0089] S41: Judge the relative motion data according to the prediction conditions and obtain the judgment result, wherein the judgment result is used to characterize whether the relative motion data meets the prediction conditions;

[0090] S42: In response to the judgment result indicating that the relative motion data meets the prediction conditions, control the dashcam to switch from normal recording state to emergency recording state.

[0091] The aforementioned judgment result can be a logical output of whether the relative motion data meets the prediction conditions. This judgment result can be used to characterize whether the motion trend between the target vehicle and the target object will lead to a potential risk to the target vehicle. The judgment result can be data in binary form, such as 1 and 0. Specifically, when the aforementioned relative motion data meets the prediction conditions, the judgment result can be determined as 1; when the aforementioned relative motion data does not meet the prediction conditions, the judgment result can be determined as 0.

[0092] The aforementioned normal recording mode refers to the working mode of the dashcam under normal driving conditions. In normal recording mode, the dashcam can record video of the front, rear, or surrounding environment of the vehicle at predetermined time intervals or continuously. However, the video files collected by the dashcam in normal recording mode will follow the principle of file cyclic overwriting. That is, when storage space is insufficient, the system will automatically delete the oldest video segments to make room for new video data.

[0093] In an exemplary application scenario, the system can retrieve prediction conditions from the storage area, assuming that these prediction conditions include a relative motion data threshold. Visual perception data (especially feature data of the target object) is acquired in real time via an in-vehicle camera and a visual recognition algorithm. The relative motion data between the target vehicle and the target object is determined using the vehicle's motion data and the visual perception data. This relative motion data is compared with the relative motion data threshold to determine if it exceeds the threshold. If the relative motion data exceeds the threshold, it is considered that the relative motion data meets the prediction conditions, and the determination result can be set to 1. Further, when the determination result is 1 (i.e., in response to the determination result indicating that the relative motion data meets the prediction conditions), the dashcam is controlled to switch from normal recording mode to emergency recording mode.

[0094] The above-mentioned optional embodiments of this application can achieve the following technical effects: through real-time analysis and intelligent judgment, it can ensure that the emergency recording function can be automatically and quickly triggered when there is a driving risk in the target vehicle, that is, control the dashcam to switch from normal recording state to emergency recording state, so as to ensure that the video recorded by the dashcam can be effectively preserved and provide evidence for subsequent accident analysis and liability determination.

[0095] Optionally, the prediction conditions include vehicle state judgment conditions and a third judgment condition. The relative motion data also includes the relative displacement change index, relative distance, and relative speed. In step S41 above, judging the relative motion data based on the prediction conditions and obtaining the judgment result includes the following steps:

[0096] S411: Determine the state result of the target vehicle based on the vehicle state judgment conditions, the relative displacement change index, and the relative speed. The vehicle state judgment conditions are used to determine whether the target vehicle is in an emergency movement state.

[0097] S412: In response to the state result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning distance threshold according to the third judgment condition to determine the judgment result, wherein the third judgment condition is used to determine whether the target vehicle is within the warning range.

[0098] The aforementioned vehicle status judgment conditions can be used to determine whether a target vehicle is in an emergency movement state. For example, thresholds can be set for the relative displacement change index and relative speed to determine the target vehicle's status. Alternatively, a comprehensive analysis of the relative displacement change index and relative speed can be performed to obtain the vehicle's status level (including Level 1, Level 2, and Level 3). Based on the status level and the vehicle status judgment conditions, the target vehicle's status is determined. These status results may include, but are not limited to, stationary and moving states (including normal and emergency movement states). The aforementioned relative distance can refer to the real-time distance between the target vehicle and the vehicle itself.

[0099] The aforementioned relative speed refers to the speed of the target object relative to the target vehicle. This relative speed can be used to characterize the speed trend of the target vehicle approaching the target object. By using onboard GPS, radar, or visual recognition technology to obtain the speed of the target vehicle and the speed of the target object, the difference between the speed of the target object and the speed of the target vehicle is obtained, and this difference is determined as the relative speed.

[0100] The relative velocity can include directional information. Specifically, when the target object and the target vehicle are moving in the same direction and the target object's velocity is greater than the target vehicle's velocity, the relative velocity between the target object and the target vehicle is positive; when the target object is stationary and the target vehicle is moving towards the target object, the relative velocity between the target object and the target vehicle is negative; when the target object is stationary and the target vehicle is moving away from the target object, the relative velocity between the target object and the target vehicle is negative; when the target object and the target vehicle are moving in the same direction and the target object's velocity is less than the target vehicle's velocity, the relative velocity between the target object and the target vehicle is negative; when the target object and the target vehicle are moving in opposite directions, the relative velocity between the target object and the target vehicle is also negative; in particular, when the target object and the target vehicle are moving in the same direction and the target object's velocity is equal to the target vehicle's velocity, the relative velocity between the target object and the target vehicle can be zero; when both the target object and the target vehicle are stationary, the relative velocity between the target object and the target vehicle can also be zero.

[0101] The above-mentioned optional embodiments of this application can achieve the following technical effects: based on the vehicle status judgment conditions, the relative displacement change index and the relative speed, it is judged whether the target vehicle is in an emergency movement state, and the status result of the target vehicle is determined; further, in response to the status result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning distance threshold according to the third judgment condition to determine the judgment result, which can ensure that the vehicle is controlled when it is in motion, and avoids the emergency recording function being accidentally triggered when the vehicle is parked.

[0102] Optionally, the vehicle state judgment conditions include a first judgment condition and a second judgment condition. In step S411 above, determining the dynamic characteristics of the target vehicle based on the relative displacement change index and relative velocity includes the following steps:

[0103] S4111: Based on the first judgment condition, the relative speed and the preset speed threshold are compared and judged to determine the speed judgment result;

[0104] S4112: Based on the second judgment condition, the relative displacement change index and the preset threshold of the index are compared and judged to determine the displacement judgment result;

[0105] S4113: Determine the state result based on the velocity judgment result and the displacement judgment result.

[0106] The first judgment condition described above can be used to determine whether the speed change between the target vehicle and the target object has reached a level that triggers an emergency recording state. The second judgment condition described above can be used to determine whether the displacement change between the target vehicle and the target object has reached a level that triggers an emergency recording state.

[0107] The aforementioned preset speed threshold can be determined based on calibration experiments conducted on the target vehicle. This preset speed threshold can be adjusted according to actual application requirements. Similarly, the aforementioned preset index threshold can be determined based on calibration experiments conducted on the target vehicle. This preset index threshold can be adjusted according to actual application requirements.

[0108] The aforementioned speed determination results can include normal motion states (e.g., when the relative speed between the target vehicle and the target object does not exceed a preset speed threshold, the relative speed can be considered within a safe range, and the speed determination result is determined to be a normal motion state) and emergency motion states (e.g., when the relative speed between the target vehicle and the target object exceeds a preset speed threshold, the relative speed is considered outside a safe range, and the speed determination result is determined to be an emergency motion state). Specifically, the preset speed threshold can be set to 0, and this speed determination result can be used to characterize whether the relative speed is less than 0.

[0109] The aforementioned displacement judgment results can include normal motion state (e.g., when the relative displacement change index between the target vehicle and the target object does not exceed a preset threshold, the relative displacement change index can be considered within a safe range, and the displacement judgment result is determined to be a normal motion state) and emergency motion state (e.g., when the relative displacement change index between the target vehicle and the target object exceeds a preset threshold, the relative displacement change index is considered outside a safe range, and the displacement judgment result is determined to be an emergency motion state). Specifically, this relative displacement judgment result can be used to characterize whether the relative displacement changes rapidly; when the relative displacement change index is greater than a preset threshold, the relative displacement can be considered to change rapidly.

[0110] In one exemplary application scenario, it is still as follows Figure 2 As shown, after identifying the target object, the relative motion data between the target object and the target vehicle is determined. Then, based on the prediction conditions and the relative motion data, a prediction is made regarding whether there is a driving risk associated with the target vehicle. Specifically, the prediction conditions may include a first judgment condition, a second judgment condition, and a third judgment condition. The process of predicting whether there is a driving risk associated with the target vehicle based on the prediction conditions and relative motion data can be as follows: A preset speed threshold is set to 0; the first judgment condition is set to "whether the relative speed is less than 0"; based on the first judgment condition, the relative speed and the preset speed threshold are compared; if the relative speed is less than the preset speed threshold, the speed judgment result is determined to be "relative speed less than 0"; if the relative speed is greater than or equal to the preset speed threshold, the speed judgment result is determined to be "relative speed not less than 0"; the second judgment condition is set to "whether the relative displacement changes". "The relative displacement changes very quickly." Further, based on the second judgment condition, the relative displacement change index and the index preset threshold are compared and judged. When the relative displacement change index is greater than the index preset threshold, the displacement judgment result is determined to be "relative displacement changes very quickly." When the relative displacement change index is not greater than the index preset threshold, the displacement judgment result is determined to be "relative displacement does not change very quickly." Then, when the speed judgment result is "relative speed is less than 0" and the displacement judgment result is "relative displacement changes very quickly," the state result can be determined to be "emergency movement state." At this time, it is necessary to further determine whether it is necessary to control the dashcam to switch to emergency recording state based on the third judgment condition.

[0111] Still in the above application scenario, the third judgment condition is used to determine whether the target vehicle is within the warning boundary. The third judgment condition is set as "whether the relative distance is within the warning boundary zone". In response to the state result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning boundary distance threshold according to the third judgment condition. When the relative distance is less than the warning boundary distance threshold, it is considered that the relative distance is within the warning boundary zone and the target vehicle is within the warning boundary. The judgment result is determined as "relative motion data meets the prediction condition", thereby controlling the dashcam to perform emergency recording (i.e., controlling the dashcam to switch to emergency recording state); when the relative distance is not less than the warning boundary distance threshold, the judgment result is determined as "relative motion data does not meet the prediction condition".

[0112] The above-mentioned optional embodiments of this application can achieve the following technical effects: This application uses multiple types of parameters to determine the state result of the target vehicle, which can more comprehensively evaluate the driving state of the vehicle, improve the accuracy of the state result, and thus ensure the accuracy of the system's warning in dynamic driving environment.

[0113] According to another aspect of the embodiments of this application, a vehicle control system is also provided, including: a target vehicle, configured to send the target vehicle's own motion data and visual perception data collected by an onboard camera, wherein the display content corresponding to the visual perception data includes a target object; a cloud computing module, connected to the target vehicle, configured to use a visual recognition algorithm to mark objects in the visual perception data to obtain a marking result, wherein the marking result is used to characterize the category of the target object; the target vehicle is further configured to use the own motion data and the marking result to determine the relative motion data between the target vehicle and the target object; the target vehicle is further configured to control the target vehicle's dashcam to switch to an emergency recording state based on the relative motion data and prediction conditions, wherein the prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording state is used to lock and retain the recorded information of the dashcam.

[0114] The vehicle control system provided in this application embodiment achieves the following technical effects: by using the target vehicle, the vehicle's own motion data and the visual perception data collected by the vehicle-mounted camera are sent to the cloud computing module connected to the target vehicle; further, by using the cloud computing module to call the visual recognition algorithm to mark the visual perception data, the cloud computing resources can be used for data processing, improving the speed of obtaining the marking results and enhancing the timeliness of the vehicle control method; further, the relative motion data between the target vehicle and the target object can be determined more promptly, and the driving risk of the target vehicle can be predicted in advance, thereby quickly controlling the dashcam to switch to emergency recording mode and locking and retaining the recorded information of the dashcam.

[0115] This application also provides a vehicle control device 300, please refer to... Figure 3 The vehicle control device 300 includes: an acquisition module 310 for acquiring the vehicle's motion data and visual perception data collected by the vehicle-mounted camera, wherein the display content corresponding to the visual perception data includes the target object; a marking module 320 for marking the visual perception data to obtain marking results, wherein the marking results are used to characterize the category of the target object; a determination module 330 for determining the relative motion data between the target vehicle and the target object using the vehicle motion data and the marking results; and a control module 340 for controlling the target vehicle's dashcam to switch to emergency recording mode based on the relative motion data and prediction conditions, wherein the prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording mode is used to lock and retain the recorded information of the dashcam.

[0116] The vehicle control device provided in this application embodiment achieves the following technical effects: Using the acquisition module 310, the device acquires the vehicle's motion data and visual perception data collected by the vehicle-mounted camera. The marking module 320 marks the visual perception data to obtain marking results, enabling real-time identification of objects around the vehicle. Furthermore, using the determination module 330, the device uses the vehicle motion data and marking results to determine the relative motion data between the target vehicle and the target object. The control module 340, combining this relative motion data and prediction conditions, can predict in advance whether there is a driving risk to the target vehicle (e.g., whether the target vehicle will collide with the target object), thereby promptly controlling the dashcam to switch to emergency recording mode and locking and storing the recorded information. Therefore, this application embodiment, by utilizing the relative motion data between the target vehicle and the target object, can quickly control the dashcam to switch to emergency recording mode, enhancing the performance of the vehicle control device.

[0117] This application also provides a vehicle 400, please refer to... Figure 4 It includes an on-board memory 410 and an on-board processor 420, wherein the on-board memory 410 is used to store computer programs; and the on-board processor 420 is used to execute the computer programs stored in the memory to implement the vehicle control method of any embodiment.

[0118] The vehicle provided in this application embodiment achieves the following technical effects: by acquiring the vehicle's own motion data and the visual perception data collected by the vehicle-mounted camera, the visual perception data is marked to obtain the marking results, enabling real-time identification of target objects around the vehicle; furthermore, by utilizing the vehicle's own motion data and the marking results, the relative motion data between the target vehicle and the target object is determined, and by combining the relative motion data and prediction conditions, it is possible to predict in advance whether there is a driving risk to the target vehicle (e.g., whether the target vehicle will collide with the target object), thereby timely controlling the dashcam to switch to emergency recording mode, locking and storing the recorded information of the dashcam, and enhancing the vehicle's intelligence.

[0119] Those skilled in the art will understand that, similarly, the aforementioned vehicle can also be a computing terminal. Figure 5 This is a hardware structure block diagram of a computing terminal for implementing a vehicle control method according to an embodiment of this application, such as... Figure 5 As shown, the computing terminal 500 (e.g., a computer terminal, a mobile smart terminal, a vehicle terminal, or a cloud computing virtual terminal) may include: one or more processors 502 (e.g., processors 502a, 502b, ..., 502n), a memory 504 for storing data, and a transmission device 506 for implementing communication functions. The processor 502 may include, but is not limited to, processing components such as a microprocessor (MCU) or a field programmable gate array (FPGA).

[0120] The aforementioned computing terminal 500 may further include: a display, an input / output interface, a Universal Serial Bus (USB) port (which can be used as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and a camera (not shown in the figure).

[0121] It should be noted that one or more processors 502 and / or other data processing circuits in the aforementioned computing terminal 500 may be wholly or partially embodied in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computing terminal 500 (or mobile device).

[0122] The memory 504 can be used to store software programs and modules of application software, such as the program instructions and data storage devices corresponding to the vehicle control method in this embodiment. The processor 502 executes various functional applications and data processing by running the software programs and modules stored in the memory 504, thereby realizing the aforementioned vehicle control method. The memory 504 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 504 may further include memory remotely located relative to the processor 502, and these remote memories can be connected to the vehicle terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0123] The transmission device 506 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the vehicle terminal's communication provider. In one example, the transmission device 506 includes a Network Interface Controller (NIC) and a network interface, which can connect to other network devices via a base station to communicate with the Internet. The transmission device 506 can use wired and / or wireless network connections for data communication. In one example, the transmission device 506 can be a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0124] The input / output interface can be connected to the corresponding input / output device of the computing terminal 500 to realize input / output functions. This input / output device may include, but is not limited to, a cursor control device, a keyboard, and a display. The aforementioned input / output device may be built into the computing terminal 500 or an external device connected to the computing terminal 500.

[0125] Those skilled in the art will understand that Figure 5 The structure of the computing terminal 500 shown is for illustrative purposes only and does not impose strict limitations on the structure of the computing terminal 500 described above. For example, the computing terminal 500 may also include components such as... Figure 5 The more or fewer components shown, or the computing terminal 500 may have the same Figure 5 The components are shown in different categories.

[0126] It should be noted that the optional implementation methods of this embodiment can be found in the relevant description in Embodiment 1, and will not be repeated here.

[0127] This application also provides an electronic device 600, please refer to... Figure 6It includes a memory 610 and a processor 620, wherein the memory 610 is used to store computer programs; and the processor 620 is used to execute the programs stored in the memory 610 to implement the vehicle control method described in any embodiment of this application.

[0128] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, and mobile internet devices (MIDs) and other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, electronic device 600 may also include components that are more... Figure 6 The more or fewer components shown (e.g., network interface, display device, etc.), or having the same Figure 6 The different configurations shown.

[0129] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle control method described in any embodiment of this application.

[0130] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0131] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0132] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0133] In this application, "multiple" refers to two or more.

[0134] In this application, unless otherwise expressly defined, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0135] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0136] The term "and / or" in this application simply describes an association between related objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects are in an "or" relationship.

[0137] Unless otherwise specified, all steps in this application may be performed sequentially or randomly. For example, if the method includes steps A and B, it means that the method may include steps A and B performed sequentially, or it may include steps B and A performed sequentially. For example, if the method may also include step C, it means that step C may be added to the method in any order. For example, the method may include steps A, B, and C, or it may include steps A, C, and B, or it may include steps C, A, and B, etc.

[0138] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A vehicle control method, characterized in that, include: Acquire the vehicle's motion data and visual perception data collected by the vehicle's camera, wherein the display content corresponding to the visual perception data includes the target object; The visual perception data is labeled to obtain a labeling result, wherein the labeling result is used to characterize the category of the target object; Using the vehicle motion data and the marking results, the relative motion data between the target vehicle and the target object is determined; Based on the relative motion data and prediction conditions, the dashcam of the target vehicle is controlled to switch to emergency recording mode. The prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording mode is used to lock and retain the recorded information of the dashcam.

2. The vehicle control method according to claim 1, characterized in that, The visual perception data includes feature data corresponding to multiple candidate objects. Object labeling is performed on the visual perception data to obtain the labeling results, including: Visual recognition algorithms are used to identify the feature data corresponding to the multiple candidate objects to obtain recognition results; Based on the recognition results, the feature data corresponding to the multiple candidate objects are labeled to obtain the labeling results.

3. The vehicle control method according to claim 2, characterized in that, Using the vehicle motion data and the marking results, the relative motion data between the target vehicle and the target object is determined as follows: Based on the marking results and the target object selection criteria, feature data corresponding to the target object is extracted from the visual perception data, wherein the target object selection criteria are used to determine whether the category of the candidate object belongs to the expected category; The relative motion data is determined using the vehicle's motion data and the feature data corresponding to the target object.

4. The vehicle control method according to claim 3, characterized in that, The relative motion data includes relative displacement and relative displacement change index. Using the vehicle motion data and the feature data corresponding to the target object, the relative motion data is determined to include: Determine the warning distance threshold based on the category of the target object; The relative displacement is determined using the vehicle motion data and the feature data corresponding to the target object; The relative displacement change index is determined based on the warning distance threshold, the relative displacement, and the exponential curvature function.

5. The vehicle control method according to any one of claims 1 to 4, characterized in that, Based on the relative motion data and prediction conditions, controlling the dashcam to switch to emergency recording mode includes: The relative motion data is judged based on the prediction conditions to obtain a judgment result, wherein the judgment result is used to characterize whether the relative motion data meets the prediction conditions; In response to the judgment result indicating that the relative motion data meets the prediction condition, the dashcam is controlled to switch from normal recording state to emergency recording state.

6. The vehicle control method according to claim 5, characterized in that, The prediction conditions include vehicle state judgment conditions and a third judgment condition. The relative motion data also includes the relative displacement change index, relative distance, and relative speed. The relative motion data is judged based on the prediction conditions to obtain the judgment results, including: The state result of the target vehicle is determined based on the vehicle state judgment condition, the relative displacement change index, and the relative speed, wherein the vehicle state judgment condition is used to determine whether the target vehicle is in an emergency movement state. In response to the state result indicating that the target vehicle is in an emergency movement state, the relative distance is compared with the warning distance threshold according to the third judgment condition to determine the judgment result, wherein the third judgment condition is used to determine whether the target vehicle is within the warning range.

7. The vehicle control method according to claim 6, characterized in that, The vehicle state determination conditions include a first determination condition and a second determination condition. Based on the relative displacement change index and the relative velocity, the dynamic characteristics of the target vehicle are determined as follows: Based on the first judgment condition, the relative speed and the preset speed threshold are compared and judged to determine the speed judgment result; Based on the second judgment condition, the relative displacement change index and the preset index threshold are compared and judged to determine the displacement judgment result; Based on the velocity determination result and the displacement determination result, the state result is determined.

8. A vehicle control system, characterized in that, include: The target vehicle is used to send the vehicle's own motion data and visual perception data collected by the vehicle's camera, wherein the display content corresponding to the visual perception data includes the target object; A cloud computing module, connected to the target vehicle, is used to perform object labeling on the visual perception data using a visual recognition algorithm to obtain labeling results, wherein the labeling results are used to characterize the category of the target object; The target vehicle is further configured to use the vehicle motion data and the marking results to determine the relative motion data between the target vehicle and the target object; The target vehicle is further configured to control its dashcam to switch to emergency recording mode based on the relative motion data and prediction conditions. The prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording mode is used to lock and retain the recording information of the dashcam.

9. A vehicle control device, characterized in that, include: The acquisition module is used to acquire the vehicle motion data of the target vehicle and the visual perception data collected by the vehicle camera, wherein the display content corresponding to the visual perception data includes the target object; A labeling module is used to label objects in the visual perception data to obtain labeling results, wherein the labeling results are used to characterize the category of the target object; The determination module is used to determine the relative motion data between the target vehicle and the target object using the vehicle motion data and the marking results; The control module is used to control the dashcam of the target vehicle to switch to emergency recording mode based on the relative motion data and prediction conditions. The prediction conditions are used to predict whether there is a driving risk in the target vehicle, and the emergency recording mode is used to lock and retain the recording information of the dashcam.

10. A vehicle, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 8.

Images