Space fusion method, system, terminal device and storage medium

Abstract

The application relates to the technical field of automatic parking, and discloses a space available fusion method, a space available fusion system, a terminal device and a storage medium, the method comprising the following steps: acquiring positioning data of a vehicle, and acquiring visual data of the vehicle; determining the positioning data corresponding to the visual data according to the time stamp of the visual data and the time stamp of the positioning data; fusing and calculating the visual data and historical space available data to obtain first fusion data; acquiring detected parking space data, fusing and processing the first fusion data and the parking space data to obtain space available region data at a current time. Through fusing of the parking space data and the visual data, errors are reduced, the accuracy of the space available region is increased, and therefore the accuracy and safety of parking are improved.

Description

Technical Field

[0001] This invention relates to the field of automated parking, and more particularly to a usable space fusion method, system, terminal device, and storage medium. Background Technology

[0002] APA parking system is an automatic parking assistance system that uses the vehicle's surround-view cameras, ultrasonic sensors, and other sensors to detect the environment around the vehicle, automatically find a suitable parking space, and automatically complete the parking operation.

[0003] In automated parking, in addition to detecting the current target parking space, it is also necessary to detect the free space (available space area) when parking. During parking planning, the system automatically avoids surrounding obstacles, walls, and pillars to ensure the vehicle is safely parked in the target space. Therefore, free space, as an important input parameter for parking path planning, is crucial to the success and safety of parking.

[0004] Existing technologies typically acquire the free space of the surrounding environment through sensors such as vehicle-mounted radar and cameras. However, these sensors have drawbacks, including low detection accuracy and susceptibility to various factors such as weather conditions and light intensity. This can lead to errors in the free space perceived by the system, significantly impacting parking success. Summary of the Invention

[0005] Firstly, this application provides a usable spatial fusion method, including:

[0006] Acquire the vehicle's location data and acquire the vehicle's visual data;

[0007] Based on the timestamp of the visual data and the timestamp of the positioning data, the positioning data corresponding to the visual data is determined;

[0008] The visual data and historical available spatial data are fused and calculated to obtain the first fused data;

[0009] The detected parking space data is acquired, and the first fused data and the parking space data are fused and processed to obtain the available space area data at the current moment.

[0010] Further, based on the timestamps of the visual data and the positioning data, the positioning data corresponding to the visual data is determined, including:

[0011] Upon receiving the positioning data, it is determined whether visual data has been received. If no visual data has been received, the positioning data is cached in a circular storage; wherein the circular storage is used to store positioning data for a preset time length.

[0012] When the visual data is received, it is determined that the timestamp of the visual data is within the range of the timestamp of the stored positioning data;

[0013] If present, the most recent location data is found based on the timestamp of the visual data.

[0014] Furthermore, the step of fusing the visual data and historical available spatial data to obtain the first fused data includes:

[0015] The visual data includes multiple spatial perception points, which are the coordinates of edge points perceived at preset angles with the vehicle as the center.

[0016] The visual data is converted into data in a global coordinate system;

[0017] The spatial sensing points are expanded through interpolation, the distance between each spatial sensing point and the vehicle is calculated, and the maximum and minimum values ​​are removed.

[0018] Obtain historical available spatial data, calculate the average value of the current visual data and the historical available spatial data, and obtain the first fused data.

[0019] Furthermore, after converting the visual data into data in a global coordinate system, the process further includes:

[0020] If the vehicle moves, the historical available spatial data will be converted into coordinate points in the vehicle coordinate system.

[0021] Furthermore, the process of fusing the first fused data and the parking space data to obtain the available space area data at the current moment includes:

[0022] The outline of the parking space is widened by a predetermined safety distance in the front-back, left-right and right directions to obtain 4 widened parking space segments;

[0023] Calculate the parking space edge points of each parking space line segment and the origin of the vehicle, and obtain the distance between each parking space edge point and the center point of the vehicle; the parking space edge points are the coordinates of points perceived at preset angles with the vehicle as the center.

[0024] The distances between the first fused data and the edge points of each parking space at the same angle are compared, and the point with the largest distance is taken as the point in the available space area data.

[0025] Furthermore, after obtaining the available spatial region data at the current moment, the process also includes:

[0026] The available spatial area data is converted into first spatial area data in the vehicle coordinate system;

[0027] Based on the current vehicle positioning data, the available spatial area data is converted into second spatial area data in a global coordinate system;

[0028] The first spatial region data is used as input parameters for parking planning, and the second spatial region data is used as historical data for spatial data fusion calculation at the next moment.

[0029] Secondly, this application also provides a usable spatial fusion system, including a positioning device, a vision device, and a fusion device;

[0030] The positioning device acquires the vehicle's positioning data, and the vision device acquires the vehicle's visual data.

[0031] The fusion device determines the positioning data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the positioning data;

[0032] The fusion device fuses the visual data and historical available spatial data to obtain first fused data.

[0033] The fusion device is also used to fuse the first fused data and the positioning data to obtain the available spatial area data at the current moment.

[0034] Furthermore, the system also includes:

[0035] The fusion device sends a synchronization signal to the positioning device and the vision device, and obtains the signal transmission time of the synchronization signal, the first response time of the positioning device, and the second response time of the vision device.

[0036] Determine the first reception time when the fusion device receives the response from the positioning device, and the second reception time when the fusion device receives the response from the vision device;

[0037] Synchronize the time of the fusion device and the positioning device according to the first response time and the first reception time;

[0038] The timing of the fusion device and the vision device is synchronized based on the second response time and the second reception time.

[0039] Thirdly, this application also provides a terminal device, including a processor and a memory, wherein the memory stores a computer program, and the computer program executes the available space fusion method when it runs on the processor.

[0040] Fourthly, this application also provides a readable storage medium storing a computer program that executes the available space fusion method when run on a processor.

[0041] This invention discloses a method for fusing available space, comprising: acquiring vehicle positioning data and acquiring visual data of the vehicle; determining the positioning data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the positioning data; fusing the visual data and historical available space data to obtain first fused data; acquiring detected parking space data, and fusing the first fused data and the parking space data to obtain available space area data at the current moment. By fusing parking space data and visual data, errors caused by camera perception misjudgment can be eliminated. Historical and existing data can be analyzed comprehensively to provide relatively accurate available space information, thereby increasing parking accuracy. Attached Figure Description

[0042] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0043] Figure 1 A schematic flowchart of an available spatial fusion method according to an embodiment of this application is shown;

[0044] Figure 2 A schematic diagram of a usable spatial fusion system structure according to an embodiment of this application is shown;

[0045] Figure 3 This illustration shows a schematic diagram of available spatial data according to an embodiment of this application;

[0046] Figure 4 A schematic diagram illustrating a usable spatial fusion method according to an embodiment of this application is shown. Detailed Description

[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0048] The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0049] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of the invention, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0050] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of the invention pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of the invention.

[0052] The technical solution of this application is applied to the automatic parking process of a vehicle. It acquires the vehicle's positioning data and visual data; determines the positioning data corresponding to the visual data based on the timestamps of the visual data and the positioning data; fuses the visual data with historical available space data to obtain first fused data; acquires detected parking space data, and fuses the first fused data with the parking space data to obtain the available space area data at the current moment. This fusion of available space data and parking space data with historical data makes the final available space area data more complete and accurate, eliminating errors caused by camera misjudgment and increasing recognition accuracy.

[0053] The technical solution of this application will be described below with specific embodiments.

[0054] Example 1

[0055] like Figure 1 As shown, the technical solution of this application includes:

[0056] Step S100: Obtain the vehicle's positioning data and the vehicle's visual data.

[0057] Vehicles contain positioning devices, such as GPS, Beidou navigation, or a combination of wheel speed pulses, steering wheel angles, IMU, etc., which can be used to calculate the vehicle's own positioning coordinates.

[0058] Visual data is acquired through sensing devices such as cameras. In this embodiment, usable spatial area data from the visual data is mainly used.

[0059] Specifically, such as Figure 2 As shown, this is the structure of the available spatial fusion system of this application, which includes: a positioning device 100, a vision device 2000, and a fusion device 300.

[0060] The fusion device 300 is used to perform the parking space data fusion operation of this application.

[0061] It is understandable that the two types of data are actually generated by two different devices, so before obtaining the two types of data, the fusion device 300 will also perform synchronous operation on the two devices.

[0062] Specifically, the fusion device 300 sends a synchronization signal to the positioning device 100 and the vision device 200, and obtains the signal transmission time of the synchronization signal, the first response time of the positioning device 100, and the second response time of the vision device 200.

[0063] Determine the first reception time when the fusion device receives the response from the positioning device, and the second reception time when the fusion device receives the response from the vision device;

[0064] Synchronize the time of the fusion device and the positioning device according to the first response time and the first reception time;

[0065] The timing of the fusion device and the vision device is synchronized based on the second response time and the second reception time.

[0066] For example, if the timestamp of the synchronization message sent by the fusion device 300 is T0, the timestamp of the response from the positioning device 100 is T0', and the timestamp of the response received by the fusion device 300 from the positioning device 100 is T1, then the one-way transmission delay of the network is δT = (T1 - T0). Thus, the time difference between the fusion device 300 and the positioning device 100 is dT = T0 - T0' + δT.

[0067] Since the positioning device 100 is the sender and the fusion device is the receiver, the conversion relationship between time T in the fusion module reference frame and T' in the positioning device reference frame is T' = T - dT.

[0068] Having established the aforementioned conversion relationships, the synchronization operation is complete. The same method can be used to achieve synchronization between the fusion device 300 and the vision device 200.

[0069] Step S200: Determine the positioning data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the positioning data.

[0070] After synchronization, the timestamps of the obtained visual data and the positioning data can both be converted to the same reference system. Therefore, the relationship between the visual data and the positioning data can be determined based on the timestamps.

[0071] In this embodiment, the main purpose is to determine the location data and visual data at the same time. Since the visual data is image data, it takes time to process. Therefore, for the fusion device 300, the speed at which it receives the visual data is slower than that of the location data. Thus, it is possible that the location data at the current time has been transmitted, but the visual data has not yet arrived. Therefore, in this embodiment, the location data is stored in a circular storage to store the location data for a preset duration. The location data for the preset duration is cached to wait for the arrival of the visual data.

[0072] When the visual data is received, it is determined that the timestamp of the visual data is within the range of the timestamp of the stored positioning data.

[0073] If present, the most recent location data is found based on the timestamp of the visual data.

[0074] For example, if 10 milliseconds of location data are cached, meaning the stored location data is 50 to 60 milliseconds, and then visual data is received, it is determined whether the timestamp of the visual data is within 1 to 10 milliseconds. If the timestamp is 56 milliseconds, it is within the range of the timestamp of the stored location data; if it is 45 milliseconds, it means it is not within the time range of the stored location data.

[0075] If the location is not within range, it is necessary to wait for the next visual data and store the location data. If the location is within range, the closest location data can be found in the cached location data by using the timestamp of the visual data, and finally the location data at the timestamp of the visual data can be obtained, thereby determining the vehicle's pose at that time.

[0076] Step S300: The visual data and historical available spatial data are fused and calculated to obtain the first fused data.

[0077] This embodiment primarily uses available spatial data from visual data. Specifically, the available spatial data is as follows: Figure 3The image shows the coordinates of edge points sensed at preset angles, centered on the vehicle. Figure 3 P1, P0, etc., where the preset angle can be 4 degrees, then there will be 90 edge points, and if it is 2 degrees, then there will be 180 edge points.

[0078] Historical available space data is the available space data calculated at previous times. By integrating historical available space data, the error of data obtained at the current time can be reduced.

[0079] Considering factors such as system computing power and the maximum range of available spatial data, the visual fusion system needs to store 180, 360, or even more points. Therefore, interpolation can be used to increase the number of these edge points.

[0080] Specifically, assuming that the original 90 points (P0, P1, ..., P89) of the available spatial data are obtained, and their distances from the center point of the vehicle are distRaw[0], distRaw[1], ..., distRaw

[89] , then the calculation formula for the distances distNew[0], distNew[1], ..., distNew

[179] of the 180 points (P0', P1', ..., P179') obtained by interpolation is as follows:

[0081] distNew[i*2] = distRaw[i];

[0082] distNew[i*2+1]=(distRaw[i]+distRaw[(i+1)mod 90]) / 2;

[0083] In the formula, distNew represents the new point obtained by interpolation, where distRaw represents the original point, and i is the subscript of the edge point, 0≤i≤89.

[0084] It's understandable that at this point, the coordinates of each point are only angles plus distances, and they need to be converted to coordinates in a Cartesian coordinate system. Therefore, we first convert them to x and y coordinates in the vehicle's coordinate system. The specific conversion formula is as follows:

[0085] x[i] = distNew[i] * sin(i * 2);

[0086] y[i] = distNew[i] * cos(i * 2);

[0087] Where 0 ≤ i ≤ 179;

[0088] Then, a coordinate transformation is performed to convert the coordinates to x', y' coordinates in the global coordinate system.

[0089] The global coordinate system refers to a coordinate system established with the center of the vehicle's rear axle as the origin at the moment the system triggers the search for parking spaces. From the driver's perspective, the X-axis is front and back, Y-axis is left and right, Z-axis is top and bottom.

[0090] Through the second step above, we have obtained the actual vehicle pose (vehicle coordinates xoc, yoc, deflection angle θ) corresponding to the current perception data. The calculation formula is as follows:

[0091] x'=xoc+x*cos(θ)-y*sin(θ);

[0092] y'=yoc+y*cos(θ)+x*sin(θ));

[0093] In the formula, xoc is the horizontal coordinate of the vehicle's current coordinates in the global coordinate system, yoc is the vertical coordinate, and θ is the vehicle's deflection angle.

[0094] Once the conversion is complete, the fusion calculation can be performed.

[0095] Before performing the fusion calculation, it is necessary to determine whether the current vehicle has moved. If it has not moved, the fusion process can be performed directly. If it has moved, the historical available spatial data also needs to be converted to the coordinates of the global coordinate system. The specific conversion process is similar to the conversion process described above, and will not be repeated here.

[0096] When fusing with historical available spatial data, the spatial sensing points are expanded through interpolation, the distance between each spatial sensing point and the vehicle is calculated, and the maximum and minimum values ​​are removed.

[0097] Then the average of the current visual data and the historical available spatial data can be calculated to obtain the first fused data.

[0098] Specifically, assuming

[0099] The first free-space distance information is (d[0,0],d[0,1],...,d[0,179]).

[0100] The free-space distance information for the second time is (d[1,0],d[1,1],...,d[1,179]). ...

[0102] The free-space distance information for the 10th time is (d[9,0],d[9,1],...,d[9,179]).

[0103] The first nine values ​​are historical, and the tenth value is the current value. The mean is calculated by removing the maximum and minimum values, using the following formula:

[0104]

[0105] (where 0 ≤ i ≤ 179)

[0106] In the formula, d' represents the first fused data that needs to be output.

[0107] Step S400: Obtain the detected parking space data, and fuse the first fused data and the parking space data to obtain the available space area data at the current moment.

[0108] After obtaining the first fused data, it is necessary to merge the first fused data with the parking space data to obtain the final usable space area data.

[0109] Because visual perception itself is affected by environmental interference, such as lighting and weather, the detected free-space range can sometimes be very limited. The range input to parking planning is too small, leading to planning failure. In this embodiment, during the vehicle's search for parking spaces, the previously calculated first fusion data is merged with the detected parking space data to ensure that a larger area can be used as the source of available space.

[0110] The specific calculation method is as follows: Each parking space's outline is widened by a certain safety distance forward and to the left and right (e.g., 1.5m forward and 0.2m left and right), resulting in four widened line segments for each parking space. The intersection points of these four line segments with rays emanating from the vehicle's origin (e.g., 180 rays ranging from 0 to 358°) are calculated, and the coordinates of these intersection points are converted into distance data at standard angles. The distance data at each angle is compared with the previously obtained distance data, and the maximum distance is taken as the final usable spatial data. After all points have been compared, the fusion calculation is completed.

[0111] The changes in usable space after its fusion are as follows: Figure 4 As shown.

[0112] Figure 4 The middle section depicts the scenario before the available space and parking spaces are merged. At this point, the available space 600 is the space detected around the vehicle 400, representing a section of space without obstacles around the vehicle. An empty parking space 500 is detected, but due to factors such as angle, not all parking spaces are included in the available space. After the merging operation in this embodiment, the parking spaces are integrated into the available space in the manner described above, thereby expanding the available space.

[0113] After completing the fusion calculation to obtain the available space area data at the current moment, it is necessary to save the data and transmit it as input parameters to the parking planning program for planning. To do this, the available space area data also needs to be converted into the first space area data in the vehicle coordinate system.

[0114] Assuming a resolution of 2°, the system has already calculated the historical distance information d'[0]~d'

[179] of 180 available spatial regions. The formula for calculating the coordinates of the feature points of each available spatial region in the vehicle body coordinate system is as follows:

[0115] x[i] = d'[i] * sin(i * 2);

[0116] y[i] = d'[i] * cos(i * 2);

[0117] Where 0 ≤ i ≤ 179;

[0118] Then, based on the current vehicle positioning data and the first spatial region coordinates obtained above, the available spatial region data is converted into second spatial region data in the global coordinate system.

[0119] The specific calculation formula is as follows:

[0120] x'[i]=xoc+x[i]*cos(θ)-y[i]*sin(θ);

[0121] y'[i]=yoc+y[i]*cos(θ)+x[i]*sin(θ));

[0122] Where 0 ≤ i ≤ 179;

[0123] The first spatial region data is used as input parameters for parking planning, while the second spatial region data, as historical data, is used for spatial data fusion calculation at the next time step.

[0124] The available space fusion method in this embodiment first synchronizes the timing of positioning and visual data to eliminate errors caused by delays in camera perception algorithm calculations and data transmission. Then, it fuses the original available space data with historical data and parking space data. The final data, after correction of historical data and expansion of parking space data, eliminates erroneous available space data caused by camera perception misjudgments. Due to lighting or environmental factors, the perception algorithm may occasionally misjudge surrounding interference signals, reporting non-existent obstacles or blank areas. Ultimately, this improves recognition accuracy, thereby increasing the success rate and safety of parking navigation.

[0125] Example 2

[0126] This application also provides a terminal device, including a processor and a memory, wherein the memory stores a computer program that executes the available space fusion method when the computer program is run on the processor.

[0127] The terminal device can be an in-vehicle computer or other intelligent terminal capable of performing the aforementioned available spatial fusion methods.

[0128] This application also provides a readable storage medium storing a computer program that executes the available space fusion method when run on a processor.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0130] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0131] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A usable spatial fusion method, characterized in that, include: Acquire the vehicle's location data and acquire the vehicle's visual data; Based on the timestamp of the visual data and the timestamp of the positioning data, the positioning data corresponding to the visual data is determined; The visual data and historical available spatial data are fused and calculated to obtain the first fused data; Acquire the detected parking space data, fuse the first fused data and the parking space data to obtain the available space area data at the current moment; The step of determining the location data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the location data includes: Upon receiving the positioning data, it is determined whether visual data has been received. If no visual data has been received, the positioning data is cached in a circular storage; wherein the circular storage is used to store positioning data for a preset time length. When the visual data is received, it is determined that the timestamp of the visual data is within the range of the timestamp of the stored positioning data; If present, the most recent location data is found based on the timestamp of the visual data.

2. The available spatial fusion method according to claim 1, characterized in that, The process of fusing the visual data and historical available spatial data to obtain the first fused data includes: The visual data includes multiple spatial perception points, which are the coordinates of edge points perceived at preset angles with the vehicle as the center. The visual data is converted into data in a global coordinate system; The spatial sensing points are expanded through interpolation, the distance between each spatial sensing point and the vehicle is calculated, and the maximum and minimum values ​​are removed. Obtain historical available spatial data, calculate the average value of the current visual data and the historical available spatial data, and obtain the first fused data.

3. The available spatial fusion method according to claim 2, characterized in that, After converting the visual data into data in a global coordinate system, the process further includes: If the vehicle moves, the historical available spatial data will be converted into coordinate points in the vehicle's coordinate system.

4. The available spatial fusion method according to claim 1, characterized in that, The step of fusing the first fused data and the parking space data to obtain the available space area data at the current moment includes: The outline of the parking space is widened by a predetermined safety distance in the front-back, left-right and right directions to obtain 4 widened parking space segments; Calculate the parking space edge points with the vehicle as the origin for each parking space line segment, and obtain the distance between each parking space edge point and the vehicle; the parking space edge points are the coordinates of points perceived at preset angles with the vehicle as the center. The distances between the first fused data and the edge points of each parking space at the same angle are compared, and the point with the largest distance is taken as the point in the available space area data.

5. The available spatial fusion method according to claim 1, characterized in that, After obtaining the available spatial region data at the current moment, the process further includes: The available spatial area data is converted into first spatial area data in the vehicle coordinate system; Based on the current vehicle positioning data, the available spatial area data is converted into second spatial area data in a global coordinate system; The first spatial region data is used as input parameters for parking planning, and the second spatial region data is used as historical data for spatial data fusion calculation at the next moment.

6. A usable spatial fusion system, characterized in that, Includes positioning devices, vision devices, and fusion devices; The positioning device acquires the vehicle's positioning data, and the vision device acquires the vehicle's visual data. The fusion device determines the positioning data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the positioning data; The fusion device fuses the visual data and historical available spatial data to obtain first fused data. The fusion device is also used to fuse the first fused data and the positioning data to obtain the available spatial area data at the current moment; The step of determining the location data corresponding to the visual data based on the timestamp of the visual data and the timestamp of the location data includes: Upon receiving the positioning data, it is determined whether visual data has been received. If no visual data has been received, the positioning data is cached in a circular storage; wherein the circular storage is used to store positioning data for a preset time length. When the visual data is received, it is determined that the timestamp of the visual data is within the range of the timestamp of the stored positioning data; If present, the most recent location data is found based on the timestamp of the visual data.

7. The usable space fusion system according to claim 6, characterized in that, Also includes: The fusion device sends a synchronization signal to the positioning device and the vision device, and obtains the signal transmission time of the synchronization signal, the first response time of the positioning device, and the second response time of the vision device. Determine the first reception time when the fusion device receives the response from the positioning device, and the second reception time when the fusion device receives the response from the vision device; Synchronize the time of the fusion device and the positioning device according to the first response time and the first reception time; The timing of the fusion device and the vision device is synchronized based on the second response time and the second reception time.

8. A terminal device, characterized in that, It includes a processor and a memory, the memory storing a computer program that, when executed on the processor, performs the available spatial fusion method according to any one of claims 1 to 5.

9. A readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the available spatial fusion method according to any one of claims 1 to 5.

Images