Tire pressure monitoring-based dynamic surround-view stitching method and system
By quantifying tire pressure values and constructing a mapping table through a tire pressure monitoring system, the problem of tire pressure changes affecting camera extrinsic parameters is solved, enabling efficient surround view stitching suitable for mobile terminals.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- SHANGHAI BAOLONG AUTOMOTIVE CORP
- Filing Date
- 2025-11-19
- Publication Date
- 2026-06-04
Smart Images
Figure CN2025135976_04062026_PF_FP_ABST
Abstract
Description
A Dynamic Surround View Stitching Method and System Based on Tire Pressure Monitoring Technical Field
[0001] This application belongs to the field of image processing technology, and relates to a dynamic surround view stitching method based on tire pressure monitoring, and particularly to a dynamic surround view stitching method and system based on tire pressure monitoring. Background Technology
[0002] With the rapid development of artificial intelligence technology, the intelligentization of automobiles is also accelerating. As Level 1 driver assistance systems mature, Level 2 advanced driver assistance systems are flourishing, especially those based on pure vision perception, which are gaining increasing popularity in the industry.
[0003] In automatic parking perception, vehicle control planning strategies are often based on surround view stitched images. When performing surround view stitching, it is necessary to use the intrinsic and extrinsic parameters of the surround view cameras, especially the calibration of extrinsic parameters. Currently, most traditional extrinsic parameter calibration methods are based on static camera extrinsic parameter calibration using a special checkerboard grid in a calibration workshop. In addition, in some cases, extrinsic parameter calibration is semi-dynamic and needs to be performed based on lane lines on the road. In this case, extrinsic parameter calibration requires driving the car on a designated straight road with lane lines, and there are certain speed requirements during extrinsic parameter calibration.
[0004] Both of the above traditional external parameter calibration methods are easily affected by the tire pressure of the car tires during external parameter calibration. When calibrating the camera's external parameters, the external parameters at the moment of calibration are only suitable for the tire pressure value at that moment. When the tire pressure changes, the image captured by the camera will shift, and this shift will cause the camera's external parameters to change, thus affecting the surround view stitching effect. Summary of the Invention
[0005] This application provides a dynamic surround view stitching method and system based on tire pressure monitoring, which solves the problem that the tire pressure value changes frequently and the magnitude of the change is inconsistent in traditional external parameter calibration methods, causing the image captured by the camera to shift and the external parameters of the camera to change, thereby affecting the surround view stitching effect.
[0006] In a first aspect, this application provides a dynamic surround-view stitching method based on tire pressure monitoring. The method includes: quantifying tire pressure values according to preset vehicle information of a target vehicle to obtain a tire pressure data segment array of the target vehicle; the tire pressure data segment array includes several tire pressure data segments; constructing a mapping relationship table for each tire pressure data segment according to each tire pressure data segment to obtain a total mapping relationship table; matching and searching the real-time tire pressure data of the target vehicle with the total mapping relationship table to obtain a target mapping relationship table for the real-time tire pressure data; and performing surround-view stitching of the target vehicle according to the target mapping relationship table.
[0007] In one implementation of the first aspect, the preset vehicle information includes images from each viewpoint and corresponding tire pressure data; performing tire pressure value quantization processing based on the preset vehicle information of the target vehicle to obtain the tire pressure data segment array of the target vehicle includes: performing pressure increase and / or pressure decrease processing based on the images from each viewpoint and corresponding tire pressure data to obtain image offset relationships; and performing tire pressure value quantization processing based on the image offset relationships to obtain the tire pressure data segment array of the target vehicle.
[0008] In one implementation of the first aspect, the process of performing pressure and / or depressurization processing based on the images from each viewpoint and the corresponding tire pressure data to obtain the image offset relationship includes: calibrating the target vehicle using grid calibration based on the images from each viewpoint to obtain first coordinate data of the target vehicle; the first coordinate data includes the coordinates of the calibrated corner points of each viewpoint; performing pressure and / or depressurization processing with a preset stride based on the tire pressure data to obtain second coordinate data of the target vehicle; the second coordinate data includes the coordinates of the calibrated corner points of each viewpoint after pressure and / or depressurization processing; calculating Euclidean distances based on the first coordinate data and the second coordinate data to obtain a first Euclidean distance set; the first Euclidean distance set includes the Euclidean distances of the calibrated corner points of each viewpoint before and after pressure and / or depressurization processing; iteratively processing to obtain N sets of Euclidean distance sets; where N>=1 and is an integer; calculating the average value of the N sets of Euclidean distance sets to obtain an average value; and obtaining the image offset relationship based on the average value.
[0009] In one implementation of the first aspect, the process of quantizing tire pressure values based on the image offset relationship to obtain a segmented array of tire pressure data for the target vehicle includes: performing pixel conversion based on the image offset relationship to obtain a tire pressure error; and obtaining a segmented array of tire pressure data for the target vehicle based on the tire pressure error and a preset tire pressure range.
[0010] In one implementation of the first aspect, constructing a mapping relationship table for each tire pressure data segment based on each tire pressure data segment to obtain a total mapping relationship table includes: obtaining target tire pressure data for each tire pressure data segment based on each tire pressure data segment; obtaining images from corresponding viewpoints based on the target tire pressure data for each tire pressure data segment; and constructing a mapping relationship table for each tire pressure data segment based on the images from each viewpoint to obtain a total mapping relationship table.
[0011] In one implementation of the first aspect, constructing a mapping relationship table for each tire pressure data segment based on the images from each of the respective viewpoints to obtain a total mapping relationship table includes: performing distortion correction processing on the images from each viewpoint to obtain correction data for each viewpoint; the correction data includes a correction image and a distortion correction lookup table; performing perspective transformation processing on the correction images from each viewpoint and the corresponding calibrated corner points to obtain perspective transformation data for each viewpoint; the perspective transformation data includes a perspective transformation matrix and the corresponding bird's-eye view image; performing fusion processing on the bird's-eye view images from each viewpoint to obtain a fusion matrix; performing fusion processing on the distortion correction lookup table, the perspective transformation matrix, and the fusion matrix for each viewpoint to obtain a mapping relationship table corresponding to the current tire pressure data segment; and using the mapping relationship table corresponding to each tire pressure data segment as the total mapping relationship table.
[0012] In one implementation of the first aspect, the fusion processing based on the distortion correction lookup table for each viewpoint, the perspective transformation matrix for each viewpoint, and the fusion matrix to obtain the mapping relationship table corresponding to the current tire pressure data segment includes: performing fusion processing based on the distortion correction lookup table for each viewpoint and the perspective transformation matrix for each viewpoint to obtain fused data for each viewpoint; the fused data includes a fusion lookup table and a viewpoint region; the viewpoint region includes a fused region and a non-fused region; establishing fusion parameters based on the fusion lookup table for each viewpoint, the fusion region for each viewpoint, and the fusion matrix to obtain the mapping relationship table corresponding to each group of tire pressure data; wherein, the fusion parameters are:
[0013] Where dist represents the Euclidean distance, px is the pixel coordinates within the fusion region of each viewpoint region, c1 and c2 represent the geometric center coordinates of two adjacent viewpoint regions, and s represents the fusion region of all viewpoint regions.
[0014] In one implementation of the first aspect, matching and searching based on the real-time tire pressure data of the target vehicle and the overall mapping table to obtain the target mapping table of the real-time tire pressure data includes: obtaining the real-time tire pressure data of the target vehicle; obtaining the tire pressure data segment to which the real-time tire pressure data belongs based on the real-time tire pressure data and the tire pressure data segment array; matching and searching based on the tire pressure data segment to which the real-time tire pressure data belongs and the overall mapping table to obtain the mapping table corresponding to the tire pressure data segment to which the real-time tire pressure data belongs, and using the mapping table as the target mapping table of the real-time tire pressure data.
[0015] In one implementation of the first aspect, performing surround view stitching of the target vehicle according to the target mapping table includes: acquiring images of each corresponding viewpoint based on the real-time tire pressure data; acquiring viewpoint regions of each viewpoint based on the images of each viewpoint; the viewpoint regions include fused regions and non-fused regions; performing fusion processing on the fused regions of each adjacent viewpoint according to the target mapping table to obtain pixel information of the fused regions of each adjacent viewpoint; calculating based on the target mapping table and the non-fused regions of each viewpoint to obtain pixel information of the non-fused regions of each viewpoint; and performing surround view stitching based on the fused regions of each adjacent viewpoint and the pixel information of the non-fused regions of each viewpoint to obtain a target surround view stitched image.
[0016] Secondly, this application provides a dynamic surround view stitching system based on tire pressure monitoring. The system includes: a tire pressure value quantification processing module, used to quantify tire pressure values according to preset vehicle information of a target vehicle to obtain a tire pressure data segment array of the target vehicle; the tire pressure data segment array includes several tire pressure data segments; a mapping relationship table construction module, used to construct a mapping relationship table for each of the tire pressure data segments to obtain a total mapping relationship table; a target mapping relationship table acquisition module, used to match and search the real-time tire pressure data of the target vehicle with the total mapping relationship table to obtain a target mapping relationship table for the real-time tire pressure data; and a surround view stitching module, used to perform surround view stitching of the target vehicle according to the target mapping relationship table.
[0017] Thirdly, this application provides an electronic device, the electronic device comprising: a memory and a processor; wherein the memory is used to store a computer program; and the processor is used to execute the computer program stored in the memory to cause the electronic device to perform the dynamic surround view stitching method based on tire pressure monitoring as described above.
[0018] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an electronic device, implements the aforementioned dynamic surround view stitching method based on tire pressure monitoring.
[0019] As described above, the dynamic surround view stitching method and system based on tire pressure monitoring described in this application has the following beneficial effects:
[0020] This application quantifies tire pressure values based on preset vehicle information of the target vehicle to obtain a tire pressure data segment array for the target vehicle. The tire pressure data segment array includes several tire pressure data segments. A mapping relationship table is constructed for each of the tire pressure data segments to obtain a total mapping relationship table. A matching lookup is performed between the real-time tire pressure data of the target vehicle and the total mapping relationship table to obtain a target mapping relationship table for the real-time tire pressure data. A surround-view stitching of the target vehicle is then performed based on the target mapping relationship table. This application reduces the computational load of the Map lookup table due to frequent changes in tire pressure values by quantifying the tire pressure values in the tire pressure monitoring system, and also reduces the computational load of subsequently establishing the tire pressure value and Map mapping relationship.
[0021] This application obtains a mapping table by performing calculations based on the tire pressure value array. By establishing a general lookup table Map for the entire surround view stitching process from distortion correction, perspective transformation, and alpha fusion to obtain the BEV bird's-eye view, the pixels at specified positions in the four original images are mapped to the BEV bird's-eye view. This reduces the calculations for distortion correction, perspective transformation, and alpha fusion, and does not rely on the high computing power brought by the GPU. The surround view stitching runs quickly and is easy to port to mobile terminals.
[0022] This application calculates and processes the tire pressure value array to obtain a mapping table. By establishing a general lookup table (Map) for the entire surround view stitching process of obtaining the BEV bird's-eye view from distortion correction, perspective transformation, and alpha fusion, the pixels in the original image are directly indexed to the BEV bird's-eye view. Then, a mapping relationship is established between the tire pressure values from the vehicle tire pressure monitoring system and the general lookup table (Map), thereby realizing a dynamic surround view stitching algorithm based on tire pressure monitoring. Attached Figure Description
[0023] Figure 1A shows a schematic diagram of an application scenario of the dynamic surround view stitching method based on tire pressure monitoring described in this application.
[0024] Figure 1B shows a schematic diagram of the mid-cloud interaction scenario in these implementation methods.
[0025] Figure 2 shows a flowchart of the dynamic surround view stitching method based on tire pressure monitoring described in the embodiments of this application.
[0026] Figure 3 shows a flowchart of a dynamic surround view stitching method based on tire pressure monitoring according to another embodiment of this application.
[0027] Figure 4 shows a schematic diagram of a bird's-eye view of the target vehicle described in an embodiment of this application.
[0028] Figure 5 shows a schematic diagram of the surround view stitching process described in an embodiment of this application.
[0029] Figure 6 shows a schematic diagram of the dynamic surround view stitching system based on tire pressure monitoring as described in an embodiment of this application.
[0030] Figure 7 shows a schematic diagram of the structure of the electronic device described in an embodiment of this application.
[0031] Component Numbering Explanation: 1. Dynamic Surround View Stitching Device Based on Tire Pressure Monitoring; 11. Vehicle Information Acquisition Equipment; 12. Local Processor; 13. Display Terminal; 2. End-to-Cloud Interaction System; 20. Terminal; 21. Cloud Server; 3. Dynamic Surround View Stitching System Based on Tire Pressure Monitoring; 31. Tire Pressure Value Quantification Processing Module; 32. Mapping Relationship Table Construction Module; 33. Target Mapping Relationship Table Acquisition Module; 34. Surround View Stitching Module; 4. Electronic Equipment; 41. Processor / Processing Unit; 42. Memory; 421. RAM; 422. Cache Memory; 423. Storage System; 424. Program / Utility; 4241. Program Module; 43. Bus; 44. Input / Output Interface; 45. Network Adapter S1~S4. Steps Detailed Implementation
[0032] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.
[0033] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0034] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.
[0035] Traditional extrinsic parameter calibration methods are easily affected by tire pressure. When calibrating camera extrinsic parameters, the parameters at the moment of calibration are only suitable for the tire pressure value at that instant. When tire pressure changes, the image captured by the camera shifts, causing changes in the camera extrinsic parameters and affecting the surround view stitching effect. Furthermore, while fisheye cameras offer a wide field of view and strong spatial depth in surround view stitching, they suffer from severe image distortion. Typically, distortion correction is performed on the fisheye image, followed by perspective transformation based on the corrected image, and then alpha fusion to obtain the surround view stitched image. This process involves multiple pixel position transformations and pixel value weighting, resulting in a complex and slow stitching algorithm, making it unsuitable for porting to the board.
[0036] The following embodiments of this application provide a dynamic surround view stitching method and system based on tire pressure monitoring, which solves the problem that in traditional external parameter calibration methods, the tire pressure value changes frequently and the magnitude of the change is inconsistent, which causes the image captured by the camera to shift, causing changes in the camera's external parameters and thus affecting the surround view stitching effect.
[0037] Figure 1A shows a schematic diagram of an application scenario for the dynamic surround view stitching method based on tire pressure monitoring described in this application. The dynamic surround view stitching device 1 based on tire pressure monitoring can be used to implement the dynamic surround view stitching method based on tire pressure monitoring provided in the embodiments of this application. However, the application scenarios of the dynamic surround view stitching method based on tire pressure monitoring provided in the embodiments of this application are not limited to the dynamic surround view stitching device 1 based on tire pressure monitoring shown in Figure 1A. As shown in Figure 1A, the dynamic surround view stitching device 1 based on tire pressure monitoring includes a vehicle information acquisition device 11, a local processor 12, and a display terminal 13. The dynamic surround view stitching method based on tire pressure monitoring provided in the embodiments of this application can be applied to the local processor 12.
[0038] In Figure 1A, the local processor 12 can be a single local processor, a cluster of multiple local processors, or a cloud computing center, etc., and is not limited here. Although Figure 1A only shows one vehicle information collection device 11, one local processor 12, and one display terminal 13, it should be understood that the example in Figure 1A is only for understanding this solution, and the specific number of local processors 12 and display terminals 13 should be flexibly determined according to the actual situation.
[0039] In some other implementations, the dynamic surround view stitching device 1 based on tire pressure monitoring may not include a display terminal 13, but only a local processor 12 with display function and a driving information collection device 11. The dynamic surround view stitching method based on tire pressure monitoring provided in this application embodiment can be applied to the local processor 12. The local processor 12 with display function may include tablet computers, laptops, handheld computers, mobile phones, personal computers (PCs), and voice interaction devices, or it may be a monitoring device, a facial recognition device, etc., which are not limited here.
[0040] In some other implementations, the dynamic surround view stitching method based on tire pressure monitoring described in this application can be applied to end-to-cloud interaction scenarios. Figure 1B shows a schematic diagram of the structure of an end-to-cloud interaction scenario in these implementations. As shown in Figure 1B, the end-to-cloud interaction system 2 includes a terminal 20 and a cloud server 21. The terminal 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless methods.
[0041] The terminal 20 can be mobile or fixed. For example, it can be a wireless terminal or a wired terminal. A wireless terminal can refer to a device with wireless transceiver capabilities, which can be deployed indoors, outdoors, and in industrial workshops. The terminal 20 can be an in-vehicle system, a mobile phone, a tablet computer, a laptop computer, etc., and is not limited thereto. The cloud server 21 can include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 can also be referred to as a server cluster, management platform, data processing center, etc., and is not limited thereto in this embodiment.
[0042] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0043] The following embodiments of this application provide a dynamic surround view stitching method based on tire pressure monitoring. This method can be implemented, for example, by a local processor 12 shown in Figure 1A or a cloud server 21 shown in Figure 1B. Figure 2 shows a flowchart of the dynamic surround view stitching method based on tire pressure monitoring according to an embodiment of this application. As shown in Figure 2, this embodiment provides a dynamic surround view stitching method based on tire pressure monitoring, which includes the following steps S1 to S4.
[0044] Step S1: Quantify the tire pressure value according to the preset vehicle information of the target vehicle to obtain the tire pressure data segment array of the target vehicle. The tire pressure data segment array includes several tire pressure data segments; the preset vehicle information includes images from each viewpoint and the corresponding tire pressure data, and the images from each viewpoint include images from the front, rear, left, and right sides of the target vehicle.
[0045] Specifically, this application quantifies tire pressure values based on preset vehicle information to obtain a segmented array of tire pressure data, thereby reducing the amount of computation required to establish a reasonable mapping relationship later.
[0046] In some implementations, this application acquires raw images (fisheye images) of the front, rear, left, and right views of the target vehicle using a surround-view camera (e.g., a fisheye camera).
[0047] The tire pressure data segment array is located within the normal range of vehicle tire pressure, for example, the normal tire pressure of a small car is within 250 kPa (2.5 bar).
[0048] In one embodiment of this application, the process of quantifying tire pressure values based on preset vehicle information of the target vehicle to obtain a segmented array of tire pressure data of the target vehicle includes the following steps S11 to S12.
[0049] Step S11: Perform pressurization and / or depressurization processing based on the images from each perspective and the corresponding tire pressure data to obtain the image offset relationship.
[0050] Step S12: Perform tire pressure value quantization processing based on the image offset relationship to obtain the tire pressure data segment array of the target vehicle.
[0051] In one embodiment of this application, performing pressurization and / or depressurization processing based on the images from each viewpoint and the corresponding tire pressure data to obtain the image offset relationship includes the following steps S111 to S116.
[0052] Step S111: Based on the images from each viewpoint, the target vehicle is calibrated using grid calibration to obtain the first coordinate data of the target vehicle; the first coordinate data includes the coordinates of the calibration corner points of each viewpoint.
[0053] Step S112: Perform pressure and / or depressurization processing according to the tire pressure data with a preset stride to obtain the second coordinate data of the target vehicle; the second coordinate data includes the coordinates of the calibrated corner points of each viewpoint after pressure and / or depressurization processing.
[0054] Step S113: Calculate the Euclidean distance based on the first coordinate data and the second coordinate data to obtain a first Euclidean distance group; the first Euclidean distance group includes the Euclidean distances of the calibrated corner points of each viewpoint before and after pressurization and / or depressurization treatment.
[0055] Step S114: Iterate sequentially to obtain N sets of Euclidean distances; where N>=1 and are integers.
[0056] Step S115: Calculate the average value of the N groups of Euclidean distances to obtain the average value.
[0057] Step S116: Obtain the image offset relationship based on the average value.
[0058] In one embodiment of this application, the process of quantizing tire pressure values based on the image offset relationship to obtain a segmented array of tire pressure data for the target vehicle includes the following steps S121 to S122.
[0059] Step S121: Perform pixel conversion based on the image offset relationship to obtain the tire pressure error.
[0060] Step S122: Obtain a segmented array of tire pressure data for the target vehicle based on the tire pressure error and the preset tire pressure range. The preset tire pressure range is the normal tire pressure range, which is 150 kPa-250 kPa.
[0061] In some implementations, this application involves covering a target vehicle with a normal tire pressure of 250 kPa with a checkerboard-like calibration cloth. Fisheye images of the vehicle's front, rear, left, and right sides are acquired using a fisheye camera installed on the vehicle. The nearest corner point to the fisheye camera in each of the four images is identified, and the image coordinates of these four points are recorded. Then, based on the alarm threshold of the vehicle's tire pressure monitoring system and the normal tire pressure range, the tire pressure is increased or decreased. The nearest corner point in each of the four fisheye images is then acquired again. This process is repeated multiple times. Finally, based on the calculated image offset errors, the tire pressure values are quantized to obtain a quantized tire pressure value array TP, reducing the amount of subsequent mapping calculations.
[0062] Since the tire pressure values in the tire pressure monitoring system change frequently and the magnitude of the changes varies, this application establishes the offset relationship between the tire pressure values in the tire pressure monitoring system and the surround view camera image, and quantifies the tire pressure values based on this offset relationship, thereby reducing the amount of calculation for establishing a reasonable mapping relationship in the future.
[0063] Step S2: Construct a mapping table for each tire pressure data segment based on the respective tire pressure data segments to obtain a total mapping table. The total mapping table includes the mapping tables for each tire pressure data segment.
[0064] Specifically, this application constructs a mapping table for each tire pressure data segment and uses the mapping table of each tire pressure data segment as the overall mapping table to facilitate the subsequent surround view stitching process.
[0065] In one embodiment of this application, the process of constructing a mapping table for each tire pressure data segment according to each tire pressure data segment to obtain a total mapping table includes the following steps S21 to S23.
[0066] Step S21: Obtain the target tire pressure data for each tire pressure data segment according to each tire pressure data segment.
[0067] Step S22: Obtain images from each viewpoint according to the target tire pressure data segmented by each tire pressure data segment.
[0068] Step S23: Construct a mapping relationship table for each tire pressure data segment based on the images from each of the aforementioned perspectives, to obtain a total mapping relationship table.
[0069] Specifically, this application constructs a mapping table for each tire pressure data segment based on the target tire pressure data of each tire pressure data segment. For example, if the tire pressure data segment array is [[150,160], [160,170], [170,180], [180,190], [190,200]], and the target tire pressure data corresponding to these five tire pressure data segments are [155, 165, 175, 185, 195], then images from each corresponding perspective are obtained based on these target tire pressure data. For example, if the target tire pressure data is 155, images from the front, rear, left, and right perspectives are obtained when the tire pressure data of the target vehicle is 155. A corresponding mapping table is constructed based on these four perspective images, and this mapping table is used as the mapping table for this tire pressure data segment. That is, when the tire pressure data of the target vehicle is in this tire pressure data segment, this mapping table is used to perform surround view stitching of the target vehicle.
[0070] It should be noted that for each tire pressure data segment, the optimal option is to take the average value of the tire pressure data within that segment as the target tire pressure data. This minimizes the error during surround view stitching. For example, for the tire pressure data segment [150, 160], if the target tire pressure data is 155, and the real-time tire pressure data of the target vehicle is 151, the error during surround view stitching is relatively small. However, if the target tire pressure data is 159, and the real-time tire pressure data of the target vehicle is 151, the error during surround view stitching is relatively large. Even when the target tire pressure data is taken from other tire pressure data within the same segment, the error during surround view stitching is still within the allowable error range, and this application does not impose this limitation.
[0071] In one embodiment of this application, the process of constructing a mapping table for each tire pressure data segment based on the images from each of the respective perspectives to obtain a total mapping table includes the following steps S231 to S235.
[0072] Step S231: Perform distortion correction processing on the images from each viewpoint to obtain correction data for each viewpoint; the correction data includes the corrected image and the distortion correction lookup table.
[0073] Step S232: Perform perspective transformation processing based on the corrected images and corresponding calibrated corner points from each viewpoint to obtain perspective transformation data for each viewpoint; the perspective transformation data includes a perspective transformation matrix and the corresponding bird's-eye view image.
[0074] Step S233: Perform fusion processing on the bird's-eye view images from each perspective to obtain a fusion matrix.
[0075] Step S234: Perform fusion processing based on the distortion correction lookup table for each viewpoint, the perspective transformation matrix for each viewpoint, and the fusion matrix to obtain the mapping relationship table corresponding to the current tire pressure data segments.
[0076] Step S235: Use the mapping relationship table corresponding to each segment of the tire pressure data as the general mapping relationship table.
[0077] In one embodiment of this application, the following steps S2341 to S2342 are performed to obtain a mapping relationship table corresponding to the current tire pressure data segment based on the distortion correction lookup table of each viewpoint, the perspective transformation matrix of each viewpoint, and the fusion matrix.
[0078] Step S2341: Perform fusion processing based on the distortion correction lookup table and perspective transformation matrix of each viewpoint to obtain fused data for each viewpoint; the fused data includes a fusion lookup table and viewpoint regions; the viewpoint regions include fused regions and non-fused regions.
[0079] Step S2342: Establish fusion parameters based on the fusion lookup table for each viewpoint, the fusion region for each viewpoint, and the fusion matrix to obtain the mapping relationship table corresponding to each group of tire pressure data; wherein, the fusion parameters are:
[0080] Where dist represents the Euclidean distance, dist(px,c1) represents the Euclidean distance of (px,c1), dist(px,c2) represents the Euclidean distance of (px,c2), px is the pixel coordinates in the fusion region of each view region, c1 and c2 represent the geometric center coordinates of two adjacent view regions, and s represents the fusion region of all view regions, s includes (s1, s2, s3, s4).
[0081] In some implementations, this application first sets several sets of tire pressure data based on the tire pressure value array (the value of each set of tire pressure data is within the range of the tire pressure value array), and acquires and records the fisheye image corresponding to each set of tire pressure data through a fisheye camera. Distortion correction is performed on the fisheye image, and a distortion correction lookup table map1 from the original image to the corrected image is calculated. Then, based on the one-to-one correspondence between the coordinates of the calibrated corner points around the vehicle in the bird's-eye view and the pixel coordinates in the distortion correction image, perspective transformation processing is performed to obtain the corresponding perspective transformation matrix H, transforming the original camera view into a bird's-eye view. Secondly, this application performs the above-mentioned bird's-eye view transformation operation on the images acquired by the four surround-view cameras (front, rear, left, and right), obtaining four bird's-eye view images (i.e., bird's-eye view images corresponding to the images acquired by the four surround-view cameras of the target vehicle). According to the parameters set for surround-view stitching, the four bird's-eye view images are alpha-fused to obtain the final surround-view stitched image, and the alpha fusion matrix B is calculated simultaneously. Finally, based on the three variables map1, H, and B, the mapping lookup table Map is calculated to represent the mapping relationship from the original fisheye image to the panoramic stitched image.
[0082] Step S3: Match and search based on the real-time tire pressure data of the target vehicle and the overall mapping table to obtain the target mapping table of the real-time tire pressure data.
[0083] Specifically, this application uses the real-time tire pressure data of the target vehicle to find which tire pressure data segment the real-time tire pressure data is located in in the tire pressure data segment array, and obtains the corresponding mapping table according to the tire pressure data segment to which the real-time tire pressure data belongs, as the target mapping table of the real-time tire pressure data.
[0084] In one embodiment of this application, the process of matching and searching based on the real-time tire pressure data of the target vehicle and the overall mapping table to obtain the target mapping table of the real-time tire pressure data includes the following steps S31 to S33.
[0085] Step S31: Obtain the real-time tire pressure data of the target vehicle.
[0086] Step S32: Obtain the tire pressure data segment to which the real-time tire pressure data belongs based on the real-time tire pressure data and the tire pressure data segment array.
[0087] Step S33: Match and search according to the tire pressure data segment to which the real-time tire pressure data belongs and the total mapping relationship table to obtain the mapping relationship table corresponding to the tire pressure data segment to which the real-time tire pressure data belongs, and use the mapping relationship table as the target mapping relationship table of the real-time tire pressure data.
[0088] Step S4: Perform surround view stitching of the target vehicle according to the target mapping relationship table.
[0089] In one embodiment of this application, performing surround view stitching of the target vehicle according to the target mapping relationship table includes the following steps S41 to S45.
[0090] Step S41: Obtain images from each perspective based on the real-time tire pressure data;
[0091] Step S42: Obtain the view region of each view based on the images from each viewpoint; the view region includes the fused region and the non-fused region;
[0092] Step S43: Perform fusion processing on the fusion regions of each adjacent viewpoint according to the target mapping relationship table to obtain pixel information of the fusion regions of each adjacent viewpoint;
[0093] Step S44: Calculate the pixel information of the non-fusion region of each viewpoint based on the target mapping relationship table and the non-fusion region of each viewpoint;
[0094] Step S45: Perform surround view stitching based on the pixel information of the fusion region of each adjacent view and the non-fusion region of each view to obtain the target surround view stitched image.
[0095] This application quantifies tire pressure values using preset vehicle information of the target vehicle, obtains a segmented array of tire pressure data for the target vehicle, and constructs a mapping table for each tire pressure data segment in the segmented array. When the target vehicle is subjected to surround view stitching, the surround view stitching process is completed based on the tire pressure data segment to which the real-time tire pressure data belongs and the corresponding mapping table.
[0096] The dynamic surround view stitching method based on tire pressure monitoring described in this application establishes a lookup table Map for the entire surround view stitching process from distortion correction, perspective transformation, and alpha fusion to obtain the BEV bird's-eye view. The pixels in the original image are directly indexed to the BEV bird's-eye view. Then, a mapping relationship is established between the values from the vehicle's tire pressure monitoring system and the lookup table Map, thereby realizing a dynamic surround view stitching algorithm based on tire pressure monitoring.
[0097] In some embodiments, Figure 3 shows a flowchart of a dynamic surround view stitching method based on tire pressure monitoring according to another embodiment of this application. Figure 4 shows a bird's-eye view of a vehicle according to an embodiment of this application. As shown in Figures 3-4, the tire pressure monitoring system inputs a tire pressure value group TP, which contains the tire pressure values of four tires. The corresponding surround view stitching lookup table is Map, where i and j are the pixel index positions of the final surround view stitched image BEV. Each index corresponds to an array [c, x1, y1, x2, y2, α] in Map. c refers to which image block. As shown in Figure 4, when c = 0, 1, 2, or 3, the corresponding image blocks are the blank areas of the four directions (front, back, left, right) in Figure 4. When c = 4, 5, 6, or 7, the corresponding image blocks are the gray areas of the four corners (upper left, upper right, lower left, and lower right) in the image, (x1, y1), (x2, y2), and (x2, y2). The numbers (x1, y1) and (x2, y2) represent the pixel indices in the input images (as shown in Figure 3, (x1, y1) corresponds to the pixel indices in input image img1, and (x2, y2) corresponds to the pixel indices in input image img2). α is the alpha fusion coefficient. The blank areas in Figure 4 do not require fusion; these are individual front, back, left, and right images, corresponding to the single image in Figure 3 (img). Only the gray areas require fusion. The top left, top right, bottom left, and bottom right corners correspond to the regions where alpha fusion is performed between the left and front views, right and front views, left and rear views, and right and rear views, respectively, which are s1, s2, s3, and s4. In Figure 3, image img1 corresponds to one of the image regions s1, s2, s3, and s4, and image img2 corresponds to one of the image regions s1, s2, s3, and s4.
[0098] In some implementations, the normal tire pressure range for passenger cars is within 250 kPa (2.5 bar). The tire pressure warning threshold varies among different passenger cars, with most having tire pressure values of 150 kPa and 180 kPa. This application selects the wider range of 150 kPa, as a tire pressure warning will occur below 150 kPa. Therefore, this application sets the normal tire pressure to 150-250 kPa (i.e., the preset tire pressure range), and the tire pressure is selected within this range. The tire pressure value group TP output by the tire pressure monitoring system is obtained by quantifying the tire pressure values between 150-250 kPa. The specific steps of the quantification process of the tire pressure value group TP include the following steps S51 to S55.
[0099] Step S51: Lay a grid calibration cloth around the vehicle for static camera calibration to find corner points. First, initialize the tire pressure of the four tires to 250 kPa, and save a set of fisheye images as initialization images. In the front, rear, left, and right views of this initialization image set, select the corner point farthest from the camera, and record the coordinates of the farthest corner point on the image as (u0, v0), (u1, v1), (u2, v2), and (u3, v3) respectively. Among them, (u0, v0) is the farthest corner point in the front view, (u1, v1) is the farthest corner point in the rear view, (u2, v2) is the farthest corner point in the left view, and (u3, v3) is the farthest corner point in the right view.
[0100] Step S52: Apply pressure to the four tires in increments of 1 kPa. After applying or reducing tire pressure, save the four corner points at this moment (1) and re-record their coordinates as (u0', v0'), (u1', v1'), (u2', v2'), and (u3', v3'). Calculate the Euclidean distance dist between the corresponding corner points in sequence. Wherein, (u0', v0') is the farthest corner point in the front view after applying or reducing tire pressure, (u1', v1') is the farthest corner point in the rear view after applying or reducing tire pressure, (u2', v2') is the farthest corner point in the left view after applying or reducing tire pressure, and (u3', v3') is the farthest corner point in the right view after applying or reducing tire pressure.
[0101] Step S53: Assign (u0', v0'), (u1', v1'), u2', v2'), and (u3', v3') to (u0, v0), (u1, v1), (u2, v2), and (u3, v3) in sequence.
[0102] Step S54: Repeat steps S52-S53 to calculate N sets of dist values, and calculate the average value of these N sets of dist values as dm.
[0103] Step S55: Based on steps S51 to S54, to quickly obtain the quantized result, this application sets N to 1000, and statistically obtains dm = 1.6. Rounding dm down to 1, this means that a 1 kPa tire pressure change is approximately converted into a change of 1 pixel in the image. From a bird's-eye view, one pixel corresponds to an actual distance of 2 cm. Here, 2 cm refers to the downsampling ratio from the field of view size of 2048x2048 to the lookup table Map size of 1024x1024. Generally, the field of view size is 1 pixel corresponding to 1 cm, but downsampling is chosen based on actual conditions. This application selects a field of view of approximately 20.48 meters. However, if a lookup table of size 2048 is built, there will be many redundant empty points, which is not conducive to storage and reducing computational load. Based on actual conditions, this application chooses a downsampling ratio of 2x. Therefore, the allowable error range for this application is within 10 em. According to experimental results, the surround view stitching effect within this error range is within the normal range. If the error is larger, stitching misalignment will occur. Therefore, this application directly quantizes the values between 150-250 kPa into TPr = [[150,160], [160,170], [170,180], [180,190], [190,200], [200,210], [210,220], [220,230], [230,240], [240,250]]. The specific tire pressure values corresponding to these 10 sub-segments are [155,165,175,185,195,205,215,225,235,245], which is the quantized tire pressure value group TPs.
[0104] In one implementation, this application sets four tire pressure values to the above-mentioned tire pressure value group TPs, records 10 sets of fisheye images imgs from the front, back, left, and right, and constructs a mapping table of corresponding tire pressure value segments based on the fisheye images imgs.
[0105] Figure 5 shows a schematic diagram of the surround view stitching process described in this application embodiment. As shown in Figure 5, the surround view stitching process mainly includes a distortion correction process from the fisheye image to the calibration image, a perspective transformation process from the calibration image to the bird's-eye view, and an alpha fusion process from the bird's-eye view to the surround view. Specifically, firstly, distortion correction is performed on the fisheye image to obtain the calibration image and the distortion correction lookup table map1, with a size of, for example, 4x2x960x1280. Here, 4 represents the dimension of the ID number array of the four cameras (front, rear, left, and right), 2 represents the position index (x, y) dimension of each pixel in the calibration image in the original fisheye image, and 960x1280 represents the size of the calibration image, which is consistent with the size of the original fisheye image. Then, based on the calibration image and the corner points on the calibration cloth around the car, the perspective transformation matrix H is calculated, with a size of 4x3x3, and the corresponding front, rear, left, and right corners are also obtained. Four bird's-eye view images from the right perspective are used. Finally, Alpha fusion is performed on the four bird's-eye view images to obtain the final surround view stitched image and fusion matrix B, which is 1x2048x2048 in size. 1 represents the dimension of the Alpha fusion coefficient of each pixel, and 2048x2048 represents the field of view of the surround view, which is the size of the surround view stitched image. In order to obtain the surround view stitched lookup table Map, which is the process of the red arrow in Figure 3, the three matrices map1, H and B need to be fused directly from the fisheye image to the surround view stitched image. The specific fusion steps are as follows: steps S61 to S62.
[0106] Step S61: Calculate the inverse matrix H-1 of the perspective transformation matrix H. Expand each index (x0, y0) in the world coordinate system range under each bird's-eye view to [x0, y0, 1], and perform an inner product with the three row vectors of H-1 to obtain [r1, r2, r3], where x3 = r1 / r3 and y3 = r2 / r3. Then, find the corresponding position (x, y) of the pixel at position (x3, y3) in the correction image in the original fisheye image. This establishes a mapping relationship from the pixel position (x, y) in the original fisheye image to the pixel position (x0, y0) under the bird's-eye view, ultimately achieving the first stage of fusion processing, merging map1 and H together to obtain map2. The calculation formula for [r1, r2, r3] is as follows:
[0107] In steps S62 and S61, map2 corresponds to four matrices representing the front, back, left, and right sides. These correspond to the four dashed areas in Figure 4, representing the index positions of pixels in the original image at the bird's-eye view. The four gray areas represent overlapping view areas, requiring alpha fusion. The remaining blank areas can use pixels from that area's view (i.e., the alpha fusion coefficient α equals 0). The four map2s are rotated, cut, and stitched together. A new fusion parameter needs to be created between the overlapping map2s and B. To reduce computation, the resolution of the panoramic view can be appropriately reduced. The 2048x2048 panoramic view is downsampled to obtain a 1024x1024 panoramic view. In this case, one pixel in the panoramic view represents 2cm, so the original Map can be initialized to 6x1024x1024, where 6 represents the dimension of the array [c, x1, y1, x2, y2, α]. Based on the conditions set in Figure 3 (c), the overlapping area is calculated, and finally, the four map2s and B are fused together to obtain the final Map. The formula for calculating α is as follows:
[0108] Where dist represents the Euclidean distance, dist(px,c1) represents the Euclidean distance of (px,c1), dist(px,c2) represents the Euclidean distance of (px,c2), px is the pixel coordinate within the gray area, c1\c2 represents the geometric center coordinates of the two connected dashed areas, and s represents the fusion area of all view areas, s includes (s1, s2, s3, s4).
[0109] This application, based on the above S61-S62, achieves the final fusion from the original image directly to the surround view stitched image. In this embodiment, based on the above tire pressure value group TPs, four tire pressure values are simultaneously set to the above values, and 10 sets of fisheye images imgs (front, rear, left, and right) are recorded. The 10 sets of fisheye images in imgs are used to obtain Map, and a mapping relationship between TP values in TPs and Map is established. Finally, based on the actual tire pressure of the target vehicle, the average value TPm of the four tire pressure values is taken, and it is determined which sub-segment TPm belongs to in TPr. Then, corresponding to the TP value in TPs, the Map that needs to be used for surround view stitching is found based on the current vehicle status, thus completing the surround view stitching based on tire pressure monitoring.
[0110] The scope of protection of the dynamic surround view stitching method based on tire pressure monitoring described in this application is not limited to the order of steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.
[0111] This application also provides a dynamic surround view stitching system based on tire pressure monitoring. The dynamic surround view stitching system based on tire pressure monitoring can implement the dynamic surround view stitching method based on tire pressure monitoring described in this application. However, the implementation device of the dynamic surround view stitching method based on tire pressure monitoring described in this application includes, but is not limited to, the structure of the dynamic surround view stitching system based on tire pressure monitoring listed in this embodiment. All structural modifications and substitutions of the prior art made according to the principles of this application are included within the protection scope of this application.
[0112] As shown in Figure 6, this embodiment provides a dynamic surround view stitching system based on tire pressure monitoring. The system 3 includes: a tire pressure value quantification processing module 31, a mapping relationship table construction module 32, a target mapping relationship table acquisition module 33, and a surround view stitching module 34.
[0113] The tire pressure value quantification processing module 31 is used to perform tire pressure value quantification processing based on the preset vehicle information of the target vehicle to obtain the tire pressure data segment array of the target vehicle; the tire pressure data segment array includes several tire pressure data segments.
[0114] The mapping relationship table construction module 32 is used to construct a mapping relationship table for each tire pressure data segment according to each tire pressure data segment, so as to obtain a total mapping relationship table;
[0115] The target mapping relationship table acquisition module 33 is used to match and search based on the real-time tire pressure data of the target vehicle and the total mapping relationship table to obtain the target mapping relationship table of the real-time tire pressure data.
[0116] The surround view stitching module 34 is used to perform surround view stitching of the target vehicle according to the target mapping relationship table.
[0117] It should be noted that the functions or operations of the tire pressure value quantification processing module 31, the mapping relationship table construction module 32, the target mapping relationship table acquisition module 33, and the surround view stitching module 34 described in this embodiment correspond one-to-one with the steps in the dynamic surround view stitching method based on tire pressure monitoring described above, and therefore will not be repeated here.
[0118] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.
[0119] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.
[0120] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0121] This application also provides an electronic device, which includes: a memory and a processor; wherein...
[0122] The memory is used to store computer programs;
[0123] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.
[0124] The processor is used to execute the computer program stored in the memory to enable the electronic device to perform the dynamic surround view stitching method based on tire pressure monitoring as described above.
[0125] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0126] As shown in Figure 7, the electronic device 4 of this application is presented in the form of a general-purpose computing device. The components of the control terminal may include, but are not limited to: one or more processors or processing units 41, a memory 42, and a bus 43 connecting different system components (including the memory 42 and the processing unit 41).
[0127] Bus 43 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0128] Control terminals typically include various computer system-readable media. These media can be any available media that can be accessed by the control terminal, including volatile and non-volatile media, and removable and non-removable media.
[0129] Memory 42 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 421 and / or cache memory 422. The control terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, memory 42 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 7, commonly referred to as a "hard disk drive"). Although not shown in FIG. 7, disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disk drives for reading and writing to removable non-volatile optical disks (e.g., CD-ROMs, DVD-ROMs, or other optical media) may be provided. In these cases, each drive may be connected to bus 43 via one or more data media interfaces. Memory 42 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0130] A program / utility 424 having a set (at least one) of program modules 4241 may be stored, for example, in memory 42. Such program modules 4241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 4241 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0131] The control terminal can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), one or more devices that enable user interaction with the control terminal, and / or any device that enables the control terminal to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 44. Furthermore, the control terminal can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 45. As shown in Figure 7, network adapter 45 communicates with other modules of the control terminal via bus 43. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the control terminal, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0132] This application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).
[0133] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.
[0134] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.
[0135] In summary, the dynamic surround view stitching method and system based on tire pressure monitoring described in this application has the following beneficial effects:
[0136] This application quantifies tire pressure values based on preset vehicle information of the target vehicle to obtain a tire pressure data segment array for the target vehicle. The tire pressure data segment array includes several tire pressure data segments. A mapping relationship table is constructed for each of the tire pressure data segments to obtain a total mapping relationship table. A matching lookup is performed between the real-time tire pressure data of the target vehicle and the total mapping relationship table to obtain a target mapping relationship table for the real-time tire pressure data. A surround-view stitching of the target vehicle is then performed based on the target mapping relationship table. This application reduces the computational load of the Map lookup table due to frequent changes in tire pressure values by quantifying the tire pressure values in the tire pressure monitoring system, and also reduces the computational load of subsequently establishing the tire pressure value and Map mapping relationship.
[0137] This application obtains a mapping table by performing calculations based on the tire pressure value array. By establishing a general lookup table Map for the entire surround view stitching process from distortion correction, perspective transformation, and alpha fusion to obtain the BEV bird's-eye view, the pixels at specified positions in the four original images are mapped to the BEV bird's-eye view. This reduces the calculations for distortion correction, perspective transformation, and alpha fusion, and does not rely on the high computing power brought by the GPU. The surround view stitching runs quickly and is easy to port to mobile terminals.
[0138] This application calculates and processes the tire pressure value array to obtain a mapping table. By establishing a general lookup table (Map) for the entire surround view stitching process of obtaining the BEV bird's-eye view from distortion correction, perspective transformation, and alpha fusion, the pixels in the original image are directly indexed to the BEV bird's-eye view. Then, a mapping relationship is established between the tire pressure values from the vehicle tire pressure monitoring system and the general lookup table (Map), thereby realizing a dynamic surround view stitching algorithm based on tire pressure monitoring.
[0139] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.
[0140] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.
Claims
1. A dynamic surround view stitching method based on tire pressure monitoring, characterized in that, The method includes: The tire pressure value is quantified based on the preset vehicle information of the target vehicle to obtain a tire pressure data segment array of the target vehicle; the tire pressure data segment array includes several tire pressure data segments. A mapping table is constructed for each of the tire pressure data segments to obtain a total mapping table. The target mapping table of the real-time tire pressure data is obtained by matching and searching the real-time tire pressure data with the overall mapping table. The target vehicle is stitched together using the target mapping table.
2. The dynamic surround view stitching method based on tire pressure monitoring according to claim 1, characterized in that, The preset vehicle information includes images from various perspectives and corresponding tire pressure data; The tire pressure value is quantified based on the preset vehicle information of the target vehicle to obtain the tire pressure data segment array of the target vehicle, including: Based on the images from each perspective and the corresponding tire pressure data, pressurization and / or depressurization processing is performed to obtain the image offset relationship; Tire pressure values are quantized based on the image offset relationship to obtain a segmented array of tire pressure data for the target vehicle.
3. The dynamic surround view stitching method based on tire pressure monitoring according to claim 2, characterized in that, Based on the images from each perspective and the corresponding tire pressure data, pressurization and / or depressurization processing is performed to obtain the image offset relationship, including: The target vehicle is calibrated using grid calibration based on the images from each viewpoint to obtain the first coordinate data of the target vehicle; the first coordinate data includes the coordinates of the calibration corner points of each viewpoint. Based on the tire pressure data, pressure and / or depressurization processes are performed at a preset stride to obtain the second coordinate data of the target vehicle; the second coordinate data includes the coordinates of the calibrated corner points of each viewpoint after pressure and / or depressurization processes. Euclidean distances are calculated based on the first coordinate data and the second coordinate data to obtain a first set of Euclidean distances; the first set of Euclidean distances includes the Euclidean distances of the calibrated corner points of each viewpoint before and after pressurization and / or depressurization treatment; The process is iterated sequentially to obtain N sets of Euclidean distances; where N>=1 and is an integer. The average value is obtained by averaging the N groups of Euclidean distances. The image offset relationship is obtained based on the average value.
4. The dynamic surround view stitching method based on tire pressure monitoring according to claim 2, characterized in that, Tire pressure values are quantized based on the image offset relationship to obtain a segmented array of tire pressure data for the target vehicle, including: Pixel conversion is performed based on the image offset relationship to obtain the tire pressure error; The tire pressure data segment array for the target vehicle is obtained based on the tire pressure error and the preset tire pressure range.
5. The dynamic surround view stitching method based on tire pressure monitoring according to claim 1, characterized in that, Based on each of the tire pressure data segments, a mapping relationship table is constructed for each of the tire pressure data segments to obtain the overall mapping relationship table, which includes: The target tire pressure data for each tire pressure data segment is obtained according to each of the tire pressure data segments. Based on the target tire pressure data segmented from each tire pressure data point, images from each corresponding perspective are obtained. Based on the images from each of the aforementioned perspectives, a mapping table for each segment of tire pressure data is constructed to obtain a total mapping table.
6. The dynamic surround view stitching method based on tire pressure monitoring according to claim 5, characterized in that, Based on the images from each of the aforementioned perspectives, a mapping table is constructed for each segment of the tire pressure data to obtain a total mapping table, including: Distortion correction processing is performed on the images from each viewpoint to obtain correction data for each viewpoint; the correction data includes the corrected image and the distortion correction lookup table; Perspective transformation processing is performed on the corrected images and corresponding calibrated corner points from each viewpoint to obtain perspective transformation data for each viewpoint; the perspective transformation data includes a perspective transformation matrix and the corresponding bird's-eye view image; The bird's-eye view images from each perspective are fused to obtain a fusion matrix; The distortion correction lookup table for each viewpoint, the perspective transformation matrix for each viewpoint, and the fusion matrix are fused together to obtain a mapping table corresponding to the current tire pressure data segments. The mapping relationship table corresponding to each segment of the tire pressure data is used as the general mapping relationship table.
7. The dynamic surround view stitching method based on tire pressure monitoring according to claim 6, characterized in that, The distortion correction lookup table for each viewpoint, the perspective transformation matrix for each viewpoint, and the fusion matrix are fused to obtain a mapping table corresponding to the current tire pressure data segments, including: The distortion correction lookup table and perspective transformation matrix of each viewpoint are used for fusion processing to obtain fused data for each viewpoint; the fused data includes a fusion lookup table and viewpoint regions; the viewpoint regions include fused regions and non-fused regions; Based on the fusion lookup table for each perspective, the fusion region for each perspective, and the fusion matrix, fusion parameters are established to obtain the mapping relationship table corresponding to each group of tire pressure data; wherein, the fusion parameters are: Where dist represents the Euclidean distance, px is the pixel coordinates within the fusion region of each viewpoint region, c1 and c2 represent the geometric center coordinates of two adjacent viewpoint regions, and s represents the fusion region of all viewpoint regions.
8. The dynamic surround view stitching method based on tire pressure monitoring according to claim 1, characterized in that, A matching search is performed based on the real-time tire pressure data of the target vehicle and the overall mapping table to obtain the target mapping table for the real-time tire pressure data, which includes: Obtain the real-time tire pressure data of the target vehicle; The tire pressure data segment to which the real-time tire pressure data belongs is obtained based on the real-time tire pressure data and the tire pressure data segment array; The real-time tire pressure data is matched and searched with the overall mapping table to obtain the mapping table corresponding to the tire pressure data segment to which the real-time tire pressure data belongs, and the mapping table is used as the target mapping table for the real-time tire pressure data.
9. The dynamic surround view stitching method based on tire pressure monitoring according to claim 1, characterized in that, The surround view stitching of the target vehicle based on the target mapping table includes: Images from various perspectives are obtained based on the real-time tire pressure data. The view regions for each viewpoint are obtained from the images at each viewpoint; the view regions include fused regions and non-fused regions. According to the target mapping relationship table, the fusion region of each adjacent viewpoint is fused to obtain the pixel information of the fusion region of each adjacent viewpoint; Calculations are performed based on the target mapping table and the non-fusion regions of each viewpoint to obtain pixel information of the non-fusion regions of each viewpoint; A surround view stitching is performed based on the pixel information of the fused regions of each adjacent viewpoint and the non-fused regions of each viewpoint to obtain a target surround view stitching image.
10. A dynamic surround view stitching system based on tire pressure monitoring, characterized in that, The system includes: The tire pressure value quantification processing module is used to quantify the tire pressure value according to the preset vehicle information of the target vehicle to obtain the tire pressure data segment array of the target vehicle; the tire pressure data segment array includes several tire pressure data segments; The mapping relationship table construction module is used to construct a mapping relationship table for each of the tire pressure data segments according to each of the tire pressure data segments, so as to obtain a total mapping relationship table; The target mapping table acquisition module is used to match and search based on the real-time tire pressure data of the target vehicle and the total mapping table to obtain the target mapping table of the real-time tire pressure data. The surround view stitching module is used to perform surround view stitching of the target vehicle according to the target mapping relationship table.