Transparent base plate display method, device, vehicle, storage medium and program product

Abstract

The present disclosure relates to a transparent underbody display method, device, vehicle, storage medium and program product. A vehicle body shadow area in a preset surround view image can be identified; a transparent underbody area in a target surround view image to be displayed is adjusted according to the vehicle body shadow area, so that the transparent underbody area covers the vehicle body shadow area, and the vehicle body shadow area is different, and the transparent underbody area is also different; the adjusted transparent underbody area in the target surround view image is filled with pixels according to a preset key frame, and the filled target surround view image is displayed. In this way, the transparent underbody area is set to a fixed area that can cover the vehicle body shadow area as large as possible, thereby solving the fish scale problem while improving the picture definition of the transparent underbody area.

Description

Technical Field

[0001] This disclosure relates to the field of driver assistance technology, and in particular to a transparent chassis display method, device, vehicle, storage medium, and program product. Background Technology

[0002] Currently, the transparent chassis function of vehicles can eliminate blind spots around the vehicle and in the chassis area, thereby helping drivers to more intuitively perceive the blind spot environment, tire position (road feel), and road conditions, avoiding potential safety hazards during driving and improving vehicle driving safety. The transparent chassis is usually implemented in the bird's-eye-view (BEV) of the panoramic surround view system. The transparent chassis algorithm caches a frame of the BEV view from a historical moment as a keyframe. As the vehicle moves, it upsamples from the cached keyframe to fill the subsequent transparent chassis area, where the keyframes are continuously updated with the vehicle's movement.

[0003] However, existing panoramic images based on transparent chassis displays often exhibit a fish-scale pattern, negatively impacting user experience. While methods in related technologies can resolve this fish-scale pattern issue, they also result in the transparent chassis area becoming very blurry and lacking clarity after updates. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a transparent chassis display method, apparatus, vehicle, storage medium, and program product.

[0005] According to a first aspect of the present disclosure, a method for displaying a transparent chassis is provided, comprising: Identify the vehicle's shadow area in a preset surround view image; The transparent chassis area in the target surround view image to be displayed is determined based on the vehicle body shadow area. The transparent chassis area covers the vehicle body shadow area, and different vehicle body shadow areas correspond to different transparent chassis areas. The transparent chassis area in the target surround view image is filled with pixels according to the preset keyframes, and the filled target surround view image is displayed.

[0006] Optionally, the vehicle body shadow area includes the vehicle body shadow areas corresponding to the outer side of the vehicle body area in at least one preset direction; The step of determining the transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area includes: Obtain the shadow width of the vehicle body shadow area corresponding to each preset direction; The transparent chassis area in the target surround view image is determined based on the shadow width of the vehicle body shadow area corresponding to each preset direction.

[0007] Optionally, determining the transparent chassis area in the target surround view image based on the shadow width of the vehicle body shadow area corresponding to each preset direction includes: For each preset vertex in the transparent chassis region, a target direction corresponding to the preset vertex is determined from a plurality of preset directions; Adjust the position of the preset vertex according to the shadow width corresponding to the target direction; The transparent chassis area is determined based on the adjusted position corresponding to each preset vertex.

[0008] Optionally, determining the transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area includes: If the image area between the preset maximum shadow area and the preset minimum shadow area does not include the vehicle body shadow area, the preset minimum shadow area is taken as the transparent chassis area; The preset minimum shadow area is the smallest image area that can cover the shadow area of ​​the vehicle body, and the preset maximum shadow area is the largest image area that can cover the shadow area of ​​the vehicle body.

[0009] Optionally, the identification of the vehicle's shadow area in the preset surround view image includes: Identify the shadow regions in the preset surround view image to obtain a global shadow mask image. The shadow regions include the image regions corresponding to the vehicle body shadow and / or the shadows of objects outside the vehicle. The vehicle body shadow region is identified based on the global shadow mask map.

[0010] Optionally, identifying the shadow region in the preset panoramic image to obtain a global shadow mask image includes: The preset surround view image is converted to a different format to obtain a surround view image in the target format. The global shadow mask image is identified based on the pixel value of each pixel in the preset channel of the target format panoramic image.

[0011] Optionally, identifying the vehicle body shadow region based on the global shadow mask map includes: Extract the target shadow region within the target area from the global shadow mask image. The target region includes the image region between the boundary of the vehicle body region in the global shadow mask image and the boundary of the preset maximum shadow region. The preset maximum shadow region is a pre-set maximum image region that can cover the vehicle body shadow region. Identify the vehicle body shadow area from the target shadow area.

[0012] Optionally, extracting the target shadow region within the target area from the global shadow mask map includes: Determine the connected components of at least one shaded region in the global shadow mask graph; A first connected component is determined from at least one of the connected components, and the image region corresponding to the first connected component includes an image region located outside the preset maximum shadow region; A second connected component is determined from at least one of the connected components, wherein the second connected component is a connected component located in the outer extension region of the vehicle body, and the outer extension region of the vehicle body is a region located outside the vehicle body region within a preset number of pixels from the vehicle body region. Based on the identifiers of the second connected component and the first connected component, the target shadow region is determined after removing the first connected component from at least one of the connected components.

[0013] Optionally, the target shadow area includes the shadow areas corresponding to the outer side of the vehicle body area in at least one preset direction; The step of identifying the vehicle body shadow region from the target shadow region includes: For each preset direction corresponding to a shadow region, the shadow region corresponding to the preset direction is scanned along the target edge of the vehicle body region to determine the shadow length of the shadow region corresponding to the preset direction, where the target edge is the edge of the vehicle body region corresponding to the preset direction; If, based on the shadow length and the length of the target side, it is determined that the shadow area corresponding to the preset direction is not a vehicle body shadow area, the shadow area corresponding to the preset direction is removed. The shadow areas that are not removed within the target shadow area are taken as the vehicle body shadow area.

[0014] According to a second aspect of the present disclosure, a transparent chassis display device is provided, comprising: The recognition module is configured to recognize the vehicle's shadow area in a preset surround view image; The determination module is configured to determine a transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area, the transparent chassis area covering the vehicle body shadow area, and different vehicle body shadow areas corresponding to different transparent chassis areas; The display module is configured to fill the transparent chassis area in the target surround view image with pixels according to a preset keyframe, and display the filled target surround view image.

[0015] According to a third aspect of the present disclosure, a vehicle is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to perform the steps of the method described in the first aspect of this disclosure.

[0016] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

[0017] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

[0018] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: the shadow area of ​​the vehicle body can be identified in real time from a preset surround view image, and the transparent chassis area to be displayed can be dynamically adjusted according to the shadow area of ​​the vehicle body. This allows the adjusted transparent chassis area to cover the shadow area of ​​the vehicle body, and different transparent chassis areas can be obtained based on different shadow areas of the vehicle body (such as different sizes and distribution positions). This avoids setting the transparent chassis area to be a fixed area that can cover the shadow area of ​​the vehicle body as large as possible, thereby solving the fish scale pattern problem and improving the image clarity of the transparent chassis area.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0021] Figure 1 A schematic diagram of a fish-scale pattern problem present in a BEV view is shown.

[0022] Figure 2 This is a flowchart illustrating a transparent chassis display method according to an exemplary embodiment.

[0023] Figure 3 It is based on Figure 2 The illustrated embodiment shows a flowchart of a transparent chassis display method.

[0024] Figure 4 This is a schematic diagram of a global shadow mask image corresponding to a preset panoramic image, according to an exemplary embodiment.

[0025] Figure 5 It is based on Figure 3 The illustrated embodiment shows a flowchart of a transparent chassis display method.

[0026] Figure 6 This is a schematic diagram illustrating a preset maximum shadow area and a preset minimum shadow area according to an exemplary embodiment.

[0027] Figure 7 This is a schematic diagram of the vehicle body extension area according to an exemplary embodiment.

[0028] Figure 8 This is a schematic diagram of a target shadowed area according to an exemplary embodiment.

[0029] Figure 9 It is based on Figure 2 The illustrated embodiment shows a flowchart of a transparent chassis display method.

[0030] Figure 10 This is a schematic diagram illustrating the determination of the shadow width of the shadow area of ​​a vehicle body according to an exemplary embodiment.

[0031] Figure 11 This is a schematic diagram illustrating the adjustment of the transparent chassis area based on the vehicle body shadow area according to an exemplary embodiment.

[0032] Figure 12 This is a schematic diagram illustrating a vehicle body shadow culling effect according to an exemplary embodiment.

[0033] Figure 13 This is a block diagram illustrating a transparent chassis display device according to an exemplary embodiment.

[0034] Figure 14 This is a block diagram illustrating a vehicle according to an exemplary embodiment. Detailed Implementation

[0035] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0036] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0037] This disclosure is primarily applied to assisted driving scenarios based on transparent chassis functionality. After activating the vehicle's transparent chassis function, the transparent chassis algorithm caches a frame of the BEV view from a historical moment as a keyframe. As the vehicle moves, it samples from the cached keyframe to fill subsequent transparent chassis areas. However, during this process, due to illumination from sources such as sunlight and headlights, vehicle shadows (outside the transparent chassis area) will appear on the BEV view. If these shadows are not identified and removed, they will be continuously introduced from keyframes into the current frame during transparent chassis updates, leading to issues such as… Figure 1 The fish scale pattern problem shown, in which, Figure 1 The box in the image represents the vehicle body area.

[0038] One related technique addresses the fish-scale pattern problem by setting the transparent chassis area large enough to cover the vehicle body shadow. This ensures the transparent chassis covers the shadow area during updates and excludes it from recorded keyframes. However, since the BEV view is obtained by remapping images captured by a fisheye camera, areas far from the vehicle body are significantly blurrier than those closer. If the transparent chassis area is set too large, the sampled area will be far from the vehicle body, resulting in a very blurry and low-resolution transparent chassis area after updates.

[0039] Another related technique involves adjusting the brightness or exposure of the shadowed area if a shadow exists in the current frame, or filling it with a shadow-free frame from an earlier historical frame. However, adjusting the brightness or exposure of the shadowed area makes it difficult to achieve a unified visual effect between the shadowed and non-shadowed areas. Filling with a shadow-free frame from an earlier historical frame would remove shadows from all objects, including the vehicle body, trees, and utility poles. This would result in shadows outside the transparent chassis area, while the transparent chassis area would be shadow-free, affecting the driver's judgment and consequently impacting the effectiveness of driver assistance systems. Furthermore, if a shadow-free frame is used for filling, at high vehicle speeds, the information in the historical frames may already be outside the current vehicle's BEV area, preventing accurate updates. At low vehicle speeds, more historical frames need to be cached to avoid introducing shadows, significantly impacting the transparent chassis processing performance and even the vehicle's infotainment system performance.

[0040] To address the aforementioned problems, this disclosure provides a transparent chassis display method, apparatus, vehicle, storage medium, and program product. The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0041] Figure 2 This is a flowchart illustrating a transparent chassis display method according to an exemplary embodiment, such as... Figure 2 As shown, the method includes the following steps: In step S201, the shadow area of ​​the vehicle body in the preset surround view image is identified.

[0042] After the vehicle starts, it can acquire environmental images around the vehicle at a preset acquisition frequency. Then, the environmental images acquired at the same time from different directions are stitched together to obtain a frame of surround view image (such as BEV view). This preset surround view image can be a frame of surround view image stitched together from surround view images acquired at a preset time from different directions. The preset time can include a preset historical time or the current time.

[0043] The preset historical time can typically be set to a historical time close to the current time, such as the previous time adjacent to the current time. Thus, the preset surround view image and the target surround view image mentioned later can be two adjacent frames. The vehicle can cache the preset surround view image acquired at the previous time (a single frame of surround view image stitched together from environmental images acquired in multiple directions at the previous time) to identify the vehicle's shadow area from the preset surround view image.

[0044] In another possible implementation, the preset surround view image can also be a surround view image corresponding to the current moment (i.e., a surround view image obtained by stitching together environmental images from multiple directions acquired at the current moment, also known as the "current frame"), so that the shadow area of ​​the vehicle body can be identified in real time from the current frame.

[0045] In addition, the vehicle body shadow area refers to the image area corresponding to the shadow of the vehicle body in the preset surround view image, and does not include the image area corresponding to the shadow of other vehicles.

[0046] It is understandable that the distribution and size of the vehicle body shadow will vary depending on the position and angle of the light source (such as the sun, lamps, etc.) relative to the vehicle. In this disclosure, the corresponding vehicle body shadow area in the preset surround view image can be identified, so as to dynamically adjust the transparent chassis area in the target surround view image acquired at the current moment based on the vehicle body shadow area.

[0047] In step S202, a transparent chassis area in the target surround view image to be displayed is determined based on the vehicle body shadow area. The transparent chassis area covers the vehicle body shadow area, and different vehicle body shadow areas correspond to different transparent chassis areas.

[0048] By performing this step, the transparent chassis area in the target surround view image acquired at the current moment can be adjusted according to the vehicle body shadow area, so that the adjusted transparent chassis area covers the vehicle body shadow area, and different vehicle body shadow areas correspond to different transparent chassis areas.

[0049] Before adjusting the transparent chassis area in the target surround view image based on the vehicle body shadow area, this transparent chassis area typically only includes the vehicle body area. The adjusted transparent chassis area, in addition to including the vehicle body area, can also include the vehicle body shadow area; that is, the adjusted transparent chassis area can cover the vehicle body shadow area. When the transparent chassis area in the target surround view image covers the vehicle body shadow area, the transparent chassis area can cover the vehicle body shadow area during pixel filling based on cached preset keyframes. This effectively removes the vehicle body shadow from the transparent chassis area, thus avoiding the fish-scale pattern problem displayed to the user in the target surround view image. Simultaneously, different vehicle body shadow areas correspond to different transparent chassis areas. This allows for dynamic adjustment of the transparent chassis area based on the vehicle body shadow area, eliminating the need to set the transparent chassis area to a fixed, as large as possible. This solves the fish-scale pattern problem while also improving the image clarity of the transparent chassis area.

[0050] It should be noted that the time difference between the preset historical time and the current time mentioned above can be equal to the preset time length, meaning that the preset historical time must change as the current time changes. Furthermore, the smaller the time difference, the higher the similarity between the preset surround view image and the target surround view image, and the higher the accuracy of adjusting the transparent chassis area in the target surround view image based on the vehicle body shadow area in the preset surround view image.

[0051] For example, assuming the time difference between the preset historical time and the current time is 1, then if the current time is T, the preset historical time is T-1, and if the current time is T+1, the preset historical time is T. This example is only for illustration and is not intended to limit the scope of this disclosure.

[0052] In step S203, the transparent chassis area in the target surround view image is filled with pixels according to the preset key frame, and the filled target surround view image is displayed.

[0053] The preset keyframe is a pre-set historical frame used to fill the transparent chassis area in the target surround view image with pixels.

[0054] In practical applications, a frame of the surround view image from a historical moment can be cached and used as the preset keyframe. This historical moment can be a moment whose time difference from the current moment is less than or equal to a preset time difference. For example, a historical frame adjacent to the acquisition time of the target surround view image can be used as the preset keyframe. This avoids obtaining a shadowless frame from an earlier historical frame for filling. When removing body shadows from the chassis area, the transparent chassis area is filled only based on the content of this preset keyframe, adapting to both low and high speeds and exhibiting a wide dynamic range.

[0055] Furthermore, the transparent chassis area in this preset keyframe is filled, and it does not include the vehicle body shadow area. This preset keyframe can also be continuously updated as the vehicle moves.

[0056] In this step, the target image region corresponding to the adjusted transparent chassis area in the target surround view image can be determined in the preset keyframe. Then, the pixels of the target image region in the preset keyframe are filled into the adjusted transparent chassis area in the target surround view image. Since the adjusted transparent chassis area in the target surround view image covers the vehicle body shadow area, and the target image region in the preset keyframe does not contain the vehicle body shadow area, the transparent chassis area in the filled target surround view image also does not contain the vehicle body shadow area. This eliminates the vehicle body shadow in the transparent chassis area of ​​the target surround view image and avoids the fish scale pattern problem.

[0057] Using the above method, the shadow area of ​​the vehicle body can be identified in real time from the preset surround view image. The transparent chassis area to be displayed can be dynamically adjusted according to the shadow area of ​​the vehicle body. This allows the adjusted transparent chassis area to cover the shadow area of ​​the vehicle body. At the same time, different transparent chassis areas can be obtained based on different shadow areas of the vehicle body (such as different sizes and distribution positions). This avoids setting the transparent chassis area to be a fixed area that can cover the shadow area of ​​the vehicle body as large as possible. This solves the fish scale pattern problem and also improves the image clarity of the transparent chassis area.

[0058] The following is about Figure 2 The specific implementation of each step in the illustrated embodiments will be described.

[0059] Figure 3 It is based on Figure 2 The illustrated embodiment shows a flowchart of a transparent chassis display method, as follows: Figure 3 As shown, step S201 includes the following sub-steps: In step S2011, the shadow areas in the preset surround view image are identified to obtain a global shadow mask image. The shadow areas include the image areas corresponding to the shadows of the vehicle body and / or the shadows of objects outside the vehicle.

[0060] The global shadow mask image refers to the shadow region mask image (a binary image) in the preset surround view image. This disclosure does not limit the specific algorithm for identifying shadow regions from the preset surround view image. The shadows of objects outside the vehicle can include, for example, the shadows of trees, buildings, streetlights, and other objects outside the vehicle.

[0061] In one possible implementation, a preset toroidal image can be format-converted to obtain a toroidal image in a target format; a global shadow mask image can be identified based on the pixel value of each pixel in the target format toroidal image in a preset channel.

[0062] The target format refers to the image format that can obtain the target channel representing the light intensity after channel decomposition. For example, the target format can be YCrCb format, Lab format, etc.

[0063] For example, the preset toroidal image is usually an RGB image. This RGB image can be converted into a YCrCb image, and the preset toroidal image can be decomposed into three channels: Y, Cr, and Cb. The Y channel can represent the intensity of light and can be used as a basis for judging shadows. Then, the mean and variance (std) of the pixel values ​​in the Y channel of the image are calculated. For each pixel in the Y channel, if the value is less than mean - std / 3, it is determined to be a shadow pixel, which can be expressed by the following formula:

[0064] Where shadow_mask represents the shadow region mask, image_Y represents the Y channel component of the image, mean represents the mean of image_Y, and std represents the variance of image_Y. A value of 1 for shadow_mask indicates the presence of a shadow, while a value of 0 indicates the absence of a shadow.

[0065] Next, morphological operations can be performed on the shadow_mask image. For example, an erosion operation can be performed using a 5×5 convolution kernel, followed by a dilation operation using a 5×5 convolution kernel. This removes noise from the shadow_mask and connects adjacent pixels to avoid pixelation. For example, Figure 4 This is a schematic diagram illustrating the process of identifying shaded areas in a preset panoramic image to obtain a global shadow mask image, as shown below. Figure 4 As shown, the left image represents the preset panoramic view image, which contains shadows of vehicle bodies, trees, and streetlights. The right image represents the corresponding global shadow mask image, where the white areas represent the shadow areas.

[0066] In step S2012, the shadow area of ​​the vehicle body is identified based on the global shadow mask map.

[0067] Considering that the fish-scale pattern in the surround view image displayed to the user after the vehicle's transparent chassis function is activated is caused by the vehicle body shadow, this disclosure addresses this issue by identifying the vehicle body shadow area from the global shadow mask image. This allows for the subsequent removal of the vehicle body shadow covered by the transparent chassis area. Furthermore, only the vehicle body shadow area is identified in the global shadow mask image; other shadow areas besides the vehicle's own shadow are not identified. This ensures that only the vehicle body shadow is removed, while retaining the shadows of other external objects such as roadside trees, utility poles, buildings, and other vehicles. This guarantees that the shadows of objects inside and outside the transparent chassis area in the surround view image displayed to the driver are consistent and match the actual external environment, without affecting the driver's judgment and ensuring the quality of assisted driving.

[0068] Figure 5 It is based on Figure 3 The illustrated embodiment shows a flowchart of a transparent chassis display method, as follows: Figure 5 As shown, step S2012 includes the following sub-steps: In step S20121, a target shadow region within the target area is extracted from the global shadow mask image. The target region includes the image region between the boundary of the vehicle body area in the global shadow mask image and the boundary of the preset maximum shadow region. The preset maximum shadow region is a pre-set maximum image region that can cover the shadow of the vehicle body.

[0069] First, the preset maximum shadow area and the preset minimum shadow area (mentioned later) will be explained. The preset maximum shadow area refers to the largest image area in the preset surround view image that can cover the vehicle's shadow. For example, in the morning or evening, the shadow area formed by sunlight shining on the vehicle is usually large. This preset maximum shadow area can be set based on the angle of sunlight incidence at morning or evening and the vehicle's size. The preset minimum shadow area refers to the smallest image area in the preset surround view image that can cover the vehicle's shadow. For example, at noon, the shadow area formed by sunlight shining on the vehicle is usually small. This preset minimum shadow area can be set based on the angle of sunlight incidence at noon and the vehicle's size.

[0070] For example, Figure 6 This is a schematic diagram illustrating a preset maximum shadow area and a preset minimum shadow area according to an exemplary embodiment. Figure 6 As shown, the diagonal line area in the left image represents the preset minimum shaded area, and the diagonal line area in the right image represents the preset maximum shaded area. Figure 6The black rectangular areas covered by the preset minimum shadow area and the preset maximum shadow area represent the vehicle body area. The distance between the upper boundary of the preset minimum shadow area and the upper boundary of the vehicle body area (and the distance between the lower boundary of the preset minimum shadow area and the lower boundary of the vehicle body area) can be denoted as `shadow_td_min`, and the distance between the left boundary of the preset minimum shadow area and the left boundary of the vehicle body area (and the distance between the right boundary of the preset minimum shadow area and the right boundary of the vehicle body area) can be denoted as `shadow_lr_min`. The distance between the upper boundary of the preset maximum shadow area and the upper boundary of the vehicle body area (and the distance between the lower boundary of the preset maximum shadow area and the lower boundary of the vehicle body area) can be denoted as `shadow_td_max`, and the distance between the left boundary of the preset maximum shadow area and the left boundary of the vehicle body area (and the distance between the right boundary of the preset maximum shadow area and the right boundary of the vehicle body area) can be denoted as `shadow_lr_max`. The specific values ​​of `shadow_td_min`, `shadow_lr_min`, `shadow_td_max`, and `shadow_lr_max` can be set based on parameters such as the vehicle body size and the angle of illumination from the light source. For example, `shadow_td_min=2px` (pixels) and `shadow_lr_min=60px` are slightly wider on the left and right sides to cover the rearview mirror shadow. `shadow_td_max=120px` and `shadow_lr_max=120px` are also set. Since the vehicle height is fixed, the maximum shadow width on the top and bottom (front and rear) sides of the vehicle and the maximum shadow width on the left and right sides of the vehicle can be set to be the same.

[0071] After determining the preset maximum shadow area and the preset minimum shadow area, if no vehicle body shadow is detected in the area between the preset maximum shadow area and the preset minimum shadow area in the preset surround view image, the transparent chassis area in the target surround view image can be set as the preset minimum shadow area. If a vehicle body shadow is detected in the area between the preset maximum shadow area and the preset minimum shadow area in the preset surround view image, the transparent chassis area in the target surround view image can be dynamically adjusted based on the vehicle body shadow area in the preset surround view image to eliminate the vehicle body shadow. Therefore, in this disclosure, the transparent chassis area in the target surround view image can dynamically change between the preset minimum shadow area and the preset maximum shadow area.

[0072] In this step, at least one connected component of a shadow region in the global shadow mask image can be determined; a first connected component is determined from the at least one connected component, the image region corresponding to the first connected component includes the image region located outside the preset maximum shadow region; a second connected component is determined from the at least one connected component, the second connected component being the connected component located in the vehicle body extension region of the at least one connected component, the vehicle body extension region being the region located within a preset number of pixels outside the vehicle body region; based on the identifier of the second connected component and the identifier of the first connected component, the target shadow region is determined after removing the first connected component from the at least one connected component.

[0073] Specifically, the vehicle body extension area is used to identify whether at least one shadow region in the global shadow mask map includes the vehicle's body shadow region. For example... Figure 7 As shown, the vehicle body expansion area can be obtained by vertically expanding outward by d pixels from each of the four sides of the vehicle body area. The value of d can be set based on actual business needs. In this disclosure, the shadow area located within the vehicle body expansion area can be regarded as the vehicle body shadow area belonging to the vehicle.

[0074] For example, the connected components of the global shadow mask image can be calculated. Connected shadow pixels are considered as a single connected component, and independent labels are assigned to them sequentially (e.g., label=1,2,3,...). Then, the image region located outside the preset maximum shadow region within this at least one connected component of the global shadow mask image is taken as the first connected component (which can be labeled as outer_labels). Since the preset maximum shadow region is the largest image region that can cover the vehicle body shadow, the image region located outside the preset maximum shadow region can be considered as not being a vehicle body shadow region.

[0075] This disclosure can also use the connected component located in the outer region of the vehicle body within the at least one connected component of the global shadow mask image as the second connected component. The second connected component located in the four directions (up, down, left, right) of the vehicle body region can be identified as labels_top, labels_down, labels_left, and labels_right, respectively. Then, shadow labels that have diffused beyond the preset maximum shadow region (i.e., the first connected component outer_labels) can be removed using the following formula, retaining labels that may be within the vehicle body shadow region:

[0076] Among them, `labels_left_keep` identifies the shadow area of ​​the vehicle body located on the left side of the vehicle body area, `labels_right_keep` identifies the shadow area of ​​the vehicle body located on the right side of the vehicle body area, `labels_top_keep` identifies the shadow area of ​​the vehicle body located on the top side of the vehicle body area, and `labels_down_keep` identifies the shadow area of ​​the vehicle body located on the bottom side of the vehicle body area. For example... Figure 8 The image shows the visualization results of the four shadow areas of the vehicle body: labels_left_keep, labels_right_keep, labels_top_keep, and labels_down_keep.

[0077] In step S20122, the vehicle body shadow area is identified from the target shadow area.

[0078] The target shadow area includes shadow areas corresponding to the outer side of the vehicle body in at least one preset direction. For example... Figure 8 As shown, the target shadow area includes the shadow area on the left side of the vehicle body, the shadow area on the right side of the vehicle body, the shadow area on the upper side of the vehicle body, and the shadow area on the lower side of the vehicle body.

[0079] During this step, for each preset direction, the shadow area corresponding to the preset direction can be scanned along the target edge of the vehicle body area to determine the shadow length of the shadow area corresponding to the preset direction. The target edge is the edge of the vehicle body area corresponding to the preset direction. If it is determined that the shadow area corresponding to the preset direction is not a vehicle body shadow area based on the shadow length and the length of the target edge, the shadow area corresponding to the preset direction is removed. The shadow area within the target shadow area that has not been removed is taken as the vehicle body shadow area.

[0080] The preset direction can include four directions: up, down, left, and right of the vehicle body area. For each preset direction, the shadow length refers to the length of the shadow area along the target edge of that preset direction.

[0081] For example, suppose the target shadow area includes the four shadow areas labeled_left_keep, labeled_right_keep, labeled_top_keep, and labeled_down_keep in the example above. To determine whether these four shadow areas contain the shadow of the car body, a scanline algorithm can be used to scan and track along the top, bottom, left, and right edges of the car body area, and record the shadow length L of each label in labeled_left_keep, labeled_right_keep, labeled_top_keep, and labeled_down_keep in the direction of the target edge of their respective car body area (for example, scanning labeled_left_keep along the left side of the car body area to obtain the shadow length L of the labeled_left_keep area in the direction of the left side of the car body, and scanning labeled_right_keep along the right side of the car body area to obtain the shadow length L of the labeled_right_keep area in the direction of the right side of the car body). Taking the determination of whether the `labels_left_keep` shadow area is a vehicle body shadow area as an example, if the shadow length L of the `labels_left_keep` shadow area on the left side of the vehicle body is greater than alpha × `car_left`, then the `labels_left_keep` shadow area is determined to be a vehicle body shadow area, and this shadow area is retained and denoted as `labels_left_shadow`; otherwise, `labels_left_keep` is discarded. Similarly, we can determine whether `labels_right_keep`, `labels_top_keep`, and `labels_down_keep` belong to the vehicle body shadow area respectively. Here, alpha is the length coefficient (0-1, for example, it can be 0.6 by default), and `car_left`, `car_right`, `car_top`, and `car_down` are the side lengths of the top / bottom / left / right sides of the vehicle body area, respectively.

[0082] Therefore, the labels of the vehicle body shadow areas in the four directions of top, bottom, left, and right on the outer side of the vehicle body area can be obtained, which can be denoted as: labels_top_shadow, labels_down_shadow, labels_left_shadow, and labels_right_shadow, respectively. The image area corresponding to the set of labels_top_shadow, labels_down_shadow, labels_left_shadow, and labels_right_shadow is the vehicle body shadow area identified from the preset surround view image. The above example is merely illustrative and is not intended to limit the scope of this disclosure.

[0083] After identifying the vehicle body shadow area in the preset surround view image, the transparent chassis area in the target surround view image to be displayed can be adjusted based on the vehicle body shadow area. The vehicle body shadow area includes the vehicle body shadow areas corresponding to the outer side of the vehicle body area in at least one preset direction. For example, it can include the four vehicle body shadow areas labeled_top_shadow, labeled_down_shadow, labeled_left_shadow, and labeled_right_shadow as shown in the example above.

[0084] Figure 9 It is based on Figure 2 The illustrated embodiment shows a flowchart of a transparent chassis display method, as follows: Figure 9 As shown, step S202 includes the following sub-steps: In step S2021, the shadow width of the vehicle body shadow area corresponding to each preset direction is obtained.

[0085] For each preset direction, the shadow width of the vehicle body shadow area corresponding to the preset direction refers to the shortest distance between the target shadow pixel of the vehicle body shadow area corresponding to the preset direction and the target edge of the vehicle body area. The target shadow pixel is the vehicle body shadow pixel farthest from the vehicle body area in the preset direction, and the target edge is the edge of the vehicle body area corresponding to the preset direction.

[0086] For example, continuing with the four shadow areas of the car body (labels_top_shadow, labels_down_shadow, labels_left_shadow, and labels_right_shadow) from the previous example, for the left side of the car body area, we can take labels_left_shadow as... Figure 10 The absolute value of the difference between the leftmost X-coordinate of the shadow and the X-coordinate of the left side of the vehicle body area is used to obtain the shadow width `shadow_left` of the `labels_left_shadow` area on the left side of the vehicle body area. For the right side of the vehicle body area, the absolute value of `labels_right_shadow` can be used. Figure 10 The absolute value of the X-coordinate of the rightmost shadow is taken by subtracting the X-coordinate of the right side of the vehicle body area from the X-coordinate of the rightmost shadow. This gives the shadow width `shadow_right` of the `labels_right_shadow` area on the right side of the vehicle body area. For the top side of the vehicle body area, `labels_top_shadow` can be taken as the shadow width. Figure 10The absolute value of the Y-coordinate of the topmost shadow is subtracted from the Y-coordinate of the top edge of the vehicle body area to obtain the shadow width `shadow_top` of the `labels_top_shadow` region on the top side of the vehicle body area. For the bottom side of the vehicle body area, the absolute value of `labels_down_shadow` can be used. Figure 10 The absolute value of the difference between the Y-coordinate of the bottommost shadow and the Y-coordinate of the bottom edge of the vehicle body area is used to obtain the shadow width `shadow_down` of the `labels_down_shadow` area on the bottom edge of the vehicle body area. This example is for illustrative purposes only and is not intended to be limiting.

[0087] In step S2022, the transparent chassis area in the target surround view image is determined based on the shadow width of the vehicle body shadow area corresponding to each preset direction.

[0088] In this step, if the target shadow area includes the vehicle's body shadow area, the transparent chassis area in the target surround view image can be adjusted according to the shadow width of the body shadow area corresponding to each preset direction.

[0089] Understandably, the transparent chassis area can be represented by multiple preset vertices. For example, when the transparent chassis area is rectangular, the position and size of the transparent chassis area can be represented by the positions of the four vertices of the rectangular area.

[0090] In one possible implementation, for each preset vertex of the transparent chassis area, the target direction corresponding to the preset vertex can be determined from multiple preset directions, and the position of the preset vertex can be adjusted according to the shadow width corresponding to the target direction; the adjusted transparent chassis area can be determined according to the adjusted position corresponding to each preset vertex.

[0091] The target direction is the preset direction corresponding to the location of the preset vertex. For example, if the preset vertex is the upper left corner vertex of the transparent chassis area, the target direction corresponding to the preset vertex is the two preset directions above and to the left of the vehicle body area. If the preset vertex is the upper right corner vertex of the transparent chassis area, the target direction corresponding to the preset vertex is the two preset directions above and to the right of the vehicle body area.

[0092] For example, such as Figure 11 As shown, before adjusting the transparent chassis area in the target panoramic image, the coordinates of the four preset vertices (top, bottom, left, and right) of the border of the transparent chassis area in the image can be set as follows: Top-left vertex 13: (tl_x, tl_y); Top right vertex 14: (tr_x, tr_y); Bottom right vertex 15: (dr_x, dr_y); Bottom left vertex 16: (dl_x, dl_y); Taking the top-left vertex as an example, the target directions corresponding to this top-left vertex are the two preset directions above and to the left of the vehicle body area. Therefore, based on the shadow width `shadow_top` of the vehicle body shadow area above the vehicle body area and the shadow width `shadow_left` of the vehicle body shadow area to the left of the vehicle body area, the position of the top-left vertex can be adjusted. The adjusted position coordinates of the top-left vertex are: Top-left vertex 13: (tl_x - shadow_top, tl_y - shadow_left); Using the same method, the adjusted position coordinates of the other three preset vertices can be obtained as follows: Bottom left vertex 14: (dl_x + shadow_down, dl_y - shadow_left); Top right vertex 15: (tr_x - shadow_top, tr_y + shadow_right); The bottom right vertex is 16: (dr_x + shadow_down, dr_y + shadow_right). Wherein, shadow_top represents the shadow width of the vehicle body shadow area on the upper side of the vehicle body area, shadow_down represents the shadow width of the vehicle body shadow area on the lower side of the vehicle body area, shadow_left represents the shadow width of the vehicle body shadow area on the left side of the vehicle body area, and shadow_right represents the shadow width of the vehicle body shadow area on the right side of the vehicle body area.

[0093] The adjusted transparent chassis area in the target surround view image can be determined based on the adjusted position coordinates of the four preset vertices. For example... Figure 11 As shown, the rectangular area formed by vertices 13, 14, 15, and 16 is the adjusted transparent chassis area containing the vehicle shadow in the target surround view image. The above example is merely illustrative and is not intended to limit the scope of this disclosure.

[0094] Additionally, during the process of adjusting the transparent chassis area in the target surround view image based on the vehicle body shadow area, if the image area between the preset maximum shadow area and the preset minimum shadow area does not include the vehicle body shadow area, the preset minimum shadow area can be used as the adjusted transparent chassis area.

[0095] As mentioned above, the preset maximum shadow area refers to the largest image area in the preset surround view image that can cover the shadow of the vehicle body, and the preset minimum shadow area refers to the smallest image area in the preset surround view image that can cover the shadow of the vehicle body. If the shadow of the vehicle body is detected in the image area between the preset maximum shadow area and the preset minimum shadow area in the preset surround view image, the transparent chassis area in the target surround view image can be dynamically adjusted based on the shadow area of ​​the vehicle body in the preset surround view image to remove the shadow of the vehicle body. If the shadow of the vehicle body is not detected in the image area between the preset maximum shadow area and the preset minimum shadow area in the preset surround view image, it indicates that the shadow area of ​​the vehicle body is only distributed within the preset minimum shadow area. Therefore, the preset minimum shadow area can be used as the transparent chassis area in the target surround view image. This ensures that the transparent chassis area can cover the shadow area of ​​the vehicle body to solve the problem of fish scale pattern, and also makes the transparent chassis area as small as possible to improve the clarity of the transparent chassis area.

[0096] Using the above method, the shadow area of ​​the vehicle body can be identified in real time from the preset surround view image. The transparent chassis area to be displayed can be dynamically adjusted according to the shadow area of ​​the vehicle body. This allows the adjusted transparent chassis area to cover the shadow area of ​​the vehicle body. At the same time, different transparent chassis areas can be obtained based on different shadow areas of the vehicle body (such as different sizes and distribution positions). This avoids setting the transparent chassis area to be a fixed area that can cover the shadow area of ​​the vehicle body as large as possible. This solves the fish scale pattern problem and also improves the image clarity of the transparent chassis area.

[0097] It should also be noted that this disclosure can use historical frames adjacent to the acquisition time of the target surround view image as preset keyframes. These preset keyframes are constantly updated as the vehicle moves. After sampling these preset keyframes, the adjusted transparent chassis area in the target surround view image is filled. This avoids obtaining shadow-free frames from earlier historical frames (relative to the current frame, which is the target surround view image) for filling. In this way, when removing vehicle body shadows from the chassis area, the transparent chassis area is filled only based on the content of these preset keyframes, which can adapt to both low and high vehicle speeds and has a large dynamic range of vehicle speed. Moreover, it can effectively remove vehicle body shadows from the transparent chassis area under any lighting conditions, such as strong midday sunlight, oblique twilight sunlight, or even complex lighting conditions such as multiple light sources in an underground parking garage.

[0098] In addition, while eliminating the shadow of the vehicle body, this disclosure can also perfectly preserve the shadows generated by other objects outside the vehicle body, such as trees, utility poles, buildings, and shadows of other vehicles, ensuring that the shadows of objects inside and outside the transparent chassis in the surround view image output to the user are consistent, without affecting the driver's judgment and ensuring the quality of assisted driving.

[0099] This disclosure also boasts strong portability. It can be ported to the implementation of transparent chassis display functionality for any vehicle type (such as SUVs). Specifically, the upper and lower boundaries of the shadow area can be dynamically configured based on the vehicle's length, width, height, and the position of the surround-view camera, ensuring the reliability of the vehicle body shadow removal results. In subsequent application expansions, the solar altitude can be calculated based on local time, and the vehicle body shadow area recognition method can be adjusted in real time based on light intensity, rain / snow, and whether the vehicle has entered an underground parking garage, ensuring effective recognition of vehicle body shadows while preserving shadows of objects outside the vehicle.

[0100] For example, Figure 12 This is a schematic diagram illustrating a vehicle body shadow culling effect according to an exemplary embodiment, such as... Figure 12 As shown, the left side is a panoramic image with dynamic shadow culling disabled, and the right side is a panoramic image with dynamic shadow culling enabled. Figure 12 As shown, if the dynamic shadow culling function is turned off, a severe fish-scale pattern will appear in the vehicle body area. However, if the dynamic shadow culling function is turned on, the fish-scale pattern can be perfectly removed, and the shadows of the vehicle body and other objects will be retained outside the vehicle body area, so as not to affect the driver's judgment of the road conditions and the real-time status of blind spots.

[0101] Figure 13 This is a block diagram illustrating a transparent chassis display device according to an exemplary embodiment, such as... Figure 13 As shown, the device includes: The recognition module 1301 is configured to recognize the shadow area of ​​the vehicle body in a preset surround view image; The determining module 1302 is configured to determine a transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area, the transparent chassis area covering the vehicle body shadow area, and different vehicle body shadow areas corresponding to different transparent chassis areas; The display module 1303 is configured to fill the transparent chassis area in the target surround view image with pixels according to a preset keyframe, and display the filled target surround view image.

[0102] Optionally, the vehicle body shadow area includes the vehicle body shadow areas corresponding to the outer side of the vehicle body area in at least one preset direction; The determining module 1302 is configured to obtain the shadow width of the vehicle body shadow area corresponding to each preset direction; and determine the transparent chassis area in the target surround view image based on the shadow width of the vehicle body shadow area corresponding to each preset direction.

[0103] Optionally, the determining module 1302 is configured to, for each preset vertex of the transparent chassis area, determine the target direction corresponding to the preset vertex from a plurality of preset directions; adjust the position of the preset vertex according to the shadow width corresponding to the target direction; and determine the transparent chassis area according to the adjusted position corresponding to each preset vertex.

[0104] Optionally, the determining module 1302 is configured to take the preset minimum shadow area as the transparent chassis area if the image area between the preset maximum shadow area and the preset minimum shadow area does not include the vehicle body shadow area. The preset minimum shadow area is the smallest image area that can cover the shadow area of ​​the vehicle body, and the preset maximum shadow area is the largest image area that can cover the shadow area of ​​the vehicle body.

[0105] Optionally, the recognition module 1301 is configured to recognize the shadow region in the preset surround view image to obtain a global shadow mask image, wherein the shadow region includes the image region corresponding to the shadow of the vehicle body and / or the shadow of objects outside the vehicle; and to recognize the shadow region of the vehicle body according to the global shadow mask image.

[0106] Optionally, the recognition module 1301 is configured to convert the preset panoramic image to a target format panoramic image; and to recognize the global shadow mask image based on the pixel value of each pixel in the target format panoramic image in a preset channel.

[0107] Optionally, the recognition module 1301 is configured to extract a target shadow region within the target area from the global shadow mask image, the target region including the image region between the boundary of the vehicle body region in the global shadow mask image and the boundary of a preset maximum shadow region; the preset maximum shadow region is a pre-set maximum image region that can cover the vehicle body shadow region; and to recognize the vehicle body shadow region from the target shadow region.

[0108] Optionally, the recognition module 1301 is configured to: determine connected components of at least one shadow region in the global shadow mask image; determine a first connected component from the at least one connected component, wherein the image region corresponding to the first connected component includes an image region located outside the preset maximum shadow region; determine a second connected component from the at least one connected component, wherein the second connected component is a connected component located in the vehicle body extension region from the at least one connected component, wherein the vehicle body extension region is a region located outside the vehicle body region within a preset number of pixels from the vehicle body region; and determine the target shadow region by removing the first connected component from the at least one connected component based on the identifier of the second connected component and the identifier of the first connected component.

[0109] Optionally, the target shadow area includes shadow areas corresponding to the outer side of the vehicle body area in at least one preset direction; the recognition module 1301 is configured to scan the shadow area corresponding to the preset direction along the target edge of the vehicle body area for each of the preset directions to determine the shadow length of the shadow area corresponding to the preset direction, wherein the target edge is the edge of the vehicle body area corresponding to the preset direction; if it is determined that the shadow area corresponding to the preset direction is not a vehicle body shadow area based on the shadow length and the length of the target edge, the shadow area corresponding to the preset direction is discarded; the shadow areas within the target shadow area that have not been discarded are taken as the vehicle body shadow area.

[0110] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0111] This disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the transparent chassis display method provided in this disclosure.

[0112] Figure 14 This is a block diagram illustrating a vehicle according to an exemplary embodiment. For example, vehicle 600 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other type of vehicle. Vehicle 600 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0113] Reference Figure 14The vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. The vehicle 600 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of the vehicle 600 can be interconnected via wired or wireless means.

[0114] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, and a navigation system, etc.

[0115] The perception system 620 may include several sensors for sensing information about the environment surrounding the vehicle 600. For example, the perception system 620 may include a global positioning system (which may be GPS, BeiDou, or other positioning systems), an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0116] The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0117] The drive system 640 may include components that provide powered motion to the vehicle 600. In one embodiment, the drive system 640 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of internal combustion engines, electric motors, and compressed air engines. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0118] Some or all of the functions of vehicle 600 are controlled by computing platform 650. Computing platform 650 may include at least one processor 651 and memory 652, processor 651 can execute instructions 653 stored in memory 652.

[0119] Processor 651 can be any conventional processor, such as a commercially available CPU. Processors may also include graphics processing units (GPUs), field-programmable gate arrays (FPGAs), systems-on-chips (SoCs), application-specific integrated circuits (ASICs), or combinations thereof.

[0120] The memory 652 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0121] In addition to instruction 653, memory 652 can also store data, such as road maps, route information, vehicle position, direction, speed, and other data. The data stored in memory 652 can be used by computing platform 650.

[0122] In this embodiment of the disclosure, processor 651 may execute instruction 653 to complete all or part of the steps of the above-described transparent chassis display method.

[0123] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described transparent chassis display method when executed by the programmable device.

[0124] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0125] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0126] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0127] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0128] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0129] In the above detailed description, reference has been made to the accompanying drawings, which illustrate specific aspects of this disclosure by way of illustration. In this regard, terms indicating direction or positional relationship, such as “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “rear,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential,” are used with reference to the orientation of the described figures. Since components of the described device can be positioned in multiple different orientations, directional terms are used for illustrative purposes and not for limitation. It should be understood that other aspects can be utilized and structural or logical changes can be made without departing from the concept of this disclosure. Therefore, the following detailed description should not be considered limiting.

[0130] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.

[0131] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," "fixing," etc., used in the embodiments of this disclosure should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.

[0132] Furthermore, the term "above" as used herein with respect to components, elements, or material layers formed or located "above" a surface may be used to indicate that the component, element, or material layer is "indirectly" positioned (e.g., placed, formed, deposited, etc.) on the surface such that one or more additional components, elements, or layers are arranged between the surface and the component, element, or material layer. However, the term "above" as used with respect to components, elements, or material layers formed or located "above" a surface may also optionally have a specific meaning: that the component, element, or material layer is "directly" positioned (e.g., placed, formed, deposited, etc.) on the surface, for example, in direct contact with the surface.

[0133] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0134] It should be understood that spatial relative terms, such as “above,” “upper,” “below,” and “lower,” are used herein to describe the relationship between one element and another shown in the figures. In addition to the orientation depicted in the figures, these spatial relative terms are also intended to encompass different orientations of the device in use or operation. For example, if the device in the figures is flipped, an element described as “above” or “upper” relative to another element would be “below” or “lower” relative to that other element. Thus, depending on the spatial orientation of the device, the term “above” encompasses both above and below orientations. Devices may have other orientations (e.g., rotated 90 degrees or in other orientations), and the spatial relative terms used herein should be interpreted accordingly.

Claims

1. A method for displaying a transparent chassis, characterized in that, include: Identify the vehicle's shadow area in a preset surround view image; The transparent chassis area in the target surround view image to be displayed is determined based on the vehicle body shadow area. The transparent chassis area covers the vehicle body shadow area, and different vehicle body shadow areas correspond to different transparent chassis areas. The transparent chassis area in the target surround view image is filled with pixels according to the preset keyframes, and the filled target surround view image is displayed.

2. The method according to claim 1, characterized in that, The vehicle body shadow area includes the vehicle body shadow area corresponding to the outer side of the vehicle body area in at least one preset direction; The step of determining the transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area includes: Obtain the shadow width of the vehicle body shadow area corresponding to each preset direction; The transparent chassis area in the target surround view image is determined based on the shadow width of the vehicle body shadow area corresponding to each preset direction.

3. The method according to claim 2, characterized in that, The step of determining the transparent chassis area in the target surround view image based on the shadow width of the vehicle body shadow area corresponding to each preset direction includes: For each preset vertex in the transparent chassis region, a target direction corresponding to the preset vertex is determined from a plurality of preset directions; Adjust the position of the preset vertex according to the shadow width corresponding to the target direction; The transparent chassis area is determined based on the adjusted position corresponding to each preset vertex.

4. The method according to claim 1, characterized in that, The step of determining the transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area includes: If the image area between the preset maximum shadow area and the preset minimum shadow area does not include the vehicle body shadow area, the preset minimum shadow area is taken as the transparent chassis area; The preset minimum shadow area is the smallest image area that can cover the shadow area of ​​the vehicle body, and the preset maximum shadow area is the largest image area that can cover the shadow area of ​​the vehicle body.

5. The method according to any one of claims 1-4, characterized in that, The identified vehicle body shadow area in the preset surround view image includes: Identify the shadow regions in the preset surround view image to obtain a global shadow mask image. The shadow regions include the image regions corresponding to the vehicle body shadow and / or the shadows of objects outside the vehicle. The vehicle body shadow region is identified based on the global shadow mask map.

6. The method according to claim 5, characterized in that, The process of identifying the shadow region in the preset panoramic image to obtain the global shadow mask image includes: The preset surround view image is converted to a different format to obtain a surround view image in the target format. The global shadow mask image is identified based on the pixel value of each pixel in the preset channel of the target format panoramic image.

7. The method according to claim 5, characterized in that, The step of identifying the vehicle body shadow region based on the global shadow mask map includes: Extract the target shadow region within the target area from the global shadow mask image. The target region includes the image region between the boundary of the vehicle body region in the global shadow mask image and the boundary of the preset maximum shadow region. The preset maximum shadow region is a pre-set maximum image region that can cover the vehicle body shadow region. Identify the vehicle body shadow area from the target shadow area.

8. The method according to claim 7, characterized in that, The step of extracting the target shadow region from the global shadow mask map includes: Determine the connected components of at least one shaded region in the global shadow mask graph; A first connected component is determined from at least one of the connected components, and the image region corresponding to the first connected component includes an image region located outside the preset maximum shadow region; A second connected component is determined from at least one of the connected components, wherein the second connected component is a connected component located in the outer extension region of the vehicle body, and the outer extension region of the vehicle body is a region located outside the vehicle body region within a preset number of pixels from the vehicle body region. Based on the identifiers of the second connected component and the first connected component, the target shadow region is determined after removing the first connected component from at least one of the connected components.

9. The method according to claim 7, characterized in that, The target shadow area includes the shadow area corresponding to the outer side of the vehicle body area in at least one preset direction; The step of identifying the vehicle body shadow region from the target shadow region includes: For each preset direction corresponding to a shadow region, the shadow region corresponding to the preset direction is scanned along the target edge of the vehicle body region to determine the shadow length of the shadow region corresponding to the preset direction, where the target edge is the edge of the vehicle body region corresponding to the preset direction; If, based on the shadow length and the length of the target side, it is determined that the shadow area corresponding to the preset direction is not a vehicle body shadow area, the shadow area corresponding to the preset direction is removed. The shadow areas that are not removed within the target shadow area are taken as the vehicle body shadow area.

10. A transparent chassis display device, characterized in that, include: The recognition module is configured to recognize the vehicle's shadow area in a preset surround view image; The determination module is configured to determine a transparent chassis area in the target surround view image to be displayed based on the vehicle body shadow area, the transparent chassis area covering the vehicle body shadow area, and different vehicle body shadow areas corresponding to different transparent chassis areas; The display module is configured to fill the transparent chassis area in the target surround view image with pixels according to a preset keyframe, and display the filled target surround view image.

11. A vehicle, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to perform the steps of the method according to any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1-9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-9.

Images