An object information determination method, apparatus, device, and storage medium

Abstract

The embodiment of the present disclosure discloses an object information determination method, device, equipment and storage medium, the method comprises: acquiring a panoramic image and image attribute information of the panoramic image; determining pixel point matrix information of the panoramic image according to the image attribute information of the panoramic image, the pixel point matrix information includes depth direction information of each pixel point in the panoramic image relative to the image capture position point; identifying the panoramic image, determining a target object in the panoramic image and object region information of the target object; and determining region attribute information of the target object according to the pixel point matrix information and the object region information. By using the method, the region attribute information of the object in the real scene can be effectively determined through the analysis of the panoramic image, the determined region attribute information of the scene object can be used as data support to participate in the actual business operation, and the cost investment of introducing the region attribute information from the data information provider is reduced.

Description

Technical Field

[0001] This disclosure relates to the field of computer vision technology, and in particular to a method, apparatus, device, and storage medium for determining object information. Background Technology

[0002] Currently, research on urban spatial construction and urban transportation planning in smart cities often involves the construction of 3D models or the determination of traffic routes. Similarly, research in augmented reality or virtual reality applications largely involves modeling real-world scenes into 3D or other dimensional spaces. Whether determining traffic routes or modeling based on real-world scenes, obtaining location information of information points or landmarks in the real space is necessary to support the relevant research.

[0003] Currently, the actual location information of objects involved in the construction of the aforementioned 3D model or the determination of traffic routes often needs to be determined manually, which results in low efficiency and poor accuracy, while also increasing the cost of information acquisition. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for determining object information, which can effectively determine the regional attribute information of objects in real-world scenarios and reduce the cost of introducing regional attribute information.

[0005] In a first aspect, embodiments of this disclosure provide a method for determining object information, the method comprising:

[0006] Acquire panoramic images and their image attribute information;

[0007] Based on the image attribute information of the panoramic image, determine the pixel matrix information of the panoramic image;

[0008] Identify the panoramic image, and determine the target object in the panoramic image and the object region information of the target object;

[0009] Based on the pixel matrix information and the object region information, the region attribute information of the target object is determined.

[0010] Secondly, embodiments of this disclosure also provide an object information determination device, the device comprising:

[0011] The acquisition module is used to acquire the panoramic image and the image attribute information of the panoramic image;

[0012] The first determining module is used to determine the pixel matrix information of the panoramic image based on the image attribute information of the panoramic image;

[0013] The second determining module is used to identify the panoramic image and determine the target object in the panoramic image and the object region information of the target object.

[0014] The third determining module is used to determine the region attribute information of the target object based on the pixel matrix information and the object region information.

[0015] Thirdly, embodiments of this disclosure also provide a computer device, the computer device comprising:

[0016] One or more processors;

[0017] Storage device for storing one or more programs.

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the object information determination method provided in any embodiment of this disclosure.

[0019] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the object information determination method provided in any embodiment of this disclosure.

[0020] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the object information determination method provided in any embodiment of this disclosure.

[0021] The technical solution of this disclosure specifically discloses a method, apparatus, device, and storage medium for determining object information. The method first acquires a panoramic image and its image attribute information; then, based on the image attribute information, it determines the pixel matrix information of the panoramic image, where the pixel matrix information includes the depth and orientation information of each pixel relative to the image capture location; next, it identifies the panoramic image to determine the target object and its object region information; finally, based on the pixel matrix information and the object region information, it determines the region attribute information of the target object. This embodiment's technical solution can determine the pixel matrix information of a panoramic image through analysis. The pixel matrix information includes the depth and orientation information of each pixel relative to the image capture location. Simultaneously, the pixels in the panoramic image can also constitute scene objects in a real scene, thereby identifying the specific object region information of different scene objects in the panoramic image. Finally, through the determined pixel matrix information and object region information, the region attribute information of the scene object in the real scene can be determined. The determined region attribute information of the scene object can be used as data support in actual business operations. This embodiment provides a method for determining object information. This method does not require a large investment of manpower and can obtain more accurate object information more efficiently and quickly. It greatly reduces the cost of related business operations such as 3D model construction or traffic route determination, while also ensuring the effectiveness of business operations. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the exemplary embodiments of this disclosure, the accompanying drawings used in describing the embodiments are briefly introduced below. Obviously, the accompanying drawings described are only a portion of the embodiments to be described in this disclosure, and not all of them. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0023] Figure 1 A flowchart illustrating an object information determination method provided in an embodiment of this disclosure;

[0024] Figure 2 This is a schematic diagram of the structure of an object information determination device provided in an embodiment of the present disclosure;

[0025] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0026] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0027] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0028] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0029] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. It should also be noted that the modifications of "a" and "a plurality of" mentioned in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0030] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0031] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0032] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0033] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0034] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0035] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0036] Figure 1 This is a flowchart illustrating an object information determination method provided in an embodiment of the present disclosure. This embodiment is applicable to the processing of panoramic images. The method can be executed by an object information determination device, which can be implemented by software and / or hardware and can be configured in a terminal and / or server to implement the object information determination method in this embodiment of the present disclosure.

[0037] like Figure 1 As shown, the object information determination method provided in this embodiment may specifically include the following steps:

[0038] S101. Obtain the panoramic image and the image attribute information of the panoramic image.

[0039] In this embodiment, the panoramic image can be considered as a 360-degree panoramic view formed by capturing images from a single image capture point in a real scene. The real scene can be an outdoor street scene or an enclosed indoor scene, etc. In practical applications, the captured 360-degree panoramic view needs to be projected onto an equidistant cylindrical surface or stitched together to obtain a two-dimensional image. The panoramic image obtained in this embodiment can be considered a two-dimensional planar image after projection or stitching, which can be presented as a 360-degree horizontal view and a 180-degree vertical view.

[0040] This embodiment can acquire panoramic images from a set of panoramic images. This set of panoramic images can contain a certain number of panoramic images formed by capturing a real scene in 360 degrees from different image capture points. Simultaneously with acquiring the panoramic images, this step can also acquire the image attribute information carried by the panoramic images. This image attribute information can be understood as the information formed during the panoramic image capture process using the image capture device.

[0041] In this embodiment, the image attribute information may include the latitude and longitude information of the image capture location point in the real scene, the capture time of the image capture, and the original depth information of the panoramic image formed by the capture. The original depth information may include the distance information and orientation information of each pixel in the panoramic image from the object surface of that point to the image capture location point.

[0042] It should be noted that this embodiment can acquire one panoramic image or multiple panoramic images through this step, and then determine the object information for each of the acquired panoramic images through the following steps. This embodiment does not specifically limit the acquisition method.

[0043] S102. Based on the image attribute information of the panoramic image, determine the pixel matrix information of the panoramic image, wherein the pixel matrix information includes the depth orientation information of each pixel in the panoramic image relative to the image capture position point.

[0044] In this embodiment, the image attribute information can be equivalent to the attribute information related to panoramic image capture. In addition to information related to the panoramic image capture location point and capture time information, it also includes the original depth information of the panoramic image. Through this original depth information, the actual point corresponding to the pixel in the panoramic image in the real scene, the distance information from the image capture location point, and the orientation information can be obtained.

[0045] In this embodiment, the pixel matrix information can be considered as a two-dimensional matrix with the image dimensions of the panoramic image as rows and columns. Each element in the matrix corresponds to a pixel in the panoramic image, and the element value can be used to characterize the distance and orientation of the pixel relative to the image capture position. In this embodiment, the element values ​​characterizing distance and orientation are regarded as depth orientation information, thus it can be considered that the pixel matrix information includes the depth orientation information of each pixel in the panoramic image relative to the image capture position.

[0046] In this embodiment, the raw depth information included in the acquired image attribute information can be considered as a string, equivalent to a string containing the depth and orientation information corresponding to all pixels. This embodiment needs to parse the raw depth information in this string to obtain the depth and orientation information represented by integers for each pixel.

[0047] Based on this, one way to implement pixel matrix information can be described as follows: First, the entire large string can be divided into substrings, thereby dividing the substrings relative to each pixel. Then, each substring can be converted into integer information of a set byte length by a given conversion function. The integer content contained in this integer information can be used to represent the depth distance and orientation of the pixel. In this embodiment, the pixel matrix information of the panoramic image can be constructed based on the integer information of each pixel and the pixel coordinates.

[0048] It should be noted that the panoramic image processed in this embodiment is a two-dimensional planar image after equidistant cylindrical projection, and the pixel matrix information formed in this step is also the depth orientation information corresponding to the panoramic image in the two-dimensional plane.

[0049] S103. Identify the panoramic image and determine the target object in the panoramic image and the object region information of the target object.

[0050] In this embodiment, the above steps are equivalent to analyzing the image attribute information carried by the panoramic image itself, thereby obtaining the actual depth and orientation information of each pixel in the panoramic image relative to the image capture point. Furthermore, the pixels in the panoramic image can also constitute different objects in a real scene.

[0051] Analysis shows that for 3D modeling, traffic route planning, or urban planning, data support is required based on the regional attribute information of objects in real-world scenarios. This regional attribute information can include the object's location, width, height, and other information within the real-world environment. Objects can be considered as non-human entities such as buildings, roads, signs, and traffic lights involved in 3D modeling, route planning, or spatial planning in different business scenarios.

[0052] As described above, if we determine which objects are included in the panoramic image and their specific locations within it, we can reconstruct the object's location and attribute information in the real-world scene based on its position within the panoramic image. Therefore, this embodiment can determine the object's location in the real-world scene, its description, and other relevant attribute information by combining the object's location information within the panoramic image with the depth and orientation information of each pixel relative to the image capture point.

[0053] Based on this, while determining the pixel matrix information through the above steps, we can also identify the objects contained in the panoramic image through this step.

[0054] In this embodiment, all objects contained in the panoramic image can be identified, or objects that meet the actual business requirements can be identified from the panoramic image; this embodiment does not impose specific limitations. The identified objects are preferably recorded as target objects. Therefore, this step can identify one or more target objects from the panoramic image. Furthermore, the identified target objects can be characterized by their object region information in the panoramic image. The object region can be the smallest bounding matrix that includes the target objects, and thus the object region information of the target objects can be constructed from the vertex coordinates of the smallest bounding matrix.

[0055] In this embodiment, as one implementation method, feature extraction can be performed directly on the panoramic image. Then, by matching the extracted features with known object features, the target objects included in the panoramic image can be determined. According to the implementation principle of image recognition, object recognition is often performed on each pixel. Thus, it is equivalent to knowing which pixels constitute the target object. Based on the pixels that constitute the target object, the minimum bounding rectangle of the target object can be determined, which is equivalent to obtaining the object region information of the target object.

[0056] It should be noted that image feature recognition is often based on network models. Considering that panoramic images have relatively high image size and resolution, directly performing image recognition on the entire panoramic image requires a large-scale and complex network model, which consumes a lot of computing resources. When the number of panoramic images acquired is also large, the hardware performance requirements are also high.

[0057] Based on the above description, regarding the execution of this step, this embodiment considers a preferred implementation method. Specifically, the panoramic image can be divided into image units of appropriate size. Considering that an image unit may contain too few image features to effectively identify objects, this embodiment will also stitch the divided image units again according to stitching conditions, such as stitching 2×2 image units. The sliding window of the stitching can be set with a sliding step size to form a certain number of sub-images. Then, object recognition can be performed on the sub-images, and finally, the target objects included in the panoramic image can be determined based on the object recognition results of the sub-images.

[0058] S104. Determine the region attribute information of the target object based on the pixel matrix information and the object region information.

[0059] In this embodiment, the regional attribute information can be considered as the object name, width and height or length and width, and location of the target object in the real scene.

[0060] The above analysis shows that the image position of the target object in the panoramic image can be correlated with its actual location in the real scene using pixel matrix information. Similarly, the size of the target object in the panoramic image can be correlated with its actual size in the real scene, thereby obtaining information such as the target object's actual location, width, and height in the real scene.

[0061] Specifically, in this embodiment, a target pixel is preferentially determined from the object region information to represent the position information of the target object in the panoramic image, thereby simplifying the calculation. The target pixel can be directly taken as the center point of the region in the object region information, or it can be determined based on the average coordinates of randomly sampled pixels in the object region information.

[0062] After identifying the target pixel, the target depth and orientation information corresponding to that pixel can be retrieved from the pixel matrix information. This target depth and orientation information can be used to characterize the distance and orientation of the target object from the image capture location. Since the panoramic image can be viewed as a scaled-down image of the real scene, the scaling ratio between the real scene and the panoramic image can also be obtained. Ultimately, this embodiment can determine the regional location information of the target object in the real scene based on the target depth and orientation information, the latitude and longitude information of the image capture location, and the scaling ratio of the panoramic image. At the same time, the width and height or length and width of the target object in the panoramic image can also be determined through the object region. Based on the scaling ratio, the width and height or length and width of the target object in the real scene can be determined accordingly.

[0063] It should be noted that, considering that panoramic images are two-dimensional planar projections of a 360-degree panoramic view, directly relying on the pixel matrix information of the panoramic image projected onto a two-dimensional plane cannot accurately obtain the regional attribute information of the target object in the real scene. Before determining the regional attribute information, it is necessary to transform each pixel into a spherical coordinate system through spherical coordinate calculation to obtain the spherical coordinate information of the pixel's distance from the image capture position point, and finally obtain the three-dimensional depth orientation information of the pixel in the spherical coordinate system. The target object can also obtain the target's three-dimensional depth orientation information in the spherical coordinate system accordingly. Finally, based on this target's three-dimensional depth orientation information and the spatial coordinate information of the image capture position point, the regional position information of the target object in the real scene can be determined, ultimately obtaining the target object's actual height, actual functions, and location, which constitute the regional attribute information of the target object.

[0064] The technical solution described in this embodiment can determine the pixel matrix information of a panoramic image through analysis. This pixel matrix information includes the depth and orientation information of each pixel relative to the image capture location. Simultaneously, the pixels in the panoramic image can also constitute scene objects in a real-world scene, thereby identifying the specific object regions of different scene objects within the panoramic image. Finally, by determining the pixel matrix information and object region information, the regional attribute information of the scene objects in the real-world scene can be determined. The determined regional attribute information of the scene objects can be used as data support in actual business operations. This determination method requires minimal manpower, enabling more efficient and rapid acquisition of more accurate object information, significantly reducing the cost of related tasks such as 3D model construction or traffic route determination, while also ensuring the effectiveness of business operations.

[0065] As a first optional embodiment of this example, based on the above embodiment, the determination of the pixel matrix information of the panoramic image according to the image attribute information of the panoramic image can be further optimized as follows:

[0066] a1) Obtain the original depth information of the panoramic image from the image attribute information.

[0067] In this embodiment, image attribute information can be generated when capturing a real scene to form a panoramic image. The image attribute information includes depth information that records the capture depth and orientation of each pixel in the panoramic image. In this embodiment, the depth information is determined as the original depth information of the panoramic image.

[0068] In this embodiment, the original depth information can be a string, and the string has a long character length, which is sufficient to include the capture attribute information of each pixel in the panoramic image relative to the image capture point. The capture attribute information includes, but is not limited to, information such as the distance and orientation of the pixel relative to the image capture point.

[0069] b1) For each pixel in the panoramic image, obtain the substring corresponding to the pixel from the original depth information. The substring is used to characterize the capture attribute information of the pixel relative to the image capture position point.

[0070] In this embodiment, the original depth information can be represented by a string that contains all pixel-related capture attribute information. It is also known that special symbols are used in this string to separate the information corresponding to different pixels. Therefore, this embodiment can extract the string according to these special symbols in this step, thereby obtaining substrings corresponding to each pixel. The characters contained in each substring represent the capture attribute information of the corresponding pixel, which may include the pixel's depth and orientation information.

[0071] c1) Decode and extract information from the substring to obtain the depth orientation information of the extracted pixel relative to the image capture location.

[0072] In this embodiment, the substring corresponding to each pixel is not suitable for direct participation in subsequent logical processing. For ease of use, this step can be used to decode and extract the effective information from the substring of each pixel. Specifically, a decoding function that converts strings into numerical information can be used. This function converts the characters in the substring corresponding to the pixel into an integer sequence represented by 8 bits. This integer sequence contains numbers representing the depth and orientation information of the pixel relative to the image capture location. This step extracts the integer sequence through information extraction operations, thereby obtaining the depth and orientation information of the pixel represented in numerical form.

[0073] d1) Based on the depth orientation information of each pixel, the pixel matrix information of the panoramic image is constructed.

[0074] In this embodiment, the depth orientation information of pixels in the panoramic image can be represented by a matrix. This matrix can have the same number of rows and columns as the panoramic image. The pixel coordinates of the pixels in the panoramic image can be used as the element index of the matrix, and the depth orientation information of the pixels can be used as the element value of the element index, thus forming the pixel matrix information of the panoramic image.

[0075] The above-described technical solution in this embodiment provides an implementation for determining the depth and orientation information of pixels in a panoramic image and constructing a pixel matrix. This technical solution makes better use of the image attribute information carried by the panoramic image. By analyzing and extracting the known image attribute information, the depth and orientation information of each pixel in the panoramic image relative to the image capture position can be obtained. The determined depth and orientation information provides data support for subsequent determination of region attribute information.

[0076] As a second optional embodiment of this example, based on the above embodiment, the identification of the panoramic image, the determination of the target object in the panoramic image, and the object coordinate information of the target object can be further specified as follows:

[0077] It should be noted that this second optional embodiment can be specifically used to identify target objects from panoramic images. Considering that the image size and dimensions of panoramic images place high demands on the network model used for image recognition, this embodiment preferably divides the panoramic image into sub-images, so as to achieve the identification of target objects in the panoramic image by recognizing objects in each sub-image separately.

[0078] a2) Divide the panoramic image into image units according to the set number of rows and columns to obtain multiple image units.

[0079] Specifically, this step first involves dividing the panoramic image into image blocks. These image blocks can be the smallest unit allowed for image division, or they can be divided according to a given number of rows and columns, which can be determined based on historical experience. This embodiment can divide the panoramic image into multiple image units arranged in rows and columns.

[0080] It should be noted that, in order to better execute the subsequent steps, an image division coordinate system for the panoramic image can be set in this embodiment. For example, the upper left vertex of the panoramic image can be used as the origin of the image division coordinate system. The image units obtained by dividing under this coordinate system can still ensure that the original pixel coordinate positions remain unchanged.

[0081] b2) Determine the target image unit from the plurality of image units according to the set image stitching conditions and stitch the target image units together to form at least one target sub-image of the panoramic image.

[0082] In this embodiment, considering that the object features contained in each image unit directly formed by segmentation are small, affecting the accuracy of object recognition, this step can be used to perform a stitching operation on the image units. The image stitching conditions can be that the number of images to be stitched and the image stitching method are determined.

[0083] For example, the number of image stitches can be set to 2×2, meaning two image units are selected in each row and column as target image units for stitching. The stitching method can be set to a sliding step of 1 to sequentially select new image units as target image units. Specifically, in the image division coordinate system, starting from the origin, two image units are selected horizontally and vertically as target image units for stitching, forming corresponding target sub-images. Then, keeping the vertical direction unchanged, one image unit is slid horizontally to the left to reselect new target image units to form the target sub-image. This leftward sliding continues until the last horizontal image unit is selected as the target image unit. Then, one image unit is slid vertically downwards, and horizontally, image units are selected again from left to right to form the target sub-image. Through this step, at least one target sub-image can be stitched from the panoramic image.

[0084] c2) Perform object recognition on each of the target sub-images to obtain the corresponding recognition results, and determine the target objects included in the panoramic image and the object region information of the target objects based on the recognition results.

[0085] In this embodiment, object recognition can be performed on each target sub-image determined in the above steps, and a corresponding recognition result can be determined for each target sub-image. The recognition result can include which objects were identified from the target sub-image, and the regional information of the identified objects in the target sub-image.

[0086] This embodiment can summarize the recognition results of each target sub-image, determine the specific target object contained in the panoramic image from the objects included in all recognition results, and the object region information of the target object in the panoramic image.

[0087] Specifically, in this second optional embodiment, as one implementation method, object recognition can be performed on each of the target sub-images to obtain corresponding recognition results, and the target objects included in the panoramic image and the object region information of the target objects can be determined based on the recognition results. This can include the following steps:

[0088] c21) For each target sub-image, perform feature analysis on the target sub-image to determine the recognition object in the target sub-image and the sub-region information of the recognition object.

[0089] In this embodiment, each target sub-image can be processed through this step and the following steps. Specifically, an image recognition model can be used to take the target sub-image as input data. The image recognition model can extract and analyze features from the target sub-image to determine the object matched by the features, and can output the location of the region occupied by the object in the target sub-image. The location of the region can be the minimum bounding rectangle.

[0090] In this embodiment, the object can be designated as the recognition object, and the vertex coordinates of the smallest bounding rectangle can be obtained to construct the sub-region information of the recognition object. It is understood that this sub-region information can also represent the width and height information or the length and width information of the recognition object. Its width and height or length and width can be determined by the object's position in the panoramic image. If the recognition object is entirely located in the ground area of ​​the image, the sub-region information can be used to represent the length and width of the recognition object. If the recognition object occupies not only the ground area but also has height information, the sub-region information can be used to represent the width and height of the recognition object.

[0091] c22) Based on the identified objects in each of the target sub-images, determine the target object of the panoramic image, and based on the sub-region information corresponding to each of the identified objects, determine the object region information of the target object.

[0092] In this embodiment, after obtaining the recognition objects of each target sub-image through the above steps, the target objects included in the panoramic image can be determined through this step. It is known that a target sub-image is a stitched image of multiple image units. When an object occupies a large area across multiple target sub-images, the recognition objects identified in multiple target sub-images may be duplicates of the same object. This step needs to identify duplicate and non-duplicate recognition objects from the recognition objects corresponding to each target sub-image. Then, the same recognition object is recorded only once, and the complete region information of the recognition object in the panoramic image can be determined based on the sub-region information of the recognition object in multiple target sub-images. For non-duplicate recognition objects, they can be directly used as a target object in the panoramic image, and the corresponding sub-region information can also be directly used as the sub-region information of the target object in the panoramic image.

[0093] Specifically, as one implementation method, determining the target object of the panoramic image based on the identified objects in each of the target sub-images, and determining the object region information of the target object based on the sub-region information corresponding to each of the identified objects, can be further specified as follows:

[0094] c221) Based on the object information possessed by each of the identified objects, determine the duplicate identified objects corresponding to the same object and the non-duplicate identified objects corresponding to different objects.

[0095] In this embodiment, the identified object may possess object information, which may include an object name. This step can determine whether the identified objects in different target sub-images are the same object based on the object name and the sub-region information of the identified object. For example, it can be determined that the identified objects are traversed to find identified objects with the same object name. Then, the target sub-image to which the identified object belongs can be determined, and the target sub-images that are adjacent in position on the panoramic image can be retained. Then, it can be determined whether the sub-regions corresponding to the identified object in the adjacent target sub-images can form a closed region. If so, the identified objects in multiple target sub-images can be considered as the same object. Thus, the identified object can be identified as a duplicate identified object of the same object. Correspondingly, identified objects that do not meet the above determination can be regarded as non-duplicate identified objects.

[0096] c222) The non-repeating identified object is directly determined as the target object in the panoramic image, and the object region information in the panoramic image is determined based on the sub-region information of the non-repeating identified object in the corresponding target sub-image.

[0097] In this embodiment, this step can identify the non-repeating recognition objects as target objects in the panoramic image. Based on the sub-region information of the non-repeating recognition objects in the corresponding target sub-image, combined with the location information of the target sub-image in the panoramic image, the object region information corresponding to the non-repeating recognition objects in the panoramic image can be determined.

[0098] c223) The same object associated with the duplicate recognition object is identified as a target object, and the object region information of the target object in the panoramic image is determined based on the sub-region information of each duplicate recognition object associated with the target object.

[0099] In this embodiment, this step can record only one instance of the duplicate recognition objects of the same object, which is equivalent to treating multiple duplicate recognition objects associated with the same object as a single target object. This step can also summarize the sub-region information of multiple duplicate recognition objects associated with the same object and merge the information of multiple sub-regions into a larger region. This step can determine the region position of the merged large region information in the panoramic image based on the position information of the target sub-images to which multiple duplicate recognition objects belong relative to the panoramic image, and use this region position as the object region information of the target object.

[0100] The above technical solution in this embodiment provides a specific implementation for identifying target objects from panoramic images and determining the object region information involved by the target objects. The determination method provided in this embodiment can effectively realize the identification of target objects and the determination of region information, providing basic data support for the subsequent determination of the region attribute information of target objects.

[0101] In this embodiment, as described above, it can be understood that pixel matrix information and object region information of the target object can be associated with the region location information of the target object in the real scene. Based on this, as a third optional embodiment of this embodiment, based on the above embodiment, the determination of the region attribute information of the target object according to the pixel matrix information and the object region information can be further specified as follows:

[0102] a3) Determine the target pixel points representing the target object and the object attribute information of the target object from the object region information.

[0103] In this embodiment, to simplify the amount of logical operations, it is not necessary for all pixels in the object region information to participate in the determination of the target object's region attribute information in the real scene. This step can be used to determine a target pixel from the object region information to represent the target object.

[0104] For example, this step can directly use the center point of the matrix of the smallest bounding rectangle formed based on the object region information as the target pixel of the target object. Alternatively, the target pixel can be determined by uniformly and randomly sampling pixels from the smallest bounding rectangle. For instance, the average pixel coordinates of the sampled pixels can be calculated to determine an average pixel coordinate. If this average pixel coordinate is directly used as a pixel in the panoramic image, then that pixel is recorded as the target pixel. If the average pixel coordinate does not directly exist in the panoramic image, then the pixel closest to the average pixel coordinate can be determined and recorded as the target pixel.

[0105] In this embodiment, the object attribute information of the target object may include the object name of the target object, and the width and height or length and width values ​​of the target object as presented in the panoramic image.

[0106] b3) Based on the pixel matrix information, determine the target depth orientation information of the target pixel relative to the image capture location point.

[0107] In this embodiment, the target pixel can be found from the pixel matrix information, thereby obtaining the depth orientation information of the target pixel from the pixel matrix information, and recording it as the target depth orientation information.

[0108] c3) Perform spherical coordinate transformation on the object attribute information and the target depth and orientation information to obtain the scene attribute information and spatial region information of the target object in the real scene.

[0109] It is understood that the target pixels and target depth orientation information determined in the above steps are information in a two-dimensional plane of the panoramic image, while the real scene is a three-dimensional spatial scene, and it is necessary to determine the spatial region information of the target object in the real scene as the region location information. Therefore, this step is necessary to perform a spherical coordinate transformation on the object attribute information and the target depth orientation information determined above. After the spherical coordinate transformation, the spatial region information of the target object in the real scene can be obtained. In addition, the actual length and width or length-width-height information of the target object in the real scene can also be obtained. In this embodiment, the object name and the actual length and width or length-width-height information of the target object can be used as the scene attribute information of the target object.

[0110] d3) Based on the scene attribute information and the spatial region information, construct the regional attribute information of the target object.

[0111] It can be seen that the scene attribute information and spatial region information determined for each target object can be used as the regional attribute information of the target object.

[0112] The technical solution described in this embodiment determines the pixel matrix information and the position and attribute information of the target object within the panoramic image by utilizing the image attribute information carried by the panoramic image itself. Finally, by combining the determined pixel matrix information and the position and attribute information of the target object in the panoramic image, the regional attribute information of the target object in the real scene can be obtained through spherical coordinate transformation. This method avoids the operation of manually collecting information about real scene objects, effectively saving the cost of information acquisition. The determined regional attribute information of the object also provides basic data support for subsequent business logic execution.

[0113] As a fourth optional embodiment of this example, based on the above embodiments, the target object and its corresponding regional attribute information can be optimized and recorded as target object information in a set information database.

[0114] In this embodiment, the target object and related regional attribute information determined by the above method can be stored. Specifically, the unique identifier of the target object and the corresponding regional attribute information can be recorded as a target object information in a pre-built information database.

[0115] It is understood that the target object information determined above in this embodiment can be specifically used in the execution of business logic. Specifically, based on the above optimizations, the method provided in this embodiment may further include:

[0116] a4) After receiving a business execution request associated with a real scenario, determine the target area range corresponding to the business execution request in the real scenario.

[0117] In this embodiment, the target object information stored in the information database involves a wide range of business scenarios. For example, it can be used in the construction of three-dimensional models for urban planning and design, in the planning of traffic routes, and in the construction of virtual scenes involving augmented reality and virtual reality.

[0118] It is understood that, regardless of the business scenario, the execution entity in this embodiment can receive business execution requests generated relative to the actual scenario involved. This step can determine the target area range of the actual scenario corresponding to the business execution request by analyzing the business execution request. This target area range can be represented using actual latitude and longitude coordinates.

[0119] b4) Locate the information database and, based on the target object information recorded in the information database, determine the scene objects included within the target area and the regional attribute information of each scene object.

[0120] In this embodiment, each piece of target object information contained in the information database records the target object's regional location information in the real scene relative to the associated target object. Based on this, after determining the target area range, this step can be used to determine the target objects whose regional location information in the information database is within the target area range, and the included target objects can be recorded as scene objects included within the target area range. At the same time, the regional attribute information of each scene object can be directly obtained.

[0121] c4) Based on the regional attribute information of each of the aforementioned scene objects, respond to the execution logic corresponding to the business execution request, and obtain the request response result of the business execution request.

[0122] In this embodiment, based on different business execution requests, it is possible to analyze what specific execution logic corresponds to each business execution request. For example, for a route planning business, after obtaining the regional attribute information of each scene object, it can be used to plan the road network information within the target area, clarify the roads included in the target area and the access permissions of those roads, and finally, by executing the logic that determines the road network information, the obtained road network information can be used as the request response result of the business execution request.

[0123] It is known that, based on the road network information that serves as the result of the request response, after clarifying the origin and destination, one or more transportation routes can be planned using the road information, traffic lights, and traffic signs included in the road network information.

[0124] Similarly, when a business execution request constructs a virtual 3D scene for a virtual reality scenario, the regional attribute information of each scene object can be used to construct a 3D virtual scene corresponding to the real scene within the target area. Ultimately, the constructed 3D virtual scene can be used as the request response result for the business execution request.

[0125] It should be noted that there are many and wide-ranging scenarios in which the regional attribute information of the scene object is used to participate in the execution of business execution requests, and this embodiment does not impose specific restrictions on the business scenarios.

[0126] The above-described technical solution in this embodiment provides a specific implementation of using the regional attribute information of the determined target object to participate in actual business operations. Compared to existing methods that require paying for data interfaces from data providers to support business operations, this technical solution can obtain accurate object information without additional cost investment, greatly reducing the cost investment in related businesses such as 3D model construction or traffic route determination, and better expanding the scope of business expansion.

[0127] Figure 2 This is a schematic diagram of an object information determination device provided in an embodiment of the present disclosure. This embodiment is applicable to the analysis and determination of panoramic images. The device can be implemented by software and / or hardware, and can be configured in a terminal and / or server to implement the object information determination method in this embodiment of the present disclosure. Specifically, the device may include: an acquisition module 21, a first determination module 22, a second determination module 23, and a third determination module 24.

[0128] The acquisition module 21 is used to acquire the panoramic image and the image attribute information of the panoramic image;

[0129] The first determining module 22 is used to determine the pixel matrix information of the panoramic image based on the image attribute information of the panoramic image. The pixel matrix information includes the depth orientation information of each pixel in the panoramic image relative to the image capture position point.

[0130] The second determining module 23 is used to identify the panoramic image and determine the target object in the panoramic image and the object region information of the target object.

[0131] The third determining module 24 is used to determine the region attribute information of the target object based on the pixel matrix information and the object region information.

[0132] This embodiment provides an object information determination device that can determine the pixel matrix information of a panoramic image through analysis. The pixel matrix information includes the depth and orientation information of each pixel relative to the image capture location. Simultaneously, the pixels in the panoramic image can also constitute scene objects in a real scene, thereby identifying the specific object region information of different scene objects in the panoramic image. Finally, by determining the pixel matrix information and object region information, the regional attribute information of the scene objects in the real scene can be determined. The determined regional attribute information of the scene objects can be used as data support in actual business operations. This determination method requires no large investment of manpower, enabling more efficient and faster acquisition of more accurate object information, significantly reducing the cost of related businesses such as 3D model construction or traffic route determination, while also ensuring the effectiveness of business operations.

[0133] Furthermore, the first determining module 22 can specifically be used for:

[0134] Obtain the original depth information of the panoramic image from the image attribute information;

[0135] For each pixel in the panoramic image, a substring corresponding to the pixel is obtained from the original depth information. The substring is used to characterize the capture attribute information of the pixel relative to the image capture position point.

[0136] The substring is decoded, converted, and information is extracted to obtain the depth and orientation information of the extracted pixel relative to the image capture location point;

[0137] The pixel matrix information of the panoramic image is constructed based on the depth orientation information of each pixel.

[0138] Furthermore, the second determining module 23 may specifically include:

[0139] A partitioning unit is used to divide the panoramic image into image units according to a set number of rows and columns to obtain multiple image units;

[0140] A stitching unit is used to determine a target image unit from the plurality of image units according to set image stitching conditions, and stitch the target image units together to form at least one target sub-image of the panoramic image;

[0141] The recognition unit is used to perform object recognition on each of the target sub-images, obtain corresponding recognition results, and determine the target objects included in the panoramic image and the object region information of the target objects based on the recognition results.

[0142] Furthermore, the identification unit may specifically include:

[0143] The identification subunit is used to perform feature analysis on each target sub-image to determine the identification object in the target sub-image and the sub-region information of the identification object;

[0144] The determining subunit is used to determine the target object of the panoramic image based on the recognition objects in each of the target sub-images, and to determine the object region information of the target object based on the sub-region information corresponding to each of the recognition objects.

[0145] Furthermore, determining the specific use of sub-units can be:

[0146] Based on the object information possessed by each of the identified objects, duplicate identified objects corresponding to the same object and non-duplicate identified objects corresponding to different objects are determined;

[0147] The non-repeating identified object is directly determined as the target object in the panoramic image, and the object region information in the panoramic image is determined based on the sub-region information of the non-repeating identified object in the corresponding target sub-image.

[0148] The same object associated with repeated identification objects is identified as a target object, and the object region information of the target object in the panoramic image is determined based on the sub-region information of each repeated identification object associated with the target object.

[0149] Furthermore, the third determining module 23 can specifically be used for:

[0150] The target pixel points representing the target object and the object attribute information of the target object are determined from the object region information;

[0151] Based on the pixel matrix information, the target depth orientation information of the target pixel relative to the image capture location point is determined;

[0152] Perform spherical coordinate transformation on the object attribute information and the target depth and orientation information to obtain the scene attribute information and spatial region information of the target object in the real scene;

[0153] Based on the scene attribute information and the spatial region information, the regional attribute information of the target object is constituted.

[0154] Furthermore, the target object and its corresponding regional attribute information are recorded as target object information in a designated information database;

[0155] Accordingly, the device also includes:

[0156] The receiving module is used to determine the target area range corresponding to the business execution request in the real scene after receiving a business execution request associated with the real scene;

[0157] The search module is used to search the information database and, based on the target object information recorded in the information database, determine the scene objects included in the target area and the regional attribute information of each scene object;

[0158] The response module is used to respond to the execution logic corresponding to the business execution request based on the regional attribute information of each of the scene objects, and to obtain the request response result of the business execution request.

[0159] The above-described apparatus can execute the methods provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the methods.

[0160] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0161] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Reference is made below. Figure 3 It illustrates a computer device suitable for implementing embodiments of the present disclosure (e.g., Figure 3 The diagram below shows the structure of the terminal device or server 30. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The computer device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0162] like Figure 3 As shown, the computer device 30 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 31, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 32 or a program loaded from a storage device 38 into a random access memory (RAM) 33. The RAM 33 also stores various programs and data required for the operation of the computer device 30. The processing unit 31, the ROM 32, and the RAM 33 are interconnected via a bus 35. An edit / output (I / O) interface 34 is also connected to the bus 35.

[0163] Typically, the following devices can be connected to I / O interface 34: input devices 36 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 37 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 38 including, for example, magnetic tapes, hard disks, etc.; and communication devices 39. Communication device 39 allows computer device 30 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 A computer device 30 with various devices is shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0164] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 39, or installed from a storage device 38, or installed from a ROM 32. When the computer program is executed by the processing device 31, it performs the functions defined in the methods of embodiments of this disclosure.

[0165] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0166] The computer device provided in this embodiment and the object information determination method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0167] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the object information determination method provided in the above embodiments.

[0168] It should be noted that the computer-readable medium described above in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0169] In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0170] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0171] The aforementioned computer-readable medium may be included in the aforementioned computer device; or it may exist independently and not assembled into the computer device.

[0172] The aforementioned computer-readable medium carries one or more programs that, when executed by the computer device, cause the computer device to:

[0173] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0175] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0176] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0177] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0178] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0179] Furthermore, although the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0180] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for determining object information, characterized in that, include: Acquire panoramic images and their image attribute information; Based on the image attribute information of the panoramic image, the pixel matrix information of the panoramic image is determined, and the pixel matrix information includes the depth orientation information of each pixel in the panoramic image relative to the image capture position point. Identify the panoramic image, and determine the target object in the panoramic image and the object region information of the target object; Based on the pixel matrix information and the object region information, the region attribute information of the target object is determined.

2. The method according to claim 1, characterized in that, Based on the image attribute information of the panoramic image, the pixel matrix information of the panoramic image is determined, including: Obtain the original depth information of the panoramic image from the image attribute information; For each pixel in the panoramic image, a substring corresponding to the pixel is obtained from the original depth information. The substring is used to characterize the capture attribute information of the pixel relative to the image capture position point. The substring is decoded, converted, and information is extracted to obtain the depth and orientation information of the extracted pixel relative to the image capture location point; The pixel matrix information of the panoramic image is constructed based on the depth orientation information of each pixel.

3. The method according to claim 1, characterized in that, The step of identifying the panoramic image and determining the target object in the panoramic image and the object coordinate information of the target object includes: The panoramic image is divided into image units according to a set number of rows and columns to obtain multiple image units; According to the set image stitching conditions, a target image unit is determined from the plurality of image units, and each target image unit is stitched together to form at least one target sub-image of the panoramic image; Object recognition is performed on each of the target sub-images to obtain corresponding recognition results, and the target objects included in the panoramic image and the object region information of the target objects are determined based on the recognition results.

4. The method according to claim 3, characterized in that, The step of performing object recognition on each of the target sub-images to obtain corresponding recognition results, and determining the target objects included in the panoramic image and the object region information of the target objects based on each of the recognition results, includes: For each target sub-image, feature analysis is performed on the target sub-image to determine the recognition object in the target sub-image and the sub-region information of the recognition object; Based on the identified objects in each of the target sub-images, the target object of the panoramic image is determined, and based on the sub-region information corresponding to each identified object, the object region information of the target object is determined.

5. The method according to claim 4, characterized in that, The step of determining the target object of the panoramic image based on the identified objects in each of the target sub-images, and determining the object region information of the target object based on the sub-region information of each of the identified objects, includes: Based on the object information possessed by each of the identified objects, duplicate identified objects corresponding to the same object and non-duplicate identified objects corresponding to different objects are determined; The non-repeating identified object is directly determined as the target object in the panoramic image, and the object region information in the panoramic image is determined based on the sub-region information of the non-repeating identified object in the corresponding target sub-image. The same object associated with repeated identification objects is identified as a target object, and the object region information of the target object in the panoramic image is determined based on the sub-region information of each repeated identification object associated with the target object.

6. The method according to claim 1, characterized in that, Determining the region attribute information of the target object based on the pixel matrix information and the object region information includes: The target pixel points representing the target object and the object attribute information of the target object are determined from the object region information; Based on the pixel matrix information, the target depth orientation information of the target pixel relative to the image capture location point is determined; Perform spherical coordinate transformation on the object attribute information and the target depth and orientation information to obtain the scene attribute information and spatial region information of the target object in the real scene; Based on the scene attribute information and the spatial region information, the regional attribute information of the target object is constituted.

7. The method according to claims 1-6, characterized in that, The target object and its corresponding regional attribute information are recorded as target object information in the designated information database; The method further includes: Upon receiving a business execution request associated with a real-world scenario, the target area range corresponding to the business execution request in the real-world scenario is determined. Search the information database, and based on the target object information recorded in the information database, determine the scene objects included within the target area and the regional attribute information of each scene object; Based on the regional attribute information of each of the aforementioned scene objects, the execution logic corresponding to the business execution request is responded to, and the request response result of the business execution request is obtained.

8. An object information determination device, characterized in that, include: The acquisition module is used to acquire the panoramic image and the image attribute information of the panoramic image; The first determining module is used to determine the pixel matrix information of the panoramic image based on the image attribute information of the panoramic image. The pixel matrix information includes the depth orientation information of each pixel in the panoramic image relative to the image capture position point. The second determining module is used to identify the panoramic image and determine the target object in the panoramic image and the object region information of the target object. The third determining module is used to determine the region attribute information of the target object based on the pixel matrix information and the object region information.

9. A computer device, characterized in that, The computer device includes: One or more processors; a storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the object information determination method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the object information determination method as described in any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the object information determination method according to any one of claims 1-7.

Images