Three-dimensional scene object identification method based on display precision

Abstract

The invention discloses a three-dimensional scene object identification method based on display precision, and the method comprises the following steps: obtaining a viewpoint parameter of a current three-dimensional scene, and determining a display precision state of current three-dimensional space data based on the viewpoint parameter and a preset precision grading strategy; calculating a model precision deviation parameter for quantifying the geometric simplification degree of the current model according to the display precision state; based on the model precision deviation parameter, dynamically determining a space determination parameter for three-dimensional space object identification; responding to a user interaction operation, obtaining a corresponding screen coordinate and mapping the screen coordinate to the three-dimensional projection space; taking the mapped projection position as a center, constructing an effective judgment area according to the dynamic space judgment parameters, judging the three-dimensional space object in the effective judgment area, and determining a target object; based on the identification information of the target object, triggering and executing an interaction processing operation associated with the target object; the method has stability and practicability in a complex large-scale scene.

Description

Technical Field

[0001] This invention relates to the field of graphical user interface interaction technology, and more specifically to a method for recognizing three-dimensional scene objects based on display accuracy. Background Technology

[0002] With the development of 3D graphics processing technology, 3D spatial data is widely used in large-scale scenarios such as urban modeling, architectural visualization, and real estate. 3D models can intuitively display the geometric shape of spatial objects and their spatial distribution relationships, providing fundamental support for users' observation and interaction in 3D scenes.

[0003] However, while existing technologies can achieve object recognition and interactive processing in 3D scenes to a certain extent, they still have the following shortcomings when using a processing method based on model display accuracy grading: First, when the model displays low precision, object recognition methods based on fixed judgment conditions are prone to recognition failures. Because the geometric representation of spatial objects is significantly simplified in low-precision display states, spatial relationship judgments based on the current display model may fail to accurately match the target object corresponding to the user's operation, thus affecting the accuracy of object recognition.

[0004] Secondly, regarding the issue of inaccurate object recognition, existing technologies typically reprocess the object recognition by increasing the model's display accuracy, thus increasing unnecessary computational and rendering overhead. In real-world 3D scenes, to avoid recognition failures, it is often necessary to adjust the viewpoint state or load higher-precision model data before performing the interaction judgment again. This approach not only increases the system's computational burden but also reduces the overall interactive response efficiency.

[0005] Third, existing object recognition methods lack an adaptive handling mechanism for changes in model display accuracy. The judgment conditions used for object recognition in existing technologies are typically statically set, failing to dynamically adjust the object recognition strategy according to changes in model display accuracy. This makes it difficult to balance recognition accuracy with processing efficiency, thus limiting the application effectiveness of such 3D interactive processing methods in large-scale scenes. Especially when model accuracy decreases, there is a certain error between the geometric position of a 3D object and its actual spatial position, causing object selection methods using fixed judgment ranges to fail to accurately reflect the actual spatial relationships of objects. Summary of the Invention

[0006] Objective of the Invention: The main objective of this invention is to provide a method for recognizing 3D scene objects based on display precision. From a supply-side perspective, without relying on improving the display precision of the model, the method adaptively adjusts the judgment conditions for object recognition based on the current display precision state of the 3D spatial data, thereby improving the accuracy of target object recognition under different display precision states and solving the problems existing in the background technology.

[0007] Technical solution: The present invention provides a method for recognizing 3D scene objects based on display accuracy, comprising the following steps: S1: Obtain the viewpoint parameters of the current 3D scene, and determine the display accuracy status of the current 3D spatial data based on the viewpoint parameters and the preset accuracy grading strategy; S2: Based on the displayed accuracy status, calculate the model accuracy deviation parameter used to quantify the degree of geometric simplification of the current model; S3: Based on the model accuracy deviation parameter, dynamically determine the spatial judgment parameters used for 3D spatial object recognition; S4: Respond to user interaction operations, obtain the corresponding screen coordinates and map them to the three-dimensional projection space; with the mapped projection position as the center, construct an effective judgment area according to the dynamic space judgment parameters, and judge the three-dimensional space objects within the effective judgment area to determine the target object; S5: Based on the identification information of the target object, trigger and execute the interactive processing operation associated with the target object.

[0008] Furthermore, in step S1, the display precision state is used to characterize the geometric detail level of the currently loaded three-dimensional spatial object and corresponds to different display precision level ranges; the viewpoint parameters include at least the viewpoint position and the spatial relationship between the viewpoint and the three-dimensional spatial object.

[0009] Furthermore, in step S2, the model accuracy deviation parameter Calculated using the following formula: ; in, Indicates the current display precision level. This indicates the preset highest display resolution level. The value range is [0, 1], and its value is used to reflect the degree of deviation between the model's geometry and the actual shape under the current display precision state.

[0010] Furthermore, in step S3, the spatial determination parameter is the dynamic interaction radius. It is determined by the following formula: ; in, The radius for determining the basic space; The adjustment coefficient is used to adjust the weight of the influence of model accuracy deviation on the spatial determination range. An adjustment function related to the viewpoint motion state is used to dynamically adjust spatial determination parameters when the viewpoint changes rapidly.

[0011] Furthermore, in step S4, when multiple candidate 3D spatial objects meet the filtering conditions, they are sorted according to the projection distance between each object and the projection position, the display level, or a preset priority rule, and the object with the best sorting is selected as the target object.

[0012] Furthermore, in step S5, the interactive processing operations include: confirming the selection of the target object, performing visual feedback processing on the target object in the 3D display interface, and calling and displaying the attribute information associated with the target object.

[0013] The present invention discloses a 3D scene object recognition system based on display precision, comprising: Accuracy Status Module: Used to obtain the viewpoint parameters of the current 3D scene, and determine the display accuracy status of the current 3D spatial data based on the viewpoint parameters and the preset accuracy grading strategy; Deviation Parameter Module: Used to calculate model accuracy deviation parameters that quantify the degree of geometric simplification of the current model, based on the displayed accuracy status; Decision Parameter Module: Used to dynamically determine spatial decision parameters for 3D object recognition based on model accuracy deviation parameters; Response module: Used to respond to user interaction operations, obtain the corresponding screen coordinates and map them to the three-dimensional projection space; with the mapped projection position as the center, construct an effective judgment area according to the dynamic space judgment parameters, and judge the three-dimensional space objects within the effective judgment area to determine the target object; Interaction module: Used to trigger and execute interactive processing operations associated with the target object based on the target object's identification information.

[0014] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the methods described herein.

[0015] An electronic device according to the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the methods described herein.

[0016] Beneficial Effects: Compared with existing technologies, this invention has the following significant advantages: This invention relies on improving model display accuracy and adaptively adjusting the judgment conditions for object recognition based on the current display accuracy of the 3D spatial data, thereby improving the accuracy of target object recognition under different display accuracy states. Furthermore, by introducing a judgment mechanism related to model display accuracy during object recognition and interaction processing, it reduces repetitive calculations and processing operations caused by inaccurate object recognition, lowers the system's computational and rendering overhead, and improves the overall response efficiency of 3D scene interaction processing. Moreover, by constructing an object recognition and interaction processing flow adapted to different model display accuracy states, the target object recognition process possesses adaptive capabilities, thereby enhancing the stability and practicality of this type of 3D interaction processing method in complex, large-scale scenes. Attached Figure Description

[0017] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be further described below with reference to the accompanying drawings.

[0019] like Figure 1 As shown, an embodiment of the present invention provides a method for recognizing 3D scene objects based on display accuracy, comprising the following steps: Step S1: Determine the display accuracy of the 3D spatial data. During the display of a 3D scene, viewpoint parameters related to the current display scene are acquired. These viewpoint parameters include at least the viewpoint position and the spatial relationship between the viewpoint and 3D spatial objects. Based on these viewpoint parameters and a preset precision grading strategy, the display precision state of the current 3D spatial data is determined. According to the current display precision state of the 3D scene, object determination conditions for 3D spatial object recognition are determined. Based on these object determination conditions, an object recognition determination region is constructed, and object recognition processing is performed. The display precision state characterizes the geometric detail level of the currently loaded 3D spatial object and corresponds to different display precision level ranges.

[0020] Step S2: Calculate the model accuracy deviation parameter based on the displayed accuracy status. To characterize the degree of geometric simplification of 3D spatial objects under the current display accuracy state, the model accuracy deviation parameter is calculated based on the current display accuracy state. In one implementation, the model accuracy deviation parameter is determined as follows: ; in, Indicates the current display precision level. This indicates the preset highest display resolution level. The value range is [0, 1], and its value is used to reflect the degree of deviation between the model's geometry and the actual shape under the current display precision state.

[0021] Step S3: Determine the spatial decision parameters based on the model accuracy deviation parameters. Based on the model accuracy deviation parameters, data processing judgment conditions for 3D object recognition are determined, and these conditions include at least spatial judgment parameters. The model accuracy deviation parameters are used to uniformly map geometric simplification differences under different display accuracy states to a standardized range, thus serving as the sole basis for adjusting the object recognition judgment conditions.

[0022] In one implementation, the spatial determination parameter is the dynamic interaction radius. It is determined in the following way: ; in, The radius for determining the basic space; The adjustment coefficient is used to adjust the weight of the influence of model accuracy deviation on the spatial determination range. An adjustment function related to the viewpoint motion state is used to dynamically adjust spatial determination parameters when the viewpoint changes rapidly.

[0023] Step S4: Perform 3D object recognition processing based on spatial determination parameters When the system receives an interactive operation command from the user in the 3D display interface, it first obtains the screen coordinate position corresponding to the interactive operation, and then maps the screen coordinate position to the projection space of the 3D scene based on the projection relationship of the current display view.

[0024] Subsequently, the system uses the mapped projection position as the center and determines the dynamic spatial parameters accordingly. The system constructs a determination region for the radius. It then filters candidate 3D spatial objects within this effective determination region in the current display scene. Specifically, this includes obtaining the projection position of each candidate 3D spatial object in the current display view and determining whether the projection position falls within the effective determination region. When a 3D spatial object satisfies the condition that its projection position falls within the effective determination region, the system identifies that 3D spatial object as the target object. When multiple 3D spatial objects meet the condition, the system further sorts the candidate objects based on the projection distance between the object and its projection position, the object's display level, or a preset priority rule, and selects the 3D spatial object with the optimal sorting result as the target object. Through this processing method, the system can still achieve stable identification of the target object corresponding to the user's interaction intent based on a dynamically adjusted determination region, even when the model display accuracy is low and the object's geometric representation is simplified.

[0025] Step S5: Trigger the interactive processing operation associated with the target object. After identifying the target 3D spatial object in step S4, the system automatically triggers the interactive processing flow associated with the target object based on this object recognition result. Upon completing target object recognition, the system generates an object selection event and passes the object identification information corresponding to the target object as an event parameter to the interactive processing module. The object identification information is used to uniquely identify the selected 3D spatial object within the system.

[0026] Upon receiving the object selection event, the interaction processing module performs preset interaction processing operations on the target object based on the object identification information. These operations include: confirming the selection of the target object; providing visual feedback to the target object in the 3D display interface, including highlighting, outlining, or color changes; generating an object selection event based on the recognition result of the target spatial object being identified, and passing the object identification information as an event parameter to the interaction processing module, which then executes the interaction response processing associated with the target object. Through this process, the system can automatically complete the interaction response driven by the object recognition result after successful target object recognition, ensuring that the geometric display of the 3D spatial object is consistent with its associated information display, thus completing a full object recognition and interaction processing process.

[0027] This example uses a 3D scene of the "Happy Home Community" in a certain city as an application example. The scene contains 50 residential buildings and approximately 12,000 spatial objects. Users need to select and view the associated information of the target spatial object located in Room 302 of Building 5 in macroscopic display resolution.

[0028] Step S1: Determine the display accuracy status (static and dynamic relationships) Static relationship: The highest display precision level of the three-dimensional spatial data is preset to [value]. And set the basic space determination parameters. Pixels are used for data processing and determination of real estate object identification at the highest display precision. The spatial determination parameter R_dynamic is defined in the screen projection coordinate system and is used to describe the projection determination range of a three-dimensional spatial object in the current display view.

[0029] Dynamic Relationships: When the viewpoint is adjusted to a macroscopic observation state, the system acquires the current viewpoint parameters and determines the current display precision level based on the spatial relationship between the viewpoint and 3D objects. This corresponds to a display precision state where geometric details are significantly simplified.

[0030] Step S2: Quantitative calculation of model accuracy deviation parameters After determining the current display accuracy state, the system calculates the model accuracy deviation parameter, which is used to quantify the degree of geometric simplification of the three-dimensional spatial object under the current display accuracy state.

[0031] The model accuracy deviation parameter is determined as follows: ; Effect: By using the model accuracy deviation parameter, the model differences under different display accuracy states are uniformly mapped to a standardized range, providing a quantitative basis for the adaptive adjustment of subsequent data processing judgment conditions.

[0032] Step S3: Dynamic determination of data processing judgment conditions Based on the model accuracy deviation parameter, the system dynamically adjusts the data processing judgment conditions used for 3D object recognition.

[0033] In this embodiment, a precision adjustment coefficient is set. When the viewpoint is in a relatively stable state, the viewpoint state adjustment function .

[0034] The dynamic space determination parameters are determined as follows: ; Effect: The system adaptively expands the data processing and judgment range for 3D object recognition based on the current display accuracy, in order to compensate for the judgment deviation caused by the geometric simplification of the model.

[0035] Step S4: Real Estate Object Identification Processing Based on Dynamic Decision Conditions When the system receives an interactive operation command from the user in the 3D display interface, it first obtains the screen coordinate position corresponding to the interactive operation, and then maps the screen coordinate position to the projection space of the 3D scene based on the projection relationship of the current display view.

[0036] Subsequently, the system uses the mapped projection position as the center and bases it on the dynamic spatial determination parameters. An effective determination region for object recognition is constructed in the screen projection coordinate system. The effective determination region is a two-dimensional determination region with the projection position as the center and a radius of R_dynamic.

[0037] The system filters candidate 3D spatial objects located within the effective determination area in the current display scene. Specifically, it obtains the projection position or projection bounding range of each candidate 3D spatial object in the current display view and determines whether the projection position or projection bounding range at least partially falls within the effective determination area.

[0038] When at least one three-dimensional spatial object satisfies that its projection position or projection bounding area falls within the effective determination area, the system determines the three-dimensional spatial object as the target object; when there are multiple three-dimensional spatial objects that meet the conditions, the system can further sort the candidate objects based on the projection distance between the object and the projection position, the display level of the object, or a preset priority rule, and select the three-dimensional spatial object with the best sorting result as the target object.

[0039] In this embodiment, because the geometric details of the 3D model are simplified under macroscopic display precision conditions, the display position of the target spatial object has a projection deviation of approximately 8 pixels relative to its actual geometric center. When using fixed judgment conditions, this deviation would cause the object to be unrecognizable; however, when using the dynamic judgment method described in this embodiment, the deviation is smaller than the dynamic spatial judgment parameters. The system is able to reliably and accurately identify objects in the target space.

[0040] Step S5: Data processing and output of real estate management information After the target spatial object is identified in step S4, the system automatically triggers the interactive processing flow associated with the target spatial object based on the identification result. Specifically, when the target spatial object is successfully identified, the system generates an object selection event and passes the object identification information corresponding to the target spatial object as an event parameter to the interactive processing module. The object identification information is used to uniquely identify the selected 3D spatial object within the system. After receiving the object selection event, the interactive processing module executes a preset interactive processing operation based on the object identification information. The interactive processing operation includes: confirming the selection of the target spatial object; performing visual feedback processing on the target spatial object in the 3D display interface to indicate the current selection status; and triggering the invocation of attribute information associated with the target spatial object based on the object identification information and displaying the corresponding associated information in the user interface. Through the above processing method, the system can realize an interactive response driven by the object identification result after the target spatial object is successfully identified, ensuring that the geometric display state of the 3D spatial object is consistent with the display process of its associated information, thereby completing a complete 3D object selection and associated information interaction process.

Claims

1. A method for recognizing 3D scene objects based on display precision, characterized in that, Includes the following steps: S1: Obtain the viewpoint parameters of the current 3D scene, and determine the display accuracy status of the current 3D spatial data based on the viewpoint parameters and the preset accuracy grading strategy; S2: Based on the displayed accuracy status, calculate the model accuracy deviation parameter used to quantify the degree of geometric simplification of the current model; S3: Based on the model accuracy deviation parameter, dynamically determine the spatial judgment parameters used for 3D spatial object recognition; S4: Respond to user interaction operations, obtain their corresponding screen coordinates and map them to the three-dimensional projection space; Centered on the mapped projection position, an effective judgment area is constructed based on dynamic spatial judgment parameters, and the three-dimensional spatial objects are judged within the effective judgment area to determine the target object; S5: Based on the identification information of the target object, trigger and execute the interactive processing operation associated with the target object.

2. The method for recognizing 3D scene objects based on display precision according to claim 1, characterized in that, In step S1, the display precision status is used to characterize the geometric detail level of the currently loaded 3D space object and corresponds to different display precision level ranges; the viewpoint parameters include at least the viewpoint position and the spatial relationship between the viewpoint and the 3D space object.

3. The method for recognizing 3D scene objects based on display precision according to claim 1, characterized in that, In step S2, the model accuracy deviation parameter Calculated using the following formula: ； in, Indicates the current display precision level. This indicates the preset highest display resolution level. The value range is [0, 1], and its value is used to reflect the degree of deviation between the model's geometry and the actual shape under the current display precision state.

4. The method for recognizing 3D scene objects based on display precision according to claim 1, characterized in that, In step S3, the spatial determination parameter is the dynamic interaction radius. It is determined by the following formula: ； in, The radius for determining the basic space; The adjustment coefficient is used to adjust the weight of the influence of model accuracy deviation on the spatial determination range. An adjustment function related to the viewpoint motion state is used to dynamically adjust spatial determination parameters when the viewpoint changes rapidly.

5. The method for recognizing 3D scene objects based on display precision according to claim 1, characterized in that, In step S4, when multiple candidate 3D spatial objects meet the filtering conditions, they are sorted at least according to the projection distance between each object and the projection position, display level, or preset priority rules, and the object with the best sorting is selected as the target object.

6. The method for recognizing 3D scene objects based on display precision according to claim 1, characterized in that, In step S5, the interactive processing operations include: confirming the selection of the target object, performing visual feedback processing on the target object in the 3D display interface, and calling and displaying the attribute information associated with the target object.

7. A 3D scene object recognition system based on display accuracy, characterized in that, include: Accuracy Status Module: Used to obtain the viewpoint parameters of the current 3D scene, and determine the display accuracy status of the current 3D spatial data based on the viewpoint parameters and the preset accuracy grading strategy; Deviation Parameter Module: Used to calculate model accuracy deviation parameters that quantify the degree of geometric simplification of the current model, based on the displayed accuracy status; Decision Parameter Module: Used to dynamically determine spatial decision parameters for 3D object recognition based on model accuracy deviation parameters; Response module: Used to respond to user interaction operations, obtain their corresponding screen coordinates and map them to the three-dimensional projection space; Centered on the mapped projection position, an effective judgment area is constructed based on dynamic spatial judgment parameters, and the three-dimensional spatial objects are judged within the effective judgment area to determine the target object; Interaction module: Used to trigger and execute interactive processing operations associated with the target object based on the target object's identification information.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-6.

Images