An adaptive pointing projection method and related device

Abstract

This application discloses an adaptive pointing projection method and related apparatus, relating to the field of adaptive projection technology. The projection apparatus includes: a spatial perception module, a processing module, and at least one light field modulation output module. The spatial perception module is used to acquire spatial state information of the scene, including the object to be projected. The processing module is used to identify the spatial features of the object to be projected based on the spatial state information and generate a light field modulation command according to the spatial features. The light field modulation output module is used to generate and output a spatial light field that matches the spatial features of the object to be projected according to the light field modulation command. When the spatial state information (such as position and / or contour shape) of the object to be projected changes, this application can sense and adaptively adjust the projected spatial light field in real time to adapt to the changes in the spatial state information of the object to be projected.

Description

Technical Field

[0001] This application relates to the field of adaptive projection technology, and in particular to an adaptive pointing projection method and related apparatus. Background Technology

[0002] Existing intelligent beam-cutting lighting modules (such as the existing solutions with publication numbers CN118375872B or CN118149329B) typically adjust the beam's emission shape or illumination area by setting multiple light-shielding components or beam cutters and employing mechanical transmission or switching mechanisms, thereby achieving lighting control for different areas. However, existing lighting solutions based on beam-cutting structures still suffer from structural complexity and insufficient adaptability when implementing flexible, directional lighting applications with variable illumination areas.

[0003] Furthermore, traditional projector-based projection systems achieve functions such as area lighting, pattern display, or information prompts by projecting image content onto a target plane. These systems rely on pre-set geometric parameters or calibration results to map the projected image to the desired location. However, existing projector-based projection systems still suffer from insufficient adaptability and limited projection accuracy when implementing variable lighting or projection applications, making it difficult to meet the demands for higher flexibility and intelligence in applications. Summary of the Invention

[0004] The purpose of this application is to provide an adaptive pointing projection method and related apparatus, which can sense and adaptively adjust the projected spatial light field in real time when the spatial state information (such as position and / or outline shape) of the object to be projected changes, so as to adapt to the change in the spatial state information of the object to be projected.

[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides an adaptive pointing projection device, comprising: a spatial sensing module, a processing module, and at least one light field modulation output module; The spatial perception module is used to acquire spatial state information of the scene, including the object to be projected. The processing module is used to identify the spatial characteristics of the object to be projected based on spatial state information, and generate light field modulation instructions according to the spatial characteristics; The light field modulation output module is used to generate and output a spatial light field that matches the spatial characteristics of the object to be projected, according to the light field modulation command.

[0006] Secondly, this application provides an adaptive pointing projection method, including: Obtain spatial state information of the scene, including the object to be projected; Based on spatial state information, the spatial characteristics of the object to be projected are identified, and light field modulation instructions are generated according to the spatial characteristics. Based on the light field modulation command, a spatial light field that matches the spatial characteristics of the object to be projected is generated and output.

[0007] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described adaptive pointing projection method.

[0008] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides an adaptive pointing projection method and related apparatus. The projection apparatus includes: a spatial perception module, a processing module, and at least one light field modulation output module. The spatial perception module is used to acquire spatial state information of the scene, including the object to be projected. The processing module is used to identify the spatial features of the object to be projected based on the spatial state information and generate a light field modulation command based on the spatial features. The light field modulation output module is used to generate and output a spatial light field that matches the spatial features of the object to be projected based on the light field modulation command. When the spatial state information (such as position and / or outline shape) of the object to be projected changes, this application can sense and adaptively adjust the projected spatial light field in real time to adapt to the changes in the spatial state information of the object to be projected. In addition, the projection apparatus designed in this application can meet both lighting and projection needs, offering greater functional flexibility. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic diagram of the structure of an adaptive pointing projection device provided in Embodiment 1 of this application; Figure 2 This is a flowchart illustrating an adaptive pointing projection method provided in Embodiment 5 of this application; Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 6 of this application. Detailed Implementation

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] Existing intelligent light-cutting modules have the following shortcomings in practical applications: 1. Complex structure and limited mechanical reliability. This type of technology relies on multiple shading components and their corresponding mechanical transmission structures, resulting in a complex overall structure with a large number of components. During long-term use, it is susceptible to wear, assembly errors, or environmental factors, thus limiting its reliability and stability.

[0013] 2. Limited flexibility in adjusting the lighting area. Due to the limited number and structure of the light-shielding components, the shape of the lighting area that can be achieved is usually a preset, limited form, making it difficult to make continuous and precise adjustments according to the actual position, shape, or size of the target object.

[0014] 3. Lack of automatic alignment capability based on visual perception. Existing intelligent light-cutting lighting modules typically use preset or manual control methods for area switching, lacking a real-time perception and feedback adjustment mechanism for the actual target area, making it difficult to achieve automatic alignment between the illuminated area and the target object.

[0015] Traditional projector-based projection systems have the following shortcomings in practical applications: 1. High dependence on the accuracy of system geometric calibration. Existing projection systems typically require precise calibration of the spatial relationship between the projection device and the imaging device, including intrinsic parameters, extrinsic parameters, and coordinate transformation relationships between them. Once the system installation environment changes, or the optical engine position shifts slightly due to vibration or aging, the original calibration results may become invalid, resulting in projection position deviation and affecting projection accuracy.

[0016] 2. The projected spatial light field is difficult to automatically align with the actual target area. Existing projection systems mostly project based on preset models or manually set parameters, lacking the ability to perceive and adjust the actual target area in real time. When the position, shape, or size of the target object changes, recalibration or manual adjustment is often required, making it difficult to achieve truly adaptive projection.

[0017] 3. Projection systems prioritize display over precise lighting or pointing control. Traditional projectors are primarily used for image display, with their design goals focused on image clarity and overall visual effect, rather than high-precision, controllable light spot or illumination pointing to specific physical areas. Therefore, existing projection systems struggle to meet the demands of applications requiring precise lighting, pointing, or high-precision light spot positioning in localized areas.

[0018] 4. Difficulty in compensating for comprehensive errors and maintaining long-term stability. Most existing projection systems adopt open-loop or weak feedback control methods, which have limited ability to compensate for comprehensive factors such as lens distortion error, sensor noise, and assembly error. As the usage time increases, their projection accuracy tends to gradually decrease, making it difficult to work stably in complex environments for a long time.

[0019] Therefore, existing intelligent light-cutting lighting modules and existing projector-based projection systems have certain shortcomings in terms of flexible pointing of the target object, perception of changes in the target object, and precise alignment between the target object and the projected content. To address this, this application proposes an adaptive pointing projection method and related apparatus. When the spatial position (three-dimensional coordinates or orientation) and contour / shape (geometric boundary) of the object to be projected change, the method collects the spatial state information of the object to be projected to analyze its spatial position and contour / shape changes, and then updates the light field modulation command and the spatial light field. This eliminates the need for mechanical structures for light-cutting processing, solving the problems of complex structures and limited mechanical reliability in existing intelligent light-cutting lighting modules, as well as the limited flexibility of the aforementioned lighting area adjustment methods. Furthermore, because this application employs a dynamic adaptive pointing method, it avoids the problem of projection accuracy gradually decreasing with increasing system usage time. Furthermore, after the projection operation is performed, the light field modulation command can be dynamically adjusted according to the actual projection result, which solves the problem of lacking automatic alignment capability based on visual perception, and solves the problem of the projected spatial light field being difficult to automatically align with the actual target area. In addition, in this application, the projected spatial light field is not only applicable to display, but can also meet the requirements of any projected spatial light field, which solves the problem that the projection system focuses more on display than on precise lighting or pointing control.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Example 1 like Figure 1 As shown, this embodiment provides an adaptive pointing projection device, including: a spatial sensing module, a processing module, and at least one light field modulation output module. The processing module communicates with the spatial sensing module and the light field modulation output module via wired or wireless means.

[0022] The spatial perception module is used to acquire scene data, including the object to be projected, and generate spatial state information of the scene and the object to be projected based on the scene data.

[0023] The spatial perception module includes a scene data acquisition unit. As an example, the scene data acquisition unit can be one or more combinations of the following sensors: RGB camera, monocular vision sensor, binocular vision sensor, depth sensor (e.g., structured light, TOF), LiDAR, millimeter-wave radar, ultrasonic sensor, inertial measurement unit (IMU), etc. Scene data includes two-dimensional images, depth maps, or three-dimensional point cloud data.

[0024] The processing module is used to identify the spatial features of the object to be projected based on spatial state information, and generate light field modulation instructions according to the spatial features. As an example, spatial features can be the three-dimensional position, boundary contour (shape), depth information, etc. of the object to be projected.

[0025] Specifically, image processing or visual recognition algorithms are used to identify the spatial features of the object to be projected from the spatial state information, thereby obtaining the object's three-dimensional position data, boundary contour data, and depth information data in the imaging coordinate system. Image processing or visual recognition algorithms include, but are not limited to, detection algorithms based on image difference, traditional image processing algorithms based on feature extraction, or segmentation algorithms based on deep learning.

[0026] The light field modulation output module is used to generate and output a spatial light field that matches the spatial characteristics of the object to be projected, based on the light field modulation command. The light field modulation output module can also be called a projection module, and the light field modulation command can also be called projection control parameters.

[0027] The light field modulation output module can employ an optical engine, which may utilize at least one projection or controllable optical emission technology, including but not limited to DLP, LCOS, LCD, LBS, Micro LED, and other controllable optical projection technologies. The optical engine supports regional cropping or spatial distribution control of the projected spatial light field. The projected spatial light field includes, but is not limited to, controllable projection information such as light spots, graphics, images, or continuous frames of images.

[0028] The shape, position, size, and depth distribution of the projected spatial light field can be dynamically adjusted according to the dynamic changes of the object to be projected. The projected spatial light field matches the boundary and spatial structure of the object to be projected, achieving precise spatial projection alignment. The projected spatial light field is not limited to light spots used for illumination, but can also be any controllable projected information used for indication, annotation, display, or enhancement, and its specific forms include, but are not limited to, light spots, graphics, images, image sequences, and invisible light. The range of spatial light fields includes visible light, invisible light, coded light, structured light, images, and image sequences.

[0029] In another exemplary embodiment of this application, the processing module includes: The feature recognition submodule is used to identify the spatial features of the object to be projected based on spatial state information.

[0030] The light field modulation instruction submodule is used to retrieve the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation instruction, and generate the light field modulation instruction based on the spatial characteristics of the object to be projected and the mapping relationship.

[0031] In another exemplary embodiment of this application, the processing module further includes a mapping relationship submodule (used to derive the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation command).

[0032] The mapping relationship submodule includes: The initial control command generation unit is used to generate the initial light field modulation command when the light field modulation output module projects the spatial light field, and to generate the initial projection content based on the initial light field modulation command.

[0033] The post-projection scene data acquisition unit is used to control the light field modulation output module to perform the projection operation based on the current projection content to project the projection content onto the object to be projected, and to control the spatial perception module to collect post-projection scene data including the target projection object and the current projection spatial light field.

[0034] The deviation calculation unit is used to determine the deviation between the spatial characteristics of the projected spatial light field and the spatial characteristics of the target projected object in the projected scene data. For point-level closed-loop mapping, spatial characteristics are feature points that characterize the spatial positions of the projected content and the target projected object (such as geometric center, axisymmetric center point, etc.), and may also include the scale characteristics of the target projected object and the projected content. For shape-level closed-loop mapping, spatial characteristics can be at least one of the coordinate position characteristics, scale parameters, rotation parameters, deformation parameters, etc. of the boundary contours of the projected content and the target projected object.

[0035] The judgment unit is used to determine whether the current iteration meets the preset iteration convergence conditions (such as the deviation being less than the preset value, or reaching the maximum number of iterations).

[0036] The loop unit is used to adjust the current light field modulation command according to the current deviation if not, update the projection content according to the current light field modulation command (adjusted), and the projection scene data acquisition unit executes the step "control the light field modulation output module to perform the projection operation according to the current projection content (updated), and control the spatial perception module to collect the projection scene data containing the target projection object and the current projection spatial light field".

[0037] The mapping relationship fitting unit is used to record the spatial features of the target projection object and the corresponding current light field modulation command if the condition is met, and to derive the mapping relationship between the spatial features of the projection object and the corresponding light field modulation command.

[0038] In another exemplary embodiment of this application, in application scenarios where the area of ​​the object to be projected is large or complex in shape, and the projection range of a single light field modulation output module is insufficient to meet the requirements, seamless splicing and coverage projection of the object to be projected is achieved through the collaborative control of multiple light field modulation output modules. To this end, the processing module is further configured to identify the area range of the object to be projected based on spatial state information, determine whether the area range of the object to be projected exceeds the projection range of a single light field modulation output module, and if so, trigger a collaborative mode. When the collaborative mode is triggered, the processing module is configured to divide the area range of the object to be projected into multiple sub-regions, match a corresponding light field modulation output module to each sub-region, and generate a light field modulation command corresponding to each sub-region based on the spatial characteristics of the object to be projected.

[0039] The adaptive pointing projection device provided in this embodiment can solve the problems of target projection area adaptability, alignment accuracy and structural complexity of existing projection or lighting devices. It can adjust the projected spatial light field according to the position change of the object to be projected, thereby improving the pointing flexibility and adaptability. Moreover, the structure is simpler and easier to integrate, reducing the complexity of the device and improving the stability of long-term use. It can improve the alignment accuracy between the projected spatial light field and the object to be projected (such as the projection area or the projected item), thereby realizing effective projection or illumination of the object to be projected.

[0040] Example 2 This embodiment proposes an adaptive pointing projection device. Unlike Embodiment 1, this embodiment derives the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation command based on the mapping relationship of point-level closed-loop alignment. Specifically, it is an adaptive pointing projection device based on a single target reference point, suitable for projection objects (target items or target areas) whose spatial position can be characterized by a single target reference point, such as centrally symmetric or axisymmetric exhibits, regular or approximately regular area outlines, etc. The projection device includes at least: a spatial sensing module, a processing module, and a light field modulation output module.

[0041] The light field modulation output module is used to project content onto a target object. The projected content includes a single alignment reference point, and the actual projection position of the single alignment reference point is determined by controllable projection control parameters. Characterization.

[0042] In some implementations, the projected content is generated based on a predefined graphic template, including but not limited to dot-shaped light spots, geometric light spots (such as rectangles, circles, polygons), two-dimensional static images and dynamic images (image frame sequences), three-dimensional solid graphics and three-dimensional dynamic scenes. The three-dimensional dynamic scene can be represented as a sequence of three-dimensional spatial information that changes over time, and the dynamic image can be represented as a time sequence of image frames. The processing module can apply the mapping relationship frame by frame to achieve spatial alignment projection of the object to be projected.

[0043] The spatial awareness module is used to acquire scene data including the projected content and the target reference point of the projected object, and output the physical coordinates of the alignment reference point of the projected content and the target reference point of the projected object. In some implementations, the spatial perception module is also configured to extract size feature information of the target projection object, including but not limited to the pixel range, feature point spacing, or boundary size parameters of the target projection object.

[0044] The processing module is used to perform image processing, error calculation, closed-loop control, mapping model construction, and projection content generation and adjustment. The specific processing content includes: (1) Definition of the alignment reference point For the content to be projected, a unique alignment reference point is defined to characterize the target projection position of the content in space. The alignment reference point can be the geometric center, centroid, intersection of the axes of symmetry of the content, or a predefined anchor point.

[0045] Alignment reference points include, but are not limited to: the geometric center of the projected content, the centroid of the projected content, the intersection of the axes of symmetry of the projected content, and pre-set or manually specified anchor points.

[0046] (2) Establishment of the target reference point set The system automatically generates or assists in selecting a set of target reference points. For example, the target reference points can be any point in the workspace (such as the wall to be projected).

[0047] The spatial perception module directly obtains the real-time physical coordinates of the target reference point: , ; Where N is the number of target reference points.

[0048] (3) Point-to-point closed-loop alignment and data acquisition For each target reference point in the target reference point set, the following closed-loop servo process is executed sequentially: a) Initial Projection According to a set of initial projection control parameters The control light field modulation output module projects content that includes a single aligned reference point.

[0049] b) Real-time sensing The spatial perception module collects scene information including the target reference point and the projected content: ① Physical coordinates of the target reference point .

[0050] ② The physical coordinates of the reference point in the projected content .

[0051] The methods for obtaining physical coordinates include, but are not limited to: measuring the depth information of the target reference point using a depth camera and converting it into three-dimensional coordinates using camera intrinsic parameters; obtaining point cloud data of the reference point using LiDAR or structured light scanning and extracting the three-dimensional coordinates of the target reference point using point cloud processing algorithms; using coded projection or laser calibration technology to project specific light spots or coded patterns and combine them with visual feedback to analyze the spatial position of the target point; and using the method of fusing inertial measurement units (IMU) and sensors to achieve dynamic reference point position estimation.

[0052] c) Deviation Calculation Calculate the three-dimensional coordinate deviation between the alignment reference point and the target reference point in the projected content: , , d) Closed-loop feedback and control Based on the three-dimensional coordinate deviation, the processing module updates the projection control parameters of the light field modulation output module using a closed-loop control algorithm (including but not limited to proportional control, PID control, or model predictive control). The physical coordinates of the reference point in the projected content converge towards the target reference point.

[0053] e) Convergence determination and recording When the 3D coordinate deviation is less than a preset threshold and remains stable, the target reference point is considered to have completed alignment. At this time, a set of point-level closed-loop calibration data is recorded: the physical coordinates of the target reference point. And the corresponding projection control parameters that ensure stable alignment of the projected content. .

[0054] Traverse all target reference points and collect multiple sets of point-level closed-loop calibration data throughout the entire working area.

[0055] In another optional implementation, the scale of the projected content can be adaptively adjusted by combining the size characteristics of the target object, thereby meeting the requirements for projection coverage in practical applications. Therefore, the size parameters of the projected content can also be adjusted in a closed loop to achieve scale closed-loop calibration. 1) Physical coordinates based on the target reference point Determine the size characteristics of the target projection object (e.g.) ).

[0056] 2) Adjust the scale control parameters of the projected content based on the size characteristics of the target object and the size characteristics of the projected content after projection. This continues until the projected content and the target object visually match in size.

[0057] Record the calibration data after convergence: .

[0058] (4) Construction of point-level mapping model Using all collected point-level closed-loop calibration data as the training set, a mapping function from camera pixel coordinates to position projection control parameters is established: .

[0059] In another alternative implementation, a mapping function is established between the size characteristics of the target projection object and the corresponding scale projection control parameters: The forms of mapping functions F and G include, but are not limited to: multinomial fitting models; lookup tables and interpolation models; machine learning models, etc. The mapping function implicitly contains comprehensive geometric relationships and error compensation information of the system.

[0060] The aforementioned point-level closed-loop alignment mapping relationship is trained during the factory or system initialization phase and can be stored as mapping functions F and G. In practical applications, the processing module can call them for actual projection applications.

[0061] The projection application process based on the mapping relationship of point-level closed-loop alignment is as follows: (1) Target reference point identification In practical applications, the spatial perception module collects scene data of the target object or target area and extracts the physical coordinates of its corresponding target reference point. .

[0062] Depending on the requirements, the size parameters of the target object or target area can also be obtained: .

[0063] (2) Generation of projection control parameters Physical coordinates of the target reference point Input the mapping function F to generate the corresponding position projection control parameters: To match the target object size Furthermore, the scale projection control parameters corresponding to the projected content can be generated based on the mapping function G: (3) Projected content generation Based on the scene data of the object to be projected collected by the spatial perception module, the projected content is generated based on the predefined graphic template and matches the image features of the object to be projected. For example, if the object to be projected is a rectangular light spot, the projected content in a rectangular shape is generated based on the predefined rectangular graphic template.

[0064] In some exemplary embodiments, scale projection control parameters are determined based on the size characteristics of the object to be projected and the mapping function G, and the graphic template is scaled based on the scale projection control parameters.

[0065] The light field modulation output module performs projection according to the position projection control parameters / scale projection control parameters, ensuring that the alignment reference point in the projected content is precisely aligned with the target reference point on the actual working plane in terms of position / size, achieving accurate point projection. For example, if the target object is a rectangular picture frame and the projected content is a rectangular light spot, after the projection operation, the intersection of the diagonals of the matrix light spot coincides with the intersection of the diagonals of the rectangular picture frame, and the rectangular light spot completely covers the interior area of ​​the rectangular picture frame.

[0066] Based on the above, the processing module also includes a mapping relationship submodule (used to derive the mapping relationship between the spatial characteristics of the projected object and the corresponding optical field modulation command).

[0067] The mapping relationship submodule includes: The initial control command generation unit is used to generate the initial light field modulation command when the light field modulation output module projects the spatial light field, and to generate the initial projection content based on the initial light field modulation command.

[0068] The post-projection scene data acquisition unit is used to control the light field modulation output module to perform the projection operation based on the current projection content to project the projection content onto the object to be projected, and to control the spatial perception module to collect post-projection scene data including the target projection object and the current projection spatial light field.

[0069] The deviation calculation unit is used to determine the deviation between the spatial characteristics (alignment reference point, or alignment reference point and size characteristics) of the projected spatial light field in the scene data after projection and the spatial characteristics (alignment reference point, or alignment reference point and size characteristics) of the target projection object.

[0070] The judgment unit is used to determine whether the current iteration meets the preset iteration convergence conditions (such as the deviation being less than the preset value, or reaching the maximum number of iterations).

[0071] The loop unit is used to adjust the current light field modulation command according to the current deviation if not, update the projection content according to the current light field modulation command (adjusted), and the projection scene data acquisition unit executes the step "control the light field modulation output module to perform the projection operation according to the current projection content (updated), and control the spatial perception module to collect the projection scene data containing the target projection object and the current projection spatial light field".

[0072] The mapping relationship fitting unit is used to record the spatial features of the target projection object and the corresponding current optical field modulation command if the condition is met, and to derive the mapping relationship (point-level closed-loop alignment mapping relationship) between the spatial features of the projection object (target reference point / size features) and the corresponding optical field modulation command.

[0073] This embodiment proposes a mapping relationship calibration method based on point-to-point closed-loop alignment, applicable to projection content whose projection position can be characterized by a single alignment reference point. The calibration method proposed in this embodiment does not rely on explicit and precise calculation of system geometric parameters (including but not limited to extrinsic parameters of the camera and projection device, 3D model of the working plane, or depth information). Instead, it establishes a point-level closed-loop alignment mapping relationship from the physical coordinates of the target reference point to the projection control parameters through physical feedback and closed-loop control, thereby compensating for comprehensive errors in the system and achieving high-precision, stable point-level projection alignment. This mapping relationship calibration method is applicable to point-level projection on a 2D working plane or in 3D space.

[0074] In this embodiment, each set of calibration data originates from physical feedback collected when the coordinates of the alignment reference point of the projected content and the target reference point of the projected object converge and remain stable through closed-loop control. No explicit calculation of extrinsic parameters, planar models, or depth information is required. Lens distortion, assembly errors, and environmental changes are implicitly encoded into the mapping function. For projection tasks that can be characterized by a single reference point, stable, fast, and high-precision point-level projection effects can be achieved with low computational complexity. Furthermore, scale parameters can be introduced. By introducing low-dimensional scale parameters, the size of the projected content can be adaptively adjusted, improving the actual coverage effect without significantly increasing computational complexity. Therefore, this embodiment can achieve stable, fast, and engineering-practical projection alignment in complex real-world environments.

[0075] This embodiment primarily addresses projection tasks that can be characterized by a single reference point, without imposing strict constraints on the shape boundaries of the projected content. When the object to be projected can be simplified into discrete key points, the point-level closed-loop alignment scheme of this embodiment can be preferentially adopted. For projections requiring precise contour fitting, multi-reference point or shape-level mapping schemes can be used.

[0076] Example 3 This embodiment proposes an adaptive pointing projection device. Unlike Embodiment 1, this embodiment derives the mapping relationship between the spatial characteristics of the projected object and the corresponding light field modulation command based on the shape-level closed-loop alignment mapping relationship. Specifically, it is an adaptive pointing (coverage) projection device based on the target contour, suitable for scenarios where the target object or target area has non-point-shaped, non-centrosymmetric, or irregular geometric boundaries, enabling the projected spatial light field to completely cover the target shape. The device includes: a spatial perception module, a processing module, and a light field modulation output module.

[0077] The light field modulation output module is used to project content onto a target object. Its projection control parameters include at least one of position, scale, rotation, and deformation parameters. Some or all parameters can be adjusted according to the complexity of the target object (for example, a simple rectangle only requires position and scale, while a complex and irregular target requires rotation and deformation). The spatial light field projected by the light field modulation output module is not limited to light spots used for illumination, but can also be any controllable projection information used for indication, annotation, display, or enhancement. Its specific forms include, but are not limited to, light spots, graphics, two-dimensional images or continuous image frames, three-dimensional graphics, and three-dimensional dynamic scene information.

[0078] The spatial perception module is used to collect scene data including the target projection object and the projection content, and output the corresponding physical coordinates.

[0079] The processing module analyzes the scene data collected by the spatial perception module, extracts the spatial features of the target projection object, performs overall deviation calculation, closed-loop control, projection content generation and adjustment, and can achieve rapid projection or similar target matching by constructing a shape-level mapping model. Shape information may include: point sequences of boundary contours, region masks, feature point sets or key point descriptions, and the most suitable feature type can be selected according to the complexity of the target.

[0080] By projecting a sequence of dynamic image frames, shape information can be extracted frame by frame and mapped to projection control parameters in real time.

[0081] The projected content is generated based on predefined graphic templates, including but not limited to outline graphics, solid patterns, combinations of basic graphic elements, static or dynamic image frame sequences, three-dimensional graphics, and three-dimensional dynamic scenes.

[0082] In this embodiment, when the target object is non-point-shaped, non-centrosymmetric, or has irregular geometric boundaries, projection based solely on discrete point-level alignment is insufficient to guarantee projection accuracy in terms of overall contour consistency, regional coverage integrity, and shape continuity. Therefore, this embodiment introduces a closed-loop feedback and servo adjustment mechanism based on the overall shape (a shape-level closed-loop alignment mapping calibration method) to achieve automatic alignment and overlay projection between the overall shape of the projected image and the geometry of the target object, thereby improving the projection accuracy and stability of complex targets. Furthermore, this embodiment can incorporate size information to achieve adaptive scaling of the projected content, meeting the coverage requirements of different target sizes.

[0083] The specific process of the mapping relationship calibration method for shape-level closed-loop alignment is as follows: Step 1: Acquiring spatial information of the target projection object The spatial perception module collects scene data containing the target projection object; the processing module extracts the shape information of the target projection object from the image. Optional feature types include, but are not limited to: boundary contour point sequence (2D / 3D), region mask (2D / 3D), feature point set or key point description (supporting 3D coordinates). The feature type can be selected according to the complexity of the target projection object.

[0084] Depending on the actual needs, the size information of the target projection object (such as maximum side length, area, or volume) can also be extracted for adaptive scaling of the projection content.

[0085] Step 2: Initial Projection Content Generation The processing module generates an initial projection content based on the shape information of the target projection object, a predefined graphic template, and initial projection control parameters; The initial projected content should be consistent with the target projected object in terms of topology or regional attributes, but the position, scale, rotation or deformation parameters can be initially set and do not need to be exactly the same.

[0086] In this embodiment, the initial projection content can be: 1) a contour graphic similar to the target contour shape; 2) a solid projection pattern covering the target area; 3) a composite projection shape formed by combining multiple basic primitives.

[0087] Step 3: Projection and Scene Data Acquisition The control light field modulation output module projects the initial projection content onto the workspace (target projection object). The spatial perception module synchronously collects scene data, including the target projection object and the projection content, as the observation input for subsequent closed-loop feedback.

[0088] For dynamic scenes, scene data can be continuously collected in real time to form a frame sequence.

[0089] Step 4: Extracting the shape of the actual projected content The processing module extracts the shape information of the actual projected content from the collected scene information. In this embodiment, the methods for extracting the shape information of the actual projected content include, but are not limited to: 1) Segment the actual projection area based on brightness, color, frequency domain or depth features to generate a region mask.

[0090] 2) Extract the contour of the region mask to obtain the feature points or key point sequence of the projected content.

[0091] 3) Calculate the three-dimensional coordinates of feature points or key points.

[0092] The generated shape information can be represented in a two-dimensional projection plane or in three-dimensional space.

[0093] Step 5: Calculation of overall shape deviation The processing module calculates the overall shape deviation between the target projection object's shape information and the actual projected content's shape information. The overall shape deviation includes, but is not limited to: 1) The average distance, maximum distance, or distribution statistics between the outline of the target object and the projected outline; 2) The overlap ratio or uncovered area ratio between the projection area and the target area (target projection object); 3) Translational error, dimensional error, and rotational error between the two shapes; 4) Shape error index that characterizes the difference in non-rigid deformation.

[0094] You can select some or all of the above deviation indicators according to your needs.

[0095] Step 6: Closed-loop feedback and projection adjustment The processing module calculates the overall shape deviation and generates adjustment instructions for the light field modulation output module. These instructions are used to adjust the projection control parameters of the projected content on the light field modulation output module side, including but not limited to: 1) Position parameters of the projected content in the projection coordinate system ; 2) Scale parameters of the projected content ; 4) Rotation parameters of the projected content ; 5) Deformation or distortion parameters of the projected content .

[0096] The above projection control parameters can be selected according to actual needs. For example, for simple targets, only position and scale can be adjusted, while for complex targets, all parameters can be adjusted.

[0097] The light field modulation output module updates the current projection content according to the adjustment command and enters the next closed-loop iteration.

[0098] If multiple projection control parameters are selected as mentioned above, a multi-level closed-loop strategy can be adopted, as an example: ① Coarse alignment stage: First, perform closed-loop control of position and scale to quickly cover the target area and achieve preliminary alignment.

[0099] ② Fine alignment stage: Based on coarse alignment, rotation and deformation closed-loop control are performed to ensure accurate fit between the projected contour and the target shape, as well as complete coverage of the area.

[0100] Each closed-loop iteration can update the projection control parameters and simultaneously acquire images to provide observation input for the next iteration.

[0101] Step 7: Iteration and Convergence Determination Repeat steps 3 through 6 until at least one of the following convergence conditions is met: 1) The overall shape deviation between the projected shape and the target projected object is less than a preset threshold.

[0102] 2) The coverage of the projection area over the target area reaches the preset ratio.

[0103] 3) The projection control parameters remain stable for several consecutive frames.

[0104] 4) The number of closed-loop iterations reaches the preset upper limit.

[0105] When the convergence condition is met, the closed-loop adjustment process is stopped.

[0106] Step 8: Record shape-level calibration data After the closed-loop adjustment is completed, the processing module records a set of shape-level calibration data, including: The shape information of the target projection object and the corresponding projection control parameters are used. Shape-level calibration data can be used for subsequent fast projection, direct matching projection of similar targets, or as training data for building a shape-level mapping model. The closed-loop iteration results can be used to build a shape-level mapping model, mapping the shape information of the target projection object to projection control parameters to achieve fast projection or similar target matching.

[0107] Shape-level mapping models can be divided into four types of sub-functions, which can be trained individually or used in combination: Location mapping: Scale mapping: Rotation mapping: Deformation mapping: The fitting of shape-level mapping models can be achieved through interpolation, polynomial fitting, machine learning models, etc., to ensure accuracy and generalization ability. This is a positional mapping relationship. This is a scale mapping relationship. This is a rotational mapping relationship. This is a deformation mapping relationship. These are the position projection control parameters. These are the scale projection control parameters. These are the rotational projection control parameters. These are the deformation projection control parameters. The coordinates of the shape outline of the target object are used for projection. The size characteristics of the target projection object. The rotational characteristics of the target projection object. The deformation characteristics of the target object being projected.

[0108] This embodiment can adaptively scale the projected content based on size characteristics to achieve complete coverage of the object to be projected. Projected content scale parameters. It can automatically adjust based on the size characteristics of the object to be projected, supporting complete coverage of targets of different sizes. The shape template generated by the projected content can be scaled or moderately deformed, achieving generalized projection without the need for separate training for each target.

[0109] Based on the above, the processing module also includes a mapping relationship submodule (used to derive the mapping relationship between the spatial characteristics of the projected object and the corresponding optical field modulation command).

[0110] The mapping relationship submodule includes: The initial control command generation unit is used to generate the initial light field modulation command when the light field modulation output module projects the spatial light field, and to generate the initial projection content based on the initial light field modulation command.

[0111] The post-projection scene data acquisition unit is used to control the light field modulation output module to perform projection operations based on the current projection content to project the projection content onto the target projection object, and to control the spatial perception module to collect post-projection scene data containing the target projection object and the current projection spatial light field.

[0112] The deviation calculation unit is used to determine the deviation between the spatial characteristics of the projected spatial light field in the projected scene data and the spatial characteristics of the target projected object. The spatial characteristics are at least one of the following: coordinate position characteristics of the boundary contour, scale parameters, rotation parameters, deformation parameters, etc.

[0113] The judgment unit is used to determine whether the current iteration meets the preset iteration convergence condition.

[0114] The loop unit is used to adjust the current light field modulation command according to the current deviation if not, update the projection content according to the current light field modulation command (adjusted), and the projection scene data acquisition unit executes the step "control the light field modulation output module to perform the projection operation according to the current projection content (updated), and control the spatial perception module to collect the projection scene data containing the target projection object and the current projection spatial light field".

[0115] The mapping relationship fitting unit is used to record the spatial features of the target projection object and the corresponding current light field modulation command if the condition is met, and to derive the mapping relationship between the spatial features of the projection object and the corresponding light field modulation command (the mapping relationship of shape-level closed-loop alignment).

[0116] This embodiment is applicable to shape-level projection on a two-dimensional working plane or in three-dimensional space. The mapping result of the shape-level closed-loop alignment in this embodiment can be combined with the mapping result of the point-level closed-loop alignment in Embodiment 2. The mapping relationship of point-level closed-loop alignment, shape-level closed-loop alignment, or a combination of both can be flexibly selected according to the complexity and accuracy requirements of the object to be projected, to achieve higher projection accuracy and applicability. When the object to be projected can be simplified to discrete key points, the mapping relationship of point-level closed-loop alignment in Embodiment 2 can be used preferentially; when the object to be projected has non-point, non-centrosymmetric, or irregular geometric boundaries, the mapping relationship of shape-level closed-loop alignment in this embodiment is preferred.

[0117] This embodiment has at least the following technical effects: (1) It can achieve overall contour alignment and overlay projection of irregular target objects; (2) No need to rely on depth information or explicit spatial perception module-projection module geometric extrinsic parameters; (3) Through the closed-loop servo mechanism, the combined error caused by system assembly error and optical distortion can be compensated; (4) It complements the point-level closed-loop calibration scheme and can be flexibly selected or combined according to the complexity of the target shape and the accuracy requirements.

[0118] (5) It can achieve size adaptation and rapid projection, improving engineering practicality and coverage effect.

[0119] (6) Real-time adaptability. The projected spatial light field can be dynamically adjusted according to the position or shape of the object to be projected, realizing intelligent projection.

[0120] Example 4 This embodiment proposes a splicing adaptive pointing projection device with coordinated multi-field modulation output modules. It is suitable for application scenarios where the target area is large and complex in shape, making the projection range of a single light field modulation output module insufficient. Through the coordinated control of multiple light field modulation output modules, seamless splicing coverage projection of the target area is achieved. The device includes: a spatial sensing module, a processing module, and at least two light field modulation output modules.

[0121] The spatial perception module is configured to acquire spatial state information of the scene, including the object to be projected.

[0122] The processing module is configured to divide the region based on the spatial position and boundary contour of the object to be projected, and coordinate and control multiple light field modulation output modules so that the spatial light field projected by each light field modulation output module forms a spliced ​​coverage within the target area (the object to be projected).

[0123] In this embodiment, the processing module performs at least the following functions: (1) Target Area Assessment The system identifies the target area based on the scene information of the object to be projected and determines whether the size of the target area exceeds the effective projection range of a single light field modulation output module. When the target area exceeds the projection capability of a single light field modulation output module, a cooperative mode (multi-light field modulation output module cooperative mode) is triggered.

[0124] (2) Regional division The target area is divided into at least two sub-regions; the sub-regions are divided in ways including but not limited to: division by geometric location; division by shape characteristics; and dynamic division based on the installation location and projection capability of the light field modulation output module. The sub-regions may partially overlap or be adjacent to each other.

[0125] (3) Allocation of optical field modulation output module At least one optical field modulation output module is assigned to each sub-region; the assignment is determined based on the relative position of the optical field modulation output module and the target region, the projection angle, or the available projection range.

[0126] (4) Sub-region projection control For each sub-region, the processing module generates a corresponding light field modulation command; the light field modulation command is used to control the corresponding light field modulation output module to generate and project a spatial light field covering the sub-region. The projected spatial light field can be a light spot, a graphic, an image, or information from consecutive frames of an image.

[0127] (5) Adjustment of splicing consistency (optional operation) The processing module can adjust the brightness, boundary position, or shape of the projected spatial light field in adjacent sub-regions to ensure consistency.

[0128] This embodiment can correct projection deviations between sub-regions through closed-loop feedback, reducing overlap or gaps.

[0129] Each light field modulation output module is used to project the corresponding spatial light field into the corresponding sub-region according to the light field modulation instructions assigned by the processing module.

[0130] Each light field modulation output module's optical engine employs at least one projection or controllable optical emission technology, including but not limited to DLP, LCOS, LCD, LBS, Micro LED, etc., and supports regional clipping or spatial distribution control of the projected spatial light field.

[0131] Each light field modulation output module can independently control the projection position, projection range, and shape of the projected spatial light field according to its own light field modulation command. The projected spatial light fields from different light field modulation output modules form a spliced ​​coverage within the target area.

[0132] The projection process of the spliced ​​adaptive pointing projection device with multi-field modulation output modules working together is as follows: (1) The spatial perception module acquires (collects) the spatial state information of the scene, including the object to be projected.

[0133] (2) The processing module identifies the area range of the object to be projected based on the spatial state information, and determines whether the area range of the object to be projected exceeds the projection range of the single light field modulation output module. If so, the cooperative mode is triggered.

[0134] (3) The processing module divides the area of ​​the object to be projected and assigns a light field modulation output module to each sub-area.

[0135] (4) Each optical field modulation output module projects a spatial optical field covering its corresponding sub-region.

[0136] (5) The processing module can stitch and adjust the projection results based on the imaging feedback so that the projected spatial light field covers the target area as a whole.

[0137] This embodiment has the following beneficial effects: (1) Supports large-size and complex-shaped targets. Through the collaboration of multi-field modulation output modules, complete coverage of large-size or complex target areas can be achieved.

[0138] (2) Avoid projection omissions or excessive overlap. Reduce gaps or overlaps between projection areas through area division and splicing control.

[0139] (3) The device has strong scalability. The number of optical field modulation output modules can be flexibly increased according to the size of the target area to adapt to different application scenarios.

[0140] This embodiment can combine the point-to-point alignment mapping calibration results of Embodiment 2 or the shape-level closed-loop alignment mapping calibration results of Embodiment 3 to achieve precise splicing projection under the multi-field modulation output module.

[0141] Example 5 This embodiment provides an adaptive pointing projection method, such as Figure 2 As shown, the method includes: S1: Obtain spatial state information of the scene, including the object to be projected.

[0142] S2: Based on spatial state information, identify the spatial characteristics of the object to be projected, and generate light field modulation instructions according to the spatial characteristics.

[0143] S3: Generate and output a spatial light field that matches the spatial characteristics of the object to be projected, according to the light field modulation command.

[0144] In another exemplary embodiment of this application, step S2, based on spatial state information, identifies the spatial characteristics of the object to be projected, and generates a light field modulation command according to the spatial characteristics, specifically including: (1) Identify the spatial characteristics of the object to be projected based on spatial state information.

[0145] (2) Retrieve the mapping relationship between the spatial characteristics of the projected object and the corresponding light field modulation command.

[0146] (3) Generate light field modulation instructions based on the spatial characteristics and mapping relationship of the object to be projected.

[0147] In another exemplary embodiment of this application, the adaptive pointing projection method further includes: fitting the mapping relationship between the spatial features of the projection object and the corresponding light field modulation command; specifically: (1) Generate the initial light field modulation command when the light field modulation output module projects the spatial light field, and generate the initial projection content based on the initial light field modulation command.

[0148] (2) Control the light field modulation output to perform the projection operation based on the current projection content, and control the spatial perception module to collect the projection scene data containing the target projection object and the current projection spatial light field.

[0149] (3) Determine the deviation between the spatial characteristics of the projected spatial light field in the scene data after projection and the spatial characteristics of the target projection object.

[0150] (4) Determine whether the current iteration meets the preset iteration convergence condition.

[0151] (5) If not, adjust the current light field modulation command according to the current deviation, update the projection content according to the current light field modulation command, and return to the step "Control the light field modulation output module to perform projection operation according to the current projection content".

[0152] (6) If so, record the spatial characteristics of the target projection object and the corresponding current light field modulation command, and obtain the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation command.

[0153] In another exemplary embodiment of this application, step S2, based on spatial state information, identifies the spatial characteristics of the object to be projected, and generates a light field modulation command according to the spatial characteristics, specifically including: (1) Identify the area range of the object to be projected based on spatial state information, and determine whether the area range of the object to be projected exceeds the projection range of a single optical field modulation output module. If so, trigger the cooperative mode.

[0154] (2) Divide the area of ​​the object to be projected into multiple sub-regions, and match the corresponding light field modulation output module for each sub-region.

[0155] (3) Generate light field modulation instructions for each sub-region based on the spatial characteristics of the object to be projected.

[0156] Example 6 This embodiment provides a computer device, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media. The database stores environmental information collected by the spatial awareness module, the actual projected image after projection operations, features identified by the processing module that characterize the spatial position and / or boundary contour of the object to be projected, and generated light field modulation instructions. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an adaptive pointing projection method.

[0157] Those skilled in the art will understand that Figure 3The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0158] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0159] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of the relevant data are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

[0161] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An adaptive pointing projection device, characterized in that, include: A spatial sensing module, a processing module, and at least one optical field modulation output module; The spatial perception module is used to acquire spatial state information of the scene, including the object to be projected. The processing module is used to identify the spatial characteristics of the object to be projected based on spatial state information, and generate light field modulation instructions according to the spatial characteristics; The light field modulation output module is used to generate and output a spatial light field that matches the spatial characteristics of the object to be projected, according to the light field modulation command.

2. The adaptive pointing projection device according to claim 1, characterized in that, The processing module includes: The feature recognition submodule is used to identify the spatial features of the object to be projected based on spatial state information; The light field modulation instruction submodule is used to retrieve the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation instruction, and generate the light field modulation instruction based on the spatial characteristics of the object to be projected and the mapping relationship.

3. The adaptive pointing projection device according to claim 2, characterized in that, The processing module also includes a mapping relationship submodule; The mapping relationship submodule includes: The initial control command generation unit is used to generate the initial light field modulation command when the light field modulation output module projects the spatial light field, and to generate the initial projection content based on the initial light field modulation command. The post-projection scene data acquisition unit is used to control the light field modulation output module to perform the projection operation based on the current projection content, and to control the spatial perception module to collect post-projection scene data including the target projection object and the current projection spatial light field; The deviation calculation unit is used to determine the deviation between the spatial characteristics of the projected spatial light field and the spatial characteristics of the target projection object in the scene data after projection. The judgment unit is used to determine whether the current iteration meets the preset iteration convergence condition; The loop unit is used to adjust the current light field modulation command according to the current deviation if not, update the projection content according to the current light field modulation command, and have the projection scene data acquisition unit execute the step "control the light field modulation output module to perform the projection operation according to the current projection content, and control the spatial perception module to collect the projection scene data including the target projection object and the current projection spatial light field"; The mapping relationship unit is used to record the spatial characteristics of the target projection object and the corresponding current light field modulation command if the condition is met, and to derive the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation command.

4. The adaptive pointing projection device according to claim 1, characterized in that, The processing module is also used to identify the area range of the object to be projected based on spatial state information, and to determine whether the area range of the object to be projected exceeds the projection range of the single light field modulation output module. If so, the cooperative mode is triggered.

5. The adaptive pointing projection device according to claim 4, characterized in that, When the collaborative mode is triggered, the processing module is used to divide the area of ​​the object to be projected into multiple sub-regions, match the corresponding light field modulation output module for each sub-region, and generate the light field modulation command corresponding to each sub-region according to the spatial characteristics of the object to be projected.

6. An adaptive pointing projection method, characterized in that, include: Obtain spatial state information of the scene, including the object to be projected; Based on spatial state information, the spatial characteristics of the object to be projected are identified, and light field modulation instructions are generated according to the spatial characteristics. Based on the light field modulation command, a spatial light field that matches the spatial characteristics of the object to be projected is generated and output.

7. The adaptive pointing projection method according to claim 6, characterized in that, Based on spatial state information, the spatial characteristics of the object to be projected are identified, and optical field modulation commands are generated according to these spatial characteristics, specifically including: Based on spatial state information, identify the spatial characteristics of the object to be projected; Retrieve the mapping relationship between the spatial characteristics of the projected object and the corresponding light field modulation command; Light field modulation instructions are generated based on the spatial characteristics and mapping relationship of the object to be projected.

8. The adaptive pointing projection method according to claim 7, characterized in that, The adaptive pointing projection method further includes: fitting the mapping relationship between the spatial features of the projection object and the corresponding optical field modulation command; specifically: The initial light field modulation command is generated when the light field modulation output module projects the spatial light field, and the initial projection content is generated based on the initial light field modulation command. Based on the current projection content, the light field modulation output module is controlled to perform the projection operation, and the spatial perception module is controlled to collect the projection scene data, which includes the target projection object and the current projection spatial light field. Determine the deviation between the spatial characteristics of the projected spatial light field in the scene data after projection and the spatial characteristics of the target projection object; Determine whether the current iteration satisfies the preset iteration convergence condition; If not, adjust the current light field modulation command according to the current deviation, update the projection content according to the current light field modulation command, and return to the step "Control the light field modulation output module to perform projection operation according to the current projection content"; If so, the spatial characteristics of the target projection object and the corresponding current light field modulation command are recorded, and the mapping relationship between the spatial characteristics of the projection object and the corresponding light field modulation command is obtained.

9. The adaptive pointing projection method according to claim 6, characterized in that, Based on spatial state information, the spatial characteristics of the object to be projected are identified, and optical field modulation commands are generated according to these spatial characteristics, specifically including: Based on spatial state information, the region of the object to be projected is identified, and it is determined whether the region of the object to be projected exceeds the projection range of a single optical field modulation output module. If so, the cooperative mode is triggered. The area to be projected is divided into multiple sub-regions. A corresponding light field modulation output module is matched for each sub-region, and a light field modulation command corresponding to each sub-region is generated according to the spatial characteristics of the object to be projected.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the adaptive pointing projection method as described in any one of claims 6-9.

Images