Data acquisition method, device and equipment for structured light camera

Abstract

The invention relates to a data acquisition method, a data acquisition device and data acquisition equipment of a structured light camera, and belongs to the technical field of data acquisition of structured light cameras. And generating a related recommendation result according to the data acquisition performance demand information in the target area and the data acquisition performance feature data of the structured light camera within the current preset time, and finally performing data acquisition according to the related recommendation result, and obtaining environment feature data in the target area. And performing data acquisition control on the structured light camera according to the environment characteristic data in the target area. According to the invention, the structured light camera meeting the working requirements is recommended according to the data acquisition performance data of the structured light camera, so that the data acquisition of the structured light camera is more reasonable, and the success rate of data acquisition is improved. And secondly, the optimal working parameters of the structured light camera are adjusted according to the change of the environment, so that the data acquisition is more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of structured light camera data acquisition, and in particular to a data acquisition method, device and equipment for a structured light camera. Background Art

[0002] The structured light device is a system structure composed of a projector and a camera. After the projector projects specific light information onto the surface of an object and the background, the camera collects the information and calculates the position and depth of the object based on the changes in the light signal caused by the object, thereby restoring the entire three-dimensional space. The structured light camera is one of the structured light devices. Nowadays, when the structured light camera is collecting data, the collected data will be abnormal due to the influence of the environment, which is not conducive to obtaining real image data, object position, depth information, etc. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a data acquisition method, device and equipment for a structured light camera.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides a data acquisition method for a structured light camera, comprising the following steps:

[0006] Acquire historical data acquisition performance change characteristic data of the structured light camera, and construct a data acquisition performance characteristic prediction model based on the historical data acquisition performance change characteristic data of the structured light camera;

[0007] Acquire data on changes in data acquisition performance characteristics of the structured light camera within a preset time, and predict data acquisition performance characteristics of the structured light camera within a current preset time based on the data acquisition performance characteristics prediction model and the data acquisition performance changes in the structured light camera within a preset time;

[0008] Obtaining data acquisition performance requirement information in the target area, and generating relevant recommendation results based on the data acquisition performance requirement information in the target area and data acquisition performance characteristic data of the structured light camera within the current preset time;

[0009] Data collection is performed according to the relevant recommendation results, and environmental feature data within the target area is obtained, and data collection control of the structured light camera is performed according to the environmental feature data within the target area.

[0010] Furthermore, in the present method, historical data acquisition performance change characteristic data of the structured light camera is obtained, and a data acquisition performance characteristic prediction model is constructed according to the historical data acquisition performance change characteristic data of the structured light camera, specifically including:

[0011] Acquire historical data acquisition performance change characteristic data of the structured light camera, build a data acquisition performance characteristic prediction model based on a deep neural network, and build a characteristic matrix according to the historical data acquisition performance change characteristic data of the structured light camera;

[0012] Inputting the feature matrix into the data acquisition performance feature prediction model for training, setting a loss function convergence threshold, and determining whether the loss function of the data acquisition performance feature prediction model converges to the loss function convergence threshold;

[0013] When the loss function of the data acquisition performance characteristic prediction model converges to a loss function convergence threshold, the model parameters of the data acquisition performance characteristic prediction model are saved, the training ends, and the data acquisition performance characteristic prediction model is output.

[0014] Furthermore, in the present method, the data acquisition performance change characteristic data of the structured light camera within a preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is predicted according to the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time, specifically:

[0015] Acquire data on changes in data acquisition performance characteristics of a structured light camera within a preset time, and input the data on changes in data acquisition performance characteristics of the structured light camera within the preset time into the data acquisition performance characteristics prediction model for prediction;

[0016] By prediction, data acquisition performance characteristic data of the structured light camera within the current preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is output.

[0017] Furthermore, in this method, the data acquisition performance requirement information in the target area is obtained, and the relevant recommendation results are generated according to the data acquisition performance requirement information in the target area and the data acquisition performance characteristic data of the structured light camera within the current preset time, specifically including:

[0018] According to the data acquisition performance characteristic data of the structured light camera within the current preset time, the data acquisition performance characteristic data of each structured light camera in the current timestamp is acquired, and a structured light camera is randomly selected for data acquisition to construct a structured light camera working set;

[0019] Acquire data acquisition performance requirement information in the target area, and acquire data acquisition performance characteristic data of each structured light camera in the structured light camera working set according to the data acquisition performance characteristic data of each structured light camera in the current timestamp;

[0020] Determine whether the data acquisition performance characteristic data of each structured light camera in the structured light camera working set are greater than the data acquisition performance requirement information in the target area, and if so, output the structured light camera working set and generate relevant recommendation results;

[0021] When the data acquisition performance characteristic data of each structured light camera in the structured light camera working set is not all greater than the data acquisition performance requirement information in the target area, the structured light camera working set is updated until all are greater than the data acquisition performance requirement information in the target area.

[0022] Furthermore, in the present method, obtaining environmental characteristic data within the target area, and performing data acquisition control on the structured light camera according to the environmental characteristic data within the target area specifically includes:

[0023] Obtaining optimal working parameters of the structured light camera with optimal data acquisition performance under each environmental feature data through big data, and inputting the optimal working parameters of the structured light camera with optimal data acquisition performance under each environmental feature data into the graph neural network;

[0024] Taking environmental feature data as a first graph node, taking optimal working parameters of the structured light camera at optimal data acquisition performance as a second graph node, connecting the first graph node with the second graph node to construct a topological structure graph;

[0025] Construct a knowledge graph, obtain a related adjacency matrix based on the topological structure graph, input the related adjacency matrix into the knowledge graph for representation, and obtain environmental feature data within the target area;

[0026] The environmental characteristic data within the target area is input into the knowledge graph to obtain the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental characteristic data, and the structured light camera is controlled for data acquisition according to the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental characteristic data.

[0027] Furthermore, in this method, the data acquisition method of the structured light camera also includes:

[0028] The image data information in the target area is collected by a structured light camera, and the pre-processed image data is obtained by filtering and denoising the image data information in the target area;

[0029] Collecting preprocessed image data within a time period, and obtaining a quality evaluation analysis result of each image by performing quality evaluation analysis on the preprocessed image data within the time period;

[0030] When the quality evaluation analysis result of the image is greater than the preset quality evaluation analysis result, outputting the preprocessed image data;

[0031] When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the preprocessed image data is reconstructed.

[0032] A second aspect of the present invention provides a data acquisition device for a structured light camera, comprising a memory and a processor, wherein the memory comprises a data acquisition method program for a structured light camera, and when the data acquisition method program for a structured light camera is executed by the processor, the steps of any one of the data acquisition methods for a structured light camera are implemented.

[0033] A third aspect of the present invention provides an electronic device, including a data acquisition method program for a structured light camera, wherein when the data acquisition method program for the structured light camera is executed by a processor, the steps of any one of the data acquisition methods for the structured light camera are implemented.

[0034] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0035] The present invention obtains the historical data acquisition performance change characteristic data of the structured light camera, and constructs a data acquisition performance characteristic prediction model based on the historical data acquisition performance change characteristic data of the structured light camera, thereby obtaining the data acquisition performance change characteristic data of the structured light camera within a preset time, and predicts the data acquisition performance characteristic data of the structured light camera within the current preset time based on the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time, thereby obtaining the data acquisition performance requirement information in the target area, and generating relevant recommendation results based on the data acquisition performance requirement information in the target area and the data acquisition performance characteristic data of the structured light camera within the current preset time, and finally performing data acquisition based on the relevant recommendation results, and obtaining the environmental characteristic data within the target area, and performing data acquisition control on the structured light camera based on the environmental characteristic data within the target area. The present invention recommends a structured light camera that meets the work requirements based on the data acquisition performance data of the structured light camera, so that the data acquisition of the structured light camera is more reasonable and the success rate of data acquisition is improved. Secondly, the present invention adjusts the optimal working parameters of the structured light camera according to the changes in the environment, so that the data acquisition is more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0037] Figure 1 The overall flow chart of the data acquisition method of the structured light camera is shown;

[0038] Figure 2 A partial flow chart of a data acquisition method for a structured light camera is shown;

[0039] Figure 3 A schematic diagram of a data acquisition device for a structured light camera is shown. DETAILED DESCRIPTION

[0040] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0042] Example 1

[0043] like Figure 1 As shown, the first aspect of the present invention provides a data acquisition method for a structured light camera, comprising the following steps:

[0044] S102: Acquire historical data acquisition performance change characteristic data of the structured light camera, and construct a data acquisition performance characteristic prediction model according to the historical data acquisition performance change characteristic data of the structured light camera;

[0045] S104: obtaining data acquisition performance change characteristic data of the structured light camera within a preset time, and predicting the data acquisition performance characteristic data of the structured light camera within the current preset time according to the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time;

[0046] S106: Acquire data acquisition performance requirement information in the target area, and generate relevant recommendation results according to the data acquisition performance requirement information in the target area and data acquisition performance characteristic data of the structured light camera within the current preset time;

[0047] S108: Collect data according to the relevant recommendation results, obtain environmental feature data within the target area, and control data collection of the structured light camera according to the environmental feature data within the target area.

[0048] It should be noted that the present invention recommends a structured light camera that meets the work requirements based on the data collection performance data of the structured light camera, so that the data collection of the structured light camera is more reasonable and the success rate of data collection is improved. Secondly, the present invention adjusts the optimal working parameters of the structured light camera according to changes in the environment, so that the data collection is more reasonable.

[0049] Furthermore, in this method, historical data acquisition performance change characteristic data of the structured light camera is obtained, and a data acquisition performance characteristic prediction model is constructed based on the historical data acquisition performance change characteristic data of the structured light camera, specifically including:

[0050] Obtain historical data acquisition performance change characteristic data of the structured light camera, build a data acquisition performance characteristic prediction model based on a deep neural network, and build a feature matrix based on the historical data acquisition performance change characteristic data of the structured light camera;

[0051] Input the feature matrix into the data acquisition performance feature prediction model for training, set the loss function convergence threshold, and determine whether the loss function of the data acquisition performance feature prediction model converges to the loss function convergence threshold;

[0052] When the loss function of the data acquisition performance characteristic prediction model converges to the loss function convergence threshold, the model parameters of the data acquisition performance characteristic prediction model are saved, the training is completed, and the data acquisition performance characteristic prediction model is output.

[0053] It should be noted that the data acquisition performance change characteristic data includes clarity characteristic data, resolution characteristic data, etc., and the deep neural network includes recursive neural network, convolutional neural network, etc. The data acquisition performance characteristics of each structured light camera can be predicted by this method.

[0054] Furthermore, in the present method, the data acquisition performance change characteristic data of the structured light camera within a preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is predicted according to the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time, specifically:

[0055] Acquire data on changes in data acquisition performance characteristics of the structured light camera within a preset time, and input the data on changes in data acquisition performance characteristics of the structured light camera within the preset time into a data acquisition performance characteristics prediction model for prediction;

[0056] Through prediction, the data acquisition performance characteristic data of the structured light camera within the current preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is output.

[0057] like Figure 2 As shown, further, in this method, the data acquisition performance requirement information in the target area is obtained, and the relevant recommendation results are generated according to the data acquisition performance requirement information in the target area and the data acquisition performance characteristic data of the structured light camera within the current preset time, specifically including:

[0058] S202: acquiring data acquisition performance characteristic data of each structured light camera in the current timestamp according to the data acquisition performance characteristic data of the structured light camera within the current preset time, and randomly selecting a structured light camera for data acquisition to construct a structured light camera working set;

[0059] S204: Acquire data acquisition performance requirement information in the target area, and acquire data acquisition performance characteristic data of each structured light camera in the structured light camera working set according to the data acquisition performance characteristic data of each structured light camera in the current timestamp;

[0060] S206: Determine whether the data acquisition performance characteristic data of each structured light camera in the structured light camera working set are greater than the data acquisition performance requirement information in the target area. If so, output the structured light camera working set and generate relevant recommendation results.

[0061] S208: When the data acquisition performance characteristic data of each structured light camera in the structured light camera working set is not all greater than the data acquisition performance requirement information in the target area, the structured light camera working set is updated until all are greater than the data acquisition performance requirement information in the target area.

[0062] It should be noted that, through this method, a structured light camera that meets the requirements can be selected to collect data on the target area, thereby improving the rationality of data collection.

[0063] Furthermore, in the present method, environmental characteristic data within the target area is obtained, and data acquisition control of the structured light camera is performed according to the environmental characteristic data within the target area, specifically including:

[0064] The optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data are obtained through big data, and the optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data are input into the graph neural network;

[0065] Taking environmental feature data as the first graph node, taking the optimal working parameters of the structured light camera at the optimal data acquisition performance as the second graph node, connecting the first graph node with the second graph node, and constructing a topological structure graph;

[0066] Construct a knowledge graph, obtain the relevant adjacency matrix based on the topological structure graph, input the relevant adjacency matrix into the knowledge graph for representation, and obtain the environmental feature data within the target area;

[0067] The environmental feature data within the target area is input into the knowledge graph to obtain the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental feature data, and the structured light camera is controlled for data acquisition based on the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental feature data.

[0068] It should be noted that environmental characteristic data include temperature, humidity, visibility and other data. In different environmental data, different working parameters (such as laser type, laser wavelength, brightness, focal length, etc.) will result in inconsistent captured images or measured distances, and there will be errors. By storing the optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data in the knowledge graph, the optimal working parameters can be obtained for data collection.

[0069] Furthermore, in this method, the data acquisition method of the structured light camera also includes:

[0070] The image data information in the target area is collected by a structured light camera, and the pre-processed image data is obtained by filtering and denoising the image data information in the target area;

[0071] Collecting preprocessed image data within a time period, and obtaining a quality evaluation analysis result of each image by performing quality evaluation analysis on the preprocessed image data within a time period;

[0072] When the quality evaluation analysis result of the image is greater than the preset quality evaluation analysis result, the preprocessed image data is output;

[0073] When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the preprocessed image data is reconstructed.

[0074] It should be noted that quality evaluation analysis can be performed through decision tree algorithm, fuzzy clustering algorithm, support vector machine and other processing methods, where the quality evaluation analysis results include high quality, medium quality, low quality, etc., and the preset quality evaluation analysis results are set by the user or are image quality requirements, etc.

[0075] When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the preprocessed image data is reconstructed, specifically including:

[0076] When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the image data continuously collected within a time period is acquired, and the image data with the maximum quality score is acquired as the reference image data for reconstruction;

[0077] By segmenting the reconstructed reference image data, an image of a region whose quality score does not meet the requirements is obtained, and by segmenting each image data image continuously collected within a time period, a plurality of segmented images are obtained;

[0078] Acquire a segmented image that is greater than a preset quality evaluation analysis result, and calculate the Mahalanobis distance between the quality evaluation analysis result and an image of a region whose quality score does not meet the requirements;

[0079] A segmented image whose Mahalanobis distance is lower than a preset Mahalanobis distance threshold is obtained, and the segmented image whose Mahalanobis distance is lower than the preset Mahalanobis distance threshold is spliced ​​to the reconstructed reference image data, covering the regional image whose quality score does not meet the requirements.

[0080] It should be noted that, in fact, image acquisition is the continuous acquisition of the target object within a period, so as to select or synthesize the image. When acquiring the image, the image that can represent a time period is reconstructed by this method to improve the quality of the image, thereby improving the rationality of data acquisition.

[0081] Example 2

[0082] like Figure 3 As shown, the second aspect of the present invention provides a data acquisition device 4 for a structured light camera, comprising a memory 41 and a processor 42. The memory 41 includes a data acquisition method program for a structured light camera. When the data acquisition method program for a structured light camera is executed by the processor 42, the technical solution of embodiment 1 is implemented. Among them, it includes:

[0083] Acquire historical data acquisition performance change characteristic data of the structured light camera, and build a data acquisition performance characteristic prediction model based on the historical data acquisition performance change characteristic data of the structured light camera;

[0084] Acquire data on changes in data acquisition performance characteristics of the structured light camera within a preset time, and predict data acquisition performance characteristics of the structured light camera within a current preset time based on a data acquisition performance characteristics prediction model and the data acquisition performance change characteristics of the structured light camera within a preset time;

[0085] Obtaining data acquisition performance requirement information in the target area, and generating relevant recommendation results based on the data acquisition performance requirement information in the target area and data acquisition performance characteristic data of the structured light camera within the current preset time;

[0086] Data is collected based on the relevant recommendation results, and environmental feature data within the target area is obtained. Data collection of the structured light camera is controlled based on the environmental feature data within the target area.

[0087] It should be noted that the present invention recommends a structured light camera that meets the work requirements based on the data collection performance data of the structured light camera, so that the data collection of the structured light camera is more reasonable and the success rate of data collection is improved. Secondly, the present invention adjusts the optimal working parameters of the structured light camera according to changes in the environment, so that the data collection is more reasonable.

[0088] Furthermore, in the present system, historical data acquisition performance change characteristic data of the structured light camera is obtained, and a data acquisition performance characteristic prediction model is constructed based on the historical data acquisition performance change characteristic data of the structured light camera, specifically including:

[0089] Obtain historical data acquisition performance change characteristic data of the structured light camera, build a data acquisition performance characteristic prediction model based on a deep neural network, and build a feature matrix based on the historical data acquisition performance change characteristic data of the structured light camera;

[0090] Input the feature matrix into the data acquisition performance feature prediction model for training, set the loss function convergence threshold, and determine whether the loss function of the data acquisition performance feature prediction model converges to the loss function convergence threshold;

[0091] When the loss function of the data acquisition performance characteristic prediction model converges to the loss function convergence threshold, the model parameters of the data acquisition performance characteristic prediction model are saved, the training is completed, and the data acquisition performance characteristic prediction model is output.

[0092] It should be noted that the data acquisition performance change characteristic data includes clarity characteristic data, resolution characteristic data, etc., and the deep neural network includes recursive neural network, convolutional neural network, etc. The data acquisition performance characteristics of each structured light camera can be predicted by this method.

[0093] Furthermore, in the present system, the data acquisition performance change characteristic data of the structured light camera within a preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is predicted according to the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time, specifically:

[0094] Acquire data on changes in data acquisition performance characteristics of the structured light camera within a preset time, and input the data on changes in data acquisition performance characteristics of the structured light camera within the preset time into a data acquisition performance characteristics prediction model for prediction;

[0095] Through prediction, the data acquisition performance characteristic data of the structured light camera within the current preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is output.

[0096] Furthermore, in the present system, the data acquisition performance requirement information in the target area is obtained, and the relevant recommendation results are generated according to the data acquisition performance requirement information in the target area and the data acquisition performance characteristic data of the structured light camera within the current preset time, specifically including:

[0097] According to the data acquisition performance characteristic data of the structured light camera within the current preset time, the data acquisition performance characteristic data of each structured light camera in the current timestamp is obtained, and the structured light camera is randomly selected for data acquisition to construct a structured light camera working set;

[0098] Acquire data acquisition performance requirement information in the target area, and acquire data acquisition performance characteristic data of each structured light camera in the structured light camera working set according to the data acquisition performance characteristic data of each structured light camera in the current timestamp;

[0099] Determine whether the data acquisition performance characteristic data of each structured light camera in the structured light camera working set are greater than the data acquisition performance requirement information in the target area. If they are greater, output the structured light camera working set and generate relevant recommendation results;

[0100] When the data acquisition performance characteristic data of each structured light camera in the structured light camera working set is not all greater than the data acquisition performance requirement information in the target area, the structured light camera working set is updated until all are greater than the data acquisition performance requirement information in the target area.

[0101] It should be noted that, through this method, a structured light camera that meets the requirements can be selected to collect data on the target area, thereby improving the rationality of data collection.

[0102] Furthermore, in the present system, environmental characteristic data within the target area is obtained, and data acquisition control of the structured light camera is performed according to the environmental characteristic data within the target area, specifically including:

[0103] The optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data are obtained through big data, and the optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data are input into the graph neural network;

[0104] Taking environmental feature data as the first graph node, taking the optimal working parameters of the structured light camera at the optimal data acquisition performance as the second graph node, connecting the first graph node with the second graph node, and constructing a topological structure graph;

[0105] Construct a knowledge graph, obtain the relevant adjacency matrix based on the topological structure graph, input the relevant adjacency matrix into the knowledge graph for representation, and obtain the environmental feature data within the target area;

[0106] The environmental feature data within the target area is input into the knowledge graph to obtain the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental feature data, and the structured light camera is controlled for data acquisition based on the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental feature data.

[0107] It should be noted that environmental characteristic data include temperature, humidity, visibility and other data. In different environmental data, different working parameters (such as laser type, laser wavelength, brightness, focal length, etc.) will result in inconsistent captured images or measured distances, and there will be errors. By storing the optimal working parameters of the structured light camera with the optimal data acquisition performance under each environmental characteristic data in the knowledge graph, the optimal working parameters can be obtained for data collection.

[0108] Furthermore, in this system, the data acquisition method of the structured light camera also includes:

[0109] The image data information in the target area is collected by a structured light camera, and the pre-processed image data is obtained by filtering and denoising the image data information in the target area;

[0110] Collecting preprocessed image data within a time period, and obtaining a quality evaluation analysis result of each image by performing quality evaluation analysis on the preprocessed image data within a time period;

[0111] When the quality evaluation analysis result of the image is greater than the preset quality evaluation analysis result, the preprocessed image data is output;

[0112] When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the preprocessed image data is reconstructed.

[0113] It should be noted that quality evaluation analysis can be performed through decision tree algorithm, fuzzy clustering algorithm, support vector machine and other processing methods, where the quality evaluation analysis results include high quality, medium quality, low quality, etc., and the preset quality evaluation analysis results are set by the user or are image quality requirements, etc.

[0114] Example 3

[0115] A third aspect of the present invention provides an electronic device, including a data acquisition method program for a structured light camera. When the data acquisition method program for the structured light camera is executed by a processor, the technical solution of embodiment 1 is implemented.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0117] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0119] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0120] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0121] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A data acquisition method for a structured light camera, characterized in that: The following steps are involved: Acquire historical data acquisition performance change characteristic data of the structured light camera, and construct a data acquisition performance characteristic prediction model based on the historical data acquisition performance change characteristic data of the structured light camera; Acquire data on changes in data acquisition performance characteristics of the structured light camera within a preset time, and predict data acquisition performance characteristics of the structured light camera within a current preset time based on the data acquisition performance characteristics prediction model and the data acquisition performance changes in the structured light camera within a preset time; Obtaining data acquisition performance requirement information in the target area, and generating relevant recommendation results based on the data acquisition performance requirement information in the target area and data acquisition performance characteristic data of the structured light camera within the current preset time; Data collection is performed according to the relevant recommendation results, and environmental feature data within the target area is obtained, and data collection control of the structured light camera is performed according to the environmental feature data within the target area.

2. The data acquisition method of a structured light camera according to claim 1, characterized in that: Acquiring historical data acquisition performance change characteristic data of the structured light camera, and building a data acquisition performance characteristic prediction model based on the historical data acquisition performance change characteristic data of the structured light camera, specifically including: Acquire historical data acquisition performance change characteristic data of the structured light camera, build a data acquisition performance characteristic prediction model based on a deep neural network, and build a characteristic matrix according to the historical data acquisition performance change characteristic data of the structured light camera; Inputting the feature matrix into the data acquisition performance feature prediction model for training, setting a loss function convergence threshold, and determining whether the loss function of the data acquisition performance feature prediction model converges to the loss function convergence threshold; When the loss function of the data acquisition performance characteristic prediction model converges to a loss function convergence threshold, the model parameters of the data acquisition performance characteristic prediction model are saved, the training ends, and the data acquisition performance characteristic prediction model is output.

3. The data acquisition method of a structured light camera according to claim 1, characterized in that: Acquire data acquisition performance change characteristic data of the structured light camera within a preset time, and predict data acquisition performance characteristic data of the structured light camera within the current preset time according to the data acquisition performance characteristic prediction model and the data acquisition performance change characteristic data of the structured light camera within the preset time, specifically: Acquire data on changes in data acquisition performance characteristics of a structured light camera within a preset time, and input the data on changes in data acquisition performance characteristics of the structured light camera within the preset time into the data acquisition performance characteristics prediction model for prediction; By prediction, data acquisition performance characteristic data of the structured light camera within the current preset time is obtained, and the data acquisition performance characteristic data of the structured light camera within the current preset time is output.

4. The data acquisition method of a structured light camera according to claim 1, characterized in that: Obtain the data acquisition performance requirement information in the target area, and generate relevant recommendation results based on the data acquisition performance requirement information in the target area and the data acquisition performance characteristic data of the structured light camera within the current preset time, including: According to the data acquisition performance characteristic data of the structured light camera within the current preset time, the data acquisition performance characteristic data of each structured light camera in the current timestamp is acquired, and a structured light camera is randomly selected for data acquisition to construct a structured light camera working set; Acquire data acquisition performance requirement information in the target area, and acquire data acquisition performance characteristic data of each structured light camera in the structured light camera working set according to the data acquisition performance characteristic data of each structured light camera in the current timestamp; Determine whether the data acquisition performance characteristic data of each structured light camera in the structured light camera working set are greater than the data acquisition performance requirement information in the target area, and if so, output the structured light camera working set and generate relevant recommendation results; When the data acquisition performance characteristic data of each structured light camera in the structured light camera working set is not all greater than the data acquisition performance requirement information in the target area, the structured light camera working set is updated until all are greater than the data acquisition performance requirement information in the target area.

5. The data acquisition method of a structured light camera according to claim 1, characterized in that: Acquiring environmental feature data within the target area, and performing data acquisition control on the structured light camera according to the environmental feature data within the target area, specifically including: Obtaining optimal working parameters of the structured light camera with optimal data acquisition performance under each environmental feature data through big data, and inputting the optimal working parameters of the structured light camera with optimal data acquisition performance under each environmental feature data into the graph neural network; Taking environmental feature data as a first graph node, taking optimal working parameters of the structured light camera at optimal data acquisition performance as a second graph node, connecting the first graph node with the second graph node to construct a topological structure graph; Construct a knowledge graph, obtain a related adjacency matrix based on the topological structure graph, input the related adjacency matrix into the knowledge graph for representation, and obtain environmental feature data within the target area; The environmental characteristic data within the target area is input into the knowledge graph to obtain the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental characteristic data, and the structured light camera is controlled for data acquisition according to the optimal working parameters of the structured light camera with optimal data acquisition performance under the current environmental characteristic data.

6. The data acquisition method of a structured light camera according to claim 1, characterized in that: Also includes: Collecting image data information in the target area by using a structured light camera, and obtaining pre-processed image data by filtering and denoising the image data information in the target area; Collecting preprocessed image data within a time period, and obtaining a quality evaluation analysis result of each image by performing quality evaluation analysis on the preprocessed image data within the time period; When the quality evaluation analysis result of the image is greater than the preset quality evaluation analysis result, outputting the preprocessed image data; When the quality evaluation analysis result of the image is not greater than the preset quality evaluation analysis result, the preprocessed image data is reconstructed.

7. A data acquisition device for a structured light camera, characterized in that: It comprises a memory and a processor, wherein the memory comprises a data acquisition method program for a structured light camera, and when the data acquisition method program for the structured light camera is executed by the processor, the steps of the data acquisition method for the structured light camera as described in any one of claims 1 to 6 are implemented.

8. An electronic device, characterized in that: It comprises a data acquisition method program for a structured light camera, and when the data acquisition method program for the structured light camera is executed by a processor, the steps of the data acquisition method for the structured light camera according to any one of claims 1 to 6 are implemented.

Images