Space detection positioning method and device, electronic equipment and readable storage medium
By performing multiple image processing and deep learning analysis in compound eye detectors, the problem of poor image quality in the prior art is solved, and the detection accuracy and effect are significantly improved.
Patent Information
- Application Number
- CN202411248361.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2025-06-03
AI Technical Summary
Existing compound eye detection methods cannot effectively process acquired images, resulting in poor image quality and affecting the asteroid detection effect.
Image feature information is extracted by controlling image capture, multiple image processing, and network segmentation methods in the compound eye detector, and deep learning algorithms are used for deep learning analysis to determine the parameter information and spatial location of the detection object.
It significantly improves the image quality and accuracy of the compound eye detector, improves the capture accuracy and positioning accuracy of the detection target, and enhances the effect of asteroid detection.
Smart Images
Figure CN120088662A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of spatial positioning, and particularly to a spatial detection and positioning method, device, electronic device and readable storage medium. Background Art
[0002] As the main technical means for asteroid positioning, a deep space exploration radar can effectively improve the orbit determination accuracy of asteroids and obtain high-resolution topographies of asteroids. The existing compound eye detection method cannot effectively process the acquired images, resulting in poor image quality and affecting the asteroid detection effect. Summary of the Invention
[0003] In order to solve the above technical problems, embodiments of the present application provide a spatial detection and positioning method, device, electronic device and readable storage medium capable of accurately positioning a detection target. The specific solutions are as follows: In a first aspect, embodiments of the present application provide a spatial detection and positioning method, which is applied to a compound eye detector and includes: Controlling the compound eye detector to capture a scene image according to preset detection parameters; Performing preset image processing on the scene image to obtain a target image, where the preset image processing includes denoising processing, contrast adjustment processing, superposition processing, and local pixel adjustment processing; Extracting image feature information in the target image based on a network segmentation method; Performing deep learning on the extraction process of the image feature information by using a preset deep learning algorithm; Analyzing the image feature information to determine parameter information of the detection object and position information of the detection object in space.
[0004] According to a specific implementation manner of embodiments of the present application, the controlling the compound eye detector to capture a scene image according to preset detection parameters includes: Obtaining preset detection parameters, where the preset detection parameters include a detection target, a detection area, and a detection time; Adjusting the compound eye lens array in the compound eye detector according to the preset detection parameters, where the adjustment parameters of the compound eye lens array include the number of compound eye lens arrays, the diameter of the compound eye lens array, and the spacing of the compound eye lens arrays; Performing image capture processing based on the adjusted compound eye detector, and converting the optical information captured by each compound eye lens array into the scene image.
[0005] According to a specific implementation manner of embodiments of the present application, the performing preset image processing on the scene image to obtain a target image includes: Denoise the scene images collected by each compound eye lens array of the compound eye detector to obtain a plurality of denoised images; Adjust the contrast of each of the denoised images to obtain a plurality of intermediate images; Superimpose each of the intermediate images to obtain an integrated image; Perform local pixel adjustment processing on the integrated image to obtain the target image.
[0006] According to a specific implementation manner of an embodiment of the present application, the extracting the image feature information from the target image based on the network segmentation method includes: Segment the target image according to a preset grid specification to obtain a plurality of sub-images; Extract features from each sub-image to obtain the image feature information.
[0007] According to a specific implementation manner of an embodiment of the present application, the preset grid specification is 6*6, 7*7 or 8*8.
[0008] According to a specific implementation manner of an embodiment of the present application, the performing deep learning on the extraction process of the image feature information by using a preset deep learning algorithm includes: Perform deep learning on the extraction process of the image feature information by using any one of a convolutional neural network, a recurrent neural network, and a long short-term memory network.
[0009] According to a specific implementation manner of an embodiment of the present application, after performing deep learning on the extraction process of the image feature information by using a preset deep learning algorithm, the method further includes: Perform a performance test on the space detection and positioning system of the compound eye detector to obtain target performance parameters, where the target performance parameters include the maximum detection distance, the maximum detection angle, and the shortest response time; Evaluate the space detection and positioning system of the compound eye detector based on the target performance parameters and forward the evaluation result to a preset terminal.
[0010] In a second aspect, an embodiment of the present application provides a space detection and positioning device, which is applied to a compound eye detector and includes: An image capture module, configured to control the compound eye detector to capture a scene image according to preset detection parameters; An image processing module, configured to perform preset image processing on the scene image to obtain a target image, where the preset image processing includes denoising processing, contrast adjustment processing, superimposing processing, and local pixel adjustment processing; A feature extraction module, configured to extract image feature information from the target image based on the network segmentation method; A deep learning module for performing deep learning on the extraction process of the image feature information using a preset deep learning algorithm; A feature analysis module for analyzing the image feature information to determine the parameter information of the detection object and the position information of the detection object in space.
[0011] In a third aspect, an embodiment of the present application provides an electronic device, which includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the space detection and positioning method in the foregoing first aspect or any implementation manner of the first aspect.
[0012] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions for causing the computer to execute the space detection and positioning method in the foregoing first aspect or any implementation manner of the first aspect.
[0013] In summary, this embodiment provides a space detection and positioning method, device, electronic device, and readable storage medium, which are applied to a compound eye detector and include: controlling the compound eye detector to capture a scene image according to preset detection parameters; performing preset image processing on the scene image to obtain a target image, where the preset image processing includes denoising processing, contrast adjustment processing, superimposing processing, and local pixel adjustment processing; extracting image feature information in the target image based on the network segmentation method; performing deep learning on the extraction process of the image feature information using a preset deep learning algorithm; analyzing the image feature information to determine the parameter information of the detection object and the position information of the detection object in space. The present invention effectively improves the image quality collected by the compound eye detector through multiple preprocessings of the scene image collected by the compound eye detector, and further improves the detection accuracy of the compound eye detector. Description of the Drawings
[0014] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0015] Figure 1 It is a schematic diagram of an application scenario of a space detection and positioning method provided by an embodiment of the present application; Figure 2Schematic flowchart of a space detection and positioning method provided by an embodiment of the present application; Figure 3 Schematic flowchart of the steps for capturing a scene image provided by an embodiment of the present application; Figure 4 Schematic flowchart of the steps for performing preset image processing on a scene image provided by an embodiment of the present application; Figure 5 Schematic flowchart of the steps for extracting image feature information from a target image provided by an embodiment of the present application; Figure 6 Schematic flowchart of the steps for performing performance testing on a space detection and positioning system provided by an embodiment of the present application; Figure 7 Schematic diagram of the device modules of a space detection and positioning device provided by an embodiment of the present application. Detailed implementation manners
[0016] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.
[0017] The following uses specific specific examples to illustrate the implementation manners of the present disclosure. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts fall within the scope of protection of the present disclosure.
[0018] It should be noted that the following describes various aspects of the embodiments within the scope of the appended claims. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. In addition, this device can be implemented and this method can be practiced using other structures and / or functions in addition to one or more of the aspects described herein.
[0019] It should also be noted that the illustrations provided in the following embodiments only schematically illustrate the basic concept of the present disclosure. The diagrams only show the components related to the present disclosure, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in its actual implementation can be arbitrarily changed, and the component layout type may also be more complex.
[0020] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.
[0021] As described in the foregoing background art section, the deep space exploration radar, as a key technology for asteroid impact defense, can greatly improve the asteroid orbit determination accuracy and obtain the high-resolution morphology of asteroids. The compound eye detector, as a deep space exploration radar, is of great significance in the problem of asteroid impact defense.
[0022] The existing space detection and positioning methods applied to compound eye detectors have the problems of inaccurate detection target positioning and low accuracy. There is an urgent need for a space detection and positioning method that can effectively improve the capture accuracy and positioning accuracy of detection targets.
[0023] The space detection and positioning method provided in the embodiments of the present application can be applied to the Figure 1 application environment shown. Among them, the compound eye detector 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. Among them, the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.
[0024] In the compound eye detector 102 in this embodiment, a space detection and positioning system for implementing the space detection and positioning method is carried. The compound eye detector 102 at least includes a compound eye lens array (sub-eye), an image sensor, a central processor, and a data memory. In this embodiment, the compound eye lens array is an optical element composed of a combination of multiple small lenses, which can be used to obtain images of space scenes. It should be noted that the compound eye lens array can also be called a compound eye sub-eye, a side-eye camera, etc. The image sensor is a device that converts optical signals into electrical signals. By capturing photons and converting them into electronic signals, digital images are generated. In actual application scenarios, the compound eye detector can capture optical signals through the compound eye sub-eye, convert the optical signals into electrical signals through the image sensor, and generate digital images to obtain the target scene images to be captured.
[0025] Refer to Figure 2, an embodiment of the present application provides a space detection and positioning method. Taking the compound eye detector shown in Figure 1 as an example, the method includes the following steps: S201, controlling the compound eye detector to capture a scene image according to preset detection parameters.
[0026] In this embodiment, a corresponding space detection and positioning system is installed in the compound eye detector. The system automatically starts after the compound eye detector is powered on, and starts a corresponding self-check program to check whether each hardware in the compound eye detector can work normally. After determining that there is no abnormality in the hardware of the compound eye detector, it performs adaptive adjustment based on the preset detection parameters.
[0027] The preset detection parameters in this embodiment include detection targets, detection areas, detection times, etc. The acquisition of the preset detection parameters can be set by the user on the control interface of the corresponding compound eye detector, or can be automatically called by the compound eye detector in the data storage or server. This embodiment does not limit the setting method of the preset detection parameters. Among them, the detection target refers to the target object that needs to be detected and positioned in the current space detection and positioning process. The detection area refers to the space area that needs to be detected in the current space detection and positioning process. The detection time refers to the execution time of the current space detection and positioning process.
[0028] The scene image refers to the image corresponding to the space area specified by the preset detection parameters. After completing the self-check program and debugging program of the compound eye detector in this embodiment, controlling the compound eye detector to perform image capture processing according to the preset detection parameters can obtain the corresponding scene image.
[0029] It should be noted that the scene image in this embodiment can be a single image or multiple images, and can be specifically determined according to the specific debugging program for image capture processing of the compound eye detector. In actual application, the scene images captured by the compound eye detector are usually multiple images, and each scene image corresponds to a compound eye sub-eye.
[0030] S202, performing preset image processing on the scene image to obtain a target image, where the preset image processing includes denoising processing, contrast adjustment processing, superimposing processing, and local pixel adjustment processing.
[0031] In this embodiment, after obtaining the scene image collected by the compound eye detector, multiple image processing will be performed on the scene image, including but not limited to denoising processing, contrast adjustment processing, superimposing processing, and local pixel adjustment processing.
[0032] Among them, the denoising process is used to remove the noise in the original scene image collected by the compound eye detector, so as to improve the image quality and clarity, prevent noise from interfering with subsequent feature extraction of the scene image, and improve the accuracy of feature extraction. In the actual application scenario, the scene image may be affected by noise during the processes of capture, conversion, and transmission processing. The noise may come from the image sensor in the compound eye detector, the external environment, or the image processing algorithm, etc.
[0033] The contrast adjustment process is used to adjust the brightness difference degree between the brightest part and the darkest part in the scene image, so as to improve the image quality and visual effect. It should be noted that in this embodiment, the contrast adjustment process adjusts the scene image according to the maximum ratio without affecting the detailed features of the scene image, so that the levels in the scene image are more distinct and the detailed features can be more prominent.
[0034] The superposition process is used to integrate the scene images obtained by multiple compound eye sub-eyes, so as to facilitate the subsequent feature extraction steps.
[0035] The local pixel adjustment process is used to adjust the pixel values of a specific area in the scene image. The pixel value adjustment includes but is not limited to brightness adjustment, contrast adjustment, and color adjustment. In this embodiment, the local area corresponding to the local pixel adjustment process can be an area adaptively set by the user according to the specific situation of the collected target image. The local area corresponding to the local pixel adjustment process can also be a specified area in the integrated scene image. For example, the specified area can be the center area or the edge area of the image.
[0036] S203, extract the image feature information in the target image based on the network segmentation method.
[0037] In this embodiment, the specific execution method of the grid separation method is to place the target image in a grid divided according to a preset grid specification, so as to divide the target image into multiple sub-images, where the grid images corresponding to each sub-image are the same.
[0038] Extract the corresponding image feature information from the corresponding sub-images according to the preset feature extraction algorithm, so as to realize the acquisition of the image feature information corresponding to the target image. It should be noted that the preset feature extraction process in this embodiment includes but is not limited to any one or more of color feature extraction, texture feature extraction, shape feature extraction scale-invariant feature transform, and convolutional neural network feature extraction.
[0039] In this embodiment, by splitting the target image into multiple sub-images, the accuracy of feature information extraction for the target image can be effectively improved, and the calculation amount of processing the image by each feature extraction algorithm can be reduced.
[0040] S204. Deeply learn the process of extracting image feature information using a preset deep learning algorithm.
[0041] In this embodiment, the process of extracting image feature information needs to further perform deep learning using a deep learning algorithm to improve the feature extraction accuracy of the next image feature information extraction process. In addition, when performing image feature extraction in this embodiment, the image feature information includes corresponding neural network information.
[0042] By introducing a deep learning algorithm in the space detection and positioning process of the compound eye detector in this embodiment, the detection accuracy and detection efficiency for the detection target can be greatly improved, and the actual application effect of the compound eye detector can be enhanced.
[0043] S205. Analyze the image feature information to determine the parameter information of the detection object and the position information of the detection object in space.
[0044] In this embodiment, after obtaining the image feature information, by comparing and analyzing the image feature information, the object type and object-related parameters of the detection object can be accurately detected, and the position information of the detection object in space can be effectively calculated to achieve precise positioning.
[0045] Among them, the parameter information of the detection object includes but is not limited to type information, size information, and running trajectory information, etc. The position information includes but is not limited to the position coordinates of the detection object in the corresponding space, etc.
[0046] In summary, this embodiment provides a space detection and positioning method. By performing multiple preprocessings on the scene image collected by the compound eye detector during the target detection and target positioning processes of the compound eye detector, the quality and accuracy of the scene image are improved, thereby effectively improving the accuracy of the compound eye detector for target detection and target positioning. And by introducing a deep learning algorithm in the feature extraction process of the scene image in this embodiment, the processing effect and processing efficiency of the feature extraction process can be greatly improved, effectively enhancing the detection efficiency and positioning efficiency of the compound eye detector, and completing a higher-quality detection and positioning step.
[0047] In one embodiment, as Figure 3 shown, controlling the compound eye detector to capture a scene image according to preset detection parameters includes: S301. Obtain preset detection parameters, where the preset detection parameters include a detection target, a detection area, and a detection time.
[0048] S302. Debug the compound eye lens array in the compound eye detector according to the preset detection parameters, where the adjustment parameters of the compound eye lens array include the number of compound eye lens arrays, the diameter of the compound eye lens array, and the spacing of the compound eye lens arrays.
[0049] S303. Based on the adjusted compound eye detector, perform image capture processing to convert the optical information captured by each compound eye lens array into a scene image.
[0050] In this embodiment, the specific description of the preset detection parameters can refer to the specific implementation manners in the foregoing embodiments, and will not be elaborated herein one by one.
[0051] In a specific embodiment, by debugging the number of compound eye lens arrays, the adjustment of the field of view angle of the compound eye detector can be achieved. By debugging the diameter of the compound eye lens arrays, the adjustment of the light passing brightness and resolution of the compound eye detector can be achieved. By adjusting the arrangement spacing of the compound eye lens arrays, the adjustment of the spatial resolution and angular resolution of the compound eye detector can be achieved.
[0052] In an actual application scenario, after determining the preset detection parameters, the compound eye detector can automatically complete the debugging of the compound eye lens arrays, such as starting the corresponding number of compound eye lens arrays, adjusting the diameter and arrangement spacing of the compound eye lens arrays. It should be noted that the compound eye lens arrays in the compound eye detector in this embodiment are arranged on corresponding movable devices to achieve automatic adjustment. The debugging steps of each compound eye lens array of the compound eye detector can also be completed manually, and can be adaptively adjusted according to the needs of the actual application scenario.
[0053] After completing the debugging process of the compound eye detector, it is possible to control each compound eye lens array of the compound eye detector to capture the incident light in the target detection area, and the image sensor converts the captured optical fiber information into an electrical signal, thereby obtaining the corresponding scene image.
[0054] According to a specific implementation manner of an embodiment of the present application, as Figure 4 shown, perform preset image processing on the scene image to obtain a target image, including: S401. Perform denoising processing on the scene images collected by each compound eye lens array of the compound eye detector to obtain a plurality of denoised images.
[0055] S402. Perform contrast adjustment processing on each denoised image to obtain a plurality of intermediate images.
[0056] S403. Perform superposition processing on each intermediate image to obtain an integrated image.
[0057] S404. Perform local pixel adjustment processing on the integrated image to obtain a target image.
[0058] In this embodiment, when the compound eye detector collects a scene image, at least two compound eye lens arrays are defaultly started for image capture to improve the accuracy of spatial detection and positioning.
[0059] The specific implementation manners of the denoising process, contrast adjustment process, superposition process, and local pixel adjustment process in steps S401 - S104 can refer to the descriptions in the foregoing embodiments, and will not be elaborated herein.
[0060] According to a specific implementation manner of an embodiment of the present application, as Figure 5 shown, to extract image feature information in a target image based on a network segmentation method, it includes: S501, perform image segmentation on the target image according to a preset grid specification to obtain a plurality of sub - images; S502, perform feature extraction on each sub - image to obtain image feature information.
[0061] Specifically, the preset grid specification is 6*6, 7*7, or 8*8.
[0062] In this embodiment, the grid specification for performing image segmentation on the target image can be configured as any one of 6*6, 7*7, or 8*8. By performing image segmentation on the target image with a fixed grid specification in this embodiment, while ensuring the accuracy of feature information collection, it is convenient for further optimization of the image feature information extraction process by deep learning methods, so as to maximize the accuracy and efficiency of the image feature extraction process.
[0063] According to a specific implementation manner of an embodiment of the present application, perform deep learning on the extraction process of image feature information by using a preset deep learning algorithm, including: Use any one of the deep learning algorithms of convolutional neural network, recurrent neural network, and long short - term memory network to perform deep learning on the extraction process of image feature information.
[0064] In this embodiment, a convolutional neural network (Convolutional Neural Networks, abbreviated as CNNs) includes corresponding convolutional layers (Convolutional Layer), activation function layers (Activation Layer), pooling layers (PoolingLayer), and fully - connected layers (Fully Connected Layer), etc., and can be used to perform multiple steps such as image recognition, image classification, image segmentation, and image feature extraction processing.
[0065] A recurrent neural network (Recurrent Neural Network, abbreviated as RNN) includes an input layer, a hidden layer, and an output layer, etc., and can be used to extract features from images and video sequences.
[0066] The Long Short-Term Memory (LSTM) network, a special variant of the Recurrent Neural Network (RNN), can address the long-term dependency problem faced by traditional RNNs when dealing with long sequence data. LSTM is also used for feature extraction from images and video sequences.
[0067] In this embodiment, by introducing a deep learning algorithm in the feature information extraction step, it is possible to optimize the next feature information extraction process after each execution of the feature information extraction step, so as to improve the accuracy and efficiency of the spatial detection and positioning of the compound eye detector.
[0068] According to a specific implementation manner of the embodiment of the present application, after performing deep learning on the extraction process of image feature information using a preset deep learning algorithm, the spatial detection and positioning method further includes: S601, perform a performance test on the spatial detection and positioning system of the compound eye detector to obtain target performance parameters, where the target performance parameters include the maximum detection distance, the maximum detection angle, and the shortest response time; S602, evaluate the spatial detection and positioning system of the compound eye detector based on the target performance parameters, and forward the evaluation result to a preset terminal.
[0069] In this embodiment, after the compound eye detector completes a spatial detection and positioning process, it is possible to perform a performance test on the spatial detection and positioning system carried on the compound eye detector to master various performance parameters of the compound eye detector, including but not limited to the maximum detection distance, the maximum detection angle, and the shortest response time, etc., so that in the next spatial detection and positioning process, the detection parameters can be determined more accurately.
[0070] In this embodiment, the evaluation result of the spatial detection and positioning system will be sent to a preset terminal to facilitate the user to timely master the real-time performance of the spatial detection and positioning system of the compound eye detector. Among them, the preset terminal can be any terminal such as a mobile terminal, a computer terminal, or a tablet terminal, and the specific type of the preset terminal is not limited in this embodiment and can be configured according to the needs of the actual application scenario.
[0071] In summary, this embodiment provides a spatial detection and positioning method. By performing multiple preprocessings on the scene images collected by the compound eye detector during the target detection and target positioning processes of the compound eye detector, the quality and accuracy of the scene images are improved, thereby effectively improving the accuracy of the compound eye detector for target detection and target positioning. And in this embodiment, a deep learning algorithm is introduced in the feature extraction process of the scene images, which can greatly improve the processing effect and processing efficiency of the feature extraction process, effectively improve the detection efficiency and positioning efficiency of the compound eye detector, and complete a higher-quality detection and positioning step.
[0072] Based on the same inventive concept, an embodiment of the present application further provides a space detection and positioning device for implementing the space detection and positioning method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the space detection and positioning device provided below can refer to the limitations on the space detection and positioning method in the above text, and will not be repeated here.
[0073] In one embodiment, referring to Figure 7 , this embodiment further provides a space detection and positioning device 700, including: an image capture module 710, an image processing module 720, a feature extraction module 730, a deep learning module 740, and a feature analysis module 750, where: The image capture module 710 is configured to control the compound eye detector to capture a scene image according to preset detection parameters; The image processing module 720 is configured to perform preset image processing on the scene image to obtain a target image, where the preset image processing includes denoising processing, contrast adjustment processing, superimposing processing, and local pixel adjustment processing; The feature extraction module 730 is configured to extract image feature information in the target image based on the network segmentation method; The deep learning module 740 is configured to perform deep learning on the extraction process of the image feature information by using a preset deep learning algorithm; The feature analysis module 750 is configured to analyze the image feature information to determine the parameter information of the detection object and the position information of the detection object in space.
[0074] In one of the embodiments, the image capture module 710 is specifically configured to obtain preset detection parameters, where the preset detection parameters include a detection target, a detection area, and a detection time; debug the compound eye lens array in the compound eye detector according to the preset detection parameters, where the adjustment parameters of the compound eye lens array include the number of compound eye lens arrays, the diameter of the compound eye lens array, and the spacing of the compound eye lens arrays; perform image capture processing based on the adjusted compound eye detector, and convert the optical information captured by each compound eye lens array into the scene image.
[0075] In one of the embodiments, the image processing module 720 is specifically configured to perform denoising processing on the scene images collected by each compound eye lens array of the compound eye detector to obtain a plurality of denoised images; perform contrast adjustment processing on each of the denoised images to obtain a plurality of intermediate images; perform superimposing processing on each of the intermediate images to obtain an integrated image; perform local pixel adjustment processing on the integrated image to obtain the target image.
[0076] In one embodiment, the feature extraction module 730 is specifically configured to perform image segmentation on the target image according to a preset grid specification to obtain a plurality of sub-images; and extract features from each sub-image to obtain the image feature information.
[0077] In one embodiment, the deep learning module 740 is specifically configured to perform deep learning on the extraction process of the image feature information by using any one of deep learning algorithms such as a convolutional neural network, a recurrent neural network, and a long short-term memory network.
[0078] In one embodiment, the space detection and positioning device further includes: An evaluation module, configured to perform performance testing on the space detection and positioning system of the compound eye detector to obtain target performance parameters, where the target performance parameters include the maximum detection distance, the maximum detection angle, and the shortest response time; evaluate the space detection and positioning system of the compound eye detector based on the target performance parameters, and forward the evaluation result to a preset terminal.
[0079] In summary, this embodiment provides a space detection and positioning device. By performing multiple preprocessings on the scene image collected by the compound eye detector during the target detection and target positioning processes of the compound eye detector, the quality and accuracy of the scene image are improved, thereby effectively improving the accuracy of the compound eye detector in target detection and target positioning. And in this embodiment, a deep learning algorithm is introduced in the feature extraction process of the scene image, which can greatly improve the processing effect and processing efficiency of the feature extraction process, effectively improve the detection efficiency and positioning efficiency of the compound eye detector, and complete higher-quality detection and positioning steps.
[0080] Figure 7 The specific implementation manner of the shown device may refer to the specific implementation manner in the foregoing method embodiment, and will not be elaborated herein.
[0081] In addition, an embodiment of the present application further provides an electronic device, where the electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the space detection and positioning method in the foregoing method embodiment.
[0082] It should be noted that the electronic device in this embodiment may be a compound eye detector device, or other electronic devices equipped with or connected to the compound eye detector device.
[0083] An embodiment of the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the space detection and positioning method in the foregoing method embodiment.
[0084] The electronic device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.
[0085] It should be noted that the computer-readable medium in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. Examples of computer-readable storage media may include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above.
[0086] In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0087] The above computer-readable medium may be included in the above electronic device; or it may exist separately without being assembled into the electronic device.
[0088] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: obtain at least two Internet protocol addresses; send a node evaluation request including the at least two Internet protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet protocol address from the at least two Internet protocol addresses and returns it; receive the Internet protocol address returned by the node evaluation device; wherein the obtained Internet protocol addresses indicate edge nodes in a content delivery network.
[0089] Alternatively, the above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet protocol addresses; select an Internet protocol address from the at least two Internet protocol addresses; return the selected Internet protocol address; wherein the received Internet protocol addresses indicate edge nodes in a content delivery network.
[0090] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
[0092] The units involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".
[0093] It should be understood that the various parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.
[0094] As described above, the above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present disclosure should be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.
Claims
1. A spatial detection and positioning method, characterized in that: Applied to a compound eye detector, including: Controlling the compound eye detector to capture scene images according to preset detection parameters; Performing preset image processing on the scene image to obtain a target image, wherein the preset image processing includes denoising processing, contrast adjustment processing, overlay processing, and local pixel adjustment processing; Extracting image feature information from the target image based on a network segmentation method; Using a preset deep learning algorithm to perform deep learning on the process of extracting the image feature information; The image feature information is analyzed to determine parameter information of the detected object and position information of the detected object in space.
2. The method according to claim 1, characterized in that The controlling the compound eye detector to capture the scene image according to the preset detection parameters includes: Acquiring preset detection parameters, wherein the preset detection parameters include detection target, detection area and detection time; Debugging the compound eye lens array in the compound eye detector according to the preset detection parameters, wherein the adjustment parameters of the compound eye lens array include the number of compound eye lens arrays, the diameter of the compound eye lens array, and the spacing of the compound eye lens array; Image capture processing is performed based on the adjusted compound eye detector to convert the optical information captured by each compound eye lens array into the scene image.
3. The method according to claim 2, characterized in that The step of performing preset image processing on the scene image to obtain a target image includes: Performing denoising processing on scene images collected by each compound eye lens array of the compound eye detector to obtain a plurality of denoised images; Performing contrast adjustment processing on each of the denoised images to obtain a plurality of intermediate images; Performing a superposition process on the intermediate images to obtain an integrated image; Performing local pixel adjustment processing on the integrated image to obtain the target image.
4. The method according to claim 1, characterized in that: The extracting of image feature information in the target image based on the network segmentation method includes: Segmenting the target image according to a preset grid specification to obtain a plurality of sub-images; Feature extraction is performed on each sub-image to obtain the image feature information.
5. The method according to claim 4, characterized in that The preset grid size is 6*6, 7*7 or 8*8.
6. The method according to claim 1, characterized in that The method of using a preset deep learning algorithm to perform deep learning on the process of extracting the image feature information includes: The image feature information extraction process is deeply learned by using any one of the deep learning algorithms including convolutional neural network, recurrent neural network and long short-term memory network.
7. The method according to claim 1, characterized in that After the preset deep learning algorithm is used to perform deep learning on the extraction process of the image feature information, the method further includes: Performing a performance test on the spatial detection and positioning system of the compound eye detector to obtain target performance parameters, wherein the target performance parameters include a maximum detection distance, a maximum detection angle, and a shortest response time; The spatial detection and positioning system of the compound eye detector is evaluated based on the target performance parameters, and the evaluation result is forwarded to a preset terminal.
8. A space detection and positioning device, characterized in that: Applied to a compound eye detector, including: An image capture module, used to control the compound eye detector to capture scene images according to preset detection parameters; An image processing module, used for performing preset image processing on the scene image to obtain a target image, wherein the preset image processing includes denoising processing, contrast adjustment processing, overlay processing and local pixel adjustment processing; A feature extraction module, used to extract image feature information in the target image based on a network segmentation method; A deep learning module, used for performing deep learning on the extraction process of the image feature information using a preset deep learning algorithm; The feature analysis module is used to analyze the image feature information to determine parameter information of the detected object and position information of the detected object in space.
9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the space detection and positioning method according to any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the spatial detection and positioning method described in any one of claims 1 to 7.