Positioning control method and device, equipment and storage medium
By performing motion state recognition and confidence thresholding on images, static and dynamic feature points are distinguished, solving the problem of low accuracy of SLAM positioning systems in dynamic environments and achieving higher positioning accuracy and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GOERTEK INC
- Filing Date
- 2025-01-02
- Publication Date
- 2026-07-10
AI Technical Summary
Existing SLAM positioning systems cannot effectively distinguish between static and dynamic feature points in dynamic environments, resulting in low positioning accuracy.
When a device startup command is received, motion state recognition is performed on the image in the current scene, image region blocks are determined based on confidence thresholds, pixel coordinates of image feature points are obtained, and static and dynamic feature points are distinguished using the target initialization module for SLAM localization.
It improves the accuracy of SLAM positioning and enhances the user experience.
Smart Images
Figure CN122368162A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent device technology, and in particular to positioning control methods, devices, equipment and storage media. Background Technology
[0002] With the continuous development of various intelligent technologies, smart devices have been widely used in entertainment, education, and healthcare, such as smart helmets. These devices rely heavily on SLAM (Simultaneous Localization and Mapping) for positioning. Currently, the common method for SLAM positioning is to use SLAM systems. However, real-world environments contain numerous dynamic objects, making the entire environment dynamic. SLAM algorithms in SLAM systems cannot distinguish between static and dynamic feature points in a dynamic environment, leading to significant positioning errors. Therefore, the accuracy of SLAM positioning using the aforementioned methods is relatively low.
[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention
[0004] The main objective of this application is to provide a positioning control method, apparatus, device, and storage medium, which aims to solve the technical problem of low accuracy in SLAM positioning in the prior art.
[0005] To achieve the above objectives, this application proposes a positioning control method, the method comprising:
[0006] Upon receiving a device startup command, motion state recognition is performed on the image in the current scene;
[0007] Based on the confidence threshold, image region blocks are determined according to the motion state recognition results;
[0008] Obtain the pixel coordinates of image feature points in the image region block, and determine static and dynamic feature points based on the pixel coordinates using the target initialization module;
[0009] SLAM localization is performed based on the static feature points and the dynamic feature points.
[0010] In one embodiment, the step of performing motion state recognition on the image in the current scene when a device start command is received includes:
[0011] Upon receiving a device start command, the image sensing device is activated;
[0012] The image sensing device acquires an image of the current scene based on the startup process;
[0013] The image is segmented according to a preset segmentation strategy to obtain image segmentation blocks;
[0014] Based on the dynamic object recognition module, motion state recognition is performed on each of the image segmentation blocks.
[0015] In one embodiment, the step of determining image region blocks based on motion state recognition results according to a confidence threshold includes:
[0016] The confidence level of each image segmentation block is obtained based on the motion state recognition results;
[0017] The confidence score of each image segmentation block is compared with a confidence threshold.
[0018] The image segmentation blocks are divided according to the confidence comparison results to obtain image region blocks.
[0019] In one embodiment, the step of obtaining the pixel coordinates of image feature points in the image region block and determining static and dynamic feature points based on the pixel coordinates using the target initialization module includes:
[0020] Feature extraction is performed on the image region block to obtain image feature points;
[0021] Obtain the pixel coordinates of the image feature points and determine the category of the pixel corresponding to the pixel coordinates;
[0022] Based on the target initialization module, static feature points and dynamic feature points are determined according to the category of the pixels.
[0023] In one embodiment, the step of determining static and dynamic feature points based on the category of the pixel using the target initialization module includes:
[0024] Based on the target initialization module, the confidence vector of the image feature points is set according to the category of the pixel;
[0025] The feature point recognition strategy is determined based on the set confidence vector;
[0026] The image feature points are identified according to the feature point recognition strategy to obtain static feature points and dynamic feature points.
[0027] In one embodiment, the step of setting the confidence vector of the image feature points according to the category of the pixel based on the target initialization module includes:
[0028] The confidence vector of the image feature points is initialized based on the vector initialization module.
[0029] When the category of the pixel is a preset category, obtain the normalized probability value;
[0030] Based on the target initialization module, the confidence vector of the feature points of the initialized image is set according to the normalized probability value.
[0031] In one embodiment, the step of performing SLAM localization based on the static feature points and the dynamic feature points includes:
[0032] Construct localization descriptors for the static feature points and the dynamic feature points respectively;
[0033] Obtain the motion parameters of the dynamic feature point at the current moment;
[0034] Based on the SLAM positioning system, SLAM positioning is performed according to the positioning descriptor and the motion parameters.
[0035] Furthermore, to achieve the above objectives, this application also proposes a positioning control device, which includes:
[0036] The recognition module is used to recognize the motion state of images in the current scene when a device start command is received;
[0037] The determination module is used to determine image region blocks based on the motion state recognition results and a confidence threshold.
[0038] The acquisition module is used to acquire the pixel coordinates of image feature points in the image region block, and based on the target initialization module, determine static feature points and dynamic feature points according to the pixel coordinates;
[0039] The localization module is used to perform SLAM localization based on the static feature points and the dynamic feature points.
[0040] In addition, to achieve the above objectives, this application also proposes a positioning control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the positioning control method as described above.
[0041] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the positioning control method described above.
[0042] One or more technical solutions proposed in this application have at least the following technical effects: Upon receiving a device startup command, motion state recognition is performed on the image in the current scene; based on a confidence threshold, image region blocks are determined according to the motion state recognition results; pixel coordinates of image feature points in the image region blocks are obtained, and static and dynamic feature points are determined based on the pixel coordinates using a target initialization module; SLAM localization is performed based on the static and dynamic feature points. Through the above method, after motion state recognition of the image in the current scene, a confidence attribute is introduced, and image region blocks are determined based on the comparison results of the confidence of each image segmentation block with the confidence threshold. At this time, a target initialization module is introduced to set the confidence vector of image feature points in the image region blocks, and then SLAM localization is performed based on the identified static and dynamic feature points. This effectively improves the accuracy of SLAM localization, thereby enhancing the user experience. Attached Figure Description
[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0045] Figure 1 This is a flowchart illustrating an embodiment of the positioning control method of this application.
[0046] Figure 2 This is a flowchart illustrating Embodiment 2 of the positioning control method of this application;
[0047] Figure 3 This is a schematic diagram of the module structure of the positioning control device according to an embodiment of this application;
[0048] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the positioning control method in the embodiments of this application.
[0049] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0050] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or positioning control device capable of performing the above functions. The following description uses a positioning control device as an example to illustrate this embodiment and the subsequent embodiments.
[0051] Based on this, embodiments of this application provide a positioning control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the positioning control method of this application.
[0052] In this embodiment, the positioning control method includes steps S10 to S40:
[0053] Step S10: Upon receiving the device start command, perform motion state recognition on the image in the current scene.
[0054] It should be noted that the device startup command refers to the command to start the device for SLAM positioning. This device startup command can be triggered by pressing the power button, and the device started can be a wearable smart device, such as a smart helmet. The image of the current scene can be acquired by an image sensing device, which can be an image sensor.
[0055] Further, step S10 includes: activating the image sensing device upon receiving a device activation command; acquiring an image of the current scene based on the activated image sensing device; segmenting the image according to a preset segmentation strategy to obtain image segmentation blocks; and performing motion state recognition on each of the image segmentation blocks based on the dynamic object recognition module.
[0056] It should be understood that the preset segmentation strategy refers to the strategy of image segmentation based on segmentation parameters, which include but are not limited to segmentation position, segmentation method, etc. After the image sensing device acquires the environmental image of the current scene, the image is divided into multiple image segmentation blocks, and then the image segmentation blocks are input to the dynamic object recognition module, which performs motion state recognition. After the recognition is completed, each image segmentation block corresponds to a confidence level.
[0057] Step S20: Based on the confidence threshold, determine the image region block according to the motion state recognition result.
[0058] It is understandable that the confidence threshold refers to the confidence level used to divide the image into segments, and the image region block refers to the image block into regions based on the confidence comparison results.
[0059] Further, step S20 includes: obtaining the confidence level of each image segmentation block based on the motion state recognition result; comparing the confidence level of each image segmentation block with a confidence threshold respectively; and dividing each image segmentation block according to the confidence comparison result to obtain image region blocks.
[0060] It should be understood that after extracting the confidence scores of each image segmentation block from the motion state recognition results, the confidence scores of each image segmentation block are compared with a confidence threshold. For example, image segmentation blocks with confidence scores less than the confidence threshold are classified into one region block, i.e., unknown motion state. Image segmentation blocks with confidence scores greater than or equal to the confidence threshold are classified into another region block, and this other region block is further divided so that each image region block corresponds to its own motion state. This motion state includes, but is not limited to, true static, temporary static, and dynamic. At this time, the image region blocks exhibit a probability distribution, for example, three probability distribution maps.
[0061] Step S30: Obtain the pixel coordinates of image feature points in the image region block, and determine static and dynamic feature points based on the pixel coordinates using the target initialization module.
[0062] It should be understood that image feature points refer to feature points that identify different image regions, and each image feature point has multiple attributes, including but not limited to pixel coordinates, angle, response intensity, layer number, point motion state, and map point index. The point motion state and map point index are newly added attributes in this embodiment, used to determine static and dynamic feature points. It can be understood that the target initialization module can be an index number initialization module, used to set the confidence vector of image feature points.
[0063] Step S40: Perform SLAM localization based on the static feature points and the dynamic feature points.
[0064] Understandably, after determining static and dynamic feature points, performing SLAM localization based on a SLAM localization system can effectively improve the accuracy of SLAM localization compared to existing technologies that perform localization without identifying static and dynamic feature points.
[0065] Further, step S40 includes: constructing localization descriptors for the static feature points and the dynamic feature points respectively; obtaining the motion parameters of the dynamic feature points at the current time; and performing SLAM localization based on the localization descriptors and the motion parameters using the SLAM localization system.
[0066] It should be understood that the localization descriptor refers to the descriptor constructed for localizing static and dynamic feature points, used to match feature points and determine location points. Motion parameters refer to the parameters of the dynamic feature point's motion at the current moment. These motion parameters include, but are not limited to, acceleration and angular velocity. At this time, SLAM localization is performed based on the localization descriptor and motion parameters, which can effectively improve the efficiency and robustness of SLAM localization.
[0067] This embodiment identifies motion states in the image of the current scene upon receiving a device startup command; determines image region blocks based on the motion state identification results using a confidence threshold; obtains the pixel coordinates of image feature points within the image region blocks; and determines static and dynamic feature points based on the pixel coordinates using a target initialization module; and performs SLAM localization based on the static and dynamic feature points. By introducing a confidence attribute after motion state identification in the image of the current scene, and determining image region blocks based on the comparison between the confidence of each image segmentation block and the confidence threshold, this embodiment effectively improves the accuracy of SLAM localization and enhances the user experience.
[0068] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S30 includes steps S301 to S303:
[0069] Step S301: Extract features from the image region block to obtain image feature points.
[0070] It should be noted that image feature points refer to the feature points that identify different image regions. These image feature points can be detected and extracted using the Shi-Tomasi corner detection algorithm.
[0071] Step S302: Obtain the pixel coordinates of the image feature points and determine the category of the pixel corresponding to the pixel coordinates.
[0072] It is understandable that image feature points have attributes such as pixel coordinates, angle, response intensity, layer number, point motion state, and map point index. The pixel coordinate attribute needs to be used, that is, to obtain the pixel coordinates of the image feature points and determine the category of the pixel corresponding to the pixel coordinates. The category of the pixel can be a known category or an unknown category.
[0073] Step S303: Based on the target initialization module, determine static feature points and dynamic feature points according to the category of the pixels.
[0074] It should be understood that static feature points refer to feature points in an image region that are in a static state, while dynamic feature points refer to feature points in an image region that are in an active state. After determining the category of the pixel corresponding to the pixel coordinate, static and dynamic feature points are determined based on the target initialization module.
[0075] Further, step S303 includes: setting the confidence vector of the image feature points according to the category of the pixel based on the target initialization module; determining the feature point recognition strategy according to the set confidence vector; and recognizing each of the image feature points according to the feature point recognition strategy to obtain static feature points and dynamic feature points.
[0076] It is understandable that the probability values set by the target initialization module for the confidence vector of image feature points are different for different pixel categories. The feature recognition strategy refers to the strategy of recognizing feature points based on the confidence vector. For example, when the confidence vector of image feature point A is set to (a,b,c,0), the image feature point is recognized as a static feature point. When the confidence vector of image feature point B is set to (c,d,e,0), the image feature point is recognized as a dynamic feature point.
[0077] Furthermore, the step of setting the confidence vector of the image feature points according to the category of the pixel based on the target initialization module includes: initializing the confidence vector of the image feature points based on the vector initialization module; obtaining a normalized probability value when the category of the pixel is a preset category; and setting the confidence vector of the initialized image feature points according to the normalized probability value based on the target initialization module.
[0078] It is understandable that the preset categories include true static category, temporary static category and dynamic category. Before setting the confidence vector of image feature points, initialization processing is required. At this time, the confidence vector of image feature points is (0,0,0,1).
[0079] It should be understood that the normalized probability value refers to the numerical value after probability normalization. The normalized probability value corresponds to the pixel's category. For example, when the pixel's category is true stillness, the normalized probability value is a, b, c. At this point, based on the target initialization module, the confidence vector of the initialized image feature points is set according to the normalized probability value; that is, the set confidence vector is (a, b, c, 0). Furthermore, when the pixel's category is not a preset category, the initialized confidence vector is retained.
[0080] It should be noted that the confidence vector of the image feature points in this embodiment can be represented as P. m = (s1, s2, s3, s4), where s1 + s2 + s3 + s4 = 1, s1 represents the confidence component in the true static state, s2 represents the confidence component in the temporarily static state, s3 represents the confidence component in the dynamic state, and s4 represents the confidence component in the unknown state.
[0081] This embodiment extracts image feature points from the image region block; obtains the pixel coordinates of the image feature points and determines the category of the pixel corresponding to the pixel coordinates; based on the target initialization module, static and dynamic feature points are determined according to the category of the pixel. Through the above method, after extracting the image feature points of the image region block, the pixels corresponding to the pixel coordinates of the image feature points are determined, and the category of the pixels is further determined. Then, it is determined whether the category of the pixel is a preset category. If so, static and dynamic feature points are determined based on the target initialization module, thereby effectively improving the accuracy of determining static and dynamic feature points.
[0082] This application also provides a positioning control device, please refer to... Figure 3 The positioning control device includes:
[0083] The recognition module 10 is used to recognize the motion state of the image in the current scene when a device start command is received.
[0084] The determination module 20 is used to determine image region blocks based on the confidence threshold and the motion state recognition results.
[0085] The acquisition module 30 is used to acquire the pixel coordinates of image feature points in the image region block, and to determine static feature points and dynamic feature points based on the pixel coordinates by the target initialization module.
[0086] The positioning module 40 is used to perform SLAM positioning based on the static feature points and the dynamic feature points.
[0087] This embodiment identifies motion states in the image of the current scene upon receiving a device startup command; determines image region blocks based on the motion state identification results using a confidence threshold; obtains the pixel coordinates of image feature points within the image region blocks; and determines static and dynamic feature points based on the pixel coordinates using a target initialization module; and performs SLAM localization based on the static and dynamic feature points. By introducing a confidence attribute after motion state identification in the image of the current scene, and determining image region blocks based on the comparison between the confidence of each image segmentation block and the confidence threshold, this embodiment effectively improves the accuracy of SLAM localization and enhances the user experience.
[0088] The positioning control device provided in this application, employing the positioning control method in the above embodiments, can solve the technical problem of low accuracy in SLAM positioning in the prior art. Compared with the prior art, the beneficial effects of the positioning control device provided in this application are the same as those of the positioning control method provided in the above embodiments, and other technical features in the positioning control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0089] In one embodiment, the recognition module 10 is further configured to: activate the image sensing device upon receiving a device activation command; acquire an image of the current scene based on the activated image sensing device; segment the image according to a preset segmentation strategy to obtain image segmentation blocks; and perform motion state recognition on each of the image segmentation blocks based on the dynamic object recognition module.
[0090] In one embodiment, the determining module 20 is further configured to obtain the confidence level of each image segmentation block based on the motion state recognition result; compare the confidence level of each image segmentation block with a confidence threshold respectively; and divide each image segmentation block according to the confidence comparison result to obtain image region blocks.
[0091] In one embodiment, the acquisition module 30 is further configured to extract features from the image region block to obtain image feature points; acquire the pixel coordinates of the image feature points and determine the category of the pixel corresponding to the pixel coordinates; and, based on the target initialization module, determine static feature points and dynamic feature points according to the category of the pixel.
[0092] In one embodiment, the acquisition module 30 is further configured to, based on the target initialization module, set the confidence vector of the image feature points according to the category of the pixels; determine the feature point recognition strategy according to the set confidence vector; and recognize each of the image feature points according to the feature point recognition strategy to obtain static feature points and dynamic feature points.
[0093] In one embodiment, the acquisition module 30 is further configured to initialize the confidence vector of the image feature points based on the vector initialization module; obtain a normalized probability value when the category of the pixel is a preset category; and set the confidence vector of the initialized image feature points according to the normalized probability value based on the target initialization module.
[0094] In one embodiment, the positioning module 40 is further configured to construct positioning descriptors for the static feature points and the dynamic feature points respectively; obtain the motion parameters of the dynamic feature points at the current time; and perform SLAM positioning based on the positioning descriptors and the motion parameters using a SLAM positioning system.
[0095] This application provides a positioning control 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 perform the positioning control method in Embodiment 1 above.
[0096] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a positioning control device suitable for implementing embodiments of this application. The positioning control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The positioning control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0097] like Figure 4As shown, the positioning control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the positioning control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the positioning control device to communicate wirelessly or wiredly with other devices to exchange data. Although positioning control devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0098] Specifically, according to the embodiments disclosed in this application, the process described above with reference to the flowcharts can be implemented as a computer software program. This computer program includes program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0099] The positioning control device provided in this application, employing the positioning control method described in the above embodiments, can solve the technical problem of low accuracy in SLAM positioning in the prior art. Compared with the prior art, the beneficial effects of the positioning control device provided in this application are the same as those of the positioning control method provided in the above embodiments, and other technical features of the positioning control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0100] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0102] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the positioning control method in the above embodiments.
[0103] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0104] The aforementioned computer-readable storage medium may be included in the positioning control device; or it may exist independently and not assembled into the positioning control device.
[0105] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0107] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0108] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described positioning control method, which can solve the technical problem of low accuracy in SLAM positioning in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the positioning control method provided in the above embodiments, and will not be repeated here.
[0109] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A positioning control method, characterized in that, The method includes: Upon receiving a device startup command, motion state recognition is performed on the image in the current scene; Based on the confidence threshold, image region blocks are determined according to the motion state recognition results; Obtain the pixel coordinates of image feature points in the image region block, and determine static and dynamic feature points based on the pixel coordinates using the target initialization module; SLAM localization is performed based on the static feature points and the dynamic feature points.
2. The method as described in claim 1, characterized in that, The step of performing motion state recognition on the image in the current scene when receiving a device start command includes: Upon receiving a device start command, the image sensing device is activated; The image sensing device acquires an image of the current scene based on the startup process; The image is segmented according to a preset segmentation strategy to obtain image segmentation blocks; Based on the dynamic object recognition module, motion state recognition is performed on each of the image segmentation blocks.
3. The method as described in claim 1, characterized in that, The step of determining image region blocks based on the motion state recognition result according to the confidence threshold includes: The confidence level of each image segmentation block is obtained based on the motion state recognition results; The confidence score of each image segmentation block is compared with a confidence threshold. The image segmentation blocks are divided according to the confidence comparison results to obtain image region blocks.
4. The method as described in claim 1, characterized in that, The step of obtaining the pixel coordinates of image feature points in the image region block and determining static and dynamic feature points based on the pixel coordinates using the target initialization module includes: Feature extraction is performed on the image region block to obtain image feature points; Obtain the pixel coordinates of the image feature points and determine the category of the pixel corresponding to the pixel coordinates; Based on the target initialization module, static feature points and dynamic feature points are determined according to the category of the pixels.
5. The method as described in claim 4, characterized in that, The step of determining static and dynamic feature points based on the category of the pixels using the target initialization module includes: Based on the target initialization module, the confidence vector of the image feature points is set according to the category of the pixel; The feature point recognition strategy is determined based on the set confidence vector; The image feature points are identified according to the feature point recognition strategy to obtain static feature points and dynamic feature points.
6. The method as described in claim 5, characterized in that, The step of setting the confidence vector of the image feature points according to the category of the pixel based on the target initialization module includes: The confidence vector of the image feature points is initialized based on the vector initialization module. When the category of the pixel is a preset category, obtain the normalized probability value; Based on the target initialization module, the confidence vector of the feature points of the initialized image is set according to the normalized probability value.
7. The method according to any one of claims 1 to 6, characterized in that, The step of performing SLAM localization based on the static feature points and the dynamic feature points includes: Construct localization descriptors for the static feature points and the dynamic feature points respectively; Obtain the motion parameters of the dynamic feature point at the current moment; Based on the SLAM positioning system, SLAM positioning is performed according to the positioning descriptor and the motion parameters.
8. A positioning control device, characterized in that, The device includes: The recognition module is used to recognize the motion state of images in the current scene when a device start command is received; The determination module is used to determine image region blocks based on the motion state recognition results and a confidence threshold. The acquisition module is used to acquire the pixel coordinates of image feature points in the image region block, and based on the target initialization module, determine static feature points and dynamic feature points according to the pixel coordinates; The localization module is used to perform SLAM localization based on the static feature points and the dynamic feature points.
9. A positioning control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the positioning control method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the positioning control method as described in any one of claims 1 to 7.