A multi-prism target recognition method and device, electronic equipment and storage medium
By acquiring and processing total station image data in real time, determining effective pixel segments and assessing connectivity, the real-time performance issue of total station in identifying prism targets was resolved, achieving efficient and accurate prism target identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI HUACE NAVIGATION TECH
- Filing Date
- 2022-12-27
- Publication Date
- 2026-06-26
AI Technical Summary
Existing total stations have poor real-time performance when identifying prism targets and cannot continuously track moving prisms, mainly because traditional digital image processing technology requires a long processing time.
The multi-prism target recognition method is adopted. By acquiring the current row of image data in real time, the effective pixel segments are determined, and the connection between the effective pixel segments of the current row and the effective pixel segments of the previous row is obtained according to the preset connectivity judgment rules. Prism target data is created or updated. The data transmission time of low-frequency sensor data to high-frequency processor is utilized to reduce data transmission delay and improve the real-time performance of recognition.
It achieves efficient identification of prism targets, improves identification efficiency and accuracy, reduces memory usage, and increases data update speed.
Smart Images
Figure CN115880474B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of prism target recognition technology, and more specifically, to a multiprism target recognition method, device, electronic device, and storage medium. Background Technology
[0002] A total station, also known as a total station electronic distance measuring instrument, is a surveying instrument that integrates optics, mechanics, and electronics. Existing automatic total stations require the identification of a prism's position to perform measurements.
[0003] Because prism target imaging is relatively simple and has certain rules, most total stations currently use traditional digital image processing technology in prism scenarios. This involves using the color and shape information of the prism to segment, extract, and identify the target. This method requires a long processing time, resulting in poor real-time performance of prism recognition and an inability to continuously track moving prisms. Summary of the Invention
[0004] The purpose of this application is to provide a prism target recognition method, device, electronic device and storage medium to improve the real-time performance of prism target recognition.
[0005] In a first aspect, embodiments of this application provide a method for identifying a multi-prism target, comprising: acquiring current row image data in real time; determining valid pixel segments in the current row image data; acquiring the connectivity between the valid pixel segments in the current row and the valid pixel segments in the previous row according to a preset connectivity judgment rule; creating or updating prism target data according to the connectivity between the valid pixel segments in the current row and the valid pixel segments in the previous row; repeating the above steps iteratively until the current row image data is the last row of image data, thereby completing the prism target identification.
[0006] In the implementation of the above scheme, the current row of image data is acquired in real time. By using row scanning, it can be determined whether the current row of image data contains a prism target based on the current row of image data and the previous row of image data. It can also be determined whether the prism target is a newly added target or the same target as the prism target identified based on the previous row of image data, thus achieving efficient identification of multiple prism targets. Since the processing is performed directly on the row of image data, the transmission time of low-frequency sensor data to high-frequency processor is fully utilized, reducing the latency caused by the data transmission process and effectively improving the real-time performance of prism target identification.
[0007] In one implementation of the first aspect, the real-time acquisition of the current row of image data includes: acquiring a first row interrupt signal, determining the first pixel data of the current row of image data based on the first row interrupt signal; acquiring a second row interrupt signal, determining the last pixel data of the current row of image data based on the second row interrupt signal.
[0008] In the implementation of the above scheme, the current row data can be obtained through the row interrupt signal, thereby realizing real-time processing of the current row data. This makes full use of the transmission time of low-frequency sensor data to high-frequency processor, thereby further improving the real-time performance of the above-mentioned multi-prism target recognition method.
[0009] In one implementation of the first aspect, determining a valid pixel segment in the current row of image data includes: determining pixels in the current row of image data whose pixel brightness value is greater than a first preset threshold as target pixels; determining consecutively arranged target pixels as target pixel segments; and determining target pixel segments containing a number of target pixels not less than a second threshold as valid pixel segments.
[0010] In the implementation of the above scheme, by initially screening the pixels, a large number of pixels that are irrelevant to the prism target are removed, and effective pixel segment data related to the prism target is retained. Subsequently, the prism target recognition result can be obtained by analyzing and processing the effective pixel segment data, which greatly improves the recognition efficiency and real-time performance of the above multi-prism target recognition method. At the same time, by using the effective pixel segment method, only the edge information of the prism target is extracted. The prism target can be recognized by using the edge information of the prism target, which makes the memory occupied by the above multi-prism target recognition method less during operation and improves the update speed of the prism target data.
[0011] In one implementation of the first aspect, the step of obtaining the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments according to a preset connectivity judgment rule includes: determining the starting column number and the ending column number of the current row of valid pixel segments; if the starting column number of the current row of valid pixel segments is not greater than the ending column number of the previous row of valid pixel segments, and the starting column number of the current row of valid pixel segments is not less than the starting column number of the corresponding valid pixel segments in the previous row, then the current row of valid pixel segments is connected to the corresponding valid pixel segments in the previous row.
[0012] In the implementation of the above scheme, the connectivity between the current row of valid pixels and the corresponding valid pixel segment in the previous row can be determined by the start and end column numbers of the valid pixel segment. This allows for the determination of whether the current row of valid pixels and the corresponding valid pixel segment in the previous row belong to the same prism target, greatly improving the recognition efficiency, accuracy, and real-time performance of the above multi-prism target recognition method.
[0013] In one implementation of the first aspect, the step of creating or updating prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments includes: if the current row of valid pixel segments is not connected to any valid pixel segment in the previous row, then the current row of valid pixel segments is determined to be a newly added prism target, a prism target storage space is created for the newly added prism target, and the data of the current row of valid pixel segments is stored in the prism target storage space; if the current row of valid pixel segments is connected to the previous row of valid pixel segments, then the current row of valid pixel segments and the previous row of valid pixel segments belong to the same prism target, and the data of the current row of valid pixel segments is updated to the prism target storage space.
[0014] In the implementation of the above scheme, the connection between the current row of valid pixels and the previous row of valid pixels is used to determine whether the current row of valid pixels and the previous row of valid pixels belong to the same prism target, thereby achieving accurate identification of a single prism target; at the same time, the pixel data of a single prism target is stored in the prism target storage space, and each prism target storage space stores only the pixel data of a single prism target, which effectively improves the recognition efficiency of the above multi-prism target recognition method.
[0015] In one implementation of the first aspect, the prism target storage space includes: a prism target cache.
[0016] In the implementation of the above scheme, a prism target cache is used to store prism target pixel data, which effectively improves the prism recognition efficiency of the above multi-prism recognition method.
[0017] Secondly, embodiments of this application provide a multi-prism target recognition device, comprising:
[0018] The current row image data acquisition module is used to acquire the current row image data in real time;
[0019] A valid pixel segment determination module is used to determine valid pixel segments in the current row of image data;
[0020] The effective pixel segment connectivity determination module is used to obtain the connectivity status between the current row of effective pixel segments and the previous row of effective pixel segments according to the preset connectivity determination rules.
[0021] The prism target data creation and update module is used to create or update prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments.
[0022] Thirdly, embodiments of this application provide a multi-prism target recognition system, including:
[0023] Image sensing devices are used to send the current row of prism target image data to image processing devices in real time;
[0024] An image processing device is used to acquire, in real time, the current row of prism target image data sent by the image sensing device; determine the effective pixel segments in the current row of image data; obtain the connection status between the current row of effective pixel segments and the previous row of effective pixel segments according to a preset connectivity judgment rule; create or update prism target data according to the connection status between the current row of effective pixel segments and the previous row of effective pixel segments; repeat the above steps iteratively until the current row of image data is the last row of image data, thus completing the prism target recognition.
[0025] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the method provided in the first aspect or any possible implementation thereof.
[0026] Fifthly, embodiments of this application provide an electronic device, including: a memory and a processor, wherein the memory stores computer program instructions, and the computer program instructions are read and executed by the processor to perform the method provided in the first aspect or any possible implementation of the first aspect.
[0027] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0029] Figure 1 A schematic flowchart illustrating the prism target recognition method provided in this application embodiment;
[0030] Figure 2 This is a schematic diagram of the structure of the multi-prism target recognition device provided in the embodiments of this application;
[0031] Figure 3 This is a schematic diagram of the structure of the multi-prism target recognition system provided in the embodiments of this application;
[0032] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0033] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.
[0034] The following embodiments are only used to illustrate the technical solutions of this application more clearly, and are therefore only examples and should not be used to limit the scope of protection of this application.
[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.
[0036] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.
[0037] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0038] Please see Figure 1 This application provides a method for identifying a multi-prism target, comprising:
[0039] Step S110: Acquire the current row of image data in real time;
[0040] Step S120: Determine the valid pixel segment in the current row of image data;
[0041] Step S130: According to the preset connectivity judgment rules, obtain the connectivity status between the current row of valid pixel segments and the previous row of valid pixel segments;
[0042] Step S140: Create or update prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments;
[0043] Step S150: Repeat the above steps until the current row of image data is the last row of image data, and complete the prism target recognition.
[0044] In the implementation of the above scheme, the current row of image data is acquired in real time. By using row scanning, it can be determined whether the current row of image data contains a prism target based on the current row of image data and the previous row of image data. It can also be determined whether the prism target is a newly added target or the same target identified based on the previous row of image data, thus achieving efficient identification of multiple prism targets. Since the processing is performed directly on the row of image data, the transmission time of low-frequency sensor data to high-frequency processor is fully utilized, reducing the latency caused by data transmission and effectively improving the real-time performance of prism target identification. At the same time, multiple prism targets can be identified by reading one frame of image at a time, with fast processing speed and low time complexity.
[0045] Steps S110 to S150 are described below:
[0046] First, the current row data obtained in step S110 refers to the image pixel data. As is well known, an image is composed of several rows of pixel data, and the pixel data obtained in step S110 is the pixel data.
[0047] As an optional implementation of the aforementioned prism target recognition method, step S110, acquiring the current row of image data, includes: acquiring a first row interruption signal, determining the first pixel data of the current row of image data based on the first row interruption signal; acquiring a second row interruption signal, and determining the last pixel data of the current row of image data based on the second row interruption signal. For example, in this implementation: the image sensing device sends target image data to the image processing device according to the image row pixel data, and the image processing device also receives target pixel data according to the image row pixel data. When receiving target image data, the image processing device sets row interruption signals. Each row interruption signal represents the end of a row of pixel data and the beginning of the next row of pixel data. Therefore, it is possible to directly determine whether the acquired pixel data is the current row data based on the row interruption signal. The time interval is determined based on the time points of receiving the first row interruption signal and the second row interruption signal, and all pixel data within this time interval is determined as the current row pixel data.
[0048] It is understandable that the first line interrupt signal mentioned above is the first line interrupt signal received, and the second line interrupt signal is the second line interrupt signal received.
[0049] It should be noted that since the image resolution is generally preset, that is, the number of pixels in each row of the target image is generally preset, the method for obtaining the current row image pixel data in step S110 can also be: after the image processing device starts receiving the target image data, it counts the amount of pixel data received, and increments the row count by one after receiving a preset number of pixel data.
[0050] Understandably, a frame interrupt signal can also be set to determine the current image. The frame interrupt signal indicates the end of an image and the beginning of the next image. By combining the frame interrupt signal and the line interrupt signal, the current line image data of the current image can be obtained.
[0051] Step S120 is described below: Since the target image data may contain environmental images other than the target prism, such as the background, it is necessary to identify the effective pixel segments that can be used for prism recognition in the target image data and remove pixels that are irrelevant to prism recognition, such as the background.
[0052] As an optional implementation of the above-described prism target recognition method, step S120, determining effective pixel segments in the current row of image data, includes: identifying pixels in the current row of image data whose pixel brightness values are greater than a first preset threshold as target pixels; identifying consecutively arranged target pixels as target pixel segments; and identifying target pixel segments containing a number of target pixels not less than a second threshold as effective pixel segments. For example, to obtain effective pixel segments, effective pixels, i.e., the aforementioned target pixels, can be identified first. Based on experience, it is known that the pixel brightness of a prism target in the target image data is generally greater than a certain threshold. Therefore, a first preset threshold is set, and pixels in the current row of image data whose pixel brightness values are greater than the first preset threshold are identified as target pixels. After obtaining the target pixels, consecutively arranged target pixels are identified as target pixel segments. Finally, among the target pixel segments, target pixel segments containing a number of target pixels not less than the second threshold are identified as effective pixel segments. For example, target pixel segments containing not less than three target pixels can be identified as effective pixel segments.
[0053] It should be noted that after obtaining the valid pixel segment, step S120 also includes: recording the start column number and end column number of the valid pixel segment, and counting the number of pixels in the valid pixel segment.
[0054] Step S130 is described in detail below:
[0055] As an optional implementation of the aforementioned prism target recognition method, step S130 obtains the connectivity status between the current row of valid pixel segments and the previous row of valid pixel segments according to a preset connectivity judgment rule, including: determining the start and end column numbers of the current row of valid pixel segments; if the start column number of the current row of valid pixel segments is not greater than the end column number of the previous row of valid pixel segments, and the start column number of the current row of valid pixel segments is not less than the start column number of the corresponding valid pixel segment in the previous row, then the current row of valid pixel segments is connected to the corresponding valid pixel segment in the previous row. For example, this implementation uses the start and end column numbers of the valid pixel segments to determine whether the current row of valid pixel segments is connected to the corresponding valid pixel segment in the previous row. Specifically, the connectivity judgment rule is: if the start column number of the current row of valid pixel segments is not greater than the end column number of the previous row of valid pixel segments, and the start column number of the current row of valid pixel segments is not less than the start column number of the corresponding valid pixel segment in the previous row, then the current row of valid pixel segments is connected to the corresponding valid pixel segment in the previous row.
[0056] It is understandable that the number of valid pixel segments in the current row and the previous row may be zero or non-zero. Furthermore, the number of valid pixel segments may be single or multiple. The following explains the possible scenarios regarding the number of valid pixel segments:
[0057] 1. The number of valid pixel segments in the current row is zero;
[0058] In this case, regardless of whether the number of valid pixel segments in the previous row is zero, there is no need to determine the connectivity of the valid pixel segments.
[0059] 2. The number of valid pixel segments in the previous row is zero, while the number of valid pixel segments in the current row is not zero;
[0060] In this case, the current row of valid pixels can be identified as the new prism target. If there is a single valid pixel segment in the current row, it is determined that there is only one new prism target. If there are multiple valid pixel segments in the current row, it is determined that there are multiple new prism targets.
[0061] 3. The number of valid pixel segments in the previous row and the number of valid pixel segments in the current row are both non-zero;
[0062] In this case, it is necessary to determine whether each valid pixel segment in the current row is connected to each valid pixel segment in the previous row.
[0063] Step S140 is described in detail below:
[0064] As an optional implementation of the above-mentioned multi-prism target recognition method, prism target data is created or updated based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments. This includes: if the current row of valid pixel segments is not connected to any valid pixel segment in the previous row, then the current row of valid pixel segments is determined to be a newly added prism target, a prism target storage space is created for the newly added prism target, and the data of the current row of valid pixel segments is stored in the prism target storage space; if the current row of valid pixel segments is connected to the previous row of valid pixel segments, then the current row of valid pixel segments and the previous row of valid pixel segments belong to the same prism target, and the data of the current row of valid pixel segments is updated to the prism target storage space. For example, this implementation involves: setting up a storage space for each prism target, with each storage space storing image pixel data of a single prism target; creating or updating prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments; if the current row of valid pixel segments is not connected to any of the previous row of valid pixel segments, it is determined that the current row of valid pixel segments belongs to a newly added prism target, a prism target storage space is created for the newly added prism target, and the data of the current row of valid pixel segments is stored in the prism target storage space; if the current row of valid pixel segments is connected to the previous row of valid pixel segments, it is determined that the current row of valid pixel segments and the previous row of valid pixel segments belong to the same prism target, and the data of the current row of valid pixel segments is updated to the prism target storage space.
[0065] It should be noted that when the current row has a single valid pixel segment and the previous row has multiple valid pixel segments, and each of the previous row's valid pixel segments is connected to the single valid pixel segment in the current row, when creating or updating prism target data based on the previous row's valid pixel segments, multiple previous row valid pixel segments may be identified as multiple prism targets. In this case, since each previous row's valid pixel segment is connected to the single valid pixel segment in the current row, the multiple valid pixel segments in the previous row and the single pixel segment in the current row can be identified as belonging to the same prism target, and the data of the previous row's valid pixel segments and the data of the current row's valid pixel segments can be merged into the same prism target storage space.
[0066] It is understandable that if multiple valid pixel segments are determined to belong to the same target, the prism target storage space can also store statistical information such as the minimum starting column number, the maximum ending column number, the number of valid pixels, and the cumulative sum of pixel brightness of the prism target in a certain row.
[0067] As an optional implementation of the aforementioned multi-prism target recognition method, the prism target storage space includes a prism target cache. For example, after a prism target is identified, a prism target cache is created for the current prism target, and the effective pixel segment data and effective pixel segment statistics related to the prism target are stored in the corresponding prism target cache.
[0068] The following details step S150: Step S150 repeats steps S110 to S140 until the current row of image data is the last row of image data, thus completing the prism target recognition.
[0069] It is understandable that step S150 can determine whether the current image transmission has ended by using the frame interrupt signal.
[0070] It should be noted that step S150 is to complete target recognition of the prism target in the current image. For a single prism target, the method for determining whether recognition has been completed can be as follows: if no update is made to a particular prism target after processing one or more rows of data, then the prism target can be considered to have been recognized. Then, the data stored in the prism target storage space corresponding to that prism target is calculated, and the target is located using the calculation result. This enables rapid response in applications such as total station target location output or target tracking.
[0071] It should be noted that the above-mentioned prism target recognition method describes the current row of data, but its essence is to process local data in the process of target image data transmission. The current row of data can also be extended to multiple rows of data. In the application scenario of multiple rows of data, the processing process for single row of data is the same as the processing process of the current row of image data by the above-mentioned prism target recognition method.
[0072] Please see Figure 2 Based on the same inventive concept, this application also provides a multi-prism target recognition device 200, comprising:
[0073] Current row image data acquisition module 210 is used to acquire current row image data in real time;
[0074] The effective pixel segment determination module 220 is used to determine the effective pixel segment in the current row of image data;
[0075] The effective pixel segment connectivity determination module 230 is used to obtain the connectivity status between the current row of effective pixel segments and the previous row of effective pixel segments according to the preset connectivity determination rules.
[0076] The prism target data creation and update module 240 is used to create or update prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments.
[0077] As an optional implementation of the aforementioned prism target recognition device, the current row image data acquisition module 210 acquires the current row image data in real time, including: acquiring a first row interruption signal, determining the first pixel data of the current row image data based on the first row interruption signal; acquiring a second row interruption signal, determining the last pixel data of the current row image data based on the second row interruption signal.
[0078] As an optional implementation of the aforementioned prism target recognition device, the effective pixel segment determination module 220 determines effective pixel segments in the current row of image data, including: determining pixels in the current row of image data whose pixel brightness value is greater than a first preset threshold as target pixels; determining consecutively arranged target pixels as target pixel segments; and determining target pixel segments containing a number of target pixels not less than a second threshold as effective pixel segments.
[0079] As an optional implementation of the aforementioned prism target recognition device, the effective pixel segment connectivity determination module 230 obtains the connectivity status between the current row of effective pixel segments and the previous row of effective pixel segments according to a preset connectivity determination rule, including: determining the start column number and end column number of the current row of effective pixel segments; if the start column number of the current row of effective pixel segments is not greater than the end column number of the previous row of effective pixel segments, and the start column number of the current row of effective pixel segments is not less than the start column number of the corresponding effective pixel segment in the previous row, then the current row of effective pixel segments is connected to the corresponding effective pixel segment in the previous row.
[0080] As an optional implementation of the aforementioned multi-prism target recognition device, the prism target data creation and update module 240 creates or updates prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments. This includes: if the current row of valid pixel segments is not connected to any valid pixel segment in the previous row, then the current row of valid pixel segments is determined to be a newly added prism target, a prism target storage space is created for the newly added prism target, and the data of the current row of valid pixel segments is stored in the prism target storage space; if the current row of valid pixel segments is connected to the previous row of valid pixel segments, then the current row of valid pixel segments and the previous row of valid pixel segments belong to the same prism target, and the data of the current row of valid pixel segments is updated to the prism target storage space.
[0081] As an optional implementation of the aforementioned multi-prism target recognition device, the prism target storage space includes: a prism target cache.
[0082] Please see Figure 3 Based on the same inventive concept, this application also provides a multi-prism target recognition system 300, comprising:
[0083] Image sensing device 310 is used to send the current row prism target image data to the image processing device in real time;
[0084] Image processing device 320 is used to acquire the current row prism target image data sent by the image sensing device in real time; determine the effective pixel segment in the current row image data; obtain the connection status between the current row effective pixel segment and the previous row effective pixel segment according to the preset connectivity judgment rule; create or update prism target data according to the connection status between the current row effective pixel segment and the previous row effective pixel segment; repeat the above steps iteratively until the current row image data is the last row of image data, and complete the prism target recognition.
[0085] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of this application. (Refer to...) Figure 4 The electronic device 400 includes a processor 410, a memory 420, and a communication interface 430. These components are interconnected and communicate with each other via a communication bus 440 and / or other forms of connection mechanism (not shown).
[0086] The memory 420 includes one or more (only one is shown in the figure), which may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The processor 410 and other possible components may access the memory 420 to read and / or write data therein.
[0087] Processor 410 includes one or more (only one is shown in the figure), which can be an integrated circuit chip with signal processing capabilities. The processor 410 can be a general-purpose processor, including a Central Processing Unit (CPU), a Microcontroller Unit (MCU), a Network Processor (NP), or other conventional processors; it can also be a special-purpose processor, including a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0088] Communication interface 430 includes one or more (only one is shown in the figure) and can be used to communicate directly or indirectly with other devices to exchange data. For example, communication interface 430 can be an Ethernet interface; it can be a mobile communication network interface, such as an interface for 3G, 4G, or 5G networks; or it can be other types of interfaces with data transmission and reception functions.
[0089] One or more computer program instructions may be stored in the memory 420, and the processor 410 may read and run these computer program instructions to implement the prism target recognition method provided in the embodiments of this application and other desired functions.
[0090] Understandable. Figure 4 The structure shown is for illustrative purposes only; the electronic device 400 may also include more than [other components]. Figure 4 The more or fewer components shown, or having the same Figure 4 The different configurations shown. Figure 4 The components shown can be implemented using hardware, software, or a combination thereof. For example, electronic device 400 can be a single server (or other device with computing power), a combination of multiple servers, a cluster of a large number of servers, etc., and can be either a physical device or a virtual device.
[0091] This application also provides a computer-readable storage medium storing computer program instructions. These instructions are read and executed by a computer's processor to perform the prism target recognition method provided in this application. For example, the computer-readable storage medium can be implemented as follows: Figure 4The memory 420 in the electronic device 400.
[0092] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0093] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0094] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0095] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.
Claims
1. A method for identifying targets using a multi-prism, characterized in that, include: During the transmission of image data line by line, the current line of image data is acquired in real time by scanning the lines. Determine the valid pixel segment in the current row of image data; Based on the preset connectivity judgment rules, obtain the connectivity status between the current row of valid pixel segments and the previous row of valid pixel segments; Based on the connectivity between the current row of valid pixels and the previous row of valid pixels, create or update the prism target data; Repeat the above steps iteratively until the current row of image data is the last row of image data, thus completing the prism target recognition.
2. The prism target recognition method according to claim 1, characterized in that, The real-time acquisition of current row image data includes: Obtain the first line interrupt signal, and determine the first pixel data of the current line of image data based on the first line interrupt signal; Obtain the second row interrupt signal, and determine the last pixel data of the current row of image data based on the second row interrupt signal.
3. The prism target recognition method according to claim 1, characterized in that, Determining the valid pixel segment in the current row of image data includes: Pixels in the current row of image data whose pixel brightness value is greater than a first preset threshold are identified as target pixels; Define consecutively arranged target pixels as target pixel segments; Target pixel segments containing a number of target pixels not less than the second threshold are identified as valid pixel segments.
4. The prism target recognition method according to claim 1, characterized in that, The step of obtaining the connectivity status between the current row of valid pixel segments and the previous row of valid pixel segments according to preset connectivity judgment rules includes: Determine the start and end column numbers of the valid pixel segment in the current row; If the starting column number of the current row's valid pixel segment is not greater than the ending column number of the previous row's valid pixel segment, and the starting column number of the current row's valid pixel segment is not less than the starting column number of the corresponding valid pixel segment in the previous row, then the current row's valid pixel segment is connected to the corresponding valid pixel segment in the previous row.
5. The prism target recognition method according to claim 1, characterized in that, The step of creating or updating prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments includes: If the current row of valid pixels is not connected to any of the previous row of valid pixels, then the current row of valid pixels is determined to be a new prism target. A prism target storage space is created for the new prism target, and the current row of valid pixels is stored in the prism target storage space. If the current row of valid pixels is connected to the previous row of valid pixels, then the current row of valid pixels and the previous row of valid pixels belong to the same prism target, and the data of the current row of valid pixels is updated to the storage space of the prism target.
6. The prism target recognition method according to claim 5, characterized in that, The prism target storage space includes: prism target cache.
7. A multi-prism target recognition device, characterized in that, include: The current row image data acquisition module is used to acquire the current row image data in real time by scanning rows during the process of transmitting image data line by line. A valid pixel segment determination module is used to determine valid pixel segments in the current row of image data; The effective pixel segment connectivity determination module is used to obtain the connectivity status between the current row of effective pixel segments and the previous row of effective pixel segments according to the preset connectivity determination rules. The prism target data creation and update module is used to create or update prism target data based on the connectivity between the current row of valid pixel segments and the previous row of valid pixel segments. The current row image data acquisition module, the effective pixel segment determination module, the effective pixel segment connectivity determination module, and the prism target data creation and update module repeatedly iterate until the current row image data is the last row of the image data, thus completing the prism target recognition.
8. A multi-prism target recognition system, characterized in that, include: Image sensing devices are used to send the current row of prism target image data to image processing devices in real time; An image processing device is used to acquire, in real time, the current row of prism target image data sent by the image sensing device in a line-by-line scanning manner during the process of the image sensing device transmitting image data line by line; determine the effective pixel segments in the current row of prism target image data; obtain the connection status between the effective pixel segments of the current row and the effective pixel segments of the previous row according to a preset connectivity judgment rule; create or update prism target data according to the connection status between the effective pixel segments of the current row and the effective pixel segments of the previous row; and repeat the above steps iteratively until the current row of image data is the last row of image data, thus completing the prism target recognition.
9. An electronic device, characterized in that, include: A processor, a memory, and a bus, wherein the processor and the memory communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor can execute the method as described in any one of claims 1 to 6 by calling the program instructions.
10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions, which, when executed by a computer, cause the computer to perform the method as described in any one of claims 1 to 6.