Method and apparatus for identifying scale value pointed at by instrument panel pointer, and computer device

Abstract

A method and apparatus for identifying a scale value pointed at by an instrument panel pointer, a computer device, and a storage medium. The method comprises: extracting feature vectors of sample images to form a feature vector set (S101); extracting a feature vector of a target image (S102); computing the similarity between the feature vector of the target image and each feature vector in the feature vector set (S103); and on the basis of the similarities, outputting the sample image having the highest similarity (S104).

Description

Method, device, and computer equipment for identifying instrument panel pointer scale values Technical Field

[0001] The present application relates to the industrial field, and in particular, to a method, apparatus, computer equipment, and storage medium for identifying the scale value of an instrument panel pointer. Background Art

[0002] Vision-based recognition of gauge pointer values ​​is crucial for computer-aided production or automated quality control systems. Due to the vast number of user scenarios, designing a universal method for gauge pointer value recognition is difficult without specialized configuration, especially for gauges designed for software graphical user interfaces (GUIs). Dashboard graphics vary greatly in many aspects, including color, style, and animation.

[0003] Summary of the Invention

[0004] This summary is provided to introduce some selected concepts in a simplified form, which will be further described in the detailed description below. This summary is not intended to identify any key features or essential features of the claimed subject matter, nor is it intended to be used to help determine the scope of the claimed subject matter.

[0005] Based on this, a method for identifying the scale value of a dashboard pointer includes: extracting feature vectors of a sample image to form a feature vector set; extracting feature vectors of a target image; calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set; and outputting a sample image with the highest similarity based on the similarity.

[0006] In the above manner, image recognition can be performed on the target image, thereby matching the sample image of the instrument panel with the highest similarity and obtaining the closest instrument panel scale value.

[0007] Furthermore, outputting the target image with the highest similarity according to the similarity includes outputting the index of the sample image with the highest similarity as a percentage value.

[0008] Through the above method, the index or position of the sample image can be conveniently and accurately located in a series of sample images using a percentage method, thereby facilitating the output of the sample image.

[0009] Furthermore, calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set includes: calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set based on Euclidean distance or cosine distance.

[0010] Through the above method, using Euclidean distance or cosine distance, the similarity value can be easily and accurately calculated, which can be used as a reference for subsequent sample image output.

[0011] Furthermore, calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set includes: calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set according to a value, a vector or a floating point number.

[0012] By using the above method, the similarity is expressed by means of values ​​or vectors, so that the calculation results of the similarity can be analyzed intuitively and conveniently.

[0013] Furthermore, the present application also provides a device for identifying the scale value of an instrument panel pointer, which includes: a sample image extraction module for extracting the feature vector of the sample image to form a feature vector set; a target image extraction module for extracting the feature vector of the target image; a similarity calculation module for calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set; and a sample image output module for outputting the sample image with the highest similarity based on the similarity.

[0014] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the above method when executing the computer program.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the above method when executed by a processor.

[0016] The present application also provides a computer program product, which is tangibly stored on a computer-readable medium and includes computer-executable instructions. When the computer-executable instructions are executed, at least one processor is caused to perform the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Implementations of the present disclosure are illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate the same or similar parts.

[0018] FIG1 is a schematic diagram of a process of a method for identifying the scale value of an instrument panel pointer according to an embodiment of the present application.

[0019] FIG2 is a schematic diagram of a device for identifying the scale value of an instrument panel pointer according to an embodiment of the present application.

[0020] FIG3 is a schematic diagram of a computer device for identifying the scale value of an instrument panel pointer according to an embodiment of the present application.

[0021] FIG4 is a schematic diagram of an embodiment of a method for identifying the scale value of an instrument panel pointer according to an embodiment of the present application.

[0022] The reference numerals are as follows: S101-S104 Step 200: Apparatus 201: Module 202: Module 203: Module 204: Module 300: Computer device 302: Processor 304: Memory DETAILED DESCRIPTION

[0023] In the following description, for the purpose of explanation, a large number of specific details are set forth. However, it is understood that the present invention can be implemented without these specific details. In other examples, well-known circuits, structures, and technologies are not shown in detail so as not to affect the understanding of the description.

[0024] References throughout this specification to "an implementation," "an implementation," "an exemplary implementation," "some implementations," "various implementations," etc., indicate that the implementations of the invention being described may include particular features, structures, or characteristics. However, it does not imply that every implementation must include those particular features, structures, or characteristics. Furthermore, some implementations may have some, all, or none of the features described for other implementations.

[0025] It should be understood that although the various steps in the flowchart of FIG1 are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in FIG1 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0026] The application scenario of this application is to arrange multiple sample images of instrument panels, extract corresponding image features, and then compare them with the features of the target image. The sample image with the highest similarity will be considered to be the image closest to the instrument scale value on the target image, thereby obtaining the corresponding approximate instrument value.

[0027] Specifically, the present application discloses a method for identifying the scale value of an instrument panel pointer, which includes:

[0028] S101, extracting feature vectors of sample images to form a feature vector set.

[0029] The sample image refers to an image of a dashboard. The image can be collected from a video and divided into multiple frames, each of which is a sample image. The sample image represents different scale values ​​of the dashboard, such as 600rpm, 1200rpm, 1800rpm, and so on. From different sample images, a sequence of continuous sample images of the same dashboard can extract a feature vector corresponding to each image. The feature vector reflects the specific content of the different sample images, that is, the images of different scale values ​​of the dashboard, such as 600rpm, 1200rpm, or 1800rpm, are converted into different feature vectors. The multiple feature vectors constitute a feature vector set.

[0030] Furthermore, to extract the feature vector of the sample image, any pre-trained neural network model (such as natural image, face image pre-trained model, etc.) can be used, or features of the image can be extracted based on a pre-designed feature descriptor (such as Dense sift, LBP, etc.).

[0031] S102, extracting the feature vector of the target image.

[0032] Similar to extracting feature vectors for the sample image, the same method can be used to extract feature vectors for the target image. The target image is also an image of the same instrument panel as the registered sample, but the scale of the target image may require identification. Therefore, the same method or model is used to extract the feature vector for the target image.

[0033] In some embodiments, the feature vector may be a feature vector of a length of 256, 512, or 1280, etc., for subsequent similarity comparison. In addition, the values ​​obtained by feature extraction and sampling of the image may also have a certain volume and redundancy to ensure subsequent calculations.

[0034] S103, calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set.

[0035] Among them, the feature vector of the target image is compared with the feature vector of each sample image, and the similarity between them is calculated.

[0036] Furthermore, calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set includes:

[0037] The similarity between the feature vector of the target image and each feature vector in the feature vector set is calculated based on Euclidean distance or cosine distance. In this way, the similarity value can be calculated using Euclidean distance or cosine distance, which can be used as a reference for subsequent sample image output.

[0038] Furthermore, calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set includes:

[0039] The similarity between the feature vector of the target image and each feature vector in the feature vector set is calculated using a value, vector, or floating-point number format. By expressing the similarity using a value or vector format, the similarity calculation results can be intuitively and conveniently analyzed. In some embodiments, the similarity value can also be a value between 0 and 1 to facilitate subsequent comparison, analysis, and extraction.

[0040] S104: Outputting a sample image with the highest similarity according to the similarity.

[0041] Among them, through the above similarity calculation, the sample image with the highest similarity is used as the output.

[0042] Furthermore, outputting a target image with the highest similarity according to the similarity includes outputting an index of the sample image with the highest similarity as a percentage value.

[0043] In a series of sample images, the index or position of the sample image can be conveniently and accurately located using the percentage method, which facilitates the output of the sample image.

[0044] Specifically, outputting the index of the sample image as a percentage can facilitate the accurate positioning and output of the sample image. Furthermore, since the sample images are sampled and sorted from the video in sequence, the percentage output format is also conducive to sequential search.

[0045] Furthermore, the present application relates to a universal method for identifying instrument panel pointer scale values.

[0046] As shown in Figure 4, this application uses a feature matching method to search for the most similar images in a pre-registered sequence feature library, and uses the peak index of the similarity vector as the percentage of the dashboard numerical recognition result. As shown in the figure, after obtaining the similarity results, the similarity results of these multiple sample images can be formed into a curve graph, and the height of the curve reflects the magnitude of the similarity results.

[0047] Specifically, during the enrollment phase, a set of dashboard images are uniformly sampled from the fully recorded dashboard video. The order of each sample is stored for further use during the testing phase. A pre-trained feature extractor is then used to map each image sample to a feature vector. In some embodiments, unlike other end-to-end training-based pointer value recognition methods, the feature extractor model does not need to be specifically trained on the required dashboard images and labels. After feature extraction, this feature library will be ready for use in the testing phase to predict the similarity vector.

[0048] During the testing phase, the dashboard image is sent to the same feature extractor to obtain its feature representation. A distance-based matching function is used to predict the similarity with all samples in the feature library. The similarity vector is then used to index the most similar sample, and its index is used as a percentage value for the dashboard image.

[0049] Previous methods have relied on either complex manual configuration or ad hoc end-to-end models. The method proposed in this application only requires recording the complete animation of the dashboard area as pre-registration, which directly predicts the dashboard pointer value. Furthermore, this method is applicable to any style of unidirectional dashboard numbers, without requiring a specific trained deep learning model.

[0050] In some embodiments, as to verifying whether the method of the present application is implemented, it can be, for example, that if a dashboard pointer value recognition method uses dashboard animation as a pre-registration step, or end-to-end prediction without training samples, then it can be inferred that the method of the present application is implemented.

[0051] FIG2 provides a device 200 for identifying the scale value of a pointer on an instrument panel, which includes:

[0052] The sample image extraction module 201 is used to extract feature vectors of the sample image and form a feature vector set;

[0053] A target image extraction module 202 is used to extract a feature vector of a target image;

[0054] A similarity calculation module 203 is used to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set;

[0055] The sample image output module 204 is configured to output the sample image with the highest similarity according to the similarity.

[0056] The sample image module 201 is further configured to output the index of the sample image with the highest similarity as a percentage value.

[0057] The similarity calculation module 203 is configured to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set based on Euclidean distance or cosine distance.

[0058] The similarity calculation module 203 is configured to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set in a value, vector or floating point manner.

[0059] It should be noted that the apparatus may include more or fewer modules to implement the described functionality. For example, at least one module in FIG. 2 may be further divided into a plurality of different submodules, each of which is configured to perform at least a portion of the operations described herein in conjunction with the corresponding module. Furthermore, in some examples, the apparatus 200 may further include additional modules for performing other operations already described in the specification. Furthermore, those skilled in the art will appreciate that the exemplary apparatus 200 may be implemented using software, hardware, firmware, or any combination thereof.

[0060] Figure 3 provides a computer device. According to one embodiment, the computer device 300 may include a processor 302, which executes a computer program stored in a memory 304. When the computer program is executed by the processor, the above method is implemented.

[0061] Those skilled in the art will understand that the structure shown in Figure 3 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0062] Those skilled in the art will appreciate that all or part of the processes in the methods for implementing the above-mentioned embodiments can be accomplished by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include processes for the implementation of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0063] The present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the above steps when the computer program is executed by a processor.

[0064] The present application also provides a computer program product, which is tangibly stored on a computer-readable medium and includes computer-executable instructions. When the computer-executable instructions are executed, the computer-executable instructions cause at least one processor to perform the above method.

[0065] Furthermore, the computer program can be stored and run in the cloud to perform the method. Furthermore, the components of the program can be deployed on multiple devices and the cloud. For example, the corresponding steps can be deployed and run on a local or local computer, or run on different cloud devices, and transmit signals through a communication connection, or can also be deployed and run on a local or local computer. This application does not limit the manner or method, and the corresponding technology can be flexibly deployed to make full use of equipment and technologies such as the cloud, big data, and supercomputing capabilities to execute and complete the method.

[0066] Some implementations of the present disclosure may include articles of manufacture. Articles of manufacture may include storage media for storing logic. Examples of storage media may include one or more types of computer-readable storage media capable of storing electronic data, including volatile or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, and the like. Examples of logic may include various software units, such as software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, processes, software interfaces, application program interfaces (APIs), instruction sets, computing codes, computer codes, code segments, computer code segments, words, values, symbols, or any combination thereof. In some implementations, for example, articles of manufacture may store executable computer program instructions that, when executed by a processor, cause the processor to perform the methods and / or operations described herein. Executable computer program instructions may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. Executable computer program instructions can be implemented according to a predefined computer language, method or syntax for commanding a computer to perform a specific function. The instructions can be implemented using any appropriate high-level, low-level, object-oriented, visual, compiled and / or interpreted programming language.

[0067] What has been described above includes examples of the disclosed architecture. It is, of course, not possible to describe every conceivable combination of components and / or methodologies, but those skilled in the art will appreciate that many other combinations and permutations are possible. Therefore, the novel architecture is intended to embrace all such alternatives, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A method for identifying the scale value of a dashboard pointer, wherein: include: Extract the feature vector of the sample image, Composed feature vector set; Extract feature vector of target image; Calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set; According to the similarity, a sample image with the highest similarity is output.

2. The method according to claim 1, wherein: According to the similarity, the sample image with the highest similarity is output, including: The index of the target image with the highest similarity is output as a percentage value.

3. The method according to claim 1, wherein: Calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set includes: The similarity between the feature vector of the target image and each feature vector in the feature vector set is calculated according to the Euclidean distance or the cosine distance.

4. The method according to claim 1, wherein: Calculating the similarity between the feature vector of the target image and each feature vector in the feature vector set, including: The similarity between the feature vector of the target image and each feature vector in the feature vector set is calculated according to the value, vector or floating point number method.

5. A device (200) for identifying the scale value of a pointer on an instrument panel, wherein: include: A sample image extraction module (201) is used to extract a feature vector of a sample image. Composed feature vector set; A target image extraction module (202), used for extracting a feature vector of a target image; A similarity calculation module (203) is used to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set; The sample image output module (204) is used to output the sample image with the highest similarity according to the similarity.

6. The device (200) according to claim 5, wherein: The sample image module (201) is further configured to output the index of the sample image with the highest similarity as a percentage value.

7. The device (200) according to claim 5, wherein: The similarity calculation module (203) is used to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set according to the Euclidean distance or the cosine distance.

8. The device (200) according to claim 5, wherein: The similarity calculation module (203) is used to calculate the similarity between the feature vector of the target image and each feature vector in the feature vector set according to a value, a vector or a floating point number.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

11. A computer program product tangibly stored on a computer readable medium and comprising computer executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1 to 4.

Images