Ranging method and system based on multi-scene image fusion

Abstract

The invention provides a distance measurement method and system based on multi-scene image fusion, and belongs to the technical field of data processing.The method comprises the steps that firstly, a controller obtains a first scene image based on a visible light sensor, performs feature extraction on the first scene image, determines a target feature corresponding to distance measurement target equipment according to a feature extraction result, and then sends the target feature to the target equipment; and performing three-dimensional reconstruction on the distance measurement target equipment based on the first target image, obtaining a second scene image through the infrared light sensor, and performing decomposition and feature matching on the infrared light image to obtain half-body models of the distance measurement target equipment in two different directions. And the distance of the distance measuring target equipment is calculated by combining the half body model with a preset distance between the visible light sensor and the infrared light sensor.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular relates to a distance measurement method and system based on multi-scene image fusion. Background Art

[0002] During the visual inspection of power equipment, it is usually necessary to obtain a large amount of data, such as infrared light spectra, distance, etc. This data is crucial for analyzing the operating status of power equipment.

[0003] Traditional distance detection equipment usually uses binocular cameras or laser rangefinders for measurement. Operators need to use a large number of devices to obtain data. The equipment is expensive and large in size, making it difficult to carry. Summary of the Invention

[0004] The embodiments of the present application provide a ranging method and system based on multi-scene image fusion to improve the above-mentioned problems.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, embodiments of the present application provide a ranging method based on multi-scene image fusion. The method is applicable to a ranging device, the ranging device including a visible light sensor, an infrared light sensor, and a controller, wherein the visible light sensor and the infrared light sensor are separated by a preset distance. The method includes:

[0007] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction;

[0008] The controller determines a first target image based on the target feature, where the first target image is a screen image occupied by the ranging target in the first scene image;

[0009] The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image;

[0010] The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image;

[0011] The controller performs three-dimensional reconstruction of the ranging target device based on the second target image and determines a corresponding second half-body model in the second scene image, wherein the second half-body model is a model corresponding to the screen of the ranging target device displayed in the second scene image in the second scene image;

[0012] The controller determines a target distance of the ranging target device based on the first half body model, the second half body model and a preset distance.

[0013] In combination with the first aspect, optionally, the controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device based on a result of the feature extraction, including:

[0014] The controller obtains a preset feature, performs feature matching on the preset feature and the first scene image, and determines a target feature according to the matching result, wherein the target feature is a contour feature.

[0015] In combination with the first aspect, optionally, the controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image, including:

[0016] The controller divides the second scene image according to grayscale gradients so that the second scene image forms a plurality of sub-images;

[0017] The controller obtains the boundary contours of all sub-images, matches the boundary contours with target features, and determines a second target image from the multiple sub-images based on the matching results.

[0018] In combination with the first aspect, optionally, the controller obtains boundary contours of all sub-images, matches the boundary contours with target features, and determines a second target image from the multiple sub-images based on the matching results, including:

[0019] The controller fits the target feature with the multiple boundary contours, sorts the multiple boundary contours according to the degree of fit, and determines the sub-image corresponding to the boundary contour with the highest degree of fit as the second target image.

[0020] In combination with the first aspect, optionally, the controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device based on a result of the feature extraction, including:

[0021] The controller extracts edge information of the device from the first scene image, wherein an algorithm adopted in the extraction process is a Canny algorithm or a Sobel algorithm;

[0022] The controller extracts corner point information of the device from the first scene image, wherein an algorithm used in the extraction process is a Harris algorithm or a FAST algorithm;

[0023] The controller matches the edge information and the corner point information with the preset features of the ranging target device and determines the target features corresponding to the ranging target device.

[0024] In combination with the first aspect, optionally, the controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device based on a result of the feature extraction, including:

[0025] The controller extracts surface texture features of the device from the first scene image.

[0026] In conjunction with the first aspect, optionally, the controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image, including:

[0027] The controller matches features in the first target image, wherein the matching process includes directly obtaining a model of the device to be detected;

[0028] The controller determines the scale size and position information of the device to be detected based on the result of the feature matching;

[0029] The controller determines the first half body model based on the scaled size and position information of the device to be detected.

[0030] In combination with the first aspect, optionally, the controller determines a target distance of the ranging target device based on the first half body model, the second half body model, and a preset distance, including:

[0031] The controller aligns the first half body model and the second half body model in three-dimensional space using common features and obtains a parallax angle;

[0032] The controller calculates the target distance of the ranging target according to the parallax angle and the preset distance through triangulation.

[0033] In a second aspect, embodiments of the present application provide a ranging system based on multi-scene image fusion. The system is applicable to a ranging device, the ranging device including a visible light sensor, an infrared light sensor, and a controller. The visible light sensor and the infrared light sensor are separated by a preset distance. The system is configured as follows:

[0034] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction;

[0035] The controller determines a first target image based on the target feature, where the first target image is a screen image occupied by the ranging target in the first scene image;

[0036] The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image;

[0037] The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image;

[0038] The controller performs three-dimensional reconstruction of the ranging target device based on the second target image and determines a corresponding second half-body model in the second scene image, wherein the second half-body model is a model corresponding to the screen of the ranging target device displayed in the second scene image in the second scene image;

[0039] The controller determines a target distance of the ranging target device based on the first half body model, the second half body model and a preset distance.

[0040] In conjunction with the second aspect, optionally, the controller acquires a first scene image based on a visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device based on a result of the feature extraction, including:

[0041] The controller obtains a preset feature, performs feature matching on the preset feature and the first scene image, and determines a target feature according to the matching result, wherein the target feature is a contour feature.

[0042] In conjunction with the second aspect, optionally, the system is configured to:

[0043] The controller acquires a second scene image based on the infrared light sensor and determines a second target image in the second scene image according to the target feature. The second target image is an infrared screen image occupied by the ranging target in the second scene image, including:

[0044] The controller divides the second scene image according to grayscale gradients so that the second scene image forms a plurality of sub-images;

[0045] The controller obtains the boundary contours of all sub-images, matches the boundary contours with target features, and determines a second target image from the multiple sub-images based on the matching results.

[0046] In conjunction with the second aspect, optionally, the system is configured to:

[0047] The controller obtains the boundary contours of all sub-images and matches the boundary contours with the target features, and determines a second target image from the multiple sub-images based on the matching results, including:

[0048] The controller fits the target feature with the multiple boundary contours, sorts the multiple boundary contours according to the degree of fit, and determines the sub-image corresponding to the boundary contour with the highest degree of fit as the second target image.

[0049] In conjunction with the second aspect, optionally, the system is configured to:

[0050] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including:

[0051] The controller extracts edge information of the device from the first scene image, wherein an algorithm adopted in the extraction process is a Canny algorithm or a Sobel algorithm;

[0052] The controller extracts corner point information of the device from the first scene image, wherein an algorithm used in the extraction process is a Harris algorithm or a FAST algorithm;

[0053] The controller matches the edge information and the corner point information with the preset features of the ranging target device and determines the target features corresponding to the ranging target device.

[0054] In conjunction with the second aspect, optionally, the system is configured to:

[0055] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including:

[0056] The controller extracts surface texture features of the device from the first scene image.

[0057] In conjunction with the second aspect, optionally, the system is configured to:

[0058] The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image, including:

[0059] The controller matches features in the first target image, wherein the matching process includes directly obtaining a model of the device to be detected;

[0060] The controller determines the scale size and position information of the device to be detected based on the result of the feature matching;

[0061] The controller determines the first half body model based on the scaled size and position information of the device to be detected.

[0062] In conjunction with the second aspect, optionally, the system is configured to:

[0063] The controller determines a target distance of the ranging target device based on the first half body model, the second half body model, and a preset distance, including:

[0064] The controller aligns the first half body model and the second half body model in three-dimensional space using common features and obtains a parallax angle;

[0065] The controller calculates the target distance of the ranging target according to the parallax angle and the preset distance through triangulation.

[0066] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0067] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method proposed in the first aspect of the embodiment of the present invention.

[0068] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method provided in the first aspect of the embodiment of the present invention is implemented.

[0069] In summary, the above method and device have the following technical effects:

[0070] The embodiments of the present application propose a ranging method and system based on multi-scene image fusion. First, the controller acquires a first scene image based on a visible light sensor and performs feature extraction on the first scene image. The target features corresponding to the ranging target device are determined based on the feature extraction results. Then, the ranging target device is three-dimensionally reconstructed based on the first target image, and a second scene image is acquired through an infrared light sensor. By decomposing and feature matching the infrared light image, a half-body model of the ranging target device in two different directions can be obtained. The half-body model is combined with a preset distance between the visible light sensor and the infrared light sensor to calculate the distance to the ranging target device. The embodiments of the present application propose a ranging method and system based on multi-scene image fusion. The feature data acquired by the visible light sensor is used to perform feature matching on the data acquired by the infrared light sensor. Depth data can be acquired using only one visible light sensor and one infrared light sensor, reducing the cost of the ranging device while also making it easier to carry. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A flowchart of a distance measurement method based on multi-scene image fusion proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0072] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0073] Traditional binocular ranging equipment requires two cameras with essentially identical parameters, making the device bulky and unwieldy. When not measuring distance, a single camera is sufficient for image acquisition. In actual detection, infrared data is often required. Therefore, the inventors devised a method to replace the binocular camera with an infrared camera, achieving the goal of monocular ranging with a single optical sensor.

[0074] This application proposes a distance measurement method based on multi-scene image fusion, which is applicable to a distance measurement device. The distance measurement device includes a visible light sensor, an infrared light sensor, and a controller. The visible light sensor and the infrared light sensor are separated by a preset distance. For example, the device can be handheld, and the visible light sensor and the infrared light sensor are respectively set on the left and right sides and facing forward. Of course, in other embodiments, they can also be set up top and bottom, which is not limited in this application. Please refer to Figure 1 , the method comprises the following steps:

[0075] S101: The controller acquires a first scene image based on a visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to a ranging target device according to a result of the feature extraction.

[0076] In the present invention, a controller uses a visible light sensor to capture a first scene image. The controller then performs a feature extraction process on the captured first scene image. By analyzing the feature extraction results, the controller can identify and determine the target features corresponding to the ranging target device.

[0077] Specifically, as an implementation method, the controller obtains a preset feature, performs feature matching on the preset feature and the first scene image, and determines a target feature according to the matching result, wherein the target feature is a contour feature.

[0078] It is understandable that in this embodiment, the controller obtains a set of pre-set feature information, which can be feature points, edges, textures, etc. commonly used in image recognition. The controller then performs a detailed feature matching analysis on these preset features and the first scene image. Through this matching process, the controller can identify the corresponding parts that match the preset features. Based on the matching results, the controller further determines the target features, which are generally contour features in the image. Contour features are a very important aspect of image recognition, which can help identify and distinguish different objects in the image.

[0079] As an embodiment, the controller can extract the edge information of the device from the first scene image, wherein the algorithm used in the extraction process is the Canny algorithm or the Sobel algorithm. The controller can extract the edge information of the device from the first scene image, wherein the algorithm used in the extraction process is the Canny algorithm or the Sobel algorithm. It is understandable. The Canny algorithm uses a Gaussian filter to smooth the image, reduce noise interference, and then identifies possible edge points by calculating the image gradient. At the same time, the Canny algorithm applies non-maximum suppression to refine the edge, and finally determines the final edge through dual threshold detection.

[0080] For the Sobel algorithm, it focuses on using the first-order derivative operator to calculate the approximate value of the image grayscale gradient to identify edges.

[0081] It can be understood that through these two algorithms, the controller can accurately extract the edge information of the device in the first scene image, providing key data for subsequent image fusion and ranging.

[0082] The controller extracts device corner information from the first scene image using a Harris algorithm or a FAST algorithm. The controller then matches the edge information and corner information with pre-set features of the ranging target device and determines the target features corresponding to the ranging target device.

[0083] Optionally, in some other embodiments, the controller extracts surface texture features of the device from the first scene image. The specific method of feature extraction is not described in detail in this application.

[0084] S102: The controller determines a first target image based on the target feature, where the first target image is a screen image occupied by the ranging target in the first scene image.

[0085] It can be understood that, based on the target features, the controller is responsible for determining a first target image. This first target image actually represents the specific screen image occupied by the ranging target in the first scene image.

[0086] S103: The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image according to the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image.

[0087] As will be appreciated, the controller uses the first target image to perform an accurate 3D reconstruction of the ranging target device. This 3D reconstruction technique enables the controller to analyze the target device's geometric structure in detail. Subsequently, based on the 3D reconstruction results, the controller further determines a first half-body model corresponding to the first scene image. This first half-body model represents the 3D model of the portion of the image presented by the ranging target device in the first scene image. In other words, the first half-body model is constructed based on the displayed portion of the ranging target device in the first scene image and accurately reflects the target device's spatial position and form within the scene.

[0088] Specifically, in this embodiment, the controller may match features in the first target image, wherein the matching process includes directly obtaining a model of the device to be detected. The controller then determines the scaled size and position information of the device to be detected based on the feature matching results. Finally, the controller determines the first half-body model based on the scaled size and position information of the device to be detected.

[0089] S104: The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image.

[0090] As can be understood, since the second scene image is an infrared image, conventional image feature recognition techniques are prone to significant errors when applied to infrared images. Therefore, in this embodiment, the controller segments the second scene image according to grayscale gradients to form multiple sub-images. The controller then obtains the boundary contours of all sub-images and matches these boundary contours with target features. Based on the matching results, the controller determines the second target image from the multiple sub-images. As can be understood, the edges of devices or objects in infrared images segmented by grayscale are inherently clear. Therefore, they can be directly used for edge matching.

[0091] Therefore, in this embodiment, the controller may fit the target feature with multiple boundary contours, sort the multiple boundary contours according to the degree of fit, and determine the sub-image corresponding to the boundary contour with the highest degree of fit as the second target image.

[0092] S105: The controller performs three-dimensional reconstruction of the ranging target device based on the second target image, and determines a corresponding second half-body model in the second scene image, wherein the second half-body model is a model corresponding to the screen of the ranging target device displayed in the second scene image in the second scene image.

[0093] It is understandable that after feature matching, the process of how to perform three-dimensional reconstruction can be referred to step S103, which will not be described in detail here.

[0094] S106: The controller determines a target distance of the ranging target device based on the first half body model, the second half body model and the preset distance.

[0095] Exemplarily, as an embodiment, the controller can align the first half body model and the second half body model through common features in three-dimensional space and obtain the parallax angle. Then, the controller calculates the target distance of the ranging target according to the parallax angle and the preset distance through triangulation.

[0096] The present application proposes a ranging method based on multi-scene image fusion. First, the controller acquires a first scene image based on a visible light sensor and performs feature extraction on the first scene image. The target features corresponding to the ranging target device are determined based on the feature extraction results. Then, the ranging target device is three-dimensionally reconstructed based on the first target image, and a second scene image is acquired through an infrared light sensor. By decomposing the infrared light image and performing feature matching, a half-body model of the ranging target device in two different directions can be obtained. The distance to the ranging target device is calculated by combining the half-body model with a preset distance between the visible light sensor and the infrared light sensor. The present application proposes a ranging method based on multi-scene image fusion. The feature data acquired by the visible light sensor is used to perform feature matching on the data acquired by the infrared light sensor. Depth data can be acquired using only one visible light sensor and one infrared light sensor, which reduces the cost of the ranging device while also making it easier to carry.

[0097] Based on the same inventive concept, an embodiment of the present application further proposes a ranging system based on multi-scene image fusion. The system is applicable to a ranging device, which includes a visible light sensor, an infrared light sensor, and a controller. The visible light sensor and the infrared light sensor are separated by a preset distance. The system is configured as follows:

[0098] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction;

[0099] The controller determines a first target image based on the target feature, where the first target image is a screen image occupied by the ranging target in the first scene image;

[0100] The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image;

[0101] The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image;

[0102] The controller performs three-dimensional reconstruction of the ranging target device based on the second target image and determines a corresponding second half-body model in the second scene image, wherein the second half-body model is a model corresponding to the screen of the ranging target device displayed in the second scene image in the second scene image;

[0103] The controller determines a target distance of the ranging target device based on the first half body model, the second half body model and a preset distance.

[0104] Optionally, the controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including:

[0105] The controller obtains a preset feature, performs feature matching on the preset feature and the first scene image, and determines a target feature according to the matching result, wherein the target feature is a contour feature.

[0106] Optionally, the system is configured to:

[0107] The controller acquires a second scene image based on the infrared light sensor and determines a second target image in the second scene image according to the target feature. The second target image is an infrared screen image occupied by the ranging target in the second scene image, including:

[0108] The controller divides the second scene image according to grayscale gradients so that the second scene image forms a plurality of sub-images;

[0109] The controller obtains the boundary contours of all sub-images, matches the boundary contours with target features, and determines a second target image from the multiple sub-images based on the matching results.

[0110] Optionally, the system is configured to:

[0111] The controller obtains the boundary contours of all sub-images and matches the boundary contours with the target features, and determines a second target image from the multiple sub-images based on the matching results, including:

[0112] The controller fits the target feature with the multiple boundary contours, sorts the multiple boundary contours according to the degree of fit, and determines the sub-image corresponding to the boundary contour with the highest degree of fit as the second target image.

[0113] Optionally, the system is configured to:

[0114] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including:

[0115] The controller extracts edge information of the device from the first scene image, wherein an algorithm adopted in the extraction process is a Canny algorithm or a Sobel algorithm;

[0116] The controller extracts corner point information of the device from the first scene image, wherein an algorithm used in the extraction process is a Harris algorithm or a FAST algorithm;

[0117] The controller matches the edge information and the corner point information with the preset features of the ranging target device and determines the target features corresponding to the ranging target device.

[0118] Optionally, the system is configured to:

[0119] The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including:

[0120] The controller extracts surface texture features of the device from the first scene image.

[0121] Optionally, the system is configured to:

[0122] The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on the result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to the screen of the ranging target device displayed in the first scene image in the first scene image, including:

[0123] The controller matches features in the first target image, wherein the matching process includes directly obtaining a model of the device to be detected;

[0124] The controller determines the scale size and position information of the device to be detected based on the result of the feature matching;

[0125] The controller determines the first half body model based on the scaled size and position information of the device to be detected.

[0126] Optionally, the system is configured to:

[0127] The controller determines a target distance of the ranging target device based on the first half body model, the second half body model, and a preset distance, including:

[0128] The controller aligns the first half body model and the second half body model in three-dimensional space using common features and obtains a parallax angle;

[0129] The controller calculates the target distance of the ranging target according to the parallax angle and the preset distance through triangulation.

[0130] The present application proposes a ranging system based on multi-scene image fusion. First, the controller acquires a first scene image based on a visible light sensor and performs feature extraction on the first scene image. The target features corresponding to the ranging target device are determined based on the feature extraction results. Then, the ranging target device is three-dimensionally reconstructed based on the first target image, and a second scene image is acquired through an infrared light sensor. By decomposing the infrared light image and performing feature matching, a half-body model of the ranging target device in two different directions can be obtained. The half-body model is combined with a preset distance between the visible light sensor and the infrared light sensor to calculate the distance to the ranging target device. The present application proposes a ranging system based on multi-scene image fusion. The feature data acquired by the visible light sensor is used to perform feature matching on the data acquired by the infrared light sensor. Depth data can be acquired using only one visible light sensor and one infrared light sensor, which reduces the cost of the ranging device while also making it easier to carry.

[0131] Based on the same inventive concept, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0132] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the automatic overheating protection method for a universal testing machine based on an embodiment of the present application.

[0133] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the automatic overheating protection method based on a universal testing machine according to an embodiment of the present application.

[0134] The following is a detailed introduction to the various components of electronic equipment:

[0135] The term "processor" is the control center of an electronic device and may be a single processor or a collective term for multiple processing elements. For example, the processor may be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0136] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0137] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0138] Alternatively, the memory may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processor through an interface circuit of the electronic device, and this is not specifically limited in the embodiments of the present invention.

[0139] A transceiver is used to communicate with network devices or terminal devices.

[0140] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0141] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0142] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, and will not be repeated here.

[0143] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0144] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0145] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function according to the embodiments of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (such as floppy disks, hard disks, tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0146] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0147] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0148] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0149] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

Claims

1. A ranging method based on multi-scene image fusion, characterized in that: The method is applicable to a distance measuring device, the distance measuring device including a visible light sensor, an infrared light sensor, and a controller, the visible light sensor and the infrared light sensor being separated by a preset distance, the method comprising: The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction; The controller determines a first target image based on the target feature, where the first target image is a screen image occupied by the ranging target in the first scene image; The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines a first half-body model corresponding to the first scene image based on a result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to a screen of the ranging target device displayed in the first scene image in the first scene image; The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, where the second target image is an infrared screen image occupied by the ranging target in the second scene image; The controller performs three-dimensional reconstruction of the ranging target device based on the second target image, and determines a second half-body model corresponding to the second scene image, wherein the second half-body model is a model corresponding to the screen of the ranging target device displayed in the second scene image in the second scene image; The controller determines a target distance of the ranging target device based on the first half-body model, the second half-body model, and the preset distance.

2. The distance measurement method according to claim 1, wherein: The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines a target feature corresponding to the ranging target device according to a result of the feature extraction, including: The controller obtains a preset feature, performs feature matching on the preset feature and the first scene image, and determines the target feature according to the matching result, wherein the target feature is a contour feature.

3. The distance measurement method according to claim 1, wherein: The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines the target feature corresponding to the ranging target device according to the result of the feature extraction, further comprising: The controller extracts edge information of the device from the first scene image, wherein an algorithm used in the extraction process is a Canny algorithm or a Sobel algorithm; The controller extracts corner point information of the device from the first scene image, wherein an algorithm used in the extraction process is a Harris algorithm or a FAST algorithm; The controller matches the edge information and the corner point information with the preset features of the ranging target device, and determines the target features corresponding to the ranging target device.

4. The distance measurement method according to claim 1, wherein: The controller acquires a first scene image based on the visible light sensor, performs feature extraction on the first scene image, and determines the target feature corresponding to the ranging target device according to the result of the feature extraction, further comprising: The controller extracts surface texture features of the device from the first scene image.

5. The distance measurement method according to claim 1, wherein: The controller performs three-dimensional reconstruction of the ranging target device based on the first target image, and determines, according to a result of the three-dimensional reconstruction, a first half-body model corresponding to the first scene image, including: The controller matches features in the first target image, wherein the matching process includes directly obtaining a model of the device to be detected; The controller determines the scaling size and position information of the device to be detected based on the result of the feature matching; The controller determines the first half-body model based on the scaled size and position information of the device to be detected.

6. The distance measurement method according to claim 1, wherein: The controller acquires a second scene image based on the infrared light sensor, and determines a second target image in the second scene image according to the target feature, including: The controller divides the second scene image according to grayscale gradients so that the second scene image forms a plurality of sub-images; The controller obtains boundary contours of all the sub-images, matches the boundary contours with the target features, and determines the second target image from the plurality of sub-images based on the matching results.

7. The distance measurement method according to claim 6, characterized in that: The controller obtains boundary contours of all the sub-images, matches the boundary contours with the target features, and determines the second target image from the plurality of sub-images based on the matching results, including: The controller fits the target feature with the plurality of boundary contours, sorts the plurality of boundary contours according to the degree of fit, and determines the sub-image corresponding to the boundary contour with the highest degree of fit as the second target image.

8. The distance measurement method according to claim 1, wherein: The controller determining the target distance of the ranging target device based on the first half body model, the second half body model and the preset distance includes: The controller aligns the first half body model and the second half body model in three-dimensional space using common features and obtains a parallax angle; The controller calculates the target distance of the ranging target according to the parallax angle and the preset distance through triangulation.

9. A ranging system based on multi-scene image fusion, characterized in that: The system is applicable to a distance measuring device, the distance measuring device including a visible light sensor, an infrared light sensor, and a controller, the visible light sensor and the infrared light sensor being separated by a preset distance, and the system including: a feature extraction module, configured to acquire a first scene image based on the visible light sensor through a controller, perform feature extraction on the first scene image, and determine a target feature corresponding to the ranging target device according to a result of the feature extraction; A first target recognition module is configured to determine a first target image based on the target features through a controller, where the first target image is a screen image occupied by the ranging target in the first scene image; a first three-dimensional modeling module, configured to perform three-dimensional reconstruction of the ranging target device based on the first target image via a controller, and determine a first half-body model corresponding to the first scene image based on a result of the three-dimensional reconstruction, wherein the first half-body model is a model corresponding to a screen of the ranging target device displayed in the first scene image in the first scene image; a second target recognition module, configured to acquire a second scene image based on the infrared light sensor through a controller, and determine a second target image in the second scene image according to the target features, where the second target image is an infrared screen image occupied by the ranging target in the second scene image; a second three-dimensional modeling module, configured to perform three-dimensional reconstruction of the ranging target device based on the second target image through a controller, and determine a corresponding second half-body model in the second scene image, wherein the second half-body model is a model corresponding to a screen of the ranging target device displayed in the second scene image in the second scene image; The distance calculation module is configured to determine the target distance of the ranging target device based on the first half body model, the second half body model and the preset distance through a controller.

10. An electronic device, characterized in that: The electronic device includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8.

Images