WO2020124701A1 - 一种温度检测方法及装置 - Google Patents
一种温度检测方法及装置 Download PDFInfo
- Publication number
- WO2020124701A1 WO2020124701A1 PCT/CN2019/070734 CN2019070734W WO2020124701A1 WO 2020124701 A1 WO2020124701 A1 WO 2020124701A1 CN 2019070734 W CN2019070734 W CN 2019070734W WO 2020124701 A1 WO2020124701 A1 WO 2020124701A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- temperature
- thermal infrared
- infrared image
- information
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000009529 body temperature measurement Methods 0.000 title abstract 3
- 238000001514 detection method Methods 0.000 claims abstract description 64
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 43
- 230000011218 segmentation Effects 0.000 claims abstract description 19
- 239000003086 colorant Substances 0.000 claims abstract description 9
- 238000013139 quantization Methods 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012015 optical character recognition Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 abstract description 9
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
- G01J5/485—Temperature profile
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/80—Calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Definitions
- This application relates to the field of electric power, and in particular, to a temperature detection method and device.
- the inspection device of the power system also becomes more and more perfect.
- the temperature will usually have a very large influence on the power equipment. Therefore, the The temperature detection of the above power equipment is very important.
- the traditional method uses a temperature sensor for detection, which makes the temperature limit of the temperature sensor will have a certain limit on the detection, and the above temperature sensor is not allowed to contact power in many cases
- the equipment makes the sensing space have deviations, which will detect unnecessary factors into it, which will reduce the measurement accuracy.
- the present application provides a temperature detection method and device, which can detect the temperature of power equipment through an external device, so that it is not limited by the temperature sensor to high and low temperature, and can also eliminate the deviation of the sensing space. Improve measurement accuracy.
- the present application provides a temperature detection method, which is applied to the field of electric power, including:
- the segmented image is an image from which image information irrelevant to the power device is removed;
- the step of detecting and analyzing the thermal infrared image according to a preset artificial intelligence model to obtain the position information of the power device includes:
- the method further includes:
- the step of quantizing the colors included in the segmented image to obtain temperature distribution information includes:
- the color detection model is obtained through training of a supervised algorithm
- the segmented image is processed according to the conversion rule to obtain temperature distribution information.
- the artificial intelligence model is a convolutional neural network artificial intelligence model.
- the convolutional neural network artificial intelligence model is based on the big data created by the pictures marked with the category and location of the power equipment. Basic training.
- the present application provides a temperature detection device, which is applied to the field of electric power, including:
- An acquisition module configured to acquire thermal infrared images of power equipment
- the detection module is configured to detect and analyze the thermal infrared image according to a preset artificial intelligence model to obtain position information of the power device; the position information is configured to represent the power device in the thermal infrared image position;
- a segmentation module configured to segment the thermal infrared image according to the location information and a preset segmentation algorithm to obtain a segmented image; the segmented image is an image from which image information irrelevant to the power device is removed;
- the quantization module is configured to quantize the color included in the divided image to obtain temperature distribution information.
- the detection module includes:
- An acquisition submodule configured to acquire a visible light image of the power equipment
- the detection sub-module is configured to detect and analyze the thermal infrared image and the visible light image according to the artificial intelligence model to obtain position information of the power device.
- the temperature detection device further includes:
- a storage module configured to store the thermal infrared image, the visible light image, and the temperature distribution information to a database, so that the database outputs an instrument including the thermal infrared image, the visible light image, and the temperature distribution information Figure.
- the present application provides a computer device, the computer device includes a memory and a processor, the memory is configured to store a computer program, and the processor runs the computer program to cause the computer device to execute the application A temperature detection method as described in the first aspect.
- the present application provides a computer-readable storage medium that stores the computer program used in the computer device described in the third aspect of the present application.
- the thermal infrared image of the power equipment in the power system can be acquired, and the thermal infrared image is detected and analyzed based on the preset artificial intelligence model to confirm the power equipment in the thermal infrared image. Specific location, and then, the thermal infrared image is segmented according to the specific location to obtain a segmented image including only power equipment, and the segmented image is quantized to obtain temperature distribution information.
- the implementation of this embodiment can detect the temperature of the power equipment through the external camera device, so that it is not limited by the temperature sensor to the high and low temperature, and the deviation of the sensing space can be eliminated by artificial intelligence to obtain accurate power equipment
- the temperature division information can improve the measurement accuracy.
- FIG. 1 is a schematic flowchart of a temperature detection method provided by the first embodiment of the present application
- FIG. 2 is a schematic flowchart of a temperature detection method provided by a second embodiment of the present application.
- FIG. 3 is a schematic structural diagram of a temperature detection device according to a third embodiment of the present application.
- this application provides a temperature detection method, which can obtain thermal infrared images of power equipment in the power system, and detect and analyze the thermal infrared images based on a preset artificial intelligence model to confirm The specific position of the power device in the thermal infrared image, and then, the thermal infrared image is segmented according to the specific position to obtain a segmented image including only the power device, and the segmented image is quantized to obtain temperature distribution information.
- the implementation of this embodiment can detect the temperature of the power equipment through the external camera device, so that it is not limited by the temperature sensor to the high and low temperature, and the deviation of the sensing space can be eliminated by artificial intelligence to obtain accurate power equipment
- the temperature division information can improve the measurement accuracy.
- the above-mentioned technical method can also be implemented by using relevant software or hardware, which will not be repeated in this embodiment.
- relevant software or hardware which will not be repeated in this embodiment.
- FIG. 1 is a schematic flowchart of a temperature detection method provided by this embodiment.
- the temperature detection method includes the following steps:
- the power equipment includes various equipment in the power system, such as voltage transformation equipment, power transmission equipment, and towers.
- the thermal infrared image is image information captured by a thermal image camera, and is also called a thermal image.
- the thermal infrared image is configured to display color information of the power device corresponding to the temperature.
- S102 Detect and analyze the thermal infrared image according to a preset artificial intelligence model to obtain position information of the power device; the position information is configured to represent the position of the power device in the thermal infrared image.
- the artificial intelligence model is a convolutional neural network artificial intelligence model.
- the convolutional neural network artificial intelligence model is obtained by training on the basis of big data created by pictures marked with categories and locations of power equipment.
- the artificial intelligence model is configured to detect and analyze the category and location of the power device on the thermal infrared image, thereby obtaining accurate location information of the power device, where the location information may include contour information of the power device.
- the location information may be the location information of the pointer to the background, and in some special cases, it may also include geographic location information, that is, latitude and longitude information.
- the position of the electronic device in the thermal infrared image is the position of the electronic device in the background of the picture.
- S103 Perform image segmentation on the thermal infrared image according to the location information and a preset segmentation algorithm to obtain a segmented image; the segmented image is an image from which image information irrelevant to the power device is removed.
- the segmentation algorithm is performed at the pixel level.
- the dedicated thermal infrared image of the power device can be completed through pixel-level image segmentation, so that the accuracy can be improved.
- the divided image includes only the image of the power device, that is, it does not include any background image.
- the segmentation algorithm may be a fitting algorithm for position information, which is configured to fit the position information to obtain a better segmentation scheme for subsequent segmentation; the segmentation algorithm may also be a multiple segmentation algorithm, which Based on the location information, the power device image can be segmented layer by layer, so as to achieve the effect of accurate segmentation.
- the image of image information irrelevant to the power device can be understood as a background image.
- the segmented image is an image with multiple colors, where each color represents a different temperature; therefore, the quantization process is to convert the above-mentioned colors into visualized temperature information, so that other equipment or workers can observe and Patrol.
- the temperature division information may include information such as temperature distribution maps and/or temperature distribution tables to combine the image data, and this embodiment is not limited in any way.
- the thermal infrared image of the power device in the power system can be obtained, and the thermal infrared image is detected and analyzed based on the preset artificial intelligence model to confirm the power device in the thermal infrared image. Specific location, and then, the thermal infrared image is segmented according to the specific location to obtain a segmented image including only power equipment, and the segmented image is quantized to obtain temperature distribution information.
- the temperature detection method described in FIG. 1 can detect the temperature of the power equipment through the external camera device, so that it is not limited by the temperature sensor to the high and low temperature, and the deviation of the sensing space can be eliminated by artificial intelligence. Accurately divide temperature information of power equipment, which can improve measurement accuracy.
- FIG. 2 is a schematic flowchart of a temperature detection method provided by this embodiment. As shown in Figure 2, the temperature detection method includes the following steps:
- the thermal infrared image includes thermal infrared images of the power equipment and the background.
- the visible light image matches the thermal infrared image.
- the visible light image can assist the thermal infrared image to effectively separate the outline and position of the power device, and at the same time, the visible light image can effectively separate the difference between the power device and the background.
- the visible light image may include a color image.
- the artificial intelligence model may include two, one of which is a convolutional neural network artificial intelligence model.
- the convolutional neural network artificial intelligence model is based on a thermal infrared image marked with the type and location of the power equipment.
- the data is based on training; the other is also an artificial neural network artificial intelligence model, but the artificial neural network model of convolutional neural network is based on the training of big data based on visible light images marked with the type and location of power equipment.
- the artificial intelligence model can also detect and analyze the two images and combine them to obtain effective position information of the power equipment.
- the artificial intelligence model can detect and analyze two different images (thermal infrared image and visible light image) to obtain respective analysis results, and according to the respective analysis results Combined to obtain the location information of the power equipment.
- the specific structure in the artificial intelligence model is not limited in this embodiment.
- S204 Perform image segmentation on the thermal infrared image according to the location information and a preset segmentation algorithm to obtain a segmented image; the segmented image is an image from which image information irrelevant to the power device is removed.
- the thermal infrared image includes temperature information, so this step may be supplemented by a visible light image or may not be a visible light image.
- Embodiment 1 the same or similar definitions can be directly referred to the content described in Embodiment 1, which is not limited in this embodiment.
- the color detection model is also an artificial intelligence model.
- the color detection model may also be a convolutional neural network artificial intelligence model; the color detection model is configured to detect the temperature meter included in the segmented image.
- the color detection model is obtained by training with a supervised algorithm.
- the temperature meter is configured to represent color conversion information between the lowest temperature and the highest temperature in the segmented image, where the temperature meter also includes information such as the highest temperature value and the lowest temperature value.
- the information included in the temperature meter includes at least the above information, and may also include temperature information higher than the highest temperature value and temperature information lower than the lowest temperature value.
- the optical character recognition technology may include OCR character recognition technology.
- the conversion rule is configured to convert the color in the divided image to a temperature value.
- the conversion rule can also be calculated by inputting the maximum temperature value, the minimum temperature value, and the color; or the temperature meter can be detected from a fixed position in the thermal infrared image, and then the minimum temperature can be obtained by optical character recognition technology The value and the maximum temperature value are calculated.
- the temperature distribution information can be made more accurate, reliable, and searchable according to the conversion rules.
- S209. Store the thermal infrared image, visible light image, and temperature distribution information to the database, so that the database outputs the instrument chart including the thermal infrared image, visible light image, and temperature distribution information.
- storing the above-mentioned various information can realize real-time storage and monitoring, and by outputting the instrument graph including the above-mentioned various information, the information can be visualized, thereby improving the visibility of the information.
- the temperature of the power equipment can be detected by the external camera device, so that it is not limited by the temperature sensor to the high and low temperature, and the deviation of the sensing space can be eliminated by artificial intelligence. Accurately divide temperature information of power equipment, which can improve measurement accuracy.
- FIG. 3 is a schematic diagram of a system structure of a temperature detection device provided by this embodiment.
- the temperature detection device is applied to the field of electric power, and the temperature detection device includes:
- the obtaining module 310 is configured to obtain the thermal infrared image of the power equipment
- the detection module 320 is configured to detect and analyze the thermal infrared image according to a preset artificial intelligence model to obtain position information of the power device; the position information is configured to represent the position of the power device in the thermal infrared image;
- the segmentation module 330 is configured to segment the thermal infrared image according to the position information and a preset segmentation algorithm to obtain a segmented image; the segmented image is an image from which image information irrelevant to the power device is removed;
- the quantization module 340 is configured to quantize the colors included in the divided image to obtain temperature distribution information.
- the detection module 320 includes:
- the acquisition submodule 321 is configured to acquire the visible light image of the power equipment
- the detection sub-module 322 is configured to detect and analyze the thermal infrared image and the visible light image according to the artificial intelligence model to obtain the position information of the power equipment.
- the temperature detection device further includes:
- the storage module 350 is configured to store the thermal infrared image, visible light image, and temperature distribution information to a database, so that the database outputs an instrument chart including the thermal infrared image, visible light image, and temperature distribution information.
- the temperature detection device can execute the temperature detection methods described in the above embodiments, and the corresponding explanations can be interpreted accordingly. For this reason, no more details will be described in this embodiment.
- the implementation of this embodiment can realize remote real-time monitoring of high-temperature or high-risk key machine equipment; and remove background interference to improve the accuracy of temperature detection; and can provide accurate quantification of equipment temperature distribution; and can be fast and simple with the above structure
- the deployment does not require high-tech deployment of sensors; finally, maintenance costs can also be reduced, in which thermal imaging cameras can be replaced at any time.
- the temperature detection device described in this embodiment can detect the temperature of the power equipment through the external camera device, so that it is not limited by the temperature sensor to the high and low temperature, and the deviation of the sensing space can be eliminated by artificial intelligence. Acquiring accurate temperature component information of power equipment can improve measurement accuracy.
- the present application also provides another computer device, and the computer device may include a smart phone, a tablet computer, an in-vehicle computer, and/or a smart wearable device.
- the computer device includes a memory and a processor.
- the memory may be configured to store a computer program.
- the processor runs the computer program, so that the computer device performs the above-mentioned method or functions of each unit in the above-mentioned apparatus.
- the memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system and at least one function required application programs (such as a sound playback function and an image playback function, etc.); the storage data area may store a computer device The use of the created data (such as audio data and phone book, etc.), etc.
- the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
- This embodiment also provides a computer storage medium configured to store the computer program used in the computer device described above.
- each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more Execute instructions. It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures.
- each block in the block diagram and/or flowchart, and a combination of blocks in the block diagram and/or flowchart can use a dedicated hardware-based system that performs the specified function or action To achieve, or can be realized by a combination of dedicated hardware and computer instructions.
- the functional modules or units in the embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
- the described functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium.
- the technical solution of the present application essentially or part of the contribution to the existing technology or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to enable a computer device (which may be a smart phone, personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
Abstract
一种温度检测方法及装置，包括：获取电力设备的热红外图像（S101）；根据预设的人工智能模型对热红外图像进行检测分析，得到电力设备的位置信息；位置信息配置成表示电力设备在热红外图像中的位置（S102）；根据位置信息和预设的分割算法对热红外图像进行图像分割，得到分割图像；分割图像是去除了与电力设备无关的图像信息的图像（S103）；对分割图像包括的颜色进行量化处理，得到温度分布信息（S104）。该温度检测方法能够通过外设的装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，还可以消除感应空间的偏差，提高测量精度。
Description
相关申请的交叉引用
本申请要求于2018年12月18日提交中国专利局的申请号为CN201811551106.5、名称为“一种温度检测方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及电力领域，具体而言，涉及一种温度检测方法及装置。
目前，随着电力系统发展的越来越完善，电力系统的巡检装置也随之变得越来越完善，其中，在电力系统中，温度会电力设备通常具有非常大的影响，因此，对上述电力设备的温度检测就显得十分重要。然而，在实践中发现，传统的方法是使用温度感应器来进行检测的，这就使得温度感应器的高低限温会对检测产生一定限制，并且上述的温度感应器在很多时候不允许接触电力设备，使得感应空间存在偏差，从而会把不必要的因素检测入内，进而导致测量精度降低。
发明内容
鉴于上述问题，本申请提供了一种温度检测方法及装置，能够通过外设的装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，并且还可以消除感应空间的偏差，提高测量精度。
为了实现上述目的，本申请采用如下的技术方案：
第一方面，本申请提供了一种温度检测方法，所述温度检测方法应用于电力领域，包括：
获取电力设备的热红外图像；
根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息；所述位置信息配置成表示所述电力设备在所述热红外图像中的位置；
根据所述位置信息和预设的分割算法对所述热红外图像进行图像分割，得到分割图像；所述分割图像是去除了与所述电力设备无关的图像信息的图像；
对所述分割图像包括的颜色进行量化处理，得到温度分布信息。
作为一种可选的实施方式，所述根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息的步骤包括：
获取所述电力设备的可见光图像；
根据所述人工智能模型对所述热红外图像和所述可见光图像进行检测分析，得到所述 电力设备的位置信息。
作为一种可选的实施方式，所述方法还包括：
存储所述热红外图像、所述可见光图像以及所述温度分布信息至数据库，以使所述数据库输出包括所述热红外图像、所述可见光图像以及所述温度分布信息的仪表图。
作为一种可选的实施方式，所述对所述分割图像包括的颜色进行量化处理，得到温度分布信息的步骤包括：
根据预设的色彩检测模型检测所述分割图像包括的温度仪表；所述色彩检测模型是通过监督式算法训练得到的；
通过光学字符识别技术识别所述温度仪表包括的最小温度值和最大温度值；
根据所述最小温度值和所述最大温度值对所述温度仪表包括的颜色进行温度值量化处理，得到颜色与温度值之间的转换规则；
根据所述转换规则对所述分割图像进行处理，得到温度分布信息。
作为一种可选的实施方式，所述人工智能模型是卷积神经网络人工智能模型，所述卷积神经网络人工智能模型是以标注了电力设备的类别和位置的图片所建立的大数据为基础训练得到的。
第二方面，本申请提供了一种温度检测装置，所述温度检测装置应用于电力领域，包括：
获取模块，配置成获取电力设备的热红外图像；
检测模块，配置成根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息；所述位置信息配置成表示所述电力设备在所述热红外图像中的位置；
分割模块，配置成根据所述位置信息和预设的分割算法对所述热红外图像进行图像分割，得到分割图像；所述分割图像是去除了与所述电力设备无关的图像信息的图像；
量化模块，配置成对所述分割图像包括的颜色进行量化处理，得到温度分布信息。
作为一种可选的实施方式，所述检测模块包括：
获取子模块，配置成获取所述电力设备的可见光图像；
检测子模块，配置成根据所述人工智能模型对所述热红外图像和所述可见光图像进行检测分析，得到所述电力设备的位置信息。
作为一种可选的实施方式，所述温度检测装置还包括：
存储模块，配置成存储所述热红外图像、所述可见光图像以及所述温度分布信息至数据库，以使所述数据库输出包括所述热红外图像、所述可见光图像以及所述温度分布信息的仪表图。
第三方面，本申请提供了一种计算机设备，所述计算机设备包括存储器以及处理器，所述存储器配置成存储计算机程序，所述处理器运行所述计算机程序以使所述计算机设备执行本申请第一方面所述的一种温度检测方法。
第四方面，本申请提供了一种计算机可读存储介质，其存储有本申请第三方面所述的计算机设备中所使用的计算机程序。
根据本申请提供的温度检测方法及装置，可以获取电力系统中电力设备的热红外图像，并以预设的人工智能模型为依据对热红外图像进行检测分析，从而确认热红外图像中电力设备的具体位置，然后，根据该具体位置对热红外图像进行分割，得到只包括电力设备的分割图像，并对该分割图像进行量化处理，得到温度分布信息。可见，实施这种实施方式，能够通过外设的摄像装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，并且可以通过人工智能消除感应空间的偏差，获取准确地电力设备的温度分部信息，从而可以提高测量精度。
为使本申请的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
为了更清楚地说明本申请实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对本申请范围的限定。
图1是本申请第一实施例提供的一种温度检测方法的流程示意图；
图2是本申请第二实施例提供的一种温度检测方法的流程示意图；
图3是本申请第三实施例提供的一种温度检测装置的结构示意图。
下面将结合本申请实施例中附图，对本申请实施例中的技术方案进行清楚且完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。
针对现有技术中的问题，本申请提供了一种温度检测方法，可以获取电力系统中电力设备的热红外图像，并以预设的人工智能模型为依据对热红外图像进行检测分析，从而确认热红外图像中电力设备的具体位置，然后，根据该具体位置对热红外图像进行分割，得到只包括电力设备的分割图像，并对该分割图像进行量化处理，得到温度分布信息。可见， 实施这种实施方式，能够通过外设的摄像装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，并且可以通过人工智能消除感应空间的偏差，获取准确地电力设备的温度分部信息，从而可以提高测量精度。下面通过实施例进行描述。
其中，上述的技术方法还可以采用相关的软件或硬件加以实现，对此本实施例中不再多加赘述。针对该温度检测方法及装置，下面通过实施例进行描述。
实施例1
请参阅图1，是本实施例提供的一种温度检测方法的流程示意图，该温度检测方法包括以下步骤：
S101、获取电力设备的热红外图像。
本实施例中，电力设备包括电力系统中的各种设备，如变压设备、电力传输设备以及杆塔等。
本实施例中，热红外图像为通过热影像摄像头拍摄到的图像信息，又称为热影像图。
本实施例中，热红外图像配置成显示电力设备的与温度相对应的颜色信息。
S102、根据预设的人工智能模型对热红外图像进行检测分析，得到电力设备的位置信息；位置信息配置成表示电力设备在热红外图像中的位置。
本实施例中，人工智能模型是卷积神经网络人工智能模型，卷积神经网络人工智能模型是以标注了电力设备的类别和位置的图片所建立的大数据为基础训练得到的。
本实施例中，人工智能模型配置成对热红外图像进行电力设备的类别以及位置的检测分析，从而得到电力设备的准确位置信息，其中，该位置信息可以包括电力设备的轮廓信息。
本实施例中，位置信息可以是指针对背景的位置信息，在某些特殊情况下，还可以包括地理位置信息即经纬度信息。
本实施例中，电子设备在热红外图像中的位置即为电子设备在该图片背景下的位置。
S103、根据位置信息和预设的分割算法对热红外图像进行图像分割，得到分割图像；分割图像是去除了与电力设备无关的图像信息的图像。
本实施例中，分割算法是以像素级别进行分割的。
实施这种实施方式，可以通过像素级别的图像分割完成对电力设备的专属热红外图像，从而可以提高精确度。
本实施例中，分割图像只包括电力设备的图像，即不包括任何背景图像。
本实施例中，分割算法可以是针对位置信息的拟合算法，配置成对位置信息进行拟合获取到更优的分割方案，从而进行后续的分割；分割算法也可以是多重分割算法，该算法 可以以位置信息为基础，一层层的对电力设备图像分割出来，从而达到精确分割的效果。
本实施例中，与电力设备无关的图像信息的图像可以理解为背景图像。
S104、对分割图像包括的颜色进行量化处理，得到温度分布信息。
本实施例中，分割图像是具有多种颜色的图像，其中每种颜色代表不同的温度；因此，量化处理是将上述的颜色转换为可视化的温度信息，以使其他设备或工作人员进行观察与巡检。
本实施例中，分割图像中具有多种颜色的问题将不再赘述。
本实施例中，温度分部信息可以包括温度分布图和/或温度分布表等图像和/或数据以使图像数据结合的信息，对此本实施例中不作任何限定。
在图1所描述的温度检测方法中，可以获取电力系统中电力设备的热红外图像，并以预设的人工智能模型为依据对热红外图像进行检测分析，从而确认热红外图像中电力设备的具体位置，然后，根据该具体位置对热红外图像进行分割，得到只包括电力设备的分割图像，并对该分割图像进行量化处理，得到温度分布信息。可见，实施图1所描述的温度检测方法，能够通过外设的摄像装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，并且可以通过人工智能消除感应空间的偏差，获取准确地电力设备的温度分部信息，从而可以提高测量精度。
实施例2
请参阅图2，图2是本实施例提供的一种温度检测方法的流程示意图。如图2所示，该温度检测方法包括以下步骤：
S201、获取电力设备的热红外图像。
本实施例中，热红外图像包括电力设备和背景的热红外图像。
S202、获取电力设备的可见光图像。
本实施例中，可见光图像与热红外图像相匹配。
本实施例中，可见光图像可以辅助热红外图像对电力设备的轮廓以及位置进行有效的分体，同时该可见光图像可以有效分别电力设备和背景之间的不同。
本实施例中，可见光图像可以包括彩色图像。
S203、根据人工智能模型对热红外图像和可见光图像进行检测分析，得到电力设备的位置信息。
本实施例中，人工智能模型可以包括两个，其中一个是卷积神经网络人工智能模型，该卷积神经网络人工智能模型是以标注了电力设备的类别和位置的热红外图像所建立的大数据为基础训练得到的；另外一个也是积神经网络人工智能模型，但该卷积神经网络人工 智能模型是以标注了电力设备的类别和位置的可见光图像所建立的大数据为基础训练得到的。
在本实施例中，人工智能模型还可以通过对两个图像进行检测分析并且相互组合，得到有效的电力设备的位置信息。
本实施例中，人工智能模型可以为一个，其中，该人工智能模型可以对两种不同的图像(热红外图像和可见光图像)进行检测分析，得到各自的分析结果，并根据该各自的分析结果结合得到电力设备的位置信息。其中，对于人工智能模型中的具体结构本实施例中不作任何限定。
S204、根据位置信息和预设的分割算法对热红外图像进行图像分割，得到分割图像；分割图像是去除了与电力设备无关的图像信息的图像。
本实施例中，热红外图像包括温度信息，因此该步骤可以以可见光图像兼以辅助，也可以不是用可见光图像。
本实施例中，对于相同或相似的定义可以直接引用实施例一所描述的内容，对此本实施例中不作任何限定。
S205、根据预设的色彩检测模型检测分割图像包括的温度仪表；色彩检测模型是通过监督式算法训练得到的。
本实施例中，色彩检测模型也是一种人工智能模型，具体的，该色彩检测模型也可以是卷积神经网络人工智能模型；该色彩检测模型配置成检测分割图像中所包括的温度仪表。
在本实施例中，色彩检测模型是通过监督式算法训练得到的。
本实施例中，温度仪表配置成表示分割图像中最低温度到最高温度之间色彩变换信息，其中该温度仪表还包括最高温度值和最低温度值等信息。
在本实施例中，温度仪表包括的信息至少包括上述信息，同时还可以包括比最高温度值更高的温度信息以及比最低温度值更低的温度信息。
S206、通过光学字符识别技术识别温度仪表包括的最小温度值和最大温度值。
本实施例中，光学字符识别技术可以包括OCR文字识别技术。
S207、根据最小温度值和最大温度值对温度仪表包括的颜色进行温度值量化处理，得到颜色与温度值之间的转换规则。
本实施例中，转换规则配置成转换分割图像中的颜色为温度值。
本实施例中，对于该转换规则还可以是通过输入最大温度值、最小温度值以及颜色计算得到的；或者是从热红外图像中固定位置检测出温度仪表，再通过光学字符识别技术获取最小温度值和最大温度值，并进行计算得到的。
S208、根据转换规则对分割图像进行处理，得到温度分布信息。
本实施例中，根据转换规则可以使得温度分布信息更加准确、可靠以及可查。
S209、存储热红外图像、可见光图像以及温度分布信息至数据库，以使数据库输出包括热红外图像、可见光图像以及温度分布信息的仪表图。
本实施例中，存储上述各种信息，可以实现实时存储和监控，并且通过输出包括上述各种信息的仪表图可以将信息可视化，从而提高信息的可见性。
可见，实施图2所描述的温度检测方法，能够通过外设的摄像装置对电力设备进行温度检测，从而不受温度感应器对高低温的限制，并且可以通过人工智能消除感应空间的偏差，获取准确地电力设备的温度分部信息，从而可以提高测量精度。
实施例3
请参阅图3，是本实施例提供的一种温度检测装置的系统结构示意图。
如图3所示，该温度检测装置应用于电力领域，并且该温度检测装置包括：
获取模块310，配置成获取电力设备的热红外图像；
检测模块320，配置成根据预设的人工智能模型对热红外图像进行检测分析，得到电力设备的位置信息；位置信息配置成表示电力设备在热红外图像中的位置；
分割模块330，配置成根据位置信息和预设的分割算法对热红外图像进行图像分割，得到分割图像；分割图像是去除了与电力设备无关的图像信息的图像；
量化模块340，配置成对分割图像包括的颜色进行量化处理，得到温度分布信息。
作为一种可选的实施方式，检测模块320包括：
获取子模块321，配置成获取电力设备的可见光图像；
检测子模块322，配置成根据人工智能模型对热红外图像和可见光图像进行检测分析，得到电力设备的位置信息。
作为一种可选的实施方式，温度检测装置还包括：
存储模块350，配置成存储热红外图像、可见光图像以及温度分布信息至数据库，以使数据库输出包括热红外图像、可见光图像以及温度分布信息的仪表图。
本实施例中，该温度检测装置可以执行上述各个实施例所描述的温度检测方法，并且对于相应的解释说明皆可以相应解释，对此，本实施例中不再多加赘述。
实施这种实施方式，可以实现远程实时监督高温度或高危险的重点机器设备；并且去除背景干扰，提升温度检测的准确度；并且可以提供精准量化设备温度分布；并且可以上述的结构进行快速简单部署，不需要高技术部署感应器；最后，还可以减少维护成本，其中，热影像摄像头可以随时替换。
可见，实施本实施例所描述的温度检测装置，能够通过外设的摄像装置对电力设备进 行温度检测，从而不受温度感应器对高低温的限制，并且可以通过人工智能消除感应空间的偏差，获取准确地电力设备的温度分部信息，从而可以提高测量精度。
此外，本申请还提供了另外一种计算机设备，该计算机设备可以包括智能电话、平板电脑、车载电脑和/或智能穿戴设备等。该计算机设备包括存储器和处理器，存储器可配置成存储计算机程序，处理器通过运行上述计算机程序，从而使计算机设备执行上述方法或者上述装置中的各个单元的功能。
存储器可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统和至少一个功能所需的应用程序(比如声音播放功能和图像播放功能等)等；存储数据区可存储根据计算机设备的使用所创建的数据(比如音频数据和电话本等)等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
本实施例还提供了一种计算机存储介质，配置成储存上述计算机设备中使用的计算机程序。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和结构图显示了根据本申请的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，上述模块、程序段或代码的一部分包含一个或多个配置成实现规定的逻辑功能的可执行指令。也应当注意，在作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，结构图和/或流程图中的每个方框、以及结构图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
另外，在本申请各个实施例中的各功能模块或单元可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或更多个模块集成形成一个独立的部分。
所描述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是智能手机、个人计算机、服务器、或者网络设备等)执行本申请各个实施例所描述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以 存储程序代码的介质。
以上所描述的内容，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。
Claims (10)
- 一种温度检测方法，其特征在于，所述温度检测方法应用于电力领域，包括：获取电力设备的热红外图像；根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息；所述位置信息配置成表示所述电力设备在所述热红外图像中的位置；根据所述位置信息和预设的分割算法对所述热红外图像进行图像分割，得到分割图像；所述分割图像是去除了与所述电力设备无关的图像信息的图像；对所述分割图像包括的颜色进行量化处理，得到温度分布信息。
- 根据权利要求1所述的温度检测方法，其特征在于，所述根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息的步骤包括：获取所述电力设备的可见光图像；根据所述人工智能模型对所述热红外图像和所述可见光图像进行检测分析，得到所述电力设备的位置信息。
- 根据权利要求2所述的温度检测方法，其特征在于，所述方法还包括：存储所述热红外图像、所述可见光图像以及所述温度分布信息至数据库，以使所述数据库输出包括所述热红外图像、所述可见光图像以及所述温度分布信息的仪表图。
- 根据权利要求1所述的温度检测方法，其特征在于，所述对所述分割图像包括的颜色进行量化处理，得到温度分布信息的步骤包括：根据预设的色彩检测模型检测所述分割图像包括的温度仪表；所述色彩检测模型是通过监督式算法训练得到的；通过光学字符识别技术识别所述温度仪表包括的最小温度值和最大温度值；根据所述最小温度值和所述最大温度值对所述温度仪表包括的颜色进行温度值量化处理，得到颜色与温度值之间的转换规则；根据所述转换规则对所述分割图像进行处理，得到温度分布信息。
- 根据权利要求1所述的温度检测方法，其特征在于，所述人工智能模型是卷积神经网络人工智能模型，所述卷积神经网络人工智能模型是以标注了电力设备的类别和位置的图片所建立的大数据为基础训练得到的。
- 一种温度检测装置，其特征在于，所述温度检测装置应用于电力领域，包括：获取模块，配置成获取电力设备的热红外图像；检测模块，配置成根据预设的人工智能模型对所述热红外图像进行检测分析，得到所述电力设备的位置信息；所述位置信息配置成表示所述电力设备在所述热红外图 像中的位置；分割模块，配置成根据所述位置信息和预设的分割算法对所述热红外图像进行图像分割，得到分割图像；所述分割图像是去除了与所述电力设备无关的图像信息的图像；量化模块，配置成对所述分割图像包括的颜色进行量化处理，得到温度分布信息。
- 根据权利要求6所述的温度检测装置，其特征在于，所述检测模块包括：获取子模块，配置成获取所述电力设备的可见光图像；检测子模块，配置成根据所述人工智能模型对所述热红外图像和所述可见光图像进行检测分析，得到所述电力设备的位置信息。
- 根据权利要求6所述的温度检测装置，其特征在于，所述温度检测装置还包括：存储模块，配置成存储所述热红外图像、所述可见光图像以及所述温度分布信息至数据库，以使所述数据库输出包括所述热红外图像、所述可见光图像以及所述温度分布信息的仪表图。
- 一种计算机设备，其特征在于，包括存储器以及处理器，所述存储器配置成存储计算机程序，所述处理器运行所述计算机程序以使所述计算机设备执行根据权利要求1至5中任一项所述的一种温度检测方法。
- 一种计算机可读存储介质，其特征在于，其存储有权利要求9所述的计算机设备中所使用的计算机程序。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811551106.5A CN109580004A (zh) | 2018-12-18 | 2018-12-18 | 一种温度检测方法及装置 |
| CN201811551106.5 | 2018-12-18 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020124701A1 true WO2020124701A1 (zh) | 2020-06-25 |
Family
ID=65929926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/070734 WO2020124701A1 (zh) | 2018-12-18 | 2019-01-08 | 一种温度检测方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109580004A (zh) |
| WO (1) | WO2020124701A1 (zh) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818816A (zh) * | 2021-01-27 | 2021-05-18 | 杭州海康威视数字技术股份有限公司 | 一种温度检测方法、装置及设备 |
| CN113295298A (zh) * | 2021-05-19 | 2021-08-24 | 深圳市朗驰欣创科技股份有限公司 | 测温方法、测温装置、终端设备及存储介质 |
| CN113850787A (zh) * | 2021-09-27 | 2021-12-28 | 广东电网有限责任公司江门供电局 | 一种开关柜运行监控系统及方法 |
| CN113899395A (zh) * | 2021-09-03 | 2022-01-07 | 珠海格力电器股份有限公司 | 温度湿度测量方法、装置、计算机设备和存储介质 |
| CN116026890A (zh) * | 2023-03-29 | 2023-04-28 | 曲阜市虹飞电缆有限公司 | 一种基于热红外图像的电力电缆热故障检测方法 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110118603B (zh) * | 2019-05-15 | 2021-07-09 | Oppo广东移动通信有限公司 | 目标对象的定位方法、装置、终端及存储介质 |
| CN110319937A (zh) * | 2019-05-21 | 2019-10-11 | 广州供电局有限公司 | 红外测温图像处理方法、装置、计算机设备和存储介质 |
| CN110544258B (zh) * | 2019-08-30 | 2021-05-25 | 北京海益同展信息科技有限公司 | 图像分割的方法、装置、电子设备和存储介质 |
| CN111105372A (zh) * | 2019-12-10 | 2020-05-05 | 北京都是科技有限公司 | 热红外图像处理器、系统、方法及装置 |
| CN111862073A (zh) * | 2020-07-29 | 2020-10-30 | 广东电网有限责任公司 | 一种电力设备的温度采集方法和装置 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7196509B2 (en) * | 2004-09-23 | 2007-03-27 | Avago Technologies Ecbu Ip (Singapore) Pte. Ltd. | Thermopile temperature sensing with color contouring |
| CN201935733U (zh) * | 2010-12-10 | 2011-08-17 | 江少成 | 一种配电柜或开关柜电气设备温度在线监测装置 |
| CN104280643A (zh) * | 2014-10-23 | 2015-01-14 | 国家电网公司 | 一种红外图谱在安卓终端上的自动分析方法 |
| CN104809722A (zh) * | 2015-04-13 | 2015-07-29 | 国家电网公司 | 一种基于红外热像的电气设备故障诊断方法 |
| CN105203210A (zh) * | 2015-10-23 | 2015-12-30 | 国网山西省电力公司大同供电公司 | 基于360°红外全景视图与支持向量机的特高压变电站变压器故障检测装置及检测方法 |
| CN108846418A (zh) * | 2018-05-24 | 2018-11-20 | 广东电网有限责任公司 | 一种电缆设备温度异常定位与识别方法 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108318781A (zh) * | 2018-01-03 | 2018-07-24 | 武汉理工大学 | 一种基于红外图像的绝缘子远程监测及故障诊断的方法 |
-
2018
- 2018-12-18 CN CN201811551106.5A patent/CN109580004A/zh active Pending
-
2019
- 2019-01-08 WO PCT/CN2019/070734 patent/WO2020124701A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7196509B2 (en) * | 2004-09-23 | 2007-03-27 | Avago Technologies Ecbu Ip (Singapore) Pte. Ltd. | Thermopile temperature sensing with color contouring |
| CN201935733U (zh) * | 2010-12-10 | 2011-08-17 | 江少成 | 一种配电柜或开关柜电气设备温度在线监测装置 |
| CN104280643A (zh) * | 2014-10-23 | 2015-01-14 | 国家电网公司 | 一种红外图谱在安卓终端上的自动分析方法 |
| CN104809722A (zh) * | 2015-04-13 | 2015-07-29 | 国家电网公司 | 一种基于红外热像的电气设备故障诊断方法 |
| CN105203210A (zh) * | 2015-10-23 | 2015-12-30 | 国网山西省电力公司大同供电公司 | 基于360°红外全景视图与支持向量机的特高压变电站变压器故障检测装置及检测方法 |
| CN108846418A (zh) * | 2018-05-24 | 2018-11-20 | 广东电网有限责任公司 | 一种电缆设备温度异常定位与识别方法 |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818816A (zh) * | 2021-01-27 | 2021-05-18 | 杭州海康威视数字技术股份有限公司 | 一种温度检测方法、装置及设备 |
| CN112818816B (zh) * | 2021-01-27 | 2024-03-01 | 杭州海康威视数字技术股份有限公司 | 一种温度检测方法、装置及设备 |
| CN113295298A (zh) * | 2021-05-19 | 2021-08-24 | 深圳市朗驰欣创科技股份有限公司 | 测温方法、测温装置、终端设备及存储介质 |
| CN113899395A (zh) * | 2021-09-03 | 2022-01-07 | 珠海格力电器股份有限公司 | 温度湿度测量方法、装置、计算机设备和存储介质 |
| CN113850787A (zh) * | 2021-09-27 | 2021-12-28 | 广东电网有限责任公司江门供电局 | 一种开关柜运行监控系统及方法 |
| CN113850787B (zh) * | 2021-09-27 | 2024-04-12 | 广东电网有限责任公司江门供电局 | 一种开关柜运行监控系统及方法 |
| CN116026890A (zh) * | 2023-03-29 | 2023-04-28 | 曲阜市虹飞电缆有限公司 | 一种基于热红外图像的电力电缆热故障检测方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109580004A (zh) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020124701A1 (zh) | 一种温度检测方法及装置 | |
| WO2021051885A1 (zh) | 目标标注的方法及装置 | |
| KR102595704B1 (ko) | 영상 검측 방법, 장치, 전자 기기, 저장 매체 및 프로그램 | |
| US10445590B2 (en) | Image processing apparatus and method and monitoring system | |
| US20230056564A1 (en) | Image authenticity detection method and apparatus | |
| CN116168351B (zh) | 电力设备巡检方法及装置 | |
| CN108921840A (zh) | 显示屏外围电路检测方法、装置、电子设备及存储介质 | |
| CN109447022B (zh) | 一种镜头类型识别方法及装置 | |
| CN112258507B (zh) | 互联网数据中心的目标对象检测方法、装置和电子设备 | |
| CN112164086A (zh) | 一种精细化的图像边缘信息确定方法、系统及电子设备 | |
| CN104065863A (zh) | 图像处理方法及处理装置 | |
| CN112613380A (zh) | 一种机房巡检方法、装置及电子设备、存储介质 | |
| CN111127358B (zh) | 图像处理方法、装置及存储介质 | |
| CN110298302B (zh) | 一种人体目标检测方法及相关设备 | |
| WO2018121414A1 (zh) | 电子设备、目标图像识别方法及装置 | |
| CN116797977A (zh) | 巡检机器人动态目标识别与测温方法、装置和存储介质 | |
| WO2021051382A1 (zh) | 白平衡处理方法和设备、可移动平台、相机 | |
| CN112818960B (zh) | 基于人脸识别的等待时长处理方法、装置、设备及介质 | |
| JP7410323B2 (ja) | 異常検出装置、異常検出方法及び異常検出システム | |
| CN116805387B (zh) | 基于知识蒸馏的模型训练方法、质检方法和相关设备 | |
| CN117314863A (zh) | 缺陷输出方法、装置、设备及存储介质 | |
| CN111369557A (zh) | 图像处理方法、装置、计算设备和存储介质 | |
| CN116993654A (zh) | 摄像头模组缺陷检测方法、装置、设备、存储介质及产品 | |
| CN114299054A (zh) | 部件缺失检测方法、装置、电子设备及存储介质 | |
| CN108875770B (zh) | 行人检测误报数据的标注方法、装置、系统和存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19898879 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19898879 Country of ref document: EP Kind code of ref document: A1 |