CN117237745A - Method, device and medium for improving fire extinguisher state identification accuracy - Google Patents
Method, device and medium for improving fire extinguisher state identification accuracy Download PDFInfo
- Publication number
- CN117237745A CN117237745A CN202311498591.5A CN202311498591A CN117237745A CN 117237745 A CN117237745 A CN 117237745A CN 202311498591 A CN202311498591 A CN 202311498591A CN 117237745 A CN117237745 A CN 117237745A
- Authority
- CN
- China
- Prior art keywords
- fire extinguisher
- image
- target
- improving
- network model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application relates to a method, a device and a medium for improving the state identification accuracy of a fire extinguisher, wherein the method for improving the state identification accuracy of the fire extinguisher comprises the following steps: acquiring a target fire extinguisher image; performing target area detection on the target fire extinguisher image through a Yolov8 network model to obtain a target fire extinguisher panel image; and identifying and classifying the target fire extinguisher panel image through an EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result. The application solves the problem that the image of the fire extinguisher panel area has small occupied ratio on the whole image of the fire extinguisher, which affects the accuracy of identifying the state of the fire extinguisher, and realizes the effect of locating the fire extinguisher panel and improving the accuracy of identifying the state of the fire extinguisher.
Description
Technical Field
The application relates to the technical field of image recognition, in particular to a method, a device and a medium for improving the accuracy of fire extinguisher state recognition.
Background
Along with the increasing importance of industrial production safety, in a dual preventive working mechanism of risk classification management and control and hidden danger investigation and treatment, the requirement that a fire extinguisher needs to be checked regularly and a pressure gauge reading in a green area needs to be determined is provided. Based on the existing image recognition technology, the image of the fire extinguisher is recognized through the network model, so that the judgment of the state of the fire extinguisher is realized, and compared with manual recognition, the efficiency of recognizing the state of a large number of fire extinguishers can be improved.
The status of a fire extinguisher is generally determined by the area of the fire extinguisher panel where the needle is located, while the fire extinguisher panel image has a small percentage of the overall fire extinguisher image. Therefore, the fire extinguisher image is directly identified through the state identification model, the fire extinguisher panel image in the fire extinguisher image is difficult to accurately identify, the identification and judgment of the pointer area can be affected, and the accuracy rate of identifying the state of the fire extinguisher is not ideal.
Aiming at the problem of lower accuracy in identifying the state of the fire extinguisher in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The application provides a method, a device and a medium for improving the state identification accuracy of a fire extinguisher, which are used for solving the problem of lower state identification accuracy of the fire extinguisher in the related technology.
In a first aspect, the application provides a method for improving the accuracy of identifying the state of a fire extinguisher, which comprises the following steps:
acquiring a target fire extinguisher image;
performing target area detection on the target fire extinguisher image through a Yolov8 network model to obtain a target fire extinguisher panel image;
and identifying and classifying the target fire extinguisher panel image through an EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
In some of these embodiments, the Yolov8 network model includes a small target detection layer that is pre-configured in the Yolov8 network model.
In some of these embodiments, the Yolov8 network model includes a plurality of network output layers, the plurality of network output layers being pre-configured in the Yolov8 network model.
In some of these embodiments, the acquiring the target fire extinguisher image comprises:
acquiring an initial fire extinguisher image;
and denoising and contrast enhancement operation is carried out on the initial fire extinguisher image by using a median filtering method, so as to obtain the target fire extinguisher image.
In some embodiments, the plurality of network output layers includes a first network output layer and a second network output layer, with a preset layer number difference between the first network output layer and the second network output layer.
In some of these embodiments, the plurality of network output layers includes four network output layers.
In some embodiments, the specific number of layers of the network output layer is 18, 21, 24, 27 layers respectively.
In a second aspect, the present application provides a device for improving the accuracy of identifying the status of a fire extinguisher, comprising:
the acquisition module is used for acquiring an image of the target fire extinguisher;
the detection module is used for detecting the target area of the target fire extinguisher image through a Yolov8 network model to obtain a target fire extinguisher panel image;
the identification module is used for identifying and classifying the target fire extinguisher panel image through the EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
In a third aspect, the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method for improving the accuracy of identifying the status of a fire extinguisher according to the first aspect when executing the computer program.
In a fourth aspect, the present application provides a storage medium having stored thereon a computer program which when executed by a processor implements the method of improving the accuracy of fire extinguisher status identification as described in the first aspect above.
Compared with the related art, in the method for improving the fire extinguisher state identification accuracy, the target area detection is carried out on the target fire extinguisher image through the Yolov8 network model, so that the fire extinguisher panel area is positioned, the fire extinguisher panel image is obtained, then the fire extinguisher panel image is identified through the EfficientNet network model, and the accurate identification and judgment of the fire extinguisher panel pointer area are realized. Through the combined use of the Yolov8 network model and the EfficientNet network model, the fire extinguisher state identification accuracy is improved, and the problem of lower fire extinguisher state identification accuracy in the related technology is solved.
In addition, the small target detection layer is configured in the Yolov8 network model, and the plurality of network output layers are arranged, so that detail loss in the image identification and positioning process is reduced to a certain extent, and the accuracy rate of fire extinguisher state identification is further improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a block diagram of the terminal hardware architecture of a method for improving the accuracy of fire extinguisher status identification.
FIG. 2 is a flow chart of a method for improving the accuracy of identifying the status of a fire extinguisher.
Fig. 3 is a block diagram of the apparatus for improving the accuracy of status recognition of fire extinguishers according to the present embodiment.
Detailed Description
The present application will be described and illustrated with reference to the accompanying drawings and examples for a clearer understanding of the objects, technical solutions and advantages of the present application.
Unless defined otherwise, technical or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," "these" and similar terms in this application are not intended to be limiting in number, but may be singular or plural. The terms "comprising," "including," "having," and any variations thereof, as used herein, are intended to encompass non-exclusive inclusion; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (units) is not limited to the list of steps or modules (units), but may include other steps or modules (units) not listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this disclosure are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. Typically, the character "/" indicates that the associated object is an "or" relationship. The terms "first," "second," "third," and the like, as referred to in this disclosure, merely distinguish similar objects and do not represent a particular ordering for objects.
The method embodiments provided in the present application may be performed in a terminal, a computer or similar computing device. Such as on a terminal, fig. 1 is a block diagram of a terminal hardware structure for performing the method for improving the accuracy of identifying the status of a fire extinguisher provided in the present application. As shown in fig. 1, the terminal may include one or more (only one is shown in fig. 1) processors 120 and a memory 140 for storing data, wherein the processors 120 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may further include a transmission device 160 for a communication function and an input-output device 180. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and is not intended to limit the structure of the terminal. For example, the terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 140 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method of improving the fire extinguisher status recognition accuracy in the present application, and the processor 120 performs various functional applications and data processing by running the computer program stored in the memory 140, i.e., implements the above-mentioned method. Memory 140 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 140 may further include memory located remotely from processor 120, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 160 is used to receive or transmit data via a network. The network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 160 includes a network adapter (Network Interface Controller, simply referred to as NIC) that may be connected to other network devices via a base station to communicate with the internet. In one example, the transmission device 160 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.
In the present application, a method for improving the accuracy of identifying the status of a fire extinguisher is provided, fig. 2 is a flowchart of the method for improving the accuracy of identifying the status of the fire extinguisher according to the present application, as shown in fig. 2, the flowchart includes the following steps:
step S210, acquiring a target fire extinguisher image. The target fire extinguisher image is the image to be identified.
In some of these embodiments, the initial fire extinguisher image acquired may be preprocessed to obtain the target fire extinguisher image in order to improve the quality of the target fire extinguisher image. The pretreatment process comprises the following steps: acquiring an initial fire extinguisher image; and denoising and contrast enhancement operation is carried out on the initial fire extinguisher image by using a median filtering method, so as to obtain a target fire extinguisher image.
In particular, during the shooting and transmission of the initial fire extinguisher image, unnecessary signals may be introduced, which may affect the quality of the image and cause corresponding disturbances in the subsequent processing of the image. Therefore, after the initial fire extinguisher image is acquired, denoising and contrast enhancement operations are carried out on the initial fire extinguisher image through a median filtering method, so that unnecessary signals in the image are removed, the overall quality of the image is improved, and finally the target fire extinguisher image is obtained.
And S220, detecting a target area of the target fire extinguisher image through the Yolov8 network model to obtain a target fire extinguisher panel image.
Yolov8 (You Only Look Once version) is an object detection algorithm for real-time object detection tasks. It is the latest version of YOLO series algorithm, and its core idea is to convert the object detection task into a single forward propagation process. Compared with Yolov5, the method has better detection precision, the Yolov8n is 55.6% in a coco data set mAP50-95, and the Yolov5n is only 53.2%.
Under the condition of higher precision requirements, the original Yolov8 network model is not provided with a small target detection layer, so that the detection effect of the Yolov8 network model cannot reach the required effect. In some of these embodiments, a Yolov8 network model is modified, the Yolov8 network model including a small target detection layer, the small target detection layer being preconfigured in the Yolov8 network model. In this embodiment, after the target fire extinguisher image is acquired, the target fire extinguisher image is extracted by using a small target detection layer added in the Yolov8 network model, so as to acquire a plurality of feature images, where the small target detection layer configured in this embodiment can detect targets above 4×4.
The Yolov8 network model includes a plurality of network output layers that are preconfigured in the Yolov8 network model. Specifically, the plurality of network output layers include a first network output layer and a second network output layer, and a preset layer number difference is formed between the first network output layer and the second network output layer. The network output layers respectively correspond to the characteristic images, after the characteristic images are acquired, partial characteristic images in the characteristic images are required to be selected for fusion and splicing, and the selection standard of the characteristic images is just according to the preset layer number difference between the corresponding first network output layer and the corresponding second network output layer, wherein the preset layer number difference can be 2 layers, 4 layers or 6 layers, and the setting standard of the preset layer number difference can be properly increased according to the requirement in practical application. In this embodiment, the plurality of network output layers includes four network output layers, more specifically, the initial network output layers of the Yolov8 network model are respectively 15, 18 and 21 layers, because the downsampling multiple of the Yolov8 network model is larger, the deeper the hierarchy of the feature image is, the lower the resolution is, the weaker the perceptibility of the image details is, and because the ratio of the fire extinguisher panel image in the target fire extinguisher image is smaller, in order to reduce the loss of the image details when the feature image is fused, the number of the network output layers is properly increased, specifically, in this embodiment, the specific layers of the network output layers are respectively 18, 21, 24 and 27 layers. And finally, positioning the area of the fire extinguisher panel in the target fire extinguisher image according to the fused characteristic image, and cutting and storing the panel area by using opencv through a positioned rectangular frame so as to obtain the target fire extinguisher panel image.
And step S230, identifying and classifying the target fire extinguisher panel image through the EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
The EfficientNet network model is an efficient convolutional neural network architecture, is widely applied to image classification and related computer vision tasks, and is designed to balance parameters, calculated amount and precision in a network structure so as to achieve the characteristics of high efficiency and accuracy. The method introduces a Compound Scaling method, and obtains better model performance by uniformly adjusting the depth, width and resolution of the network.
In some of these embodiments, for the Effectent Net network model, the Effectent Net network model can be trained in advance, the training steps including, but not limited to, the following: and constructing an initial EfficientNet network model, and presetting model parameters. And then collecting fire extinguisher panel sample images of known fire extinguisher states, inputting the fire extinguisher panel sample images into an initial EfficientNet network model for training, and adjusting model parameters until the output results are consistent with the fire extinguisher states of the corresponding fire extinguisher panel sample images. And taking the model parameters at the moment as the model parameters of the final EfficientNet, thereby determining the EfficientNet network model. For example, when determining the fire extinguisher status in the target fire extinguisher image, the determination of the fire extinguisher status may be made based on the area of the dial of the target fire extinguisher image where the pointer is located.
And detecting a target area of the target fire extinguisher image through the Yolov8 network model to obtain a target fire extinguisher panel image, and then accurately identifying and judging a pointer area of the target fire extinguisher panel image by utilizing the EfficientNet network model. Through the combined use of the Yolov8 network model and the EfficientNet network model, the problem that the fire extinguisher state recognition accuracy is reduced due to the fact that other parts of the fire extinguisher occupy larger areas and the panel pointer area occupies smaller areas is solved, the effect of positioning the fire extinguisher panel and improving the fire extinguisher state recognition accuracy is achieved.
In order to verify the effect of the method, in the hardware environment of ubuntu20.04, i9-13900k and RTX4080, the Yolov8n network model is used for positioning 212 target fire extinguisher images, then the EfficientNet network model is used for identification, and the final accuracy rate is 93.87%. And the accuracy rate of classification by only using the Efficient Net network model is 97.64%, so that the overall accuracy rate is improved by 4.02%.
It should be noted that the steps illustrated in the above-described flow or flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
The application also provides a device for improving the accuracy of identifying the state of the fire extinguisher, which is used for realizing the embodiment and the preferred implementation mode, and the description is omitted. The terms "module," "unit," "sub-unit," and the like as used below may refer to a combination of software and/or hardware that performs a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.
FIG. 3 is a block diagram of a device for improving the accuracy of identifying the status of a fire extinguisher according to the present application, as shown in FIG. 3, comprising:
the acquisition module 301 is used for acquiring an image of a target fire extinguisher;
the detection module 302 is configured to perform target area detection on a target fire extinguisher image through a Yolov8 network model, so as to obtain a target fire extinguisher panel image;
and the identification module 303 is used for identifying and classifying the target fire extinguisher panel image through the EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
Target area detection is carried out on the target fire extinguisher image through utilizing the Yolov8 network model in the detection module, a target fire extinguisher panel image is obtained, and then accurate identification and judgment of the pointer area are carried out on the target fire extinguisher panel image through utilizing the EfficientNet network model in the identification module. Through the combined use of the Yolov8 network model and the EfficientNet network model, the problem that the fire extinguisher state recognition accuracy is reduced due to the fact that other parts of the fire extinguisher occupy larger areas and the panel pointer area occupies smaller areas is solved, the effect of positioning the fire extinguisher panel and improving the fire extinguisher state recognition accuracy is achieved.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
There is also provided in the application an electronic device comprising a memory in which a computer program is stored and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic device may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in one embodiment, the processor may be arranged to perform the following steps by a computer program:
s1, acquiring an image of the target fire extinguisher.
S2, detecting a target area of the target fire extinguisher image through the Yolov8 network model to obtain a target fire extinguisher panel image.
And S3, identifying and classifying the panel image of the target fire extinguisher through the EfficientNet network model, and determining the fire extinguisher state in the image of the target fire extinguisher according to the identification and classification result.
It should be noted that, the specific examples of the present electronic device may refer to examples described in the embodiments and the optional implementations of the method, and are not described in detail in this embodiment.
In addition, in combination with the method for improving the accuracy rate of identifying the state of the fire extinguisher provided by the application, a storage medium can be provided for realizing the method. The storage medium has a computer program stored thereon; the computer program when executed by a processor implements any of the methods of the above embodiments to improve the accuracy of fire extinguisher status identification.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure in accordance with the embodiments provided herein.
It is to be understood that the drawings are merely illustrative of some embodiments of the present application and that it is possible for those skilled in the art to adapt the present application to other similar situations without the need for inventive work. In addition, it should be appreciated that while the development effort might be complex and lengthy, it will nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and further having the benefit of this disclosure.
The term "embodiment" in this disclosure means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive. It will be clear or implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.
Claims (10)
1. The method for improving the fire extinguisher state identification accuracy is characterized by comprising the following steps of:
acquiring a target fire extinguisher image;
performing target area detection on the target fire extinguisher image through a Yolov8 network model to obtain a target fire extinguisher panel image;
and identifying and classifying the target fire extinguisher panel image through an EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
2. The method for improving fire extinguisher status recognition accuracy of claim 1, wherein the Yolov8 network model comprises a small target detection layer, the small target detection layer being pre-configured in the Yolov8 network model.
3. The method for improving fire extinguisher status recognition accuracy of claim 1, wherein the Yolov8 network model comprises a plurality of network output layers, the plurality of network output layers being pre-configured in the Yolov8 network model.
4. The method for improving fire extinguisher status recognition accuracy according to claim 1, wherein the acquiring the target fire extinguisher image comprises:
acquiring an initial fire extinguisher image;
and denoising and contrast enhancement operation is carried out on the initial fire extinguisher image by using a median filtering method, so as to obtain the target fire extinguisher image.
5. A method for improving accuracy of fire extinguisher status recognition according to claim 3, wherein the plurality of network output layers comprises a first network output layer and a second network output layer, and the first network output layer and the second network output layer have a preset layer number difference therebetween.
6. A method of improving fire extinguisher condition recognition accuracy as claimed in claim 3, wherein a plurality of said network output layers comprises four network output layers.
7. The method for improving the accuracy of fire extinguisher status recognition according to claim 5, wherein the number of layers of the network output layer is 18, 21, 24, 27 respectively.
8. The utility model provides a promote device of fire extinguisher state discernment rate of accuracy which characterized in that includes:
the acquisition module is used for acquiring an image of the target fire extinguisher;
the detection module is used for detecting the target area of the target fire extinguisher image through a Yolov8 network model to obtain a target fire extinguisher panel image;
the identification module is used for identifying and classifying the target fire extinguisher panel image through the EfficientNet network model, and determining the fire extinguisher state in the target fire extinguisher image according to the identification and classification result.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of improving fire extinguisher status recognition accuracy of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method of improving fire extinguisher status recognition accuracy of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311498591.5A CN117237745A (en) | 2023-11-13 | 2023-11-13 | Method, device and medium for improving fire extinguisher state identification accuracy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311498591.5A CN117237745A (en) | 2023-11-13 | 2023-11-13 | Method, device and medium for improving fire extinguisher state identification accuracy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117237745A true CN117237745A (en) | 2023-12-15 |
Family
ID=89098624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311498591.5A Pending CN117237745A (en) | 2023-11-13 | 2023-11-13 | Method, device and medium for improving fire extinguisher state identification accuracy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237745A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659626A (en) * | 2019-09-30 | 2020-01-07 | 上海眼控科技股份有限公司 | Image detection method, device and equipment |
| CN113888535A (en) * | 2021-11-23 | 2022-01-04 | 北京羽医甘蓝信息技术有限公司 | Wisdom tooth arrhythmic type identification method and system |
| CN116030455A (en) * | 2022-12-30 | 2023-04-28 | 上海零咔智能科技有限公司 | Food heat measuring and calculating algorithm based on Yolo-EffiientNet double-layer model |
| CN116823738A (en) * | 2023-06-05 | 2023-09-29 | 盐城工学院 | PCB bare board surface defect detection method based on YOLOv8 |
-
2023
- 2023-11-13 CN CN202311498591.5A patent/CN117237745A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659626A (en) * | 2019-09-30 | 2020-01-07 | 上海眼控科技股份有限公司 | Image detection method, device and equipment |
| CN113888535A (en) * | 2021-11-23 | 2022-01-04 | 北京羽医甘蓝信息技术有限公司 | Wisdom tooth arrhythmic type identification method and system |
| CN116030455A (en) * | 2022-12-30 | 2023-04-28 | 上海零咔智能科技有限公司 | Food heat measuring and calculating algorithm based on Yolo-EffiientNet double-layer model |
| CN116823738A (en) * | 2023-06-05 | 2023-09-29 | 盐城工学院 | PCB bare board surface defect detection method based on YOLOv8 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105828068A (en) | Method and device for carrying out occlusion detection on camera and terminal device | |
| CN111310727B (en) | Object detection method and device, storage medium and electronic device | |
| CN109901754B (en) | Data self-calibration method and related device | |
| CN109525836B (en) | Embedded multimode is survey device simultaneously based on FPGA | |
| CN111383278A (en) | Calibration method, device and equipment for double cameras | |
| CN117237745A (en) | Method, device and medium for improving fire extinguisher state identification accuracy | |
| CN110955390A (en) | Data processing method and device and electronic equipment | |
| CN111833341A (en) | Method and device for determining stripe noise in image | |
| CN111387932A (en) | Vision detection method, device and equipment | |
| CN113963045B (en) | Depth map acquisition method, structured light camera, electronic device, and storage medium | |
| CN116017306A (en) | Position determining method and device of UWB (ultra Wide band) tag and UWB tag | |
| CN113067984B (en) | Binocular shooting correction method, binocular shooting correction device and electronic equipment | |
| CN112731102B (en) | Liquid crystal display television backlight fault detection method | |
| CN115358992A (en) | Light spot detection method and device, electronic equipment and storage medium | |
| CN113139563A (en) | Optimization method and device of image classification model | |
| CN113870275A (en) | Rivet expansion amount detection method and device, storage medium and equipment | |
| CN113963428A (en) | Model training method, occlusion detection method, system, electronic device, and medium | |
| CN114286084A (en) | Video link test method and device | |
| CN109309637B (en) | Data storage method, device and storage medium for transmission signals | |
| CN112907593A (en) | Method and device for identifying colloid fault position of mobile phone lens and related equipment | |
| CN116934847B (en) | Discharging method, discharging device, electronic equipment and storage medium | |
| CN109409159A (en) | A kind of fuzzy two-dimensional code detection method and device | |
| CN115439630B (en) | Mark point splicing method, photogrammetry method, device and electronic device | |
| CN113034617B (en) | Method, device and equipment for acquiring focal length of camera | |
| CN115493512B (en) | Data processing method, three-dimensional scanning system, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |