CN116109607A - Power transmission line engineering defect detection method based on image segmentation - Google Patents
Power transmission line engineering defect detection method based on image segmentation Download PDFInfo
- Publication number
- CN116109607A CN116109607A CN202310151436.XA CN202310151436A CN116109607A CN 116109607 A CN116109607 A CN 116109607A CN 202310151436 A CN202310151436 A CN 202310151436A CN 116109607 A CN116109607 A CN 116109607A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- transmission line
- power transmission
- layer
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a transmission line engineering defect detection method based on image segmentation, which comprises the steps of acquiring an image of a transmission line and geographic position information associated with the image through image acquisition equipment; preprocessing the power transmission line image to obtain a preprocessed image; image segmentation is carried out on the preprocessed image based on an A-UNet network model to obtain segmented images, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures; the obtained segmented image has clear boundary, is beneficial to subsequent defect detection, improves the defect detection precision, inputs the segmented image into a defect detection model for defect detection, obtains the detection result of the power transmission line, and improves the defect detection efficiency.
Description
Technical Field
The invention relates to transmission line engineering defect detection, in particular to transmission line engineering defect detection based on image segmentation.
Background
With the development of the innovation and the development of national economy in China, the power grid scale is larger and larger. The geographical environment that the transmission line passed through is complicated, keeps away from main traffic artery, and the transmission line is easily influenced by factors such as natural disasters and artificial damage in long-term operation, when the transmission line suffered thunderbolt, icing and external damage, if not in time discover the defect that the transmission line exists, can seriously influence the operation safety of electric wire netting.
In order to find out defects in the power transmission line in time, various devices on the power transmission line are detected on line through an infrared detection technology, and then the acquired infrared images are analyzed and processed based on an image recognition technology, so that the line defects are determined. However, the infrared image contains a lot of noise and responsible background information, resulting in low recognition accuracy.
With the continuous development of artificial intelligence and deep learning, the image can be segmented and identified by an image identification method based on a deep learning algorithm, and the conditions of missing detection and false detection can be avoided, so that the defect reporting and processing efficiency can be improved. However, the transmission line engineering defect detection method based on deep learning in the prior art is low in detection precision.
How to overcome the problem of image quality and realize high-precision defect detection of the power transmission line engineering still has challenges, so the power transmission line engineering defect detection method based on image segmentation is provided, and the power transmission line engineering defect is detected more efficiently and accurately.
Disclosure of Invention
The invention aims to solve the problem of low accuracy of the transmission line engineering defect detection method in the prior art, and provides the transmission line engineering defect detection method based on image segmentation.
The invention is realized by the following technical scheme:
the invention provides a transmission line engineering defect detection method based on image segmentation, which is characterized by comprising the following steps of:
s1: acquiring the power transmission line image and geographic position information associated with the image through an image acquisition device;
s2: preprocessing the power transmission line image to obtain a preprocessed image;
s3: image segmentation is carried out on the preprocessed image based on an A-UNet network model to obtain segmented images, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures;
s4: inputting the segmented image into a defect detection model for defect detection, and obtaining a detection result of the power transmission line;
s5: and (3) outputting the detection result obtained in the step (S4), and when the detection result is that the defect exists, sending the transmission line image, the segmentation image and the geographic position information related to the image to related staff.
Further, the step S2 of preprocessing the power transmission line image to obtain a preprocessed image, where the preprocessing includes: median filtering and histogram equalization processing.
Further, the A-Unet network model is based on U-Net, an ATM self-adaptive adjusting module is added, the ATM self-adaptive adjusting module is used for adjusting edge textures, and the A-Unet network model comprises:
the device comprises an input layer, a downsampling module, an upsampling module and an ATM self-adaptive regulating module;
the downsampling module includes: the device comprises a first feature extraction module, a first pooling layer, a second feature extraction module, a second pooling layer, a third feature extraction module, a third pooling layer, a fourth feature extraction module, a fourth pooling layer and a fifth feature extraction module; the feature extraction module includes 2 3*3 convolutional layers; the outputs of the first to fifth feature extraction modules are respectively marked as F1, F2, F3, F4 and F5;
the up-sampling module includes: a fourth deconvolution layer, a fourth up-sampling module, a third deconvolution layer, a third up-sampling module, a second deconvolution layer, a second up-sampling module, a first deconvolution layer, a first up-sampling module; the outputs of the first up-sampling module to the fourth up-sampling module are respectively marked as U1, U2, U3 and U4;
f1', F2', F3', F4' are obtained after F1, F2, F3 and F4 are copied and cut, the input of the fourth up-sampling module is the output of F4 'and F5 input to the fourth deconvolution layer for deconvolution operation, the input of the third up-sampling module is the output of F3' and U4 input to the third deconvolution layer for deconvolution operation, the input of the second up-sampling module is the output of F2 'and U3 input to the second deconvolution layer for deconvolution operation, and the input of the first up-sampling module is the output of F1' and U2 input to the first deconvolution layer for deconvolution operation;
inputting the U1, U2, U3 and U4 into a Concat layer to obtain a characteristic U;
and inputting the characteristics U and F1 into an ATM self-adaptive adjusting module to obtain a segmented image.
Further, the ATM adaptive adjustment module specifically includes:
inputting the characteristic F1 into a first attention module to obtain F1a;
inputting the characteristic U into a second attention module to obtain Ua;
and after the F1a and the Ua are subjected to feature fusion, inputting a BN layer and a softmax layer to obtain a segmented image.
Further, the first attention module is: a spatial attention module.
Further, the second attention module is: a channel attention module.
Further, the pooling layer is a maximum pooling layer.
Further, the defect detection model is a cascade defect detection model, and the cascade defect detection model includes: the first stage detection model and the second stage detection model specifically comprise:
s41: inputting the segmented image into a first-stage detection model, outputting a normal or defect detection result, and executing step S42 when the detection result is a defect;
s42: and inputting the segmented image into a second stage detection model, and classifying the defect types to obtain a detection result of the defect types.
Compared with the prior art, the invention can bring the following technical effects:
1. the method comprises the steps that image segmentation is carried out on the preprocessed image based on an A-UNet network model, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures, so that the obtained segmented image is clear in boundary, subsequent defect detection is facilitated, and the defect detection precision is improved;
2. according to the method and the device, the defect detection is carried out based on the cascade defect detection model, and when the defect detection is that the defect exists, the defect type is identified, so that the defect detection efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for the description of the embodiments or the prior art will be briefly described, and it is apparent that the drawings in the following description are only one embodiment of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting defects of a power transmission line project based on image segmentation;
fig. 2 is a block diagram of an a-UNet network model.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the present invention easy to understand, the technical solutions in the embodiments of the present invention are clearly and completely described below to further illustrate the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all versions.
The invention is described in further detail below with reference to the attached drawing figures:
as shown in fig. 1, the invention provides a transmission line engineering defect detection method based on image segmentation, which is characterized in that:
s1: acquiring the power transmission line image and geographic position information associated with the image through an image acquisition device;
s2: preprocessing the power transmission line image to obtain a preprocessed image;
s3: image segmentation is carried out on the preprocessed image based on an A-UNet network model to obtain segmented images, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures;
s4: inputting the segmented image into a defect detection model for defect detection, and obtaining a detection result of the power transmission line;
s5: and (3) outputting the detection result obtained in the step (S4), and when the detection result is that the defect exists, sending the transmission line image, the segmentation image and the geographic position information related to the image to related staff.
Further, the step S2 of preprocessing the power transmission line image to obtain a preprocessed image, where the preprocessing includes: median filtering and histogram equalization processing.
Further, the A-Unet network model is based on U-Net, and an ATM self-adaptive adjusting module is added, and is used for adjusting edge textures, and the A-Unet network model shown in fig. 2 comprises:
the device comprises an input layer, a downsampling module, an upsampling module and an ATM self-adaptive regulating module;
the downsampling module includes: the device comprises a first feature extraction module, a first pooling layer, a second feature extraction module, a second pooling layer, a third feature extraction module, a third pooling layer, a fourth feature extraction module, a fourth pooling layer and a fifth feature extraction module; the feature extraction module includes 2 3*3 convolutional layers; the outputs of the first to fifth feature extraction modules are respectively marked as F1, F2, F3, F4 and F5;
the up-sampling module includes: a fourth deconvolution layer, a fourth up-sampling module, a third deconvolution layer, a third up-sampling module, a second deconvolution layer, a second up-sampling module, a first deconvolution layer, a first up-sampling module; the outputs of the first up-sampling module to the fourth up-sampling module are respectively marked as U1, U2, U3 and U4;
f1', F2', F3', F4' are obtained after F1, F2, F3 and F4 are copied and cut, the input of the fourth up-sampling module is the output of F4 'and F5 input to the fourth deconvolution layer for deconvolution operation, the input of the third up-sampling module is the output of F3' and U4 input to the third deconvolution layer for deconvolution operation, the input of the second up-sampling module is the output of F2 'and U3 input to the second deconvolution layer for deconvolution operation, and the input of the first up-sampling module is the output of F1' and U2 input to the first deconvolution layer for deconvolution operation;
inputting the U1, U2, U3 and U4 into a Concat layer to obtain a characteristic U;
and inputting the characteristics U and F1 into an ATM self-adaptive adjusting module to obtain a segmented image.
Further, the ATM adaptive adjustment module specifically includes:
inputting the characteristic F1 into a first attention module to obtain F1a;
inputting the characteristic U into a second attention module to obtain Ua;
and after the F1a and the Ua are subjected to feature fusion, inputting a BN layer and a softmax layer to obtain a segmented image.
Further, the first attention module is: a spatial attention module.
Further, the second attention module is: a channel attention module.
Further, the pooling layer is a maximum pooling layer.
Further, the defect detection model is a cascade defect detection model, and the cascade defect detection model includes: the first stage detection model and the second stage detection model specifically comprise:
s41: inputting the segmented image into a first-stage detection model, outputting a normal or defect detection result, and executing step S42 when the detection result is a defect;
s42: and inputting the segmented image into a second stage detection model, and classifying the defect types to obtain a detection result of the defect types.
Compared with the prior art, the invention can bring the following technical effects:
1. the method comprises the steps that image segmentation is carried out on the preprocessed image based on an A-UNet network model, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures, so that the obtained segmented image is clear in boundary, subsequent defect detection is facilitated, and the defect detection precision is improved;
2. according to the method and the device, the defect detection is carried out based on the cascade defect detection model, and when the defect detection is that the defect exists, the defect type is identified, so that the defect detection efficiency is improved.
Having described the main technical features and fundamental principles of the present invention and related advantages, it will be apparent to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, but may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The above detailed description is, therefore, to be taken in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present disclosure describes embodiments in terms of various embodiments, not every embodiment is described in terms of a single embodiment, but rather that the descriptions of embodiments are merely provided for clarity, and that the descriptions of embodiments in terms of various embodiments are provided for persons skilled in the art on the basis of the description.
Claims (8)
1. A transmission line engineering defect detection method based on image segmentation is characterized by comprising the following steps of:
s1: acquiring the power transmission line image and geographic position information associated with the image through an image acquisition device;
s2: preprocessing the power transmission line image to obtain a preprocessed image;
s3: image segmentation is carried out on the preprocessed image based on an A-UNet network model to obtain segmented images, wherein the A-UNet network model is formed by adding an ATM self-adaptive adjusting module on the basis of U-Net, and the ATM self-adaptive adjusting module is used for adjusting edge textures;
s4: inputting the segmented image into a defect detection model for defect detection, and obtaining a detection result of the power transmission line;
s5: and (3) outputting the detection result obtained in the step (S4), and when the detection result is that the defect exists, sending the transmission line image, the segmentation image and the geographic position information related to the image to related staff.
2. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 1, wherein the method comprises the following steps: s2, preprocessing the power transmission line image to obtain a preprocessed image, wherein the preprocessing comprises the following steps: median filtering and histogram equalization processing.
3. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 1, wherein the method comprises the following steps: the A-Unet network model is based on U-Net, an ATM self-adaptive adjusting module is added, the ATM self-adaptive adjusting module is used for adjusting edge textures, and the A-Unet network model comprises:
the device comprises an input layer, a downsampling module, an upsampling module and an ATM self-adaptive regulating module;
the downsampling module includes: the device comprises a first feature extraction module, a first pooling layer, a second feature extraction module, a second pooling layer, a third feature extraction module, a third pooling layer, a fourth feature extraction module, a fourth pooling layer and a fifth feature extraction module; the feature extraction module includes 2 3*3 convolutional layers; the outputs of the first to fifth feature extraction modules are respectively marked as F1, F2, F3, F4 and F5;
the up-sampling module includes: a fourth deconvolution layer, a fourth up-sampling module, a third deconvolution layer, a third up-sampling module, a second deconvolution layer, a second up-sampling module, a first deconvolution layer, a first up-sampling module; the outputs of the first up-sampling module to the fourth up-sampling module are respectively marked as U1, U2, U3 and U4; f1', F2', F3', F4' are obtained after F1, F2, F3 and F4 are copied and cut, the input of the fourth up-sampling module is the output of F4 'and F5 input to the fourth deconvolution layer for deconvolution operation, the input of the third up-sampling module is the output of F3' and U4 input to the third deconvolution layer for deconvolution operation, the input of the second up-sampling module is the output of F2 'and U3 input to the second deconvolution layer for deconvolution operation, and the input of the first up-sampling module is the output of F1' and U2 input to the first deconvolution layer for deconvolution operation;
inputting the U1, U2, U3 and U4 into a Concat layer to obtain a characteristic U;
and inputting the characteristics U and F1 into an ATM self-adaptive adjusting module to obtain a segmented image.
4. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 1, wherein the method comprises the following steps: the ATM self-adaptive adjusting module specifically comprises:
inputting the characteristic F1 into a first attention module to obtain F1a;
inputting the characteristic U into a second attention module to obtain Ua;
and after the F1a and the Ua are subjected to feature fusion, inputting a BN layer and a softmax layer to obtain a segmented image.
5. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 4, wherein the method comprises the following steps: the first attention module is: a spatial attention module.
6. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 4, wherein the method comprises the following steps: the second attention module is: a channel attention module.
7. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 3, wherein the method comprises the following steps of: the pooling layer is the largest pooling layer.
8. The method for detecting the defects of the power transmission line engineering based on the image segmentation according to claim 1, wherein the method comprises the following steps: the defect detection model is a cascade defect detection model, and the cascade defect detection model comprises: the first stage detection model and the second stage detection model specifically comprise:
s41: inputting the segmented image into a first-stage detection model, outputting a normal or defect detection result, and executing step S42 when the detection result is a defect;
s42: and inputting the segmented image into a second stage detection model, and classifying the defect types to obtain a detection result of the defect types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310151436.XA CN116109607B (en) | 2023-02-22 | 2023-02-22 | Power transmission line engineering defect detection method based on image segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310151436.XA CN116109607B (en) | 2023-02-22 | 2023-02-22 | Power transmission line engineering defect detection method based on image segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116109607A true CN116109607A (en) | 2023-05-12 |
| CN116109607B CN116109607B (en) | 2023-10-20 |
Family
ID=86256017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310151436.XA Active CN116109607B (en) | 2023-02-22 | 2023-02-22 | Power transmission line engineering defect detection method based on image segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109607B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10482603B1 (en) * | 2019-06-25 | 2019-11-19 | Artificial Intelligence, Ltd. | Medical image segmentation using an integrated edge guidance module and object segmentation network |
| CN112508864A (en) * | 2020-11-20 | 2021-03-16 | 昆明理工大学 | Retinal vessel image segmentation method based on improved UNet + |
| CN113012172A (en) * | 2021-04-09 | 2021-06-22 | 杭州师范大学 | AS-UNet-based medical image segmentation method and system |
| CN113298757A (en) * | 2021-04-29 | 2021-08-24 | 同济大学 | Metal surface defect detection method based on U-NET convolutional neural network |
| CN114612472A (en) * | 2022-05-11 | 2022-06-10 | 泉州装备制造研究所 | SegNet improvement-based leather defect segmentation network algorithm |
| WO2022120665A1 (en) * | 2020-12-09 | 2022-06-16 | 电子科技大学 | Capacitance defect intelligent detection method based on deep learning |
| KR20220087699A (en) * | 2020-12-18 | 2022-06-27 | 한국공학대학교산학협력단 | Method and apparatus for inspecting tire appearance based on deep learning |
| CN115409789A (en) * | 2022-08-17 | 2022-11-29 | 广东电网有限责任公司 | Power transmission line engineering defect detection method based on image semantic segmentation |
-
2023
- 2023-02-22 CN CN202310151436.XA patent/CN116109607B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10482603B1 (en) * | 2019-06-25 | 2019-11-19 | Artificial Intelligence, Ltd. | Medical image segmentation using an integrated edge guidance module and object segmentation network |
| CN112508864A (en) * | 2020-11-20 | 2021-03-16 | 昆明理工大学 | Retinal vessel image segmentation method based on improved UNet + |
| WO2022120665A1 (en) * | 2020-12-09 | 2022-06-16 | 电子科技大学 | Capacitance defect intelligent detection method based on deep learning |
| KR20220087699A (en) * | 2020-12-18 | 2022-06-27 | 한국공학대학교산학협력단 | Method and apparatus for inspecting tire appearance based on deep learning |
| CN113012172A (en) * | 2021-04-09 | 2021-06-22 | 杭州师范大学 | AS-UNet-based medical image segmentation method and system |
| CN113298757A (en) * | 2021-04-29 | 2021-08-24 | 同济大学 | Metal surface defect detection method based on U-NET convolutional neural network |
| CN114612472A (en) * | 2022-05-11 | 2022-06-10 | 泉州装备制造研究所 | SegNet improvement-based leather defect segmentation network algorithm |
| CN115409789A (en) * | 2022-08-17 | 2022-11-29 | 广东电网有限责任公司 | Power transmission line engineering defect detection method based on image semantic segmentation |
Non-Patent Citations (1)
| Title |
|---|
| 郭瑞琦 等: "基于U-Net卷积神经网络的轮毂缺陷分割", 自动化与仪表, no. 04, pages 49 - 53 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116109607B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648310B (en) | Weak supervision casting defect identification method based on attention mechanism | |
| CN111368825B (en) | Pointer positioning method based on semantic segmentation | |
| CN110717481A (en) | Method for realizing face detection by using cascaded convolutional neural network | |
| CN109712127B (en) | Power transmission line fault detection method for machine inspection video stream | |
| CN111738054B (en) | Behavior anomaly detection method based on space-time self-encoder network and space-time CNN | |
| CN116579616B (en) | Risk identification method based on deep learning | |
| Thanikkal et al. | Advanced plant leaf classification through image enhancement and canny edge detection | |
| CN114332008B (en) | Unsupervised defect detection and positioning method based on multi-level feature reconstruction | |
| CN113936132B (en) | Method and system for detecting water pollution of chemical plant based on computer vision | |
| CN114170144A (en) | Power transmission line pin defect detection method, equipment and medium | |
| CN110599458A (en) | Underground pipe network detection and evaluation cloud system based on convolutional neural network | |
| CN117557775B (en) | Substation power equipment detection method and system based on infrared and visible light fusion | |
| CN116030050A (en) | On-line detection and segmentation method for surface defects of fan based on unmanned aerial vehicle and deep learning | |
| CN112686261A (en) | Grape root system image segmentation method based on improved U-Net | |
| CN112884721A (en) | Anomaly detection method and system and computer readable storage medium | |
| CN113920080A (en) | Power grid fault positioning method based on generation countermeasure network | |
| CN117115715A (en) | Video anomaly detection method based on combination of stream reconstruction and frame prediction | |
| CN117237683B (en) | Chip defect intelligent detection system based on improved neural network | |
| CN112614094B (en) | Insulator string abnormity positioning and identifying method based on sequence state coding | |
| CN117789109A (en) | Unattended abnormal behavior detection method and system in industrial scene | |
| CN116109607B (en) | Power transmission line engineering defect detection method based on image segmentation | |
| CN113012107A (en) | Power grid defect detection method and system | |
| CN117036266A (en) | Industrial image anomaly detection method and system based on knowledge distillation | |
| CN110599460A (en) | Underground pipe network detection and evaluation cloud system based on hybrid convolutional neural network | |
| CN115719428A (en) | Face image clustering method, device, equipment and medium based on classification model |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |