CN113436259A - Deep learning-based real-time positioning method and system for substation equipment - Google Patents
Deep learning-based real-time positioning method and system for substation equipment Download PDFInfo
- Publication number
- CN113436259A CN113436259A CN202110700043.0A CN202110700043A CN113436259A CN 113436259 A CN113436259 A CN 113436259A CN 202110700043 A CN202110700043 A CN 202110700043A CN 113436259 A CN113436259 A CN 113436259A
- Authority
- CN
- China
- Prior art keywords
- substation equipment
- training
- deep learning
- weight file
- images
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000003786 synthesis reaction Methods 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The disclosure provides a transformer substation equipment real-time positioning method and system based on deep learning, which comprises the following steps: processing the collected transformer substation equipment images and generating a weight file by utilizing model training; loading a model training generation weight file, and inputting an image to be detected for preprocessing; carrying out target positioning identification on the image to be detected by utilizing the model parameters; when the weight file is generated through model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, the large graph is cut and amplified according to an agreed rule, and then training is carried out to generate the weight file. The problem of device positioning failure caused by light rays and small targets is effectively avoided, and the robustness of recognition of different scenes, different angles, small targets and the like is improved.
Description
Technical Field
The disclosure relates to the technical field of robots, in particular to a transformer substation equipment real-time positioning method and system based on deep learning.
Background
In the field, target positioning for substation equipment is an important technical means in the technical field of substation monitoring and management, and in the prior art, the existing technical means mainly comprises the steps of dividing tracking into two parts of target positioning and scale selection and carrying out related filtering matching on targets with different scales; or effective object classification is carried out, and meanwhile, a unified network is used for positioning, identifying and the like.
The scheme mainly has the following problems:
(1) the traditional target positioning precision is not high, and the adaptability is poor;
(2) the current deep learning method has simple use scene and poor positioning precision for small targets;
(3) the complexity of the existing algorithm is high, the execution time is long, the real-time detection effect cannot be achieved, and the requirement of real-time monitoring unattended operation of a transformer substation cannot be met;
(4) at present, a large amount of configuration work is introduced into the algorithm, the algorithm is flexible and poor, and the robustness is not high.
Disclosure of Invention
In view of this, an object of the embodiment of the present disclosure is to provide a method for positioning substation equipment in real time based on deep learning, which improves the problem of positioning targets of different types, models, and sizes to be detected by a robot in an inspection process, increases positioning accuracy, and ensures accuracy of subsequent target equipment analysis and identification.
In order to achieve the above object, one or more embodiments of the present disclosure provide the following technical solutions:
in a first aspect, an embodiment of the present specification provides a deep learning-based substation device real-time positioning method, including:
processing the collected transformer substation equipment images and generating a weight file by utilizing model training;
loading a model training generation weight file, and inputting an image to be detected for preprocessing;
carrying out target positioning identification on the image to be detected by utilizing the model parameters;
when the weight file is generated through model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, the large graph is cut and amplified according to an agreed rule, and then training is carried out to generate the weight file.
In a second aspect, embodiments of the present specification provide a deep learning based substation device real-time positioning system, including:
a weight file generation module configured to: processing the collected transformer substation equipment images and generating a weight file by utilizing model training;
when the weight file is generated by model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, and the large graph is cut and amplified according to an agreed rule and then trained to generate the weight file;
an image positioning and identifying module to be detected is configured to: loading a model training generation weight file, and inputting an image to be detected for preprocessing; and carrying out target positioning identification on the image to be detected by utilizing the model parameters.
Compared with the prior art, the beneficial effect of this disclosure is:
the utility model discloses a transformer substation equipment real-time positioning method based on deep learning develops relevant system, uses the mode of convolution neural network to fix a position transformer substation equipment, uses the model parameter of training to realize equipment automatic positioning, no longer relies on manual configuration template, has solved the various transformer substation equipment types and has leaded to investing in the problem of a large amount of manual configurations.
A multi-resolution data fusion sample expansion technology is provided, a multi-scale data enhancement algorithm is designed, target devices under multiple scales are randomly fused into a large image, the large image is cut and amplified according to an agreed rule and then trained, the problem of device positioning failure caused by light and small target is effectively solved, and the robustness of recognition of different scenes, different angles, small targets and the like is improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
Fig. 1 is a flowchart of a deep learning-based substation device real-time positioning method according to an embodiment of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example one
The embodiment discloses a transformer substation equipment real-time positioning method based on deep learning, which comprises the following overall steps: carrying out data annotation on the sample image, and training by utilizing a deep learning neural network model to generate a weight file; and loading a model weight file, inputting an image to be detected for preprocessing, and performing target positioning identification on the image to be detected by using model parameters.
As shown in fig. 1, specifically:
the method comprises the following steps: calibrating all equipment sample images needing to be positioned in the transformer substation;
step two: expanding a sample image library for the data in the step one in a data enhancement mode;
step three: using the sample data in the second step, adopting two-stage deep learning neural network model training to generate a weight file;
step four: inputting an image, and positioning the position in the image of the target equipment by using the training weight file generated in the third step;
step five: and obtaining the equipment ROI and then carrying out subsequent identification processing.
In one embodiment, the specific steps in the first step are as follows: and screening sample images of the equipment from a routing inspection database, wherein the number of the images is N, calibrating targets in the sample images to obtain parameter files, and the parameter files are used for storing calibration information and the number of the parameter files is N.
And in the second step, the training data samples are expanded. According to the characteristics of training targets, the characteristics of various types and different sizes of equipment, the targets under 1080P are processed in two modes:
(1) cutting the target area from the original image according to a fixed size smaller than the size of the original image to form sub-images and corresponding calibration parameter files, wherein the number of the sub-images is larger than N;
(2) and (2) randomly selecting the subgraphs in the step (1), wherein N subgraphs are a group of subgraphs randomly arranged in a large graph, and synthesizing the large graph by using an image synthesis technology, so that a plurality of target files of the large graph are finally generated, wherein M is larger than N, and the N number can be set to different values according to the types of the targets.
Performing secondary processing on the M images, setting five rectangles with the same size in total at the four corners and the center, wherein the size of each rectangle is three fifths and one half of the original image, so that the rectangles are equivalent to two groups of rectangles with different sizes, one group is three fifths of the original image, and the other group is one half of the original image, so that ten rectangles are generated in total, taking three-fifths sub-images of the four original images from the four corners successively according to the above, taking one three-fifths sub-image of the original image from the middle, and taking five sub-images of one half of the original image in the same way, so that extra ten sub-images are obtained, and the number of the training images is M +10 × M; on this basis, the ten sub-graphs are enlarged to the original size, resulting in 10 × M new graphs, thus a total of M +10 × M images, and the target training is performed with this new expanded data set.
In a further specific embodiment, the expanded data set is trained by using a two-stage CNN (neural network) network, the polling target is secondarily expanded in the training process, such as brightness adjustment, rotation and the like, network iteration is performed, the training is terminated after the loss value is reduced and the network converges, and a training weight file is obtained, wherein the training weight file is a training result file and is used for later prediction.
In the above embodiment of the present disclosure, based on a variety of types of substation devices, to reduce workload of manual configuration in device positioning, deep learning-based real-time positioning of the substation device is introduced. The method can realize the purposes of one-time training and multi-station application by adopting a pre-training mode, and does not need a large amount of environment deployment work.
On the other hand, the transformer substation equipment is various in types, diversity optimization is carried out on the training process for ensuring the precision of the positioning algorithm, the interference of severe environments such as illumination is solved, and the positioning precision of small targets is effectively ensured.
Example two
The embodiment discloses a transformer substation equipment real-time positioning system based on deep learning, include:
a weight file generation module configured to: processing the collected transformer substation equipment images and generating a weight file by utilizing model training;
when the weight file is generated by model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, and the large graph is cut and amplified according to an agreed rule and then trained to generate the weight file;
an image positioning and identifying module to be detected is configured to: loading a model training generation weight file, and inputting an image to be detected for preprocessing; and carrying out target positioning identification on the image to be detected by utilizing the model parameters.
EXAMPLE III
The present embodiment is directed to a computing device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the specific steps in the first implementation example.
Example four
An object of the present embodiment is to provide a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the specific steps of the first embodiment.
The steps involved in the apparatus of the above embodiment correspond to the first embodiment of the method, and the detailed description thereof can be found in the relevant description of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media containing one or more sets of instructions; it should also be understood to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any of the methods of the present disclosure.
Those skilled in the art will appreciate that the modules or steps of the present disclosure described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code executable by computing means, whereby the modules or steps may be stored in memory means for execution by the computing means, or separately fabricated into individual integrated circuit modules, or multiple modules or steps thereof may be fabricated into a single integrated circuit module. The present disclosure is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. The transformer substation equipment real-time positioning method based on deep learning is characterized by comprising the following steps of:
processing the collected transformer substation equipment images and generating a weight file by utilizing model training;
loading a model training generation weight file, and inputting an image to be detected for preprocessing;
carrying out target positioning identification on the image to be detected by utilizing the model parameters;
when the weight file is generated through model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, the large graph is cut and amplified according to an agreed rule, and then training is carried out to generate the weight file.
2. The deep learning-based substation equipment real-time positioning method according to claim 1, wherein the processing of the collected substation equipment images specifically comprises:
and screening sample images of the equipment from a routing inspection database, wherein the number of the images is N, calibrating targets in the sample images to obtain parameter files, and the parameter files are used for storing calibration information and the number of the parameter files is N.
3. The deep learning-based substation equipment real-time positioning method according to claim 1, wherein the training data samples are expanded:
and cutting the target area from the original image according to the fixed size smaller than the size of the original image to form sub-images and corresponding calibration parameter files, wherein the number of the sub-images is larger than N.
4. The deep learning-based substation equipment real-time positioning method according to claim 3, wherein the expanding of the training data samples further comprises:
randomly selecting subgraphs, arranging N subgraphs in a large graph in a random mode, and synthesizing the large graph by using an image synthesis technology, wherein the large graph contains a plurality of target files, and finally generating M image objects, wherein M is larger than N.
5. The deep learning-based substation equipment real-time positioning method according to claim 4, wherein the n number sets different values according to target types.
6. The deep learning-based substation equipment real-time positioning method according to claim 4, wherein after performing secondary processing on the M images:
setting five rectangles with the same size in total at four corners and the center, wherein the size of each rectangle is three fifths and one half of the original image, taking four subgraphs with the three fifths of the original image from the four corners successively, taking one subgraph with the three fifths of the original image from the middle, taking five subgraphs with the one half of the original image in the same mode, and obtaining ten extra subgraphs, wherein the number of the training images is M + 10M; on this basis, the ten sub-graphs are enlarged to the original size, resulting in 10 × M new graphs, and a total of M +10 × M images, and the target training is performed with the new data set expanded.
7. The deep learning-based substation equipment real-time positioning method according to claim 6, wherein the expanded data set is trained by adopting a two-stage neural network, the routing inspection target is secondarily expanded in the training process, and the training is terminated after the network converges to obtain a training weight file.
8. Real-time positioning system of substation equipment based on degree of depth study, characterized by includes:
a weight file generation module configured to: processing the collected transformer substation equipment images and generating a weight file by utilizing model training;
when the weight file is generated by model training, substation equipment is positioned in a deep learning convolutional neural network mode, target equipment under multiple scales is randomly fused into a large graph, and the large graph is cut and amplified according to an agreed rule and then trained to generate the weight file;
an image positioning and identifying module to be detected is configured to: loading a model training generation weight file, and inputting an image to be detected for preprocessing; and carrying out target positioning identification on the image to be detected by utilizing the model parameters.
9. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700043.0A CN113436259A (en) | 2021-06-23 | 2021-06-23 | Deep learning-based real-time positioning method and system for substation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700043.0A CN113436259A (en) | 2021-06-23 | 2021-06-23 | Deep learning-based real-time positioning method and system for substation equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113436259A true CN113436259A (en) | 2021-09-24 |
Family
ID=77755168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110700043.0A Pending CN113436259A (en) | 2021-06-23 | 2021-06-23 | Deep learning-based real-time positioning method and system for substation equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113436259A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236042A (en) * | 2013-04-27 | 2013-08-07 | 崔红保 | Self-adaptive picture processing method and device |
| CN108986058A (en) * | 2018-06-22 | 2018-12-11 | 华东师范大学 | The image interfusion method of lightness Consistency Learning |
| CN109816024A (en) * | 2019-01-29 | 2019-05-28 | 电子科技大学 | A kind of real-time automobile logo detection method based on multi-scale feature fusion and DCNN |
| CN111062885A (en) * | 2019-12-09 | 2020-04-24 | 中国科学院自动化研究所 | Mark detection model training and mark detection method based on multi-stage transfer learning |
| CN111079844A (en) * | 2019-12-19 | 2020-04-28 | 新立讯科技股份有限公司 | Image cutting and data enhancement method, system and equipment |
| CN111339839A (en) * | 2020-02-10 | 2020-06-26 | 广州众聚智能科技有限公司 | Intensive target detection and metering method |
| CN111881720A (en) * | 2020-06-09 | 2020-11-03 | 山东大学 | Data automatic enhancement expansion method, data automatic enhancement identification method and data automatic enhancement expansion system for deep learning |
| CN112215074A (en) * | 2020-09-10 | 2021-01-12 | 鲁东大学 | Real-time target identification and detection tracking system and method based on unmanned aerial vehicle vision |
| CN112380952A (en) * | 2020-11-10 | 2021-02-19 | 广西大学 | Power equipment infrared image real-time detection and identification method based on artificial intelligence |
| WO2021057810A1 (en) * | 2019-09-29 | 2021-04-01 | 深圳数字生命研究院 | Data processing method, data training method, data identifying method and device, and storage medium |
| CN112926614A (en) * | 2019-12-06 | 2021-06-08 | 顺丰科技有限公司 | Box labeling image expansion method and device and computer readable storage medium |
-
2021
- 2021-06-23 CN CN202110700043.0A patent/CN113436259A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236042A (en) * | 2013-04-27 | 2013-08-07 | 崔红保 | Self-adaptive picture processing method and device |
| CN108986058A (en) * | 2018-06-22 | 2018-12-11 | 华东师范大学 | The image interfusion method of lightness Consistency Learning |
| CN109816024A (en) * | 2019-01-29 | 2019-05-28 | 电子科技大学 | A kind of real-time automobile logo detection method based on multi-scale feature fusion and DCNN |
| WO2021057810A1 (en) * | 2019-09-29 | 2021-04-01 | 深圳数字生命研究院 | Data processing method, data training method, data identifying method and device, and storage medium |
| CN112926614A (en) * | 2019-12-06 | 2021-06-08 | 顺丰科技有限公司 | Box labeling image expansion method and device and computer readable storage medium |
| CN111062885A (en) * | 2019-12-09 | 2020-04-24 | 中国科学院自动化研究所 | Mark detection model training and mark detection method based on multi-stage transfer learning |
| CN111079844A (en) * | 2019-12-19 | 2020-04-28 | 新立讯科技股份有限公司 | Image cutting and data enhancement method, system and equipment |
| CN111339839A (en) * | 2020-02-10 | 2020-06-26 | 广州众聚智能科技有限公司 | Intensive target detection and metering method |
| CN111881720A (en) * | 2020-06-09 | 2020-11-03 | 山东大学 | Data automatic enhancement expansion method, data automatic enhancement identification method and data automatic enhancement expansion system for deep learning |
| CN112215074A (en) * | 2020-09-10 | 2021-01-12 | 鲁东大学 | Real-time target identification and detection tracking system and method based on unmanned aerial vehicle vision |
| CN112380952A (en) * | 2020-11-10 | 2021-02-19 | 广西大学 | Power equipment infrared image real-time detection and identification method based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 孙慧 等: "基于场景建模的电力巡检异物检测样本扩充方法", 《电网技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Multi-label image recognition by recurrently discovering attentional regions | |
| CN110135503B (en) | Deep learning identification method for parts of assembly robot | |
| WO2020177432A1 (en) | Multi-tag object detection method and system based on target detection network, and apparatuses | |
| Bian et al. | Multiscale fully convolutional network with application to industrial inspection | |
| CN112508975A (en) | Image identification method, device, equipment and storage medium | |
| CN111738070A (en) | Automatic accurate detection method for multiple small targets | |
| CN112819110B (en) | Incremental small sample target detection method and system based on weight generation | |
| Vaviya et al. | Identification of artificially ripened fruits using machine learning | |
| Yu et al. | Exemplar-based recursive instance segmentation with application to plant image analysis | |
| CN113487610B (en) | Herpes image recognition method and device, computer equipment and storage medium | |
| CN113762159A (en) | Target grabbing detection method and system based on directional arrow model | |
| CN112434581A (en) | Outdoor target color identification method and system, electronic device and storage medium | |
| CN116994049A (en) | Full-automatic flat knitting machine and method thereof | |
| CN113743434A (en) | Training method of target detection network, image augmentation method and device | |
| Tang et al. | Two-stage filtering method to improve the performance of object detection trained by synthetic dataset in heavily cluttered industry scenes | |
| CN113436259A (en) | Deep learning-based real-time positioning method and system for substation equipment | |
| CN113657444A (en) | Interface element identification method and system | |
| CN112766387A (en) | Error correction method, device, equipment and storage medium for training data | |
| CN111144422A (en) | Positioning identification method and system for aircraft component | |
| EP4189584A1 (en) | Automated annotation of visual data through computer vision template matching | |
| CN117173122B (en) | Lightweight ViT-based image leaf density determination method and device | |
| CN113111804B (en) | Face detection method and device, electronic equipment and storage medium | |
| Andrade et al. | A robust methodology for outdoor optical mark recognition | |
| WO2023015914A1 (en) | Method and apparatus for obtaining gravity direction of image, electronic device, and storage medium | |
| CN111259843B (en) | Multimedia navigator testing method based on visual stability feature classification registration |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210924 |
|
| RJ01 | Rejection of invention patent application after publication |