CN116883817A - Target enhancement detection method and system based on artificial intelligence - Google Patents
Target enhancement detection method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116883817A CN116883817A CN202310926874.9A CN202310926874A CN116883817A CN 116883817 A CN116883817 A CN 116883817A CN 202310926874 A CN202310926874 A CN 202310926874A CN 116883817 A CN116883817 A CN 116883817A
- Authority
- CN
- China
- Prior art keywords
- image
- enhancement
- target
- data
- network
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 18
- 230000007246 mechanism Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012217 deletion Methods 0.000 claims description 6
- 230000037430 deletion Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/247—Aligning, centring, orientation detection or correction of the image by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application provides a target enhancement detection method and system based on artificial intelligence, and the method has the advantages that: through a deep learning technology, the accuracy and the robustness of target detection are improved; through data enhancement and image enhancement technologies, the diversity and complexity of a data set are increased, and the generalization capability of a model is improved; the whole system has high-efficiency processing speed, and can perform target detection in real time in practical application. By combining image enhancement and data enhancement through a deep learning technology, the problems of low accuracy and poor robustness in the prior art when complex scenes such as target scale change, occlusion, low resolution and noise interference are processed are solved.
Description
Technical Field
The application relates to the technical field of network security, in particular to an artificial intelligence-based target enhancement detection method and system.
Background
In the field of computer vision, object detection is an important research topic. The existing target detection method mainly comprises a detection algorithm based on a region and a single-shot detection algorithm. However, these methods have problems of low accuracy and poor robustness in handling complex scenes such as target scale changes, occlusion, low resolution, and noise interference.
Disclosure of Invention
The application aims to provide an artificial intelligence-based target enhancement detection method and system, which are realized by combining image enhancement and data enhancement through a deep learning technology.
In a first aspect, the present application provides an artificial intelligence based target enhancement detection method, the method comprising:
step one, collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
preprocessing image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of an image data set are increased, and an image to be detected is obtained;
the image enhancement in the second step comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the second step is not limited to any one or a combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of labeling data in the training process;
inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and fifthly, managing and controlling according to the identification result.
In a second aspect, the present application provides an artificial intelligence based object enhancement detection system, the system comprising:
a data collection module for collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
the preprocessing module is used for preprocessing the image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of the image data set are increased, and an image to be detected is obtained;
the image enhancement in the preprocessing module comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the preprocessing module is not limited to any one or combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
the training module is used for training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of marking data in the training process;
the target enhancement detection module is used for inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and the execution module is used for controlling according to the identification result.
In a third aspect, the present application provides an artificial intelligence based object enhancement detection system comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the method according to any one of the four possible aspects of the first aspect according to instructions in the program code.
In a fourth aspect, the present application provides a computer readable storage medium for storing program code for performing the method of any one of the four possibilities of the first aspect.
Advantageous effects
The application provides a target enhancement detection method and system based on artificial intelligence, and the method has the advantages that: through a deep learning technology, the accuracy and the robustness of target detection are improved; through data enhancement and image enhancement technologies, the diversity and complexity of a data set are increased, and the generalization capability of a model is improved; the whole system has high-efficiency processing speed, and can perform target detection in real time in practical application. By combining image enhancement and data enhancement through a deep learning technology, the problems of low accuracy and poor robustness in the prior art when complex scenes such as target scale change, occlusion, low resolution and noise interference are processed are solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a general flow chart of an artificial intelligence based target enhancement detection method of the present application;
FIG. 2 is a block diagram of an artificial intelligence based object enhancement detection system of the present application.
Detailed Description
The preferred embodiments of the present application will be described in detail below with reference to the accompanying drawings so that the advantages and features of the present application can be more easily understood by those skilled in the art, thereby making clear and defining the scope of the present application.
FIG. 1 is a schematic flow chart of an artificial intelligence based target enhancement detection method according to the present application, the method comprising:
step one, collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
preprocessing image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of an image data set are increased, and an image to be detected is obtained;
the image enhancement in the second step comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the second step is not limited to any one or a combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of labeling data in the training process;
inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and fifthly, managing and controlling according to the identification result.
In some preferred embodiments, the overall network includes a feature extraction network and an object detection network.
In some preferred embodiments, the target enhancement detection method further includes an attention mechanism, configured to perform fine recognition on a key area of the target object, so as to improve capturing capability of texture detail information and noise suppression capability in the image.
The attention mechanism mainly comprises the following steps:
calculating an input representation vector: first, the input information is represented as a vector or matrix. This vector or matrix may be calculated by the neural network layer or may be pre-processed.
Calculating attention weight: next, the weights of the different parts of the input are calculated by one attention mechanism. This weight is typically calculated by comparing the correlation of different parts of the input with the information of current interest.
Calculating a weighted sum: and according to the calculated weight, carrying out weighted sum calculation on different input parts to obtain a final output. This output is typically a vector or matrix representing a weighted sum of the different parts of the input information.
Differentiable attention mechanisms: finally, the attention weight is combined with the input vector or matrix by a differentiable attention mechanism to obtain the final output. This attention mechanism may be a differentiable mechanism such as dot product, additive, multi-layer perceptron, etc., so that the overall calculation process can be optimized by a back propagation algorithm.
In some preferred embodiments, the target enhancement detection method further comprises an ensemble learning process and a model compression process.
The ensemble learning process is a learning method that combines multiple single predictive models into a more powerful predictive system. In the ensemble learning process, the following steps are generally adopted:
collecting a data set: first, enough datasets need to be collected to train multiple single predictive models. The data may be obtained from different sources or may be pre-processed and/or feature-engineered data.
Training a single model: next, a plurality of single predictive models are trained using the collected data set. These single models may be trained using different algorithms, deep learning models, or conventional machine learning algorithms.
Integrating multiple models: once multiple single models are trained, they need to be integrated to achieve more robust predictive performance. The method of integration may be voting, stacking, feature beam, etc.
Evaluation and adjustment: finally, the integrated model needs to be evaluated and adjusted. The method of evaluation may be cross-validation, test set validation, or the like. If adjustment is needed, the optimization can be performed by adjusting super parameters, changing the model structure and the like.
The model compression process is a method of compressing large neural network models into smaller, lighter weight models for deployment on resource constrained devices. In model compression, the following steps are generally employed:
collecting a training data set: first, enough datasets need to be collected to train a large neural network model.
Training a large model: a large neural network model is trained using the collected data set. The number of layers and parameters of this model is typically large in order to obtain better performance.
Compressing the large model: once a large model is trained, it needs to be compressed into a smaller model. The compression method may be pruning, quantization, decomposition weights, etc.
Evaluation and adjustment: and finally, evaluating and adjusting the compressed model. The method of evaluation may be cross-validation, test set validation, or the like. If adjustment is required, optimization can be performed by parameters of pruning algorithm, quantization scheme and the like.
FIG. 2 is a block diagram of an artificial intelligence based target enhancement detection system according to the present application, the system comprising:
a data collection module for collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
the preprocessing module is used for preprocessing the image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of the image data set are increased, and an image to be detected is obtained;
the image enhancement in the preprocessing module comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the preprocessing module is not limited to any one or combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
the training module is used for training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of marking data in the training process;
the target enhancement detection module is used for inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and the execution module is used for controlling according to the identification result.
The application provides an artificial intelligence-based target enhancement detection system, which comprises: the system includes a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the method according to any of the embodiments of the first aspect according to instructions in the program code.
The present application provides a computer readable storage medium for storing program code for performing the method of any one of the embodiments of the first aspect.
In a specific implementation, the present application also provides a computer storage medium, where the computer storage medium may store a program, where the program may include some or all of the steps in the various embodiments of the present application when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
It will be apparent to those skilled in the art that the techniques of embodiments of the present application may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.
The same or similar parts between the various embodiments of the present description are referred to each other. In particular, for the embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference should be made to the description of the method embodiments for the matters.
The embodiments of the present application described above do not limit the scope of the present application.
Claims (7)
1. An artificial intelligence-based target enhancement detection method, comprising:
step one, collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
preprocessing image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of an image data set are increased, and an image to be detected is obtained;
the image enhancement in the second step comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the second step is not limited to any one or a combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of labeling data in the training process;
inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and fifthly, managing and controlling according to the identification result.
2. The method according to claim 1, characterized in that: the whole network comprises a feature extraction network and a target detection network.
3. The method according to claim 1, characterized in that: the target enhancement detection method further comprises an attention mechanism, wherein the attention mechanism is used for carrying out fine recognition on a key area of a target object, and capturing capability of texture detail information and noise suppression capability in an image are improved.
4. A method according to claim 3, characterized in that: the target enhancement detection method also comprises an ensemble learning process and a model compression process.
5. An artificial intelligence based target enhancement detection system, the system comprising:
a data collection module for collecting an image dataset containing target objects, wherein the target objects comprise objects of various different types;
the preprocessing module is used for preprocessing the image data, wherein the preprocessing comprises image enhancement and data enhancement, so that the diversity and complexity of the image data set are increased, and an image to be detected is obtained;
the image enhancement in the preprocessing module comprises the steps of converting an input RGB image into an HSV image, wherein a V channel represents the brightness of the image, and the subsequent processing is only aimed at the V channel; the subsequent processing comprises the steps of obtaining a smooth brightness map through a stacked self-encoder, dividing the HSV image by the brightness map to obtain an initial reflection map, amplifying noise of the initial reflection map in the brightness enhancement process through a convolution self-encoder to obtain a reflection map and a brightened image, and multiplying the brightened image by the reflection map to obtain an image to be detected;
the data enhancement in the preprocessing module is not limited to any one or combination of the following:
filling operation: adding some noise, interference, or distortion to the image to increase the diversity of the data;
deletion operation: deleting certain areas or pixels in the image to simulate the situation of data loss;
blurring operation: blurring processing is carried out on the image so as to simulate noise and interference in the image acquisition process;
scaling operation: scaling the image to increase the size variation of different objects;
rotation operation: rotating the image to increase the angle change condition of different objects;
and (3) overturning operation: the image is turned horizontally or vertically to increase the symmetry of different objects;
deformation operation: deforming the image to simulate dynamic changes of the object;
the training module is used for training an integral network comprising a feature extraction network and a target detection network by using a deep learning technology, and optimizing parameters of the integral network by using a large amount of marking data in the training process;
the target enhancement detection module is used for inputting the image to be detected into the whole network, extracting the characteristics of the image to be detected and identifying the position and the category of the target object;
and the execution module is used for controlling according to the identification result.
6. An artificial intelligence based object enhancement detection system, the system comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the method according to any of the claims 1-4 according to instructions in the program code.
7. A computer readable storage medium, characterized in that the computer readable storage medium is for storing a program code for performing a method implementing any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926874.9A CN116883817A (en) | 2023-07-26 | 2023-07-26 | Target enhancement detection method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310926874.9A CN116883817A (en) | 2023-07-26 | 2023-07-26 | Target enhancement detection method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116883817A true CN116883817A (en) | 2023-10-13 |
Family
ID=88260332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310926874.9A Pending CN116883817A (en) | 2023-07-26 | 2023-07-26 | Target enhancement detection method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883817A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070183A (en) * | 2019-03-11 | 2019-07-30 | 中国科学院信息工程研究所 | A kind of the neural network model training method and device of weak labeled data |
| CN112465057A (en) * | 2020-12-08 | 2021-03-09 | 中国人民解放军空军工程大学 | Target detection and identification method based on deep convolutional neural network |
| CN113962898A (en) * | 2021-11-03 | 2022-01-21 | 大连海事大学 | Low-illumination image enhancement method based on illumination map optimization and adaptive gamma correction |
| CN115661622A (en) * | 2022-09-27 | 2023-01-31 | 北京航空航天大学 | Merle crater detection method based on image enhancement and improved YOLOv5 |
-
2023
- 2023-07-26 CN CN202310926874.9A patent/CN116883817A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070183A (en) * | 2019-03-11 | 2019-07-30 | 中国科学院信息工程研究所 | A kind of the neural network model training method and device of weak labeled data |
| CN112465057A (en) * | 2020-12-08 | 2021-03-09 | 中国人民解放军空军工程大学 | Target detection and identification method based on deep convolutional neural network |
| CN113962898A (en) * | 2021-11-03 | 2022-01-21 | 大连海事大学 | Low-illumination image enhancement method based on illumination map optimization and adaptive gamma correction |
| CN115661622A (en) * | 2022-09-27 | 2023-01-31 | 北京航空航天大学 | Merle crater detection method based on image enhancement and improved YOLOv5 |
Non-Patent Citations (6)
| Title |
|---|
| PHOENIXLXL: "注意力机制", pages 1 - 4, Retrieved from the Internet <URL:https://blog.csdn.net/phoenixlxl/article/details/130266030> * |
| 吴茂贵等著: "《智能系统与技术丛书 Python深度学习 基于TensorFlow 第2版》", 31 October 2022, 北京：机械工业出版社, pages: 208 - 211 * |
| 杨贞著: "《图像特征处理技术及应用》", 31 August 2020, 科学技术文献出版社, pages: 119 - 123 * |
| 王悦: "基于深度学习的暗光图像增强与目标检测算法研究及应用", 《万方数据库》, 19 October 2022 (2022-10-19), pages 15 - 19 * |
| 笨笨犬牙: "整理学习之注意力机制", pages 1 - 11, Retrieved from the Internet <URL:https://blog.csdn.net/qq_43254330/article/details/124083522> * |
| 网友: "注意力机制是怎么实现的", pages 1 - 2, Retrieved from the Internet <URL:https://wenku.csdn.net/answer/7845fbab9dac4484becff2762fc21827> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052886B (en) | Intelligent human body action posture estimation method and device based on convolutional neural network | |
| CN111639692B (en) | Shadow detection method based on attention mechanism | |
| CN108427920B (en) | Edge-sea defense target detection method based on deep learning | |
| JP2023003026A (en) | Method for identifying rural village area classified garbage based on deep learning | |
| CN110929610B (en) | Plant disease identification method and system based on CNN model and transfer learning | |
| Kadam et al. | Detection and localization of multiple image splicing using MobileNet V1 | |
| CN111209921A (en) | License plate detection model based on improved YOLOv3 network and construction method | |
| KR20190123372A (en) | Apparatus and method for robust face recognition via hierarchical collaborative representation | |
| CN112862023B (en) | Object density determination method and device, computer equipment and storage medium | |
| CN115222998B (en) | Image classification method | |
| CN111241550B (en) | Vulnerability detection method based on binary mapping and deep learning | |
| CN115880495A (en) | Ship image target detection method and system under complex environment | |
| CN113344110B (en) | Fuzzy image classification method based on super-resolution reconstruction | |
| CN115830449A (en) | Remote sensing target detection method with explicit contour guidance and spatial variation context enhancement | |
| CN112560034A (en) | Malicious code sample synthesis method and device based on feedback type deep countermeasure network | |
| CN110503157B (en) | Image steganalysis method of multitask convolution neural network based on fine-grained image | |
| CN117315499A (en) | Satellite remote sensing image target detection method and system | |
| CN112132207A (en) | Target detection neural network construction method based on multi-branch feature mapping | |
| KR102005952B1 (en) | Apparatus and Method for refining data of removing noise data in Machine learning modeling | |
| CN116740808A (en) | Animal behavior recognition method based on deep learning target detection and image classification | |
| CN116843952A (en) | Small sample learning classification method for fruit and vegetable disease identification | |
| CN115311550B (en) | Remote sensing image semantic change detection method and device, electronic equipment and storage medium | |
| CN116883817A (en) | Target enhancement detection method and system based on artificial intelligence | |
| WO2023086198A1 (en) | Robustifying nerf model novel view synthesis to sparse data | |
| CN115346063A (en) | Class attention mechanism construction method and target detection method |
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 |