CN114494055B - Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network - Google Patents
Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network Download PDFInfo
- Publication number
- CN114494055B CN114494055B CN202210062731.3A CN202210062731A CN114494055B CN 114494055 B CN114494055 B CN 114494055B CN 202210062731 A CN202210062731 A CN 202210062731A CN 114494055 B CN114494055 B CN 114494055B
- Authority
- CN
- China
- Prior art keywords
- target
- neural network
- sequence
- network
- training
- 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.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 87
- 238000003384 imaging method Methods 0.000 title claims abstract description 49
- 125000004122 cyclic group Chemical group 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 79
- 108010076504 Protein Sorting Signals Proteins 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 21
- 230000000306 recurrent effect Effects 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 230000007787 long-term memory Effects 0.000 claims description 2
- 239000000523 sample Substances 0.000 claims 1
- 238000005070 sampling Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 22
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
Ghost imaging method, system, equipment and storage medium based on cyclic neural network, the method comprises: acting a set of random speckle sequences on targets in the training set to enable each target to obtain a corresponding barrel detection signal sequence; splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence; taking a real target in the training set as a training target of the cyclic neural network, training the cyclic neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained cyclic neural network; detecting a target area by using the same set of random speckle during training the cyclic neural network, and splicing the random speckle and the barrel detection signal sequence to obtain a second network input sequence; and inputting the second network input sequence into the trained cyclic neural network, and outputting the target image. The invention can rapidly output the target image with high resolution by using the cyclic neural network under the condition of low sampling rate.
Description
Technical Field
The invention relates to the technical field of ghost imaging, in particular to a ghost imaging method, a ghost imaging system, ghost imaging equipment and a ghost imaging storage medium based on a recurrent neural network.
Background
Ghost imaging, also known as correlated imaging, is a novel imaging technique for recovering spatial information of an object to be detected by utilizing composite detection. Compared with the traditional imaging technology, the existing imaging technology mainly utilizes first-order correlation information (intensity and phase) of a light field, and classical ghost imaging utilizes second-order correlation of the light field, and is regarded as statistical correlation of intensity fluctuation. The imaging process comprises the steps of irradiating a target by utilizing a plurality of speckles, collecting barrel detection signals, and carrying out correlation operation on the speckles and the collected barrel detection signals to obtain a target image. The method is a basic correlation method in the field of ghost imaging, and has the advantages of simple operation, low imaging resolution and high-resolution image acquisition by multiple detection. And the repeated detection brings about larger time consumption, which limits the application prospect of the ghost imaging method.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provide a ghost imaging method, a ghost imaging system, ghost imaging equipment and a storage medium based on a cyclic neural network, which can quickly reconstruct a clear target image at a lower sampling rate.
In order to achieve the above purpose, the present invention has the following technical scheme:
a ghost imaging method based on a recurrent neural network comprises the following steps:
acting a set of random speckle sequences on targets in the training set to enable each target to obtain a corresponding barrel detection signal sequence;
splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence;
taking a real target in the training set as a training target of the cyclic neural network, training the cyclic neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained cyclic neural network;
detecting a target area by using the same set of random speckle during training the cyclic neural network, and splicing the random speckle and the barrel detection signal sequence to obtain a second network input sequence;
and inputting the second network input sequence into the trained cyclic neural network, and outputting the target image.
Preferably, in the step of performing the splicing process on the bucket detection signal sequence of each target and the corresponding random speckle sequence, the process of the splicing process is to adjust the two-dimensional speckle to a one-dimensional structure, and splice the corresponding bucket detection signal to the one-dimensional structure as a primary detection result.
Furthermore, the detection sequence is a corresponding detection sequence obtained by splicing after the target acts with different speckles for a plurality of times.
Preferably, the cyclic neural network adopts a long-term and short-term memory network, when the network is trained, a target is used as a label for network training, a plurality of obtained detection sequences are used as input data of the network, and the output of the network is a predicted target image.
Furthermore, the cyclic neural network calculates a loss function according to the predicted target image and the target to be identified, and updates network parameters by optimizing the loss;
the loss function is expressed as:
Loss rec ＝F(y i ,y p )
wherein y is i For the purpose, y p For the predicted target image, F is used to calculate y i And y is p And errors between them.
Preferably, the training the recurrent neural network by using the detection sequence corresponding to the real target as the first network input sequence includes:
taking the detection sequence as input of a cyclic neural network to obtain a predicted target image to be identified;
and taking the target to be identified as a target of network training, calculating the loss between the predicted target image and the target, and updating network parameters by optimizing the loss until the loss or the iteration number reaches a certain preset value.
Preferably, the barrel detection signal is received by a barrel detector or a single antenna.
A ghost imaging system based on a recurrent neural network, comprising:
the speckle action module is used for acting a set of random speckle sequences on targets in the training set to enable each target to obtain a corresponding barrel detection signal sequence;
the preprocessing module is used for splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence;
the network training module is used for taking a real target in the training set as a training target of the circulating neural network, training the circulating neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained circulating neural network;
the target detection module is used for detecting a target area by using the same set of random speckles during training of the cyclic neural network, and splicing the random speckles with the barrel detection signal sequence to obtain a second network input sequence;
and the target recognition module is used for inputting the second network input sequence into the trained cyclic neural network and outputting a target image.
An electronic device, the electronic device comprising:
a memory storing at least one instruction; and
A processor executing instructions stored in the memory to implement a recurrent neural network-based ghosting method as in any of claims 1 to 7.
A computer-readable storage medium having stored therein at least one instruction for execution by a processor in an electronic device to implement the recurrent neural network-based ghosting method.
Compared with the prior art, the invention has at least the following beneficial effects:
according to the ghost imaging method, a real target in a training set is used as a training target of the circulating neural network, a detection sequence corresponding to the real target is used as a first network input sequence to train the circulating neural network, and the trained circulating neural network is obtained. And then the same set of random speckle used for training the cyclic neural network is used for detecting the target area, the random speckle and the barrel detection signal sequence are spliced to obtain a second network input sequence, the second network input sequence is input into the trained cyclic neural network, the target image is output, and the cyclic neural network can be used for rapidly outputting the target image with high resolution under the condition of low sampling rate.
Drawings
Fig. 1 is a flowchart of a ghost imaging method based on a recurrent neural network according to an embodiment of the present application;
FIG. 2 is a schematic diagram of ghosting imaging with handwritten numbers as an objective in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a ghost imaging system based on a recurrent neural network according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of a preferred embodiment of a ghost imaging method based on a recurrent neural network. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.
A ghost imaging method based on a recurrent neural network comprises the following steps:
s1, a set of random speckle sequences acts on targets in a training set, so that each target obtains a corresponding barrel detection signal sequence. For each target, acting with one speckle pattern at a time will produce a corresponding bin detect signal.
S2, splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence. The splicing process is to firstly adjust the two-dimensional speckle into a one-dimensional structure, and then splice the corresponding barrel detection signal to the one-dimensional structure to serve as a primary detection result. And after the targets react with different speckles for many times, the corresponding detection sequences are obtained through splicing treatment.
S3, taking a real target in the training set as a training target of the circulating neural network, training the circulating neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained circulating neural network.
The recurrent neural network in the embodiment is a recurrent neural network which takes sequence data as input, performs recursion in the evolution direction of the sequence and has memory, so the recurrent neural network has the advantage of being friendly to the sequence data. In one embodiment, a Long Short-term memory network (LSTM) is used as the network to be trained. The LSTM is a special cyclic neural network and is mainly used for solving the long-term dependence problem existing in the common cyclic neural network. When the network is trained, the target is used as a label for network training, a plurality of detection sequences are obtained and used as input data of the network, and the output of the network is a predicted target image. And calculating a loss function according to the predicted target image and the target to be identified. Its loss function can be expressed as:
Loss rec ＝F(y i ,y p )
wherein y is i For the purpose, y p For the predicted target image, F is used to calculate y i And y is p The error may be a Mean Square Error (MSE) or a Structural Similarity (SSIM), and is not limited in this application.
The training cyclic neural network using a detection sequence corresponding to a real target as a first network input sequence includes:
taking the detection sequence as input of a cyclic neural network to obtain a predicted target image to be identified;
and taking the target to be identified as a target of network training, calculating the loss between the predicted target image and the target, and updating network parameters by optimizing the loss until the loss or the iteration number reaches a certain preset value.
S4, detecting a target area by using the same set of random speckle during training of the cyclic neural network, and splicing the random speckle and the barrel detection signal sequence to obtain a second network input sequence;
when the target area is detected, the speckle sequence and the network training stage are the same set of speckle sequence, and the obtained barrel detection signal sequence and the speckle sequence are spliced to obtain the detection sequence of the target area.
S5, inputting the second network input sequence into the trained cyclic neural network, and outputting the target image.
In one possible embodiment, the bucket detection signal is obtained using a bucket detector or a single antenna.
As shown in fig. 2, according to the ghost imaging method based on the cyclic neural network, the target is sequentially subjected to barrel detection and splicing processing to obtain a detection sequence, the detection sequence is input into the trained cyclic neural network, and the network outputs a target image.
As shown in fig. 3, an embodiment of the present invention further provides a ghost imaging system based on a recurrent neural network, including:
the speckle acting module 301 is configured to act a set of random speckle sequences on the targets in the training set, so that each target obtains a corresponding bucket detection signal sequence;
the preprocessing module 302 is configured to splice the bucket detection signal sequence of each target with a corresponding random speckle sequence to obtain a detection sequence;
the network training module 303 is configured to train the cyclic neural network by using a detection sequence corresponding to a real target as a first network input sequence, and obtain a trained cyclic neural network;
the target detection module 304 is configured to detect a target area by using the same set of random speckle during training the cyclic neural network, and splice the random speckle and the bucket detection signal sequence to obtain a second network input sequence;
the target recognition module 305 is configured to input the second network input sequence into the trained recurrent neural network, and output a target image.
Since each functional module of the ghost imaging system based on the recurrent neural network in the present application corresponds to a step of the above-mentioned embodiment of the ghost imaging method based on the recurrent neural network, for details not disclosed in the embodiment of the ghost imaging system based on the recurrent neural network in the present application, please refer to the above-mentioned embodiment of the ghost imaging method based on the recurrent neural network in the present disclosure.
Another embodiment also discloses an electronic device, including:
a memory storing at least one instruction; and
And the processor executes the instructions stored in the memory to realize the ghost imaging method based on the cyclic neural network.
A computer-readable storage medium having stored therein at least one instruction for execution by a processor in an electronic device to implement the recurrent neural network-based ghosting method.
The instructions stored in the memory may be partitioned into one or more modules/units, which are stored in a computer-readable storage medium and executed by the processor to perform the recurrent neural network-based ghost imaging method of the present invention. The one or more modules/units may be a series of computer readable instruction segments capable of performing a specified function, which describes the execution of the computer program in a server.
The electronic equipment can be a smart phone, a notebook computer, a palm computer, a cloud server and other computing equipment. The electronic device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the electronic device may also include more or fewer components, or may combine certain components, or different components, e.g., the electronic device may also include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (CentraL Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DigitaL SignaL Processor, DSP), application specific integrated circuits (AppLication Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (fierld-ProgrammabLe Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the server, such as a hard disk or a memory of the server. The memory may also be an external storage device of the server, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure DigitaL (SD) Card, a FLash Card (FLash Card) or the like, which are provided on the server. Further, the memory may also include both an internal storage unit and an external storage device of the server. The memory is used to store the computer readable instructions and other programs and data required by the server. The memory may also be used to temporarily store data that has been output or is to be output.
It should be noted that, because the content of information interaction and execution process between the above module units is based on the same concept as the method embodiment, specific functions and technical effects thereof may be referred to in the method embodiment section, and details thereof are not repeated herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. The ghost imaging method based on the cyclic neural network is characterized by comprising the following steps of:
acting a set of random speckle sequences on targets in the training set to enable each target to obtain a corresponding barrel detection signal sequence;
splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence;
taking a real target in the training set as a training target of the cyclic neural network, training the cyclic neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained cyclic neural network;
detecting a target area by using the same set of random speckle during training the cyclic neural network, and splicing the random speckle and the barrel detection signal sequence to obtain a second network input sequence;
inputting the second network input sequence into a trained cyclic neural network, and outputting a target image;
in the step of splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence, the two-dimensional speckle is firstly adjusted to be a one-dimensional structure, and then the corresponding barrel detection signal is spliced to the one-dimensional structure and used as a primary detection result;
the detection sequence is a corresponding detection sequence obtained by splicing after the target acts with different speckles for a plurality of times.
2. The ghost imaging method based on the cyclic neural network according to claim 1, wherein the cyclic neural network adopts a long-term and short-term memory network, when the network is trained, a target is used as a label for network training, a plurality of obtained detection sequences are used as input data of the network, and the output of the network is a predicted target image.
3. The ghost imaging method based on a recurrent neural network according to claim 2, wherein the recurrent neural network calculates a loss function according to the predicted target image and the target to be identified, and updates network parameters by optimizing the loss;
the loss function is expressed as:
Loss rec ＝F(y i ,y p )
wherein y is i For the purpose, y p For the predicted target image, F is used to calculate y i And y is p And errors between them.
4. The ghost imaging method based on a recurrent neural network according to claim 1, wherein training the recurrent neural network using the probe sequence corresponding to the real target as the first network input sequence comprises:
taking the detection sequence as input of a cyclic neural network to obtain a predicted target image to be identified;
and taking the target to be identified as a target of network training, calculating the loss between the predicted target image and the target, and updating network parameters by optimizing the loss until the loss or the iteration number reaches a certain preset value.
5. The ghost imaging method based on a recurrent neural network as claimed in claim 1, wherein the barrel detection signal is obtained by a barrel detector or a single antenna.
6. A ghost imaging system based on a recurrent neural network, comprising:
the speckle action module is used for acting a set of random speckle sequences on targets in the training set to enable each target to obtain a corresponding barrel detection signal sequence;
the preprocessing module is used for splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence to obtain a detection sequence; in the step of splicing the barrel detection signal sequence of each target with the corresponding random speckle sequence, the two-dimensional speckle is firstly adjusted to be a one-dimensional structure, and then the corresponding barrel detection signal is spliced to the one-dimensional structure and used as a primary detection result;
the detection sequence is a corresponding detection sequence obtained by splicing after the target acts with different speckles for many times;
the network training module is used for taking a real target in the training set as a training target of the circulating neural network, training the circulating neural network by taking a detection sequence corresponding to the real target as a first network input sequence, and obtaining a trained circulating neural network;
the target detection module is used for detecting a target area by using the same set of random speckles during training of the cyclic neural network, and splicing the random speckles with the barrel detection signal sequence to obtain a second network input sequence;
and the target recognition module is used for inputting the second network input sequence into the trained cyclic neural network and outputting a target image.
7. An electronic device, the electronic device comprising:
a memory storing at least one instruction; and
A processor executing instructions stored in the memory to implement a recurrent neural network-based ghosting method as in any of claims 1 to 5.
8. A computer-readable storage medium, characterized by: the computer-readable storage medium having stored therein at least one instruction for execution by a processor in an electronic device to implement the recurrent neural network-based ghosting method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210062731.3A CN114494055B (en) | 2022-01-19 | 2022-01-19 | Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210062731.3A CN114494055B (en) | 2022-01-19 | 2022-01-19 | Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114494055A CN114494055A (en) | 2022-05-13 |
| CN114494055B true CN114494055B (en) | 2024-02-06 |
Family
ID=81472028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210062731.3A Active CN114494055B (en) | 2022-01-19 | 2022-01-19 | Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494055B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930317A (en) * | 2019-10-30 | 2020-03-27 | 西安交通大学 | Ghost imaging method based on convolutional neural network |
| WO2021102655A1 (en) * | 2019-11-25 | 2021-06-03 | 深圳市欢太科技有限公司 | Network model training method, image property recognition method and apparatus, and electronic device |
| CN113269243A (en) * | 2021-05-18 | 2021-08-17 | 西安交通大学 | Association identification method and device based on generative countermeasure network |
| CN113706408A (en) * | 2021-08-11 | 2021-11-26 | 西安交通大学 | Ghost imaging denoising method and device based on noise reduction convolutional neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11030780B2 (en) * | 2018-03-26 | 2021-06-08 | The Board Of Trustees Of The Leland Stanford Junior University | Ultrasound speckle reduction and image reconstruction using deep learning techniques |
-
2022
- 2022-01-19 CN CN202210062731.3A patent/CN114494055B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930317A (en) * | 2019-10-30 | 2020-03-27 | 西安交通大学 | Ghost imaging method based on convolutional neural network |
| WO2021102655A1 (en) * | 2019-11-25 | 2021-06-03 | 深圳市欢太科技有限公司 | Network model training method, image property recognition method and apparatus, and electronic device |
| CN113269243A (en) * | 2021-05-18 | 2021-08-17 | 西安交通大学 | Association identification method and device based on generative countermeasure network |
| CN113706408A (en) * | 2021-08-11 | 2021-11-26 | 西安交通大学 | Ghost imaging denoising method and device based on noise reduction convolutional neural network |
Non-Patent Citations (3)
| Title |
|---|
| 噪声环境下基于单像素成像系统和深度学习的目标识别方法;石峰;陆同希;杨书宁;苗壮;杨晔;张闻文;何睿清;;红外与激光工程(第06期);全文 * |
| 基于卷积神经网络的计算鬼成像方法研究;冯维;赵晓冬;吴贵铭;叶忠辉;赵大兴;;光子学报(第06期);全文 * |
| 循环神经网络在语音识别模型中的训练加速方法;冯诗影;韩文廷;金旭;迟孟贤;安虹;;小型微型计算机系统(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114494055A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033026B (en) | Target detection method, device and equipment for continuous small sample images | |
| CN110991506B (en) | Vehicle brand identification method, device, equipment and storage medium | |
| CN104636118A (en) | QR two-dimensional code self-adaptation binarization processing method and device based on light balance | |
| CN105893405A (en) | Repetitive video detection method and system | |
| CN111967573A (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN112966553A (en) | Strong coupling target tracking method, device, medium and equipment based on twin network | |
| CN115657012A (en) | Matching method, device and equipment of image target and radar target and storage medium | |
| Ma et al. | Cross-scale fusion and domain adversarial network for generalizable rail surface defect segmentation on unseen datasets | |
| CN113158904B (en) | Twin network target tracking method and device based on double-mask template updating | |
| CN107392948B (en) | Image registration method of amplitude-division real-time polarization imaging system | |
| CN112200004B (en) | Training method and device for image detection model and terminal equipment | |
| CN116912635B (en) | Target tracking method and device | |
| CN114494055B (en) | Ghost imaging method, ghost imaging system, ghost imaging equipment and ghost imaging storage medium based on cyclic neural network | |
| CN113920382A (en) | Cross-domain image classification method based on class consistency structured learning and related device | |
| CN113962877B (en) | Pixel distortion correction method, correction device and terminal | |
| CN115690747B (en) | Vehicle blind area detection model test method and device, electronic equipment and storage medium | |
| CN112418089A (en) | Gesture recognition method and device and terminal | |
| CN111179218A (en) | Conveyor belt material detection method and device, storage medium and terminal equipment | |
| CN113723431B (en) | Image recognition method, apparatus and computer readable storage medium | |
| CN114998283A (en) | Lens blocking object detection method and device | |
| CN114429429B (en) | Ghost imaging inversion method, ghost imaging inversion system, electronic equipment and storage medium | |
| CN108830290B (en) | SAR image classification method based on sparse representation and Gaussian distribution | |
| CN108335403B (en) | Banknote thickness detection method and device, terminal equipment and storage medium | |
| CN117474037B (en) | Knowledge distillation method and device based on space distance alignment | |
| CN113673268B (en) | Identification method, system and equipment for different brightness |
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 |