CN112799143B - Target identification method, photoelectric system and readable storage medium - Google Patents
Target identification method, photoelectric system and readable storage medium Download PDFInfo
- Publication number
- CN112799143B CN112799143B CN202011377920.7A CN202011377920A CN112799143B CN 112799143 B CN112799143 B CN 112799143B CN 202011377920 A CN202011377920 A CN 202011377920A CN 112799143 B CN112799143 B CN 112799143B
- Authority
- CN
- China
- Prior art keywords
- spectral
- target
- band
- narrow
- distribution histogram
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
Landscapes
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a method for identifying a target in an infrared image, an optoelectronic system and a readable storage medium, wherein the method comprises the following steps: scanning through a multi-spectral TDI infrared detector to obtain radiation information of a target; performing spectral calculation on the radiation information to obtain a target spectral distribution histogram; deep learning is carried out on a multi-target spectral characteristic sample library, and a multi-target standard spectral characteristic database is constructed; and the target type identification is realized by intelligently matching the unknown target spectral characteristics with the standard spectral feature library. According to the embodiment of the invention, the multi-spectral-segment TDI type infrared detector is used for scanning to obtain the radiation information of the target, performing spectral calculation, constructing the standard spectral feature database, and finally performing intelligent matching identification.
Description
Technical Field
The present invention relates to the field of infrared image recognition technologies, and in particular, to a target recognition method, an optoelectronic system, and a readable storage medium.
Background
For long-distance target detection, targets have the characteristics of weak and small in infrared images and are easily submerged or interfered by background radiation; because of the lack of sufficient target characteristic information, cloud background radiation, other flying objects in the air, and other stray light can all generate similar 'point' signal characteristics, which generates false alarms.
At present, aiming at weak and small target detection, common detection algorithms comprise a background suppression method, a wavelet transformation method, an inter-frame difference method, an infrared weak and small target detection method based on field gray entropy and classification and the like, and the traditional method mostly utilizes gray energy information corresponding to the radiation intensity of a received target to complete target detection and has the defects of large calculated amount, complexity and low detection performance.
Spectral radiation is an inherent property of the target, its spectral characteristics, and its material, size and state, etc. Compared with the brightness characteristic, the spectral characteristic can reflect the characteristic difference among different targets, and has great advantages in the aspect of type identification of the targets. At present, the conventional spectral imaging technology is mainly dispersive, and is typically characterized in that a slit aperture is arranged on an image plane. However, the traditional spectral imaging detection system has mutual constraints in the aspects of spatial resolution, spectral resolution, signal-to-noise ratio, time synchronism and the like, and the improvement of one index will bring about the reduction of other indexes. The traditional dispersive spectral imaging method reduces the luminous flux of the system, so that the application of the traditional dispersive spectral imaging method to the spectral detection of a remote stealth weak and small target is greatly limited.
Disclosure of Invention
The embodiment of the invention provides a target identification method, an optoelectronic system and a readable storage medium, which are used for remotely detecting and identifying invisible small targets.
In a first aspect, an embodiment of the present invention provides a target identification method, configured to perform type identification on a target in an infrared image, where the method includes:
scanning through a multi-spectral TDI infrared detector to obtain radiation information of a target;
performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
and matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type.
Optionally, before scanning by the multi-spectral-segment TDI type infrared detector to acquire radiation information of the target, the method further includes:
and configuring the multispectral TDI infrared detector and a corresponding optical scanning imaging system.
Optionally, a standard feature library is constructed in advance, including:
acquiring narrow-band spectral distribution histograms of different targets for multiple times, and establishing a multi-target spectral characteristic sample library;
deep learning is carried out on the samples in the multi-target spectral characteristic sample library through a preset deep learning algorithm;
and establishing a standard feature library according to the deep learning result.
Optionally, the performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target includes:
performing image registration and fusion on each spectral band of the radiation information to construct a broadband spectral distribution histogram of the target;
and band subdivision is carried out on the broadband spectral distribution histogram, and a narrow-band spectral distribution histogram of the target is constructed.
Optionally, before constructing the broadband spectral distribution histogram of the target, the method further includes:
modeling background radiation characteristics in the radiation information to remove background effects.
Optionally, matching the narrow-band spectrum distribution histogram with a spectrum characteristic in a pre-constructed standard feature library to identify a target type includes:
and matching according to the narrow-band spectral distribution histogram and spectral characteristics in a pre-constructed standard feature library through a preset identification algorithm so as to judge the type of the target.
In a second aspect, an embodiment of the present invention provides an optoelectronic system for performing type recognition on an object in an infrared image, where the optoelectronic system includes:
the optical scanning imaging system is used for scanning through a multi-spectral TDI infrared detector to acquire radiation information of a target;
the data processing module is used for carrying out spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
and the identification module is used for matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, where an implementation program for information transfer is stored, and when the program is executed by a processor, the program implements the foregoing steps of the object identification method.
According to the embodiment of the invention, an unknown target is scanned by a multi-spectral-segment TDI infrared detector to obtain the radiation information of the target, spectral calculation is carried out, the spectral characteristics of the unknown target and data in a preset standard feature library are subjected to matching analysis, and the type of the target is identified. The method can improve the signal-to-noise ratio of spectral detection and realize remote target detection and type identification, thereby solving the problem of false alarm of remote detection of weak and small targets in the prior art and obtaining positive technical effects.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a basic flow diagram of a first embodiment of the present invention;
FIG. 2 is a general flow chart of the first embodiment of the present invention;
FIG. 3 is a schematic diagram of a first embodiment of a multi-spectral-segment TDI detector in accordance with the present invention;
fig. 4 is an example of constructing a spectrum distribution histogram according to the first embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example one
A first embodiment of the present invention provides a target identification method, configured to perform type identification on a target in an infrared image, as shown in fig. 1 and 2, where the method includes:
scanning through a multi-spectral TDI infrared detector to obtain radiation information of a target;
performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
and matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type.
The method realizes artificial intelligent identification of the target type based on the spectral characteristics. The method comprises the steps of scanning and imaging through a multi-spectral-segment TDI detector, simultaneously obtaining a plurality of wide spectrum detection information of a target, ensuring that the sufficient signal to noise ratio of the target can be obtained through the wide spectrum detection, realizing remote detection, obtaining narrow-band spectrum distribution of the target through spectrum calculation, and realizing target type judgment through matching with spectral characteristics in a pre-constructed standard feature library.
More specifically, the embodiment of the invention scans through a multi-spectral-segment TDI type infrared detector to obtain the radiation information of the target, performs spectral calculation to obtain the spectral characteristics of the target, and constructs a spectral characteristic database to realize artificial intelligent identification of the target. The method can improve the signal-to-noise ratio of spectral detection, realize remote detection and target identification, and solve the problem that the prior art is limited to stealth weak and small targets.
Optionally, before scanning by the multi-spectral-segment TDI type infrared detector to acquire radiation information of the target, the method further includes: and configuring the multispectral TDI infrared detector and a corresponding optical scanning imaging system.
Specifically, in the embodiment of the present invention, a multispectral TDI infrared detector needs to be configured first, for example, in an optional implementation manner of the present invention, configuring a multispectral TDI infrared detector includes configuring different spectral bands, for example, an optional configuration manner is that, in a spectral band 1: 7.5-9.6 μm, band 2: 8.0-10.0 μm, band 3: 8.5-10.5 μm, band 4: 9.0-11.0 μm, band 5: 9.5-11.5 μm, spectrum 6: 7.5-11.5 μm, as shown in fig. 3, the configured multispectral TDI type infrared detector can perform 360-degree circumferential scanning to realize the omnibearing search of the space target after the configuration is completed.
The identification of the target spectral distribution histogram needs to be completed, and a standard target spectral feature database is further constructed in the embodiment. The method specifically comprises the following steps of performing deep learning on spectral signal characteristics of known targets, clutter and interference signals to construct a target spectral characteristic database:
collecting narrow-band spectral distribution histograms of different targets for multiple times, and establishing a multi-target spectral characteristic sample library;
deep learning is carried out on samples in the multi-target spectral characteristic sample library through a preset deep learning algorithm;
and establishing a standard feature library according to the deep learning result.
Specifically, the spectral signal characteristics (time domain and frequency domain) of known targets, clutter and interference signals are deeply learned, and a spectral signal standard characteristic library of different types of targets is constructed, wherein the deep learning method includes but is not limited to an artificial neural network and a deep learning theory.
After a preset standard target feature database is obtained, the spectral distribution histogram of the suspected target and the built standard feature databases of different types of targets are subjected to intelligent matching analysis, and the type of the suspected target is judged.
Optionally, the performing spectrum calculation on the radiation information to obtain a narrow-band spectrum distribution histogram of the target includes:
performing image registration fusion on each spectral band of the radiation information to construct a broadband spectral distribution histogram of the target;
and band subdivision is carried out on the broadband spectral distribution histogram, and a narrow-band spectral distribution histogram of the target is constructed.
Specifically, as shown in fig. 2, a gray level histogram corresponding to the radiation information is constructed by performing image registration on the radiation information.
On the basis of the multispectral TDI infrared detector configured in the embodiment, radiation information of the suspected target in six wide spectral bands is obtained based on scanning of the multispectral TDI infrared detector, and gray level histogram representation of the multispectral radiation information of the suspected target is constructed through image registration and fusion.
And performing spectrum calculation based on the gray level histogram to acquire the spectrum information of the target in a preset waveband range. In the present embodiment, as shown in fig. 3, the gray level histogram corresponding to the radiation information of six wide bands obtained as described above is input into the calculation spectral imaging software to perform spectral calculation, so as to obtain the spectral information of the target in a preset band range (for example, in a band range of 7.7 μm to 11.5 μm based on the foregoing embodiment, with an interval of 0.5 μm). Before constructing a broadband spectral distribution histogram of the target, the method further comprises: modeling background radiation characteristics in the radiation information to remove background effects. And then constructing a broadband spectral distribution histogram of the target according to the spectral information, and finally performing band subdivision on the broadband spectral distribution histogram to construct a narrow-band spectral distribution histogram of the target.
After the corresponding narrow-band spectral information is obtained through calculation, in this embodiment, a target spectral distribution histogram is further constructed according to the spectral information, and in an embodiment of the present invention, the constructed spectral distribution histogram is as shown in fig. 4.
In some embodiments, matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to achieve identification of a target type includes:
and matching according to the narrow-band spectral distribution histogram and spectral characteristics in a pre-constructed standard feature library through a preset identification algorithm so as to judge the type of the target.
In summary, the method of the present invention provides a method for obtaining spectrum information of a target in a calculation spectrum form based on a multi-spectral TDI detector in order to obtain the spectrum information of the target without losing luminous flux, and can solve the problem of low remote signal-to-noise ratio through wide-spectral detection, and obtain radiation distribution of each narrow spectral band through calculation, and at the same time, the method has the dual advantages of wide-spectral intensity detection and calculation spectrum detection, and can effectively solve the problems of remote detection and identification of the target.
Compared with the prior art which utilizes a spectrum detection mode of arranging a slit aperture on an image surface, the method provided by the invention provides a spectrum detection method based on a multispectral TDI detector, so that the target spectrum information with high luminous flux and high signal-to-noise ratio can be obtained, and the method can be carried to an airplane platform to realize the remote type identification of the target.
Example two
A second embodiment of the invention provides a system for type recognition of targets in an infrared image, the optoelectronic system comprising:
the optical scanning imaging system is used for scanning through the multi-spectral TDI infrared detector to acquire radiation information of a target;
the data processing module is used for carrying out spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
and the identification module is used for matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type.
The embodiment provides a photoelectric system for acquiring target spectral characteristics in a spectrum calculation mode based on a multispectral TDI detector, which can solve the problem of low remote signal-to-noise ratio through wide-spectrum detection, obtain narrow-spectrum radiation distribution through calculation, have the dual advantages of wide-spectrum intensity detection and spectrum calculation detection, and can effectively solve the problem of target remote detection type identification.
Aiming at the acquisition of target wide-spectrum-band energy, the multi-spectrum-band TDI detector can simultaneously acquire a plurality of pieces of target spectrum-band information in the working process, is different from the conventional mode that a plurality of detectors with different wave bands are integrated to acquire the multi-spectrum-band information of the target, and is more suitable for the requirements of small size and light weight under an airplane platform.
The embodiment of the invention provides a further airplane, and the airplane is provided with the photoelectric system.
The embodiment of the present invention provides a computer-readable storage medium, where an implementation program for information transfer is stored, and when the implementation program is executed by a processor, the method implements the steps of the foregoing method.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (4)
1. An object recognition method for performing type recognition on an object in an infrared image, the method comprising:
configuring a multispectral TDI (time delay integration) type infrared detector and a corresponding optical scanning imaging system, wherein the configuring of the multispectral TDI type infrared detector comprises configuring a plurality of spectral bands;
scanning through a multi-spectral TDI infrared detector to obtain radiation information of a target;
performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type;
pre-constructing a standard feature library, which comprises the following steps:
collecting narrow-band spectral distribution histograms of different targets for multiple times, and establishing a multi-target spectral characteristic sample library;
deep learning is carried out on the samples in the multi-target spectral characteristic sample library through a preset deep learning algorithm;
establishing a standard feature library according to a deep learning result;
the performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target includes:
performing image registration fusion on each spectral band of the radiation information to construct a broadband spectral distribution histogram of the target;
performing band subdivision on the broadband spectral distribution histogram to construct a narrow-band spectral distribution histogram of the target;
matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize target type identification comprises the following steps:
and matching according to the narrow-band spectral distribution histogram and spectral characteristics in a pre-constructed standard feature library through a preset identification algorithm so as to judge the type of the target.
2. The method of claim 1, wherein prior to constructing the histogram of the broadband spectral distribution of the target, the method further comprises:
modeling background radiation characteristics in the radiation information to remove background effects.
3. An optoelectronic system for type recognition of a target in an infrared image, the optoelectronic system comprising:
configuring a multi-spectral TDI-type infrared detector and a corresponding optical scanning imaging system, wherein configuring the multi-spectral TDI-type infrared detector comprises configuring a plurality of spectral bands;
the optical scanning imaging system is used for scanning through the multi-spectral TDI infrared detector to acquire radiation information of a target;
the data processing module is used for carrying out spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target;
the identification module is used for matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize the identification of the target type;
pre-constructing a standard feature library, comprising:
collecting narrow-band spectral distribution histograms of different targets for multiple times, and establishing a multi-target spectral characteristic sample library;
deep learning is carried out on the samples in the multi-target spectral characteristic sample library through a preset deep learning algorithm;
establishing a standard feature library according to a deep learning result;
the performing spectral calculation on the radiation information to obtain a narrow-band spectral distribution histogram of the target includes:
performing image registration and fusion on each spectral band of the radiation information to construct a broadband spectral distribution histogram of the target;
performing band subdivision on the broadband spectral distribution histogram to construct a narrow-band spectral distribution histogram of the target;
matching the narrow-band spectral distribution histogram with spectral characteristics in a pre-constructed standard feature library to realize target type identification, wherein the target type identification comprises the following steps:
and matching according to the narrow-band spectral distribution histogram and spectral characteristics in a pre-constructed standard feature library through a preset identification algorithm so as to judge the type of the target.
4. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an implementation program of information transfer, which when executed by a processor implements the steps of the object recognition method of claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377920.7A CN112799143B (en) | 2020-12-01 | 2020-12-01 | Target identification method, photoelectric system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011377920.7A CN112799143B (en) | 2020-12-01 | 2020-12-01 | Target identification method, photoelectric system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112799143A CN112799143A (en) | 2021-05-14 |
| CN112799143B true CN112799143B (en) | 2023-03-03 |
Family
ID=75806082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011377920.7A Active CN112799143B (en) | 2020-12-01 | 2020-12-01 | Target identification method, photoelectric system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112799143B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589311B (en) * | 2021-07-15 | 2023-11-28 | 中国科学院上海技术物理研究所 | Infrared differential detection method for dim and weak targets |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252677A (en) * | 2007-10-19 | 2008-08-27 | 西安交通大学 | Object tracking method based on multi-optical spectrum image sensor |
| CN102466521A (en) * | 2010-11-12 | 2012-05-23 | 南京理工大学 | TDI (Time Delay Integration) scan imaging method for Snapshot type area array infrared detector |
| CN107995460A (en) * | 2017-11-20 | 2018-05-04 | 天津津航技术物理研究所 | A kind of more spectral coverage adaptive image transmission devices based on TDI detectors |
| CN109271921A (en) * | 2018-09-12 | 2019-01-25 | 合刃科技（武汉）有限公司 | A kind of intelligent identification Method and system of multispectral imaging |
| CN109697431A (en) * | 2018-12-29 | 2019-04-30 | 哈尔滨工业大学 | A kind of detection method of small target based on high spectrum image |
| CN110567589A (en) * | 2019-09-11 | 2019-12-13 | 北京空间飞行器总体设计部 | Multi-spectral-segment multi-linear detector system for detecting and identifying moving target |
| CN110823374A (en) * | 2019-10-31 | 2020-02-21 | 中国科学院西安光学精密机械研究所 | Spectral imaging method and system for simultaneously obtaining high-space and high-spectral-resolution spectral images |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8964182B2 (en) * | 2012-04-13 | 2015-02-24 | Raytheon Company | Adaptive multispectral imaging |
-
2020
- 2020-12-01 CN CN202011377920.7A patent/CN112799143B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252677A (en) * | 2007-10-19 | 2008-08-27 | 西安交通大学 | Object tracking method based on multi-optical spectrum image sensor |
| CN102466521A (en) * | 2010-11-12 | 2012-05-23 | 南京理工大学 | TDI (Time Delay Integration) scan imaging method for Snapshot type area array infrared detector |
| CN107995460A (en) * | 2017-11-20 | 2018-05-04 | 天津津航技术物理研究所 | A kind of more spectral coverage adaptive image transmission devices based on TDI detectors |
| CN109271921A (en) * | 2018-09-12 | 2019-01-25 | 合刃科技（武汉）有限公司 | A kind of intelligent identification Method and system of multispectral imaging |
| CN109697431A (en) * | 2018-12-29 | 2019-04-30 | 哈尔滨工业大学 | A kind of detection method of small target based on high spectrum image |
| CN110567589A (en) * | 2019-09-11 | 2019-12-13 | 北京空间飞行器总体设计部 | Multi-spectral-segment multi-linear detector system for detecting and identifying moving target |
| CN110823374A (en) * | 2019-10-31 | 2020-02-21 | 中国科学院西安光学精密机械研究所 | Spectral imaging method and system for simultaneously obtaining high-space and high-spectral-resolution spectral images |
Non-Patent Citations (3)
| Title |
|---|
| "高分五号"卫星多谱段集成TDI线列红外探测器;王成刚等;《航天返回与遥感》;20180630;第39卷(第3期);全文 * |
| 多谱段集成长线列拼接TDI红外探测器技术;徐丽娜等;《上海航天》;20191025;第36卷;全文 * |
| 天空背景下红外弱小目标的检测与跟踪算法研究;龙波;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20120615(第6期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112799143A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862705B (en) | Unmanned aerial vehicle small target detection method based on motion characteristics and deep learning characteristics | |
| CN108710910B (en) | Target identification method and system based on convolutional neural network | |
| CN108389188B (en) | Sparse hyperspectral abnormal target detection method | |
| CN111461037B (en) | End-to-end gesture recognition method based on FMCW radar | |
| CN110728197B (en) | Single-tree-level tree species identification method based on deep learning | |
| CN110751087B (en) | EOF-based unmanned aerial vehicle signal identification system and method | |
| Moradi et al. | Scale-space point spread function based framework to boost infrared target detection algorithms | |
| CN107561509B (en) | Airborne millimeter wave radar power line detection method | |
| CN112799143B (en) | Target identification method, photoelectric system and readable storage medium | |
| Zhang et al. | Spectral clustering based unsupervised change detection in SAR images | |
| CN109375187B (en) | Method and device for determining radar target | |
| Hussein et al. | An alternative method to discover concealed weapon detection using critical fusion image of color image and infrared image | |
| CN111680537A (en) | Target detection method and system based on laser infrared compounding | |
| Deng et al. | EMD based infrared image target detection method | |
| Kowalski et al. | Improvement of passive THz camera images | |
| CN111784743B (en) | Infrared weak and small target detection method | |
| CN114913415A (en) | Disease and pest detection system based on remote sensing monitoring | |
| CN114694043A (en) | Ground wounded person identification method, device and medium of airborne multispectral multi-domain preferred features under complex scene | |
| Liu et al. | Target detection of hyperspectral image based on convolutional neural networks | |
| CN109471106B (en) | SAR ocean internal wave stripe recognition method combining clustering analysis and boundary tracking method | |
| Gueguen et al. | Multitemporal analysis of multisensor data: Information theoretical approaches | |
| Diao et al. | Metrics for performance evaluation of preprocessing algorithms in infrared small target images | |
| Shayei et al. | A machine learning approach for material classification in MMW imaging systems based on frequency spectra | |
| Ozisik Baskurt et al. | Catadioptric hyperspectral imaging, an unmixing approach | |
| Wu et al. | Spectra-difference based anomaly-detection for infrared hyperspectral dim-moving-point-target detection |
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 |