CN109102003A - A kind of small target detecting method and system based on Infrared Physics Fusion Features - Google Patents
A kind of small target detecting method and system based on Infrared Physics Fusion Features Download PDFInfo
- Publication number
- CN109102003A CN109102003A CN201810790004.2A CN201810790004A CN109102003A CN 109102003 A CN109102003 A CN 109102003A CN 201810790004 A CN201810790004 A CN 201810790004A CN 109102003 A CN109102003 A CN 109102003A
- Authority
- CN
- China
- Prior art keywords
- infrared
- image
- target
- targeted
- target region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Transforming Light Signals Into Electric Signals (AREA)
Abstract
The invention discloses a kind of small target detecting method and system based on Infrared Physics Fusion Features, wherein method includes: that the Small object in sample multiband infrared image is marked, obtain label target, randomly select in sample multiband infrared image non-targeted is marked, it obtains marking non-targeted, using label target and non-targeted feature vector training classifier is marked, obtains object classifiers.Infrared image is split, segmented image is obtained, segmented image is marked to obtain candidate target region；The feature vector of candidate target region is inputted object classifiers by the feature vector for extracting candidate target region in infrared image, and whether detection candidate target region has Small object.The false alarm rate that the present invention improves small target deteection rate under complex background, reduces small target deteection.
Description
Technical field
The invention belongs to technical field of image processing, more particularly, to a kind of based on the small of Infrared Physics Fusion Features
Object detection method and system.
Background technique
Small target deteection under complex background is a difficulties.The information content that Small object carries is few, and contrast is low, holds
Easily fall into oblivion in complex background.Improving target acquisition performance using the information of different-waveband infrared image is an important way
Diameter.The information of fusion different-waveband infrared image, which improves small target detection performance, to have great importance.
Object detection method based on image co-registration is broadly divided into three classes, the small target deteection side based on Pixel-level fusion
Method, the small target detecting method based on feature-based fusion and the small target detecting method based on decision level fusion.Based on Pixel-level
The small target detecting method of fusion carries out medium wave and LONG WAVE INFRARED image using the methods of linear fusion, multiresolution analysis fusion
Fusion, then carries out target detection in blending image, the small target deteection effect of such methods depend on it is small in convergence strategy
Targets improvement degree.Method based on feature-based fusion is less to be used for small target deteection, this is because the few hardly possible of Small object information content
To extract suitable feature.Small target detecting method based on decision level fusion carries out Small object inspection in different-waveband respectively
It surveys, then fusion is carried out to testing result and provides final testing result.The target detection performance of such methods depends on different waves
The small target deteection result of section.Small target deteection is difficult under existing complex background, is easy erroneous detection and missing inspection.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the present invention provides one kind to be based on Infrared Physics Fusion Features
Small target detecting method and system, thus solve under existing complex background that small target deteection is difficult, be easy erroneous detection and missing inspection
Technical problem.
To achieve the above object, according to one aspect of the present invention, it provides a kind of based on Infrared Physics Fusion Features
Small target detecting method, comprising:
(1) infrared image is split, obtains segmented image, segmented image is marked to obtain candidate target area
Domain；
(2) feature vector for extracting candidate target region in infrared image, the feature vector of candidate target region is inputted
Whether object classifiers, detection candidate target region have Small object；
The training of the object classifiers includes: that the Small object in sample multiband infrared image is marked, and is obtained
Mark target, randomly select in sample multiband infrared image it is non-targeted be marked, obtain marking non-targeted, utilize label
The target feature vector training classifier non-targeted with label, obtains object classifiers.
Further, Small object is pixel dimension less than 6 × 6, and target of the local SNR less than 3.
Further, step (1) includes:
(11) morphologic filtering processing is carried out to infrared image, obtains filtered image, calculates the segmentation of filtered image
Threshold value；
(12) filtered image is split using segmentation threshold, obtains segmented image, segmented image is marked
Obtain candidate target region.
Further, step (2) includes:
(21) infrared image is subjected to imaging inversion process, obtains infrared energy image, from infrared energy
The infrared energy magnitude that candidate target region is obtained in image calculates the part letter of the center pixel position of candidate target region
It makes an uproar ratio；
(22) by the part of the infrared energy magnitude of candidate target region and the center pixel position of candidate target region
Snr value combines to obtain the feature vector of candidate target region, and the feature vector of candidate target region is inputted target classification
Whether device, detection candidate target region have Small object.
Further, label target and the acquisition of non-targeted feature vector is marked to include:
Imaging inversion process is carried out to sample multiband infrared image, obtains the infrared medium wave radiation energy of sample multiband
Image obtains label target from the infrared medium wave radiation energy image of sample multiband and marks the non-targeted infrared spoke of multiband
Energy value is penetrated, label target is calculated separately and marks the local SNR value of non-targeted center pixel position, target will be marked
With the part for the center pixel position for marking non-targeted multiband infrared radiation energy value and label target and label non-targeted
Snr value combines to obtain label target and marks non-targeted feature vector.
It is another aspect of this invention to provide that a kind of small target deteection system based on Infrared Physics Fusion Features is provided,
Include:
Classifier training module obtains label mesh for the Small object in sample multiband infrared image to be marked
Mark, randomly select in sample multiband infrared image it is non-targeted be marked, obtain marking it is non-targeted, using label target and
Non-targeted feature vector training classifier is marked, object classifiers are obtained；
Image segmentation module obtains segmented image, segmented image is marked for being split to infrared image
To candidate target region；
Module of target detection, for extracting the feature vector of candidate target region in infrared image, by candidate target region
Feature vector input object classifiers, detection candidate target region whether have Small object.
Further, Small object is pixel dimension less than 6 × 6, and target of the local SNR less than 3.
Further, image segmentation module includes:
Image filtering submodule obtains filtered image, calculates filter for carrying out morphologic filtering processing to infrared image
The segmentation threshold of image after wave；
Image segmentation submodule obtains segmented image for being split using segmentation threshold to filtered image, to point
Image is cut to be marked to obtain candidate target region.
Further, module of target detection includes:
Image transformation submodule obtains infrared energy image for infrared image to be carried out imaging inversion process；
Radiation energy extracting sub-module, for obtaining the infra-red radiation of candidate target region from infrared energy image
Energy value；
Local SNR extracting sub-module, the local SNR of the center pixel position for calculating candidate target region
Value；
Combination of eigenvectors submodule, for by the infrared energy magnitude of candidate target region and candidate target region
The local SNR value of center pixel position combines to obtain the feature vector of candidate target region；
Target detection submodule detects candidate mesh for the feature vector of candidate target region to be inputted object classifiers
Whether mark region has Small object.
Further, label target and the acquisition of non-targeted feature vector is marked to include:
Imaging inversion process is carried out to sample multiband infrared image, obtains the infrared medium wave radiation energy of sample multiband
Image obtains label target from the infrared medium wave radiation energy image of sample multiband and marks the non-targeted infrared spoke of multiband
Energy value is penetrated, label target is calculated separately and marks the local SNR value of non-targeted center pixel position, target will be marked
With the part for the center pixel position for marking non-targeted multiband infrared radiation energy value and label target and label non-targeted
Snr value combines to obtain label target and marks non-targeted feature vector.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, can obtain down and show
Beneficial effect:
(1) present invention is first split infrared image, and Preliminary detection is marked to segmented image and goes out candidate target area
Domain；The feature vector of candidate target region is inputted target by the feature vector for then extracting candidate target region in infrared image
Whether classifier, detection candidate target region have Small object；Small object is detected using coarse-fine two-stage treatment mode, while being utilized red
The feature vector of candidate target region is differentiated in outer image, can reduce the false alarm rate of small target deteection, improves Small object
Verification and measurement ratio.
(2) feature vector of the invention has merged infrared energy magnitude drawn game portion snr value, and Small object can be improved
Information content and then raising small target deteection rate.In training, it is infrared that multiband is obtained to multiband infrared image progress inverse transformation
Radiation energy image extracts the infrared energy magnitude drawn game portion snr value composition characteristic vector of multiband infrared image；With
The prior art is compared, and the present invention utilizes multiwave Infrared Physics radiation feature by feature level fusing method, can be with
It improves Small object information content and then improves small target deteection rate.
Detailed description of the invention
Fig. 1 is a kind of process of small target detecting method based on Infrared Physics Fusion Features provided in an embodiment of the present invention
Figure；
Fig. 2 (a) is the medium-wave infrared image that the embodiment of the present invention 1 provides；
Fig. 2 (b) is the LONG WAVE INFRARED image that the embodiment of the present invention 1 provides；
Fig. 3 be the embodiment of the present invention 1 provide label target and non-targeted image；
Fig. 4 is the Preliminary detection result that the embodiment of the present invention 1 provides；
Fig. 5 is the small target deteection result that the embodiment of the present invention 1 provides.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
As shown in Figure 1, a kind of small target detecting method based on Infrared Physics Fusion Features, comprising:
(1) infrared image is split, obtains segmented image, segmented image is marked to obtain candidate target area
Domain；
(2) feature vector for extracting candidate target region in infrared image, the feature vector of candidate target region is inputted
Whether object classifiers, detection candidate target region have Small object；
The training of the object classifiers includes: that the Small object in sample multiband infrared image is marked, and is obtained
Mark target, randomly select in sample multiband infrared image it is non-targeted be marked, obtain marking non-targeted, utilize label
The target feature vector training classifier non-targeted with label, obtains object classifiers.
Embodiment 1
A kind of small target detecting method based on Infrared Physics Fusion Features, comprising:
(1) infrared image is split, obtains segmented image, segmented image is marked to obtain candidate target area
Domain；
(2) feature vector for extracting candidate target region in infrared image, the feature vector of candidate target region is inputted
Whether object classifiers, detection candidate target region have Small object；
The training of the object classifiers includes: to the medium-wave infrared image as shown in Fig. 2 (a) and as shown in Fig. 2 (b)
LONG WAVE INFRARED image carries out imaging inversion process, and inverse transformation formula isWherein, g is medium-wave infrared image or length
Wave infrared image, K and B are the conversion parameter using blackbody demarcation, obtain infrared medium wave and long-wave radiation energy image pair.Such as figure
Shown in 3, the Small object of infrared medium wave and long-wave radiation energy image pair is marked, label target is obtained, randomly selects
Non-targeted being marked of infrared medium wave and long-wave radiation energy image pair, obtains marking non-targeted.
It extracts label target and marks the medium-wave infrared radiation energy magnitude L of non-targeted middle pixel (x, y)M(x, y) and long wave
Infrared energy magnitude LL(x, y).
The local SNR value for calculating separately pixel (x, y), according to formulaCalculating pixel (x,
Y) snr value of 21 × 21 regional areas centered on, obtains SNRM(x, y) and SNRL(x, y)；μTIndicate object pixel gray scale
Mean value, μBIndicate background pixel gray average in 21 × 21 contiguous ranges of goal-orientation, σBFor pixel in the contiguous range
The mean square deviation of gray scale.
The value of the medium wave of the pixel (x, y) of extraction and LONG WAVE INFRARED radiation energy magnitude and local SNR is combined into spy
Levy vector EV (x, y)=(LM(x, y), LL(x, y), SNRM(x, y), SNRL(x, y)).
Specifically, step (1) includes:
(11) morphologic filtering processing is carried out to infrared image, obtains filtered image, calculates the segmentation of filtered image
Threshold value；The calculation formula of segmentation threshold is Th=μ+k σ, and μ is mean value after filtering, and σ is variance after filtering, and parameter k is adjustable；
(12) filtered image is split using segmentation threshold, obtains segmented image, segmented image is marked
Multiple candidate target regions are obtained, see the region for marking in Fig. 4 and being.
Divide formula are as follows:I (x, y) is the pixel of pixel (x, y)
Value.
Specifically, step (2) includes:
(21) infrared image is subjected to imaging inversion process, obtains infrared energy image, from infrared energy
The infrared energy magnitude that each candidate target region is obtained in image calculates the center pixel position of each candidate target region
Local SNR value；
(22) by the center pixel position of the infrared energy magnitude of each candidate target region and corresponding candidate target region
The local SNR value set combines to obtain the feature vector of each candidate target region, by the feature of each candidate target region to
Amount input object classifiers, detect whether each candidate target region has Small object, obtain final small target deteection as a result, seeing
The region of white box is marked in Fig. 5.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of small target detecting method based on Infrared Physics Fusion Features characterized by comprising
(1) infrared image is split, obtains segmented image, segmented image is marked to obtain candidate target region；
(2) feature vector of candidate target region is inputted target by the feature vector for extracting candidate target region in infrared image
Whether classifier, detection candidate target region have Small object；
The training of the object classifiers includes: that the Small object in sample multiband infrared image is marked, and is marked
Target, randomly select in sample multiband infrared image it is non-targeted be marked, obtain marking non-targeted, utilize label target
Non-targeted feature vector training classifier, obtains object classifiers with label.
2. a kind of small target detecting method based on Infrared Physics Fusion Features as described in claim 1, which is characterized in that institute
Stating Small object is pixel dimension less than 6 × 6, and target of the local SNR less than 3.
3. a kind of small target detecting method based on Infrared Physics Fusion Features as claimed in claim 1 or 2, feature exist
In the step (1) includes:
(11) morphologic filtering processing is carried out to infrared image, obtains filtered image, calculates the segmentation threshold of filtered image；
(12) filtered image is split using segmentation threshold, obtains segmented image, segmented image is marked to obtain
Candidate target region.
4. a kind of small target detecting method based on Infrared Physics Fusion Features as claimed in claim 1 or 2, feature exist
In the step (2) includes:
(21) infrared image is subjected to imaging inversion process, obtains infrared energy image, from infrared energy image
The middle infrared energy magnitude for obtaining candidate target region, calculates the local SNR of the center pixel position of candidate target region
Value；
(22) by the local noise of the infrared energy magnitude of candidate target region and the center pixel position of candidate target region
Ratio combines to obtain the feature vector of candidate target region, and the feature vector of candidate target region is inputted object classifiers, inspection
Survey whether candidate target region has Small object.
5. a kind of small target detecting method based on Infrared Physics Fusion Features as claimed in claim 1 or 2, feature exist
In the label target and the acquisition for marking non-targeted feature vector include:
Imaging inversion process is carried out to sample multiband infrared image, obtains the infrared medium wave radiation energy spirogram of sample multiband
Picture obtains label target from the infrared medium wave radiation energy image of sample multiband and marks non-targeted multiband infrared radiation
Energy value calculates separately label target and marks the local SNR value of non-targeted center pixel position, will label target and
The part letter for the center pixel position for marking non-targeted multiband infrared radiation energy value and label target and label non-targeted
Ratio of making an uproar combines to obtain label target and marks non-targeted feature vector.
6. a kind of small target deteection system based on Infrared Physics Fusion Features characterized by comprising
Classifier training module obtains label target for the Small object in sample multiband infrared image to be marked, with
Machine choose in sample multiband infrared image it is non-targeted be marked, obtain marking non-targeted, utilize label target and label
Non-targeted feature vector training classifier, obtains object classifiers；
Image segmentation module obtains segmented image, is marked and is waited to segmented image for being split to infrared image
Select target area；
Module of target detection, for extracting the feature vector of candidate target region in infrared image, by the spy of candidate target region
It levies vector and inputs object classifiers, whether detection candidate target region has Small object.
7. a kind of small target deteection system based on Infrared Physics Fusion Features as claimed in claim 6, which is characterized in that institute
Stating Small object is pixel dimension less than 6 × 6, and target of the local SNR less than 3.
8. a kind of small target deteection system based on Infrared Physics Fusion Features as claimed in claims 6 or 7, feature exist
In described image segmentation module includes:
Image filtering submodule obtains filtered image, after calculating filtering for carrying out morphologic filtering processing to infrared image
The segmentation threshold of image；
Image segmentation submodule obtains segmented image, to segmentation figure for being split using segmentation threshold to filtered image
As being marked to obtain candidate target region.
9. a kind of small target deteection system based on Infrared Physics Fusion Features as claimed in claims 6 or 7, feature exist
In the module of target detection includes:
Image transformation submodule obtains infrared energy image for infrared image to be carried out imaging inversion process；
Radiation energy extracting sub-module, for obtaining the infrared energy of candidate target region from infrared energy image
Value；
Local SNR extracting sub-module, the local SNR value of the center pixel position for calculating candidate target region；
Combination of eigenvectors submodule, for by the infrared energy magnitude of candidate target region and the center of candidate target region
The local SNR value of location of pixels combines to obtain the feature vector of candidate target region；
Target detection submodule detects candidate target area for the feature vector of candidate target region to be inputted object classifiers
Whether domain has Small object.
10. a kind of small target deteection system based on Infrared Physics Fusion Features as claimed in claims 6 or 7, feature exist
In the label target and the acquisition for marking non-targeted feature vector include:
Imaging inversion process is carried out to sample multiband infrared image, obtains the infrared medium wave radiation energy spirogram of sample multiband
Picture obtains label target from the infrared medium wave radiation energy image of sample multiband and marks non-targeted multiband infrared radiation
Energy value calculates separately label target and marks the local SNR value of non-targeted center pixel position, will label target and
The part letter for the center pixel position for marking non-targeted multiband infrared radiation energy value and label target and label non-targeted
Ratio of making an uproar combines to obtain label target and marks non-targeted feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810790004.2A CN109102003B (en) | 2018-07-18 | 2018-07-18 | Small target detection method and system based on infrared physical characteristic fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810790004.2A CN109102003B (en) | 2018-07-18 | 2018-07-18 | Small target detection method and system based on infrared physical characteristic fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109102003A true CN109102003A (en) | 2018-12-28 |
| CN109102003B CN109102003B (en) | 2020-07-10 |
Family
ID=64846711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810790004.2A Active CN109102003B (en) | 2018-07-18 | 2018-07-18 | Small target detection method and system based on infrared physical characteristic fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109102003B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291762A (en) * | 2020-03-10 | 2020-06-16 | 上海航天控制技术研究所 | Multi-band image fusion detection method based on multi-feature point difference |
| CN111401195A (en) * | 2020-03-10 | 2020-07-10 | 上海航天控制技术研究所 | Sea surface target detection method based on multiband infrared image |
| CN112837335A (en) * | 2021-01-27 | 2021-05-25 | 上海航天控制技术研究所 | Medium-long wave infrared composite anti-interference method |
| CN113450413A (en) * | 2021-07-19 | 2021-09-28 | 哈尔滨工业大学 | Ship target detection method based on GF4 single-frame image |
| CN114463619A (en) * | 2022-04-12 | 2022-05-10 | 西北工业大学 | Infrared dim target detection method based on integrated fusion features |
| CN115830470A (en) * | 2022-12-29 | 2023-03-21 | 中国科学院长春光学精密机械与物理研究所 | Method, device and equipment for detecting weak-strength small-scale target of remote sensing image |
| CN116486086A (en) * | 2023-04-28 | 2023-07-25 | 安徽星太宇科技有限公司 | Target detection method based on thermal infrared remote sensing image |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102034239A (en) * | 2010-12-07 | 2011-04-27 | 北京理工大学 | Local gray abrupt change-based infrared small target detection method |
| US7965890B2 (en) * | 2007-01-05 | 2011-06-21 | Raytheon Company | Target recognition system and method |
| CN104899866A (en) * | 2015-05-05 | 2015-09-09 | 河南三联网络技术有限公司 | Intelligent infrared small target detection method |
-
2018
- 2018-07-18 CN CN201810790004.2A patent/CN109102003B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7965890B2 (en) * | 2007-01-05 | 2011-06-21 | Raytheon Company | Target recognition system and method |
| CN102034239A (en) * | 2010-12-07 | 2011-04-27 | 北京理工大学 | Local gray abrupt change-based infrared small target detection method |
| CN104899866A (en) * | 2015-05-05 | 2015-09-09 | 河南三联网络技术有限公司 | Intelligent infrared small target detection method |
Non-Patent Citations (2)
| Title |
|---|
| 刘峰 等: "基于特征级融合的多波段舰船目标识别方法", 《光谱学与光谱分析》 * |
| 王培早 等: "基于多级综合分类器的红外目标检测", 《软件工程》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291762B (en) * | 2020-03-10 | 2022-12-13 | 上海航天控制技术研究所 | Multi-feature-point-difference-based multi-band image fusion detection method |
| CN111401195A (en) * | 2020-03-10 | 2020-07-10 | 上海航天控制技术研究所 | Sea surface target detection method based on multiband infrared image |
| CN111291762A (en) * | 2020-03-10 | 2020-06-16 | 上海航天控制技术研究所 | Multi-band image fusion detection method based on multi-feature point difference |
| CN111401195B (en) * | 2020-03-10 | 2023-11-14 | 上海航天控制技术研究所 | Sea surface target detection method based on multiband infrared image |
| CN112837335A (en) * | 2021-01-27 | 2021-05-25 | 上海航天控制技术研究所 | Medium-long wave infrared composite anti-interference method |
| CN112837335B (en) * | 2021-01-27 | 2023-05-09 | 上海航天控制技术研究所 | Medium-long wave infrared composite anti-interference method |
| CN113450413A (en) * | 2021-07-19 | 2021-09-28 | 哈尔滨工业大学 | Ship target detection method based on GF4 single-frame image |
| CN114463619B (en) * | 2022-04-12 | 2022-07-08 | 西北工业大学 | Infrared dim target detection method based on integrated fusion features |
| CN114463619A (en) * | 2022-04-12 | 2022-05-10 | 西北工业大学 | Infrared dim target detection method based on integrated fusion features |
| CN115830470A (en) * | 2022-12-29 | 2023-03-21 | 中国科学院长春光学精密机械与物理研究所 | Method, device and equipment for detecting weak-strength small-scale target of remote sensing image |
| CN115830470B (en) * | 2022-12-29 | 2024-07-09 | 中国科学院长春光学精密机械与物理研究所 | Method, device and equipment for detecting weak-intensity small-scale target of remote sensing image |
| CN116486086A (en) * | 2023-04-28 | 2023-07-25 | 安徽星太宇科技有限公司 | Target detection method based on thermal infrared remote sensing image |
| CN116486086B (en) * | 2023-04-28 | 2023-10-03 | 安徽星太宇科技有限公司 | Target detection method based on thermal infrared remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109102003B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102003A (en) | A kind of small target detecting method and system based on Infrared Physics Fusion Features | |
| CN108090888B (en) | Fusion detection method of infrared image and visible light image based on visual attention model | |
| CN108009531B (en) | Multi-strategy anti-fraud face recognition method | |
| CN107610114B (en) | optical satellite remote sensing image cloud and snow fog detection method based on support vector machine | |
| CN102722891B (en) | Method for detecting image significance | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN102663393B (en) | Method for extracting region of interest of finger vein image based on correction of rotation | |
| CN106371148B (en) | A kind of human body foreign body detection method and system based on millimeter-wave image | |
| WO2016107474A1 (en) | Vehicle checking method and system | |
| CN105956578A (en) | Face verification method based on identity document information | |
| CN108563990B (en) | Certificate authentication method and system based on CIS image acquisition system | |
| CN102496016B (en) | Infrared target detection method based on space-time cooperation framework | |
| CN102819740B (en) | A kind of Single Infrared Image Frame Dim targets detection and localization method | |
| CN104463877B (en) | A kind of water front method for registering based on radar image Yu electronic chart information | |
| CN107392885A (en) | A kind of method for detecting infrared puniness target of view-based access control model contrast mechanism | |
| CN109977877A (en) | A kind of safety check is intelligent to be assisted sentencing drawing method, system and system control method | |
| CN109559324A (en) | A kind of objective contour detection method in linear array images | |
| CN110659649A (en) | Image processing and character recognition algorithm based on near infrared light imaging | |
| CN107463895B (en) | Weak and small damage target detection method based on neighborhood vector PCA | |
| CN111738211B (en) | PTZ camera moving object detection and recognition method based on dynamic background compensation and deep learning | |
| CN105069805A (en) | Passive terahertz image segmentation method | |
| CN106682678A (en) | Image angle point detection and classification method based on support domain | |
| CN106326834A (en) | Human body gender automatic identification method and apparatus | |
| CN108108740B (en) | Active millimeter wave human body image gender identification method | |
| US20170270668A1 (en) | Discrete Edge Binning Template Matching System, Method And Computer Readable Medium |
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 |