CA2535058A1 - An adaptive constant false alarm rate detection system - Google Patents
An adaptive constant false alarm rate detection system Download PDFInfo
- Publication number
- CA2535058A1 CA2535058A1 CA002535058A CA2535058A CA2535058A1 CA 2535058 A1 CA2535058 A1 CA 2535058A1 CA 002535058 A CA002535058 A CA 002535058A CA 2535058 A CA2535058 A CA 2535058A CA 2535058 A1 CA2535058 A1 CA 2535058A1
- Authority
- CA
- Canada
- Prior art keywords
- data
- block
- detection
- cfar
- matched filter
- 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.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/28—Investigating the spectrum
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/9021—SAR image post-processing techniques
- G01S13/9027—Pattern recognition for feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/28—Details of pulse systems
- G01S7/285—Receivers
- G01S7/292—Extracting wanted echo-signals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/904—SAR modes
- G01S13/9076—Polarimetric features in SAR
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
A method and apparatus of Constant False Alarm Rate (CFAR) detection results in optimal detection in the Neyman Pearson sense independent of the type of the input data. The whole system consists three major blocks: pre-processing block, data fusion block and adaptive multi-CFAR
detection block. For any kind of input data, various appropriate data processing techniques could be chosen and applied in parallel in the pro-processing unit for the purpose of enhancing Signal to Noise Ratio (SNR) and fusion. The SNRs of the output data from the pre-processing block will be compared and the top couples will be transmitted to the data fusion block for further SNR
enhancement by performing appropriate data fusion technique. The adaptive multi-CFAR detector will then be applied at the last stage to get the final decision.
In the application of this system on hyperspectral data, a new Transform Based Matched Filter (TBMF) detection algorithm is proposed in the pre-processing unit. The TBMF
algorithm employs a transformation before the traditional matched filter to make the background subspace and target subspace orthogonal, hence enhance the detection performance of the matched filter algorithm.
detection block. For any kind of input data, various appropriate data processing techniques could be chosen and applied in parallel in the pro-processing unit for the purpose of enhancing Signal to Noise Ratio (SNR) and fusion. The SNRs of the output data from the pre-processing block will be compared and the top couples will be transmitted to the data fusion block for further SNR
enhancement by performing appropriate data fusion technique. The adaptive multi-CFAR detector will then be applied at the last stage to get the final decision.
In the application of this system on hyperspectral data, a new Transform Based Matched Filter (TBMF) detection algorithm is proposed in the pre-processing unit. The TBMF
algorithm employs a transformation before the traditional matched filter to make the background subspace and target subspace orthogonal, hence enhance the detection performance of the matched filter algorithm.
Description
An Adaptive Constant False Alarm Rate Detection System Description The structure of an adaptive Constant False Alarm Rate (CFAR) detector is designed which is suitable for any input data type, such as polarimetric Synthetic Aperture Radar (SAR) data, hyperspectral image data and so on. CFAR detection is a detection technique that adjusts the threshold to maintain a user defined constant false alarm probability based on the statistics of the background. It is widely used in military, geology, forestry, agriculture and many other fields.
Figure 1 presents the structure of the proposed system, which consists three major units: data pre-processing unit, data fusion unit and adaptive multi-CFAR detection unit that is depicted in Figure 2.
For different input data, any appropriate data processing techniques could be chosen and used in parallel in the pro-processing unit for the purpose of enhancing Signal to Noise Ratio (SNR) and fusion. The SNRs of the output images from the pre-processing block and in some cases the original images will be calculated and compared. The top couple of images will be transmitted to the data fusion block for further SNR enhancement. The adaptive multi-CFAR detection will then be performed at the last stage to get the final decision.
Figure 2 presents the structure of the adaptive multi-CFAR detector. For any input, the background statistics will be estimated. Several different single CFAR detectors will then be applied in parallel and their decisions will be fused to get the final result. In estimating the background statistics the Generalized Gamma model is used, which is a general statistics model that a lot of other probability density functions could be represented by adjust its three parameters. By using this model, more accurate statistics model could be estimated.
Normally the performance of CFAR algorithms depend on the type of the input data, and a lot of CFAR algorithms can not preserve the user defined false alarm rate in real applications because of using inaccurate background statistics model. For the proposed system the flexible choice of the pre-processing algorithms combined with the adaptive multi-CFAR detector make the whole system data independent. The fusion of data with complementary information produced through different pre-processing algorithms has the capability to increase SNR, hence enhance the detection performance. By using the Generalized Gamma model in the CFAR detection, more accurate estimation of the background statistics could be resulted than any other traditional CFAR detectors, hence the user defined false alarm rate could be assured.
The proposed system could be applied to any type of input data, such as polarimetric SAR data, hyperspectral image data and so on. If the input is polarimetric SAR images, the pre-processing algorithms could be any polarimetric transformations and decompositions, such as Cloude-Pottier decomposition, Cameron decomposition, even and odd bounce, polarimetric whitening filter and any other user defined polarimetric decompositions and transformations. Adaptive Principle Component Analysis (PCA) could be employed in the data fusion block. If the input is hyperspectral images, various clutter suppression techniques could be involved in the pre-processing block, such as matched filter, adaptive matched filter, spectral angle mapper, orthogonal subspace projector and many other algorithms. In these hyperspectral clutter suppression algorithms, the matched filter is widely used because of its good performance and simplicity. But its performance will be decreased when the target and the background subspace are not orthogonal to each other, and it is usually the case in practical. The proposed new Transformation Based Matched Filter (TBMF) clutter suppression method for hyperspectral images can solve this problem by applying a transformation to both the target and background subspace to satisfy the orthogonality property hence enhance the performance.
Figure 1 presents the structure of the proposed system, which consists three major units: data pre-processing unit, data fusion unit and adaptive multi-CFAR detection unit that is depicted in Figure 2.
For different input data, any appropriate data processing techniques could be chosen and used in parallel in the pro-processing unit for the purpose of enhancing Signal to Noise Ratio (SNR) and fusion. The SNRs of the output images from the pre-processing block and in some cases the original images will be calculated and compared. The top couple of images will be transmitted to the data fusion block for further SNR enhancement. The adaptive multi-CFAR detection will then be performed at the last stage to get the final decision.
Figure 2 presents the structure of the adaptive multi-CFAR detector. For any input, the background statistics will be estimated. Several different single CFAR detectors will then be applied in parallel and their decisions will be fused to get the final result. In estimating the background statistics the Generalized Gamma model is used, which is a general statistics model that a lot of other probability density functions could be represented by adjust its three parameters. By using this model, more accurate statistics model could be estimated.
Normally the performance of CFAR algorithms depend on the type of the input data, and a lot of CFAR algorithms can not preserve the user defined false alarm rate in real applications because of using inaccurate background statistics model. For the proposed system the flexible choice of the pre-processing algorithms combined with the adaptive multi-CFAR detector make the whole system data independent. The fusion of data with complementary information produced through different pre-processing algorithms has the capability to increase SNR, hence enhance the detection performance. By using the Generalized Gamma model in the CFAR detection, more accurate estimation of the background statistics could be resulted than any other traditional CFAR detectors, hence the user defined false alarm rate could be assured.
The proposed system could be applied to any type of input data, such as polarimetric SAR data, hyperspectral image data and so on. If the input is polarimetric SAR images, the pre-processing algorithms could be any polarimetric transformations and decompositions, such as Cloude-Pottier decomposition, Cameron decomposition, even and odd bounce, polarimetric whitening filter and any other user defined polarimetric decompositions and transformations. Adaptive Principle Component Analysis (PCA) could be employed in the data fusion block. If the input is hyperspectral images, various clutter suppression techniques could be involved in the pre-processing block, such as matched filter, adaptive matched filter, spectral angle mapper, orthogonal subspace projector and many other algorithms. In these hyperspectral clutter suppression algorithms, the matched filter is widely used because of its good performance and simplicity. But its performance will be decreased when the target and the background subspace are not orthogonal to each other, and it is usually the case in practical. The proposed new Transformation Based Matched Filter (TBMF) clutter suppression method for hyperspectral images can solve this problem by applying a transformation to both the target and background subspace to satisfy the orthogonality property hence enhance the performance.
Claims (8)
1 Initial Claims What is claimed is:
1. A general detection system comprising three blocks: 1) data pre-processing block; 2) data fusion block; 3) adaptive multi-CFAR detection block.
1. A general detection system comprising three blocks: 1) data pre-processing block; 2) data fusion block; 3) adaptive multi-CFAR detection block.
2. The system of claim 1 wherein the input data could be any kind of image data with single or multiple bands, such as polarimetric Synthetic Aperture Radar (SAR) image data, hyperspectral image data and so on. For the multiple band images, the images should be registered before transmitted to this system.
3. The system of claim 1, for polarimetric SAR image data input the data pre-processing block involves various polarimetric decompositions and transformations, such as Cloude-Pottier Decomposition, Cameron Decomposition, even and odd bounce, Polarimetric Whitening Filter (PWF) and other user defined polarimetric decompositions/transformations.
4. The system of claim 1, for hyperspectral data input the data pre-processing block comprises various hyperspectral clutter suppression methods, such as Matched Filter (MF), Adaptive Cosine (ACE), Adaptive Subspace Detector (ASD), Orthogonal Subspace Projector (OSP), Signature Space Orthogonal Projection classifier (SSC), A.U.G. Signals' Transformation Based Matched Filtering (TBMF) detection method and so on.
5. The system of claim 4 wherein the detailed procedures of TBMF detector are listed as follows:
To enhance the performance of the matched filter algorithm for hyperspectral data detection, a transformation is applied before the traditional matched filter to make the background subspace and the signature of interest orthogonal to each other. Let's denote the transformation as W, which is a M × M matrix, where M is the number of bands. ~, which has length M, represents the signature of interest, and H, with dimension M
× L, denotes the background matrix with background signatures ~ as its columns. L is the total number of background signatures. We use the notation ~ for the vector [y1 y2 ... yM]T.
The employment of W makes the signature of interest and the background in the transformed domain orthogonal to each other. That is, (WH)[(WH)T WH]-1(WH)T W~ = 0. (1) Any W which has the property H T W T W ~ =O (2) could be the solution of (1).
A practical and simple solution of (1) could be found by setting W to be a diagonal matrix, i.e.
By doing this, the transformation is putting different weights to all bands.
Using this diagonal W, equation (2) can be rewritten as Rearrange this equation we have where ~i =[hi1 hi2 ... hi M]T is the ith background feature.
To avoid the weights being zeros, (zero vector is one of the solutions of the above equation), a constraint (W ~)T (W ~) = C, (4) is applied, where c is a positive constant. Usually we use a large positive number for c to emphasize the target pixel, hence enhance the performance.
From equations (3) and (4), we finally have SH ~ = ~, (5) where Equation (5) could be solved using the least squared method. The solution is expressed as follows:
~LS = (S~SH)-1 S~~.
The corresponding W LS could be found by knowing ~ LS. Applying W LS to the image and then followed by a traditional matched filter, the resulting abundance image could be get.
Suppose ~
is the pixel for testing, the proposed algorithm is given by
To enhance the performance of the matched filter algorithm for hyperspectral data detection, a transformation is applied before the traditional matched filter to make the background subspace and the signature of interest orthogonal to each other. Let's denote the transformation as W, which is a M × M matrix, where M is the number of bands. ~, which has length M, represents the signature of interest, and H, with dimension M
× L, denotes the background matrix with background signatures ~ as its columns. L is the total number of background signatures. We use the notation ~ for the vector [y1 y2 ... yM]T.
The employment of W makes the signature of interest and the background in the transformed domain orthogonal to each other. That is, (WH)[(WH)T WH]-1(WH)T W~ = 0. (1) Any W which has the property H T W T W ~ =O (2) could be the solution of (1).
A practical and simple solution of (1) could be found by setting W to be a diagonal matrix, i.e.
By doing this, the transformation is putting different weights to all bands.
Using this diagonal W, equation (2) can be rewritten as Rearrange this equation we have where ~i =[hi1 hi2 ... hi M]T is the ith background feature.
To avoid the weights being zeros, (zero vector is one of the solutions of the above equation), a constraint (W ~)T (W ~) = C, (4) is applied, where c is a positive constant. Usually we use a large positive number for c to emphasize the target pixel, hence enhance the performance.
From equations (3) and (4), we finally have SH ~ = ~, (5) where Equation (5) could be solved using the least squared method. The solution is expressed as follows:
~LS = (S~SH)-1 S~~.
The corresponding W LS could be found by knowing ~ LS. Applying W LS to the image and then followed by a traditional matched filter, the resulting abundance image could be get.
Suppose ~
is the pixel for testing, the proposed algorithm is given by
6. The system of claim 1 wherein any applicable pre-processing algorithms can be involved in block 2 and there is no limitation to the number or type of the pre-processing algorithms applied.
7. The system of claim 1 wherein the SNRs of output images of block 2 and in some cases the original images are calculated and compared. The top couple of images will be transmitted into block 3 where appropriate data fusion technique is applied. The fused data will then be transmitted to the final block.
8. The system of claim 1 wherein adaptive multi-CFAR detector displayed in Figure 2 is employed as the final block, which comprises three major parts: local clutter statistics analysis, single CFAR detection and decision fusion. Generalized Gamma model is used in estimating the background clutter statistics. Various single CFAR detectors are employed in parallel and their outputs will be transmitted to the decision fusion unit to get the final decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CA002535058A CA2535058A1 (en) | 2005-12-19 | 2005-12-19 | An adaptive constant false alarm rate detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CA002535058A CA2535058A1 (en) | 2005-12-19 | 2005-12-19 | An adaptive constant false alarm rate detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA2535058A1 true CA2535058A1 (en) | 2007-06-19 |
Family
ID=38175443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002535058A Abandoned CA2535058A1 (en) | 2005-12-19 | 2005-12-19 | An adaptive constant false alarm rate detection system |
Country Status (1)
| Country | Link |
|---|---|
| CA (1) | CA2535058A1 (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103353594A (en) * | 2013-06-17 | 2013-10-16 | 西安电子科技大学 | Two-dimensional self-adaptive radar CFAR (constant false alarm rate) detection method |
| CN106652393A (en) * | 2015-10-30 | 2017-05-10 | 三星Sds株式会社 | Method for determining false alarm |
| CN109375037A (en) * | 2018-11-16 | 2019-02-22 | 杭州电子科技大学 | A design method of single-phase ground fault alarm for medium voltage ship power system |
| CN109446899A (en) * | 2018-09-20 | 2019-03-08 | 西安空间无线电技术研究所 | A kind of cloud object detection method based on four spectral coverage remote sensing images |
| CN109752700A (en) * | 2019-01-15 | 2019-05-14 | 哈尔滨工程大学 | A Constant False Alarm Signal Detection Method Based on Adaptive Filtering |
| CN110441766A (en) * | 2019-07-02 | 2019-11-12 | 中国航空工业集团公司雷华电子技术研究所 | A kind of airfield pavement FOD detection radar change Threshold detection method |
| CN110596653A (en) * | 2019-09-24 | 2019-12-20 | 江苏集萃智能传感技术研究所有限公司 | Multi-radar data fusion method and device |
| WO2021007704A1 (en) * | 2019-07-12 | 2021-01-21 | Huawei Technologies Co., Ltd. | Method and apparatus for object detection system |
| CN112346029A (en) * | 2020-10-30 | 2021-02-09 | 中国人民解放军空军预警学院 | Variable reference window unit average constant false alarm rate detection method based on unit to be detected |
| CN112558066A (en) * | 2020-10-30 | 2021-03-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Dual-polarization SAR image system |
| CN113253235A (en) * | 2021-06-22 | 2021-08-13 | 中国人民解放军空军预警学院 | Self-adaptive signal detection method and system in severe non-uniform environment |
| CN114578384A (en) * | 2022-05-07 | 2022-06-03 | 成都凯天电子股份有限公司 | Self-adaptive constant false alarm detection method for laser atmospheric system |
-
2005
- 2005-12-19 CA CA002535058A patent/CA2535058A1/en not_active Abandoned
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103353594A (en) * | 2013-06-17 | 2013-10-16 | 西安电子科技大学 | Two-dimensional self-adaptive radar CFAR (constant false alarm rate) detection method |
| CN103353594B (en) * | 2013-06-17 | 2015-01-28 | 西安电子科技大学 | Two-dimensional self-adaptive radar CFAR (constant false alarm rate) detection method |
| CN106652393A (en) * | 2015-10-30 | 2017-05-10 | 三星Sds株式会社 | Method for determining false alarm |
| CN106652393B (en) * | 2015-10-30 | 2020-03-17 | 三星Sds株式会社 | False alarm determination method and device |
| CN109446899A (en) * | 2018-09-20 | 2019-03-08 | 西安空间无线电技术研究所 | A kind of cloud object detection method based on four spectral coverage remote sensing images |
| CN109375037A (en) * | 2018-11-16 | 2019-02-22 | 杭州电子科技大学 | A design method of single-phase ground fault alarm for medium voltage ship power system |
| CN109752700A (en) * | 2019-01-15 | 2019-05-14 | 哈尔滨工程大学 | A Constant False Alarm Signal Detection Method Based on Adaptive Filtering |
| CN110441766A (en) * | 2019-07-02 | 2019-11-12 | 中国航空工业集团公司雷华电子技术研究所 | A kind of airfield pavement FOD detection radar change Threshold detection method |
| CN110441766B (en) * | 2019-07-02 | 2023-02-17 | 中国航空工业集团公司雷华电子技术研究所 | Airport pavement FOD detection radar variable threshold detection method |
| CN112492888A (en) * | 2019-07-12 | 2021-03-12 | 华为技术有限公司 | Method and apparatus for an object detection system |
| WO2021007704A1 (en) * | 2019-07-12 | 2021-01-21 | Huawei Technologies Co., Ltd. | Method and apparatus for object detection system |
| US11061113B2 (en) | 2019-07-12 | 2021-07-13 | Huawei Technologies Co., Ltd. | Method and apparatus for object detection system |
| CN110596653A (en) * | 2019-09-24 | 2019-12-20 | 江苏集萃智能传感技术研究所有限公司 | Multi-radar data fusion method and device |
| CN112346029A (en) * | 2020-10-30 | 2021-02-09 | 中国人民解放军空军预警学院 | Variable reference window unit average constant false alarm rate detection method based on unit to be detected |
| CN112558066A (en) * | 2020-10-30 | 2021-03-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Dual-polarization SAR image system |
| CN112558066B (en) * | 2020-10-30 | 2023-08-18 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Dual polarized SAR image system |
| CN112346029B (en) * | 2020-10-30 | 2024-02-23 | 中国人民解放军空军预警学院 | Variable reference window unit average constant false alarm detection method based on unit to be detected |
| CN113253235A (en) * | 2021-06-22 | 2021-08-13 | 中国人民解放军空军预警学院 | Self-adaptive signal detection method and system in severe non-uniform environment |
| CN114578384A (en) * | 2022-05-07 | 2022-06-03 | 成都凯天电子股份有限公司 | Self-adaptive constant false alarm detection method for laser atmospheric system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Saxena et al. | Noises and image denoising techniques: a brief survey | |
| Schaum | Hyperspectral anomaly detection beyond RX | |
| Anandhi et al. | An algorithm for multi-sensor image fusion using maximum a posteriori and nonsubsampled contourlet transform | |
| Renard et al. | Improvement of target detection methods by multiway filtering | |
| CA2535058A1 (en) | An adaptive constant false alarm rate detection system | |
| Karalı et al. | Adaptive image enhancement based on clustering of wavelet coefficients for infrared sea surveillance systems | |
| Dong et al. | Segmentation of radar imagery using the Gaussian Markov random field model | |
| Molina et al. | Gibbs random field models for model-based despeckling of SAR images | |
| Parthasarathy et al. | Fusion based multi scale RETINEX with color restoration for image enhancement | |
| JP2001134750A (en) | Method and device for processing image by generating stochastic distribution of image | |
| Vongsy et al. | A comparative study of spectral detectors | |
| CN107169516B (en) | Saliency detection method of small targets at sea based on K-L transform | |
| Zhou et al. | Automatic Side‐Scan Sonar Image Enhancement in Curvelet Transform Domain | |
| Xu et al. | Multisensor concealed weapon detection using the image fusion approach | |
| Mahalanobis et al. | Efficient target detection using an adaptive compressive imager | |
| Murugan et al. | Speckle noise removal using dual tree complex wavelet transform | |
| Bhatnagar et al. | Navigation and surveillance using night vision and image fusion | |
| Chari et al. | LWIR and MWIR fusion algorithm comparison using image metrics | |
| Raizer | Multisensor data fusion for advanced ocean remote sensing studies | |
| Pacifici | Change detection algorithms: State of the art | |
| Ke et al. | An efficient blind detection algorithm of median filtered image | |
| Gupta et al. | Object recognition based on template matching and correlation method in hyperspectral images | |
| Tayal et al. | A robust hybrid steganography mechanism for security in data communication networks | |
| Mohan et al. | AN ENHANCEMENT PROCESS FOR GRAY-SCALE IMAGES RESULTED FROM IMAGE FUSION USING MULTIRESOLUTION AND LAPLACIAN PYRAMID. | |
| Thankachan et al. | Edge Detection in Polarimetric SAR Image based on Bandelet Transform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FZDE | Dead |