Classification of Multi-Temporal Sar Images for Rice Crops Using Combined Entropy Decomposition and Support Vector Machine Technique

Tan, Chue Poh; Koay, Jun Yi; Lim, Koeng Su; Ewe, Hong Tat; Chuah, H. T.

doi:10.2528/pier07012903

Cited by 57 publications

(25 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The SVM optimization problem can be solved by dual formulation using many special-purpose solvers [17,18]. One of the most commonly used solvers is LIBSVM [19].…”

Section: Reconstruction Of Network Topology From Reflectometry Responmentioning

confidence: 99%

Reconstruction of Faulty Cable Network Using Time-Domain Reflectometry

Zhang¹,

Zhang²,

Liu³

2013

PIER

View full text Add to dashboard Cite

Abstract-Based on Time-Domain Reflectometry (TDR) technique, a novel method which could locate faults on the coaxial cable distribution network by using Support Vector Machine (SVM) is proposed in this paper. This approach allows the faulty network to be reconstructed by estimating the lengths of branches. A State-transition Matrix model is employed to simulate the TDR response at any port and evaluate the transfer function between two points. SVM is used to solve the inversion problem through training datasets created by the State-transition matrix model. Compared to the existing reflectometry methods, our proposed method can tackle multiple faults in the complex cable networks. Numerical and experimental results pointing out the performance of the SVM model in locating faults are reported.

show abstract

“…The SVM optimization problem can be solved by dual formulation using many special-purpose solvers [17,18]. One of the most commonly used solvers is LIBSVM [19].…”

Section: Reconstruction Of Network Topology From Reflectometry Responmentioning

confidence: 99%

Reconstruction of Faulty Cable Network Using Time-Domain Reflectometry

Zhang¹,

Zhang²,

Liu³

2013

PIER

View full text Add to dashboard Cite

show abstract

“…Thus, completely non-negative sparse coding have been investigated in [23]. Recently, NNSC has emerged as a useful feature extraction method in areas related to face recognition and image denoising [24,25]. In this work, non-negative T -F representations has been applied to target HRR profiles to obtain non-negative T -F data matrix, so NNSC is naturally considered for non-negative T -F feature extraction.…”

Section: Introductionmentioning

confidence: 99%

HRR Profiles Time-Frequency Non-Negative Sparse Coding for Sar Target Classification

Zhang¹,

Wu²,

Liu³

et al. 2014

PIER B

View full text Add to dashboard Cite

Abstract-A new approach to classify synthetic aperture radar (SAR) targets is presented based on high range resolution (HRR) profiles time-frequency matrix non-negative sparse coding (NNSC). Firstly, SAR target images have been converted into HRR profiles. And the non-negative time-frequency matrix for each of the profiles is obtained by using an adaptive Gaussian representation (AGR). Secondly, NNSC is applied to learn target time-frequency basis of the training set. Feature vectors are constructed by projecting each HRR profile time-frequency matrix to low dimensional time-frequency basis space. Finally, the target classification decision is found with support vector machine and nearest neighbor algorithm respectively. To demonstrate the performance of the proposed approach, experiments are performed with Moving and Stationary Target Acquisition and Recognition (MSTAR) public release SAR database. The experimental results support the effectiveness of the proposed technique for SAR target classification.

show abstract

“…Correct height retrieval is an integral part of many applications using InSAR, such as remote sensing [5,6], and data correction using multiple satellites may also benefit other SAR applications [7][8][9]. Simple ways like using a low-pass (averaging) filter have been proposed, and they work well sometimes.…”

Section: Introductionmentioning

confidence: 99%

Insar Height Inversion by Using 3-D Phase Projection With Multiple Baselines

Yeung²,

Yoshihisa³

et al. 2009

PIER

View full text Add to dashboard Cite

Abstract-This study introduces the notion of 2-D and 3-D Phase Projection in our search for a simple and elegant solution to further reduce noise during InSAR post-processing steps with multiple baselines. Projection is a powerful tool to reduce noise in a system of more than two satellites. It does so by noting that the geometry of the satellite configuration restricts the range of values over which the wrapped phases can assume. Projection in general reduces noise in the system by utilizing the information provided by the configuration of the satellites to reduce the set of allowed phase points, thereby improving the robustness of the system in the presence of noise. Our results show that, for most cases, whether with the extremely small baseline distance or non-integer baseline ratios, using 3-D Projection gives better height inversion results.

show abstract

Classification of Multi-Temporal Sar Images for Rice Crops Using Combined Entropy Decomposition and Support Vector Machine Technique

Cited by 57 publications

References 30 publications

Reconstruction of Faulty Cable Network Using Time-Domain Reflectometry

Reconstruction of Faulty Cable Network Using Time-Domain Reflectometry

HRR Profiles Time-Frequency Non-Negative Sparse Coding for Sar Target Classification

Insar Height Inversion by Using 3-D Phase Projection With Multiple Baselines

Contact Info

Product

Resources

About