LEADER 05557nam 22004573 450 001 9910847077303321 005 20240412080246.0 010 $a981-9997-99-2 035 $a(CKB)31253117300041 035 $a(MiAaPQ)EBC31266965 035 $a(Au-PeEL)EBL31266965 035 $a(MiAaPQ)EBC31233399 035 $a(Au-PeEL)EBL31233399 035 $a(EXLCZ)9931253117300041 100 $a20240412d2024 uy 0 101 0 $aeng 135 $aur||||||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aInfrared Small Target Detection $eTheory, Methods, and Algorithms 205 $a1st ed. 210 1$aSingapore :$cSpringer Singapore Pte. Limited,$d2024. 210 4$dİ2024. 215 $a1 online resource (178 pages) 311 $a981-9997-98-4 327 $aIntro -- Preface -- Acknowledgements -- Contents -- Acronyms -- 1 Introduction -- 1.1 Overview -- 1.1.1 Infrared Information -- 1.1.2 Tasks -- 1.2 Infrared Target Prediction -- 1.2.1 Prediction Filtering -- 1.2.2 Prediction Methods -- 1.3 Methods of Infrared Target Prediction -- 1.3.1 Morphological Transformation -- 1.3.2 Tensor Decomposition -- 1.3.3 Low-Rank Presentation -- 1.3.4 Deep Learning -- 1.4 Book Structure -- 2 Preliminaries -- 2.1 Morphological Operation -- 2.2 Principal Component Analysis -- 2.3 Alternating Direction Method of Multipliers -- 2.4 Evaluation Metrics -- 2.5 Conclusion -- 3 Morphological Transformation for Infrared Small Object Detection -- 3.1 Morphological Operation -- 3.2 Notations -- 3.2.1 Mathematical Morphology and Top-Hat Transformation -- 3.2.2 Guided Filter -- 3.2.3 Weight Local Entropy -- 3.3 Entropy-Driven Top-Hat Transformation -- 3.3.1 The Proposed Entropy-Driven Top-Hat Transformation with Local Mean Entropy -- 3.3.2 Adaptive Structural Elements Based on Guided Filter Kernel -- 3.3.3 Target Detection Based on Overall Model -- 3.3.4 Analysis of the Adaptive Structural Elements -- 3.3.5 Analysis of Our Proposed Local Mean Entropy -- 3.4 Balanced Ring Top-Hat Transformation -- 3.4.1 The Target Detection Based on Our Overall Model -- 3.4.2 Adaptive Structuring Element Based on Guided Filter Kernel -- 3.4.3 A Balanced Ring Shape for Structuring Elements -- 3.5 Adaptive M-estimator Ring Top-Hat Transformation -- 3.5.1 The Adaptive Structural Element Based on M-estimator -- 3.5.2 Ring Top-Hat Transformation Based on the Proposed Novel Local Entropy -- 3.5.3 Our Proposed Small Target Detection Method -- 3.6 Conclusion -- 4 Low-Rank Tensor Decomposition -- 4.1 Introduction -- 4.2 Notations -- 4.2.1 Classic Low-Rank Matrix Method -- 4.2.2 Detection Based on Entropy Method -- 4.3 Generalized Low-Rank Double-Tensor. 327 $a4.3.1 The Ring Structural Element for Top-Hat Regularization Transformation -- 4.3.2 Infrared Small Target Detection Model Based on Low-Rank Double-Tensor Nuclear Norm -- 4.3.3 The Noise GN -- 4.3.4 Model Formulation -- 4.3.5 Optimization -- (1) Update Noise -- (2) Update Target -- (3) Update Background -- (4) Update Others -- 4.4 Tensor Ring Decomposition -- 4.4.1 The Improved Target Detection Task -- 4.4.2 Motivations on Multiscale Morphological Transformation -- 4.4.3 Tensor Decomposition Based on Tensor Ring Low-Rank Kernel -- 4.4.4 Proposed Model for Small Target Detection -- 4.4.5 The Optimization of the Proposed Method with ADMM -- (1) Update of G(n) -- (2) Update of M(n,i) -- (3) Update of P(n,i) -- (4) Update of IN -- (5) Update of IT -- (6) Update of IB -- (7) Update of Y -- 4.4.6 Complexity and Convergence Analysis -- 4.5 Top-Hat Regularization -- 4.5.1 The Ring Structural Element for Top-Hat Transformation -- 4.5.2 The Low-Rank Tensor Model in Infrared Background -- 4.5.3 Noise Estimate -- 4.5.4 The Proposed Model for Small Target Detection -- (1) Under the No Noise Assumption -- (2) Under the Random Noise Assumption -- 4.5.5 The Solution of Our Proposed Model -- (1) The Solution of Noise (IN) -- (2) The Solution of Target (IT) -- (3) The Solution of Background (IB) -- (4) The Solution of Yi -- 4.6 Saliency Filtering -- 4.6.1 The Non-local Low-Rank Matrix Recovery -- 4.6.2 Saliency Filtering Based on Image Entropy -- 4.6.3 The Formulation of Small Target Detection -- 4.6.4 The Solution of Low-Rank Matrix Li -- 4.6.5 The Solution of Background Image fB -- 4.6.6 The Solution of Target Image fT -- 5 Deep Learning Methods for Infrared Small Object Detection -- 5.1 Introduction -- 5.2 Notations -- 5.3 Variational U-Net Network Structure Model -- 5.3.1 Network Structure -- 5.3.2 Loss Function Based on Variation. 327 $a5.4 Convolutional Neural Network Algorithm -- 5.4.1 Gabor Filter -- 5.4.2 Gabor Network Model -- 5.5 Co-occurrence Neural Network for Image Segmentation -- 5.5.1 Co-occurrence Filter Convolutional Layer -- 5.5.2 Co-occurrence Residual Block -- 5.5.3 Reverse Attention Mechanism -- 5.5.4 Model Structure -- 5.6 Conclusion -- 6 Performance of Different Methods -- 6.1 Experimental Setting -- 6.2 Baseline Methods -- 6.3 Performance Comparison of Different Methods -- 6.4 Conclusions -- 7 Summary and Outlook of Research on Infrared Small Target Detection -- 7.1 Summary -- 7.2 Future Outlook -- Bibliography. 676 $a621.3672 700 $aZhu$b Hu$01735440 701 $aPan$b Yushan$01735441 701 $aDeng$b Lizhen$01735442 701 $aXu$b Guoxia$01735443 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910847077303321 996 $aInfrared Small Target Detection$94154610 997 $aUNINA