Image and graphics technologies and applications. 13th conf., IGTA 2018

Preface......Page 6
Organization......Page 7
Contents......Page 10
 1 Introduction......Page 16
  2.1 Building the Spray Model Based on SPH......Page 17
  2.2 Spray Visualizations Using Particle System......Page 19
  3.1 Discretization of the Rice Model......Page 20
  3.2 Deformation of Rice Model......Page 21
 4 Simulation Results and Analysis......Page 22
 5 Discussion and Conclusions......Page 23
 References......Page 24
 1 Introduction......Page 26
 2 Variational Model......Page 27
  3.1 Iterative Approach......Page 28
  3.2 Fast Linear Solver......Page 29
 4 Experiments and Comparison......Page 30
  4.2 Timing......Page 31
  4.3 Comparison......Page 32
 References......Page 35
 1 Introduction......Page 37
 2 Collision Characteristics of Petals in Flowers......Page 39
  3.2 Projection and Collision Detection of Petals......Page 41
  3.3 Collision Detection After the Correction Method......Page 43
 4 Simulation Experiment Process......Page 44
 References......Page 48
 1 Introduction......Page 50
 2 Related Work......Page 51
 3 Strong Noise Denoising Filtering......Page 52
   4.3.2 Label Treatment of Left and Right Boundaries......Page 55
   4.3.3 Unilateral Scanning Part......Page 56
   4.3.4 Experiment on Navigation Algorithm Under Other Paths......Page 57
 References......Page 58
 1 Introduction......Page 60
  2.2 LLRC......Page 62
  3.1 Problem Formulation......Page 63
  3.2 Problem Solving......Page 64
  4.1 Experiments on ORL Database......Page 66
  4.2 Experiments on CMU PIE Database......Page 69
 References......Page 70
 1 Introduction......Page 72
 2 Embedding Space Method......Page 73
  2.2 Mapping Consensus......Page 74
  2.3 Optimization Method......Page 76
  3.1 Regression Method......Page 78
  4.1 Data Sets......Page 79
  4.3 Experimental Settings......Page 80
  4.4 Experiment Result......Page 81
 References......Page 83
 1 Introduction......Page 85
 2 Method......Page 86
   2.2.1 Translational Motion of the 1D Signal......Page 87
   2.2.2 Alignment and Matching......Page 88
 3 Experimental Results......Page 89
 5 Conclusion......Page 93
 References......Page 94
 1 Introduction......Page 95
  2.1 Early Object Detection Networks......Page 96
  3.1 Feature Extraction Network......Page 97
  3.3 Towards a More Efficient Detection Network......Page 98
  4.2 VOC 2007 Detection......Page 99
  4.3 Experiments on VOC2007......Page 100
 References......Page 101
 1 Introduction......Page 103
  2.2 Image Stitching Based on Marked Structure......Page 105
  2.3 Extracting the Lens Shape......Page 109
 4 Conclusion and Outlook......Page 111
 References......Page 112
 1 Introduction......Page 113
 2 Tongue Body Assessment Method......Page 114
  2.1 Angle-Based Energy......Page 116
  3.1 Parameters Setting......Page 117
  3.2 Qualitative Experiment......Page 118
 4 Conclusion......Page 119
 References......Page 120
 1 Introduction......Page 121
  2.1 Theoretical Background......Page 122
  2.2 Instructional Design......Page 123
  2.3 Teaching Aids Design......Page 124
  2.4 Pilot Study......Page 125
 3 Results and Discussion......Page 126
 Acknowledgements......Page 127
 References......Page 128
 1 Introduction......Page 129
  3.1 Neighborhood Particle Search Algorithm......Page 130
  4.1 Liquid Mixing Model......Page 132
  4.2 Gas-Liquid Mixing Model......Page 133
   4.2.1 Pressure Calculation......Page 134
 5 Experiments Result......Page 135
 Acknowledgement......Page 137
 References......Page 138
 1 Introduction......Page 139
  2.1 Augmented Reality Flight Simulator......Page 140
  3.1 Flight Simulator for Control Principle Instruction......Page 141
  3.4 Measurements......Page 144
  4.1 Comprehension Assessment......Page 145
  4.2 Learning Experience Assessment......Page 146
 5 Discussion and Conclusions......Page 147
 Acknowledgements......Page 148
 References......Page 149
 1 Introduction......Page 150
 2 Related Work......Page 151
 3 Method......Page 152
  3.2 Visual Analysis of Various Factors and Dengue......Page 153
  3.3 Build Prediction Model......Page 156
 4 Result......Page 157
 References......Page 159
 1 Dongba Culture......Page 161
 2 Virtual Museum......Page 162
  4.1 Data Collection......Page 163
  4.2 Model Building and Optimizing......Page 164
  5.2 Consulting Artifacts Module......Page 165
  5.3 Consulting Artifacts Module......Page 167
 6 System Test......Page 168
 7 System Test......Page 169
 References......Page 170
  1.1 Dongba Hieroglyphic Introduction......Page 172
  1.2 The Analysis of Dongba Hieroglyph......Page 173
  2.1 Connected Domain Priority Marking Algorithm for Contour Tracking......Page 174
  2.2 Connected Domain Priority Marking Algorithm for Skeleton Partition......Page 176
  2.3 The Analysis of Computational Complexity......Page 178
  3.2 Skeleton Partition and Sorting Locally for SSG......Page 180
 References......Page 182
 1 Introduction......Page 183
 2 Related Work......Page 184
 3 Algorithm Overview......Page 185
 4 Implementation......Page 187
  4.2 Sampling Cone......Page 188
  4.4 Search Fragments......Page 189
 5 Results......Page 191
 References......Page 193
 1 Introduction......Page 195
 2 Ellipse Based Subpixel Edge Detection......Page 196
  2.2 Ellipse Based Subpixel Edge Detection......Page 197
  2.3 Subpixel Edge Points Filter......Page 199
  3.1 Experiment on Synthetic Ellipse Data......Page 200
  3.3 Ellipse Detection in Complex Scene......Page 202
  3.4 Ellipse Detection in Infrared Images......Page 204
 References......Page 205
 1 Introduction......Page 207
 2 Related Work......Page 208
  3.1 The Local Matching......Page 209
  3.2 The Global Matching......Page 210
  4.1 Analysis of the Matching Method......Page 211
  4.2 Results on MPI-Sintel......Page 212
 References......Page 214
 1 Introduction......Page 216
  2.1 Cross-Media Retrieval......Page 217
  2.2 Curriculum Learning......Page 218
 3 Progressive Cross-Media Correlation Learning......Page 219
  3.1 Hierarchical Correlation Learning Architecture......Page 220
  3.2 Progressive Correlation Learning Strategy......Page 221
  4.1 Dataset Introduction......Page 222
  4.3 Experimental Results......Page 223
 5 Conclusion......Page 224
 References......Page 225
 1 Introduction......Page 227
  2.1 Algorithm Design......Page 228
  2.2 The Spatio-Temporal Context Template Updating Based on MSM Space Model......Page 230
  2.3 A Method for Determining the Target Location from Multi Peak Points of Saliency......Page 231
  3.1 Qualitative Analysis......Page 232
  3.2 Quantitative Analysis......Page 233
 References......Page 234
 1 Introduction......Page 235
 2 Related Work......Page 236
  3.1 Training Image Generation......Page 237
  3.2 FCN for Semantic Segmentation......Page 238
 4 Experimental Results......Page 239
 References......Page 240
 1 Introduction......Page 243
 2 Blockchain......Page 244
  3.1 Defects in Existing Solutions......Page 245
  3.2 Architecture Design Based on Consortium Blockchain......Page 246
  3.3 Digital Image Copyright Registration Logic......Page 248
 4 Prototype Implementation......Page 250
 5 Conclusions......Page 251
 References......Page 252
 Abstract......Page 253
 1 Introduction......Page 254
  2.2 Pretrained CNN Models......Page 255
  2.3 Transfer Learning......Page 256
 3 Multi-model Feature Extraction Framework and Feature Fusion......Page 257
 4 Model......Page 258
  5.1 Datasets......Page 259
   5.2.1 The Performance of Model Test on UC Merced Dataset......Page 260
   5.2.2 The Performance of Model Test on the AID Dataset......Page 264
 References......Page 265
 1 Introduction......Page 267
  2.1 The Proposed Hidden Random Disturbance......Page 268
  2.2 The Proposed Feistel RPMPFrHT Network......Page 269
  2.3 The Proposed LD_UAGV......Page 270
 3 Experimental Results and Performance Analysis......Page 271
  3.2 Histogram Analysis......Page 272
  3.4 Correlation Analysis......Page 274
 References......Page 276
 1 Introduction......Page 278
  2.1 System Architecture......Page 279
  2.2 Fall Detection Algorithm......Page 280
 3 Experiments and Results......Page 282
  3.1 Experiments on Public Dataset......Page 283
  3.2 Subjective Experiments......Page 284
 4 Conclusion......Page 285
 References......Page 286
 1 Introduction......Page 287
 2 Theory......Page 288
  3.2 Background Prediction Based on LI......Page 289
 4 Expriments and Results......Page 290
  4.1 Small Target Detection......Page 291
  4.2 Area Target Detection......Page 292
 References......Page 294
 1 Introduction......Page 296
  2.1 Methods Overview......Page 297
  2.2 Preprocessing......Page 298
  2.3 Foreground Mask Acquisition......Page 299
  2.4 CNN Structure......Page 301
  3.2 Algorithm Performance......Page 302
 4 Conclusion and Future Work......Page 304
 References......Page 305
 1 Introduction......Page 307
  2.1 Experimental Materials......Page 308
  2.2 Citrus Image Feature Extraction......Page 309
  2.3 The Principle of SVM Algorithm and the Determination of Key Parameters......Page 310
  2.4 Feature Mapping Table for Dimensionality Reduction......Page 311
  2.5 The Initial Choice of Citrus Regional Characteristics......Page 312
  3.1 Experimental Results......Page 313
 References......Page 316
 1 Introduction......Page 317
 2 Related Work......Page 318
 3 Proposed Method......Page 319
 4 Experimental Results......Page 321
 References......Page 323
 1 Introduction......Page 325
  2.1 Grid-Based Motion Statistics......Page 326
  2.2 AC-RANSAC......Page 327
 3 Experiments......Page 328
  3.1 Feasibility of Method......Page 329
  3.2 Robustness to the Angle Interval......Page 330
  3.3 Application......Page 331
 References......Page 332
 1 Introduction......Page 334
  2.1 Architecture of Crop Disease Classification Model......Page 336
  3.1 Material Preparation......Page 338
 4 Results and Discussion......Page 340
 References......Page 343
 1 Introduction......Page 345
 2 Related Work......Page 346
  3.1 Atrous Convolution......Page 347
  3.3 Pyramid Sampling......Page 348
  3.5 PASDNet......Page 349
  4.1 Dataset and Evaluation Metrics......Page 350
  4.3 Results and Analysis......Page 351
 References......Page 354
 1 Introduction......Page 356
 2 Related Work......Page 358
  3.1 Input Data and Feature Extraction......Page 359
  3.3 Splitting Based Multi-scale Feature Learning......Page 360
 4 Experiments and Results......Page 361
 5 Conclusion......Page 362
 References......Page 363
 1 Introduction......Page 364
  2.1 CCD Imaging Model......Page 365
  2.2 Visibility Calculation Method......Page 366
  3.2 Orbit Dynamic Model......Page 368
  3.3 Orbit Determination Algorithm......Page 369
  4.2 Maneuver Detection in Continuous Thrust Condition......Page 370
  5.1 Simulation of Impulse Thrust Detection......Page 371
  5.2 Simulation of Continuous Thrust Detection......Page 372
 References......Page 373
 1 Introduction......Page 374
 2 Related Work......Page 375
  3.1 Dataset......Page 376
  3.3 Evaluation Metrics......Page 377
  4.2 Multi-task Manifold Ranking......Page 378
  5.2 Ranking with Boundary Priors......Page 380
 6 Experiments......Page 381
  6.3 Components Analysis......Page 382
 References......Page 383
 1 Introduction......Page 385
  2.1 Feature Extraction Methods Using LBP......Page 386
  2.2 δ-LBP......Page 387
  3.1 Facial Expression Representation Based on Single δ-LBP......Page 388
  3.2 Facial Expression Representation Using Double δ-LBP......Page 389
  4.1 Database......Page 390
  4.2 Experiments on Single δ-LBP Method......Page 391
  4.4 Experiment on Double δ-LBP Method......Page 392
 References......Page 393
 1 Introduction......Page 395
  2.1 Tensor-Based Temporal Data Representation......Page 397
  2.2 3D Convolutional Neural Networks......Page 398
  2.3 Multi-channel Fusion 3D Convolutional Neural Networks......Page 399
  3.1 Data Preprocessing, Augmentation and Sampling......Page 400
  3.2 Results......Page 401
  3.3 Analysis......Page 402
 References......Page 403
 1 Introduction......Page 405
 2 Related Work......Page 406
  3.1 Correlation Filter Based on Compound Features......Page 407
  3.2 Selection of Detector......Page 409
  3.3 Activation of the Detector According to the Confidence Level......Page 410
 4 Algorithm Process......Page 413
  5.1 Introduction of the Datasets......Page 414
  5.3 OTB Results......Page 415
 References......Page 416
 1 Introduction......Page 418
 2 Proposed Method......Page 419
  2.1 Feature Extraction......Page 420
  2.2 Retrieve Method Based on Hashing Codes......Page 421
 3 Experiments Results and Analysis......Page 422
  3.1 Comparison with Other Common Features......Page 423
 4 Conclusions......Page 424
 References......Page 425
 1 Introduction......Page 426
 2 Proposed Method......Page 427
  2.1 CNNs Architecture......Page 428
  2.2 Loss Function......Page 429
  3.1 Implementation Details......Page 431
  3.2 Experiments on LFW......Page 432
 References......Page 433
 1 Introduction......Page 436
  2.1 Data Preprocessing......Page 437
  2.3 Convolutional Long Short-Term Memory......Page 438
  2.4 Model Architecture......Page 439
  2.5 Abnormal Event Detection......Page 440
  3.1 Datasets......Page 441
  3.3 Experiment 1: Effect of the Time Length......Page 442
  3.4 Experiment 2: Normalized Reconstruction Error for Detecting Anomalies......Page 443
 References......Page 445
 1 Introduction......Page 447
  2.1 Fragment Reassembly......Page 448
  3.1 Definition......Page 449
  3.2 Properties of GDS......Page 450
  4.1 GDS-Based Matching......Page 451
  4.2 ICP-Based Registration......Page 452
  5.1 Experimental Results......Page 453
  5.2 Comparison with Existing Methods......Page 454
 References......Page 455
 1 Introduction......Page 457
 2 Automatic Mass Detection Framework with Region-Based CNN......Page 458
  2.1 Hierarchical Candidate Mass Region Generation Method......Page 459
  2.2 Mass Detection with AMDR-CNN......Page 460
  3.2 Evaluation of the Proposed AMDR-CNN......Page 461
  3.3 Visualization of Mass Detection Results......Page 462
 4 Conclusion......Page 463
 References......Page 464
  1.1 Related Work......Page 466
  1.2 Stereoscopic Saliency Detection......Page 467
 2 Improved Saliency Detection Model......Page 468
  2.2 Depth Prior......Page 469
  2.3 Surface Orientation Prior......Page 470
  2.4 Background Prior......Page 471
  3.1 Visual Comfort Perception Features......Page 472
  3.2 Visual Comfort Prediction......Page 473
 References......Page 474
 1 Introduction......Page 476
  2.1 Deep Convolutional Neural Network......Page 477
  2.2 Multi-features Integration......Page 478
  3.1 Architecture......Page 479
  3.2 Confidence Embedding......Page 480
  3.3 Online Optimizing......Page 481
 4 Experiments......Page 482
  4.2 Experiments on OTB2013 and OTB2015......Page 483
 References......Page 484
 1 Introduction......Page 486
 2 Related Work......Page 488
 3 Correlation Filters......Page 489
  4.1 Single-Layer Convolutional Features and Bandwidth Adjustment Strategy......Page 490
  4.2 High-Confidence Model Update......Page 491
 5 Experiments......Page 492
 References......Page 496
 1 Introduction......Page 498
 2 Method of Scale Calibration and Registration......Page 499
  2.1 Relationship Between Coordinate Systems with Different Scales......Page 500
  2.3 Solving the Scale Factor with Optimization......Page 501
 3 AR System Based on the Proposed Method......Page 502
  4.1 Performance Analysis......Page 504
  4.2 Interactive Application......Page 506
 References......Page 507
 1 Introduction......Page 509
 3 Cross-Modal Sparse Representation......Page 511
  4.1 Bayesian Filtering Framework......Page 513
  4.2 Discriminative Likelihood......Page 514
  5.1 Evaluation Settings......Page 516
  5.3 Component Analysis......Page 517
 6 Conclusion......Page 518
 References......Page 519
 1 Introduction......Page 521
  2.2 Manifold Regularized Low-Rank Approximation......Page 523
  3.1 Datasets and Settings......Page 526
  3.3 Robust to Noise......Page 527
 4 Conclusion......Page 528
 References......Page 529
 1 Introduction......Page 532
  3.1 Review: Context-Aware Correlation Filter Tracker......Page 534
  3.3 Distractor Detection......Page 535
  3.4 Tracking......Page 536
  4.1 Baseline Trackers......Page 537
  4.3 Comparison Result......Page 538
 References......Page 540
 1 Introduction......Page 542
  2.1 Creation of the Superpixel Map......Page 543
   2.2.2 Spatial Information Based Partition......Page 544
  2.3 PM Index......Page 545
 3 Experiments and Results......Page 547
 References......Page 549
 1 Introduction......Page 551
  2.2 Restricted Boltzmann Machines......Page 553
 3 Materials and Methods......Page 554
  3.1 Preprocessing......Page 555
  3.2 Training DBN......Page 556
 4 Segmentation and Results......Page 557
 5 Discussion and Conclusion......Page 558
 References......Page 559
 1 Introduction......Page 561
 2 Our Method......Page 562
  2.2 Network Structure of FCN......Page 563
  3.1 Experimental Setting......Page 565
  3.2 Semantic Segmentation Performance......Page 566
  3.3 Parameter Analysis......Page 567
 4 Conclusions......Page 569
 References......Page 570
 1 Introduction......Page 571
 2 The Biological Model of Flocking......Page 572
  3.1 Main Algorithm......Page 573
  3.2 Local Behavior Rule......Page 574
  4.1 The Influence of the Acceptable Interval on the Formation of Opinions......Page 575
  4.2 The Influence of External Factors on the Formation of Opinions......Page 577
 5 Conclusions......Page 579
 References......Page 580
 1 Introduction......Page 581
  3.1 Tab Overview......Page 582
  3.3 Jaccard Distance......Page 583
   4.1.1 Distance Definition of the Same Type of Object......Page 584
   4.1.2 Distance Definition of the Different Type of Object......Page 585
   4.2.1 Model Evolution Process Design......Page 586
   4.2.2 Object Aggregation Design......Page 587
  5.1 Network Evolves with Time Step (T)......Page 588
  5.2 Introduced Parameter u to Control the Scale of the Network......Page 589
  5.3 Object Aggregation Analysis......Page 590
 6 Conclusions......Page 591
 References......Page 592
 1 Introduction......Page 593
  2.1 Materials......Page 594
  2.2 Filter of Dataset......Page 596
  3.2 Results......Page 597
 4 Conclusion......Page 599
 References......Page 600
 1 Introduction......Page 601
  2.1 Materials......Page 603
  2.2 Detection Networks......Page 604
  2.3 Quality Assessment......Page 605
  3.1 Detection Network......Page 606
  3.2 IQA Criteria......Page 607
 4 Conclusion......Page 608
 References......Page 609
 1 Introduction......Page 611
  2.1 Estimating the Initial Transmission......Page 612
  2.3 Recovering the Scene Reflection......Page 613
 3 Experimental Data and Set-Up......Page 614
  3.1 Qualitative Comparison......Page 615
  3.2 Quantitative Comparison......Page 617
 References......Page 618
 1 Introduction......Page 620
 2 Related Work......Page 621
  3.1 Experiment Design for User-Generated Gestures......Page 622
  3.2 Framework for 3D Dynamic Hand Gesture Recognition......Page 624
  4.1 The Selection for Gesture Lexicon......Page 625
  5.1 Discussion......Page 628
 References......Page 629
 1 Introduction......Page 631
 2 Design Method with Case-Based Reasoning......Page 632
  3.2 Extraction of Concepts and Attributes......Page 633
  3.3 Retrieval Matching of Case......Page 637
 5 Conclusion......Page 638
 References......Page 639
 1 Introduction......Page 641
 2 Preliminaries......Page 643
 3 The Improved Geometric Model......Page 644
  4.1 Identify the Coded Ring Marker......Page 645
 5 Experiment......Page 647
 6 Conclusion......Page 648
 References......Page 649
 1 Introduction......Page 650
 2 Related Work......Page 651
   3.1.1 Hand Localization and Hand Contour Identification......Page 652
   3.1.3 Implementation of SVM Algorithm......Page 653
   3.2.1 Identification of Gesticulation Trail......Page 654
 4 Experimental Results and Discussion......Page 658
 5 Conclusion......Page 660
 References......Page 661
 1 Introduction......Page 662
  2.2 Establish Equipment Solid Models......Page 663
   3.1.3 Ammunition Warhead Combat Power Field Numerical Simulation Analysis......Page 665
   3.2.2 Intersection Space Relationship Analysis of Ammo and Target......Page 667
   3.2.3 The Armored Equipment Parts Damage Judgment......Page 669
   3.2.4 The Equipment Damage Components Database......Page 670
 References......Page 671
Author Index......Page 672