Advertisement

Artificial Intelligence Review

, Volume 48, Issue 3, pp 299–329 | Cite as

Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives

  • Kunfeng Wang
  • Chao Gou
  • Nanning Zheng
  • James M. Rehg
  • Fei-Yue Wang
Article

Abstract

In the study of image and vision computing, the generalization capability of an algorithm often determines whether it is able to work well in complex scenes. The goal of this review article is to survey the use of photorealistic image synthesis methods in addressing the problems of visual perception and understanding. Currently, the ACP Methodology comprising artificial systems, computational experiments, and parallel execution is playing an essential role in modeling and control of complex systems. This paper extends the ACP Methodology into the computer vision field, by proposing the concept and basic framework of Parallel Vision. In this paper, we first review previous works related to Parallel Vision, in terms of synthetic data generation and utilization. We detail the utility of synthetic data for feature analysis, object analysis, scene analysis, and other analyses. Then we propose the basic framework of Parallel Vision, which is composed of an ACP trilogy (artificial scenes, computational experiments, and parallel execution). We also present some in-depth thoughts and perspectives on Parallel Vision. This paper emphasizes the significance of synthetic data to vision system design and suggests a novel research methodology for perception and understanding of complex scenes.

Keywords

Visual perception Complex scenes Parallel Vision ACP Methodology Computer graphics Image synthesis 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (No. 61533019 and No. 71232006).

References

  1. Allain P, Courty N, Corpetti T (2012) AGORASET: a dataset for crowd video analysis. In: 2012 ICPR international workshop on pattern recognition and crowd analysisGoogle Scholar
  2. Angel Arul Jothi J, Mary Anita Rajam V (2017) A survey on automated cancer diagnosis from histopathology images. Artif Intell Rev 48(1):31–81. doi: 10.1007/s10462-016-9494-6 CrossRefGoogle Scholar
  3. Aubry M, Russell BC (2015) Understanding deep features with computer-generated imagery. In: IEEE international conference on computer vision, pp 2875–2883. doi: 10.1109/ICCV.2015.329
  4. Bainbridge WS (2007) The scientific research potential of virtual worlds. Science 317(5837):472–476. doi: 10.1126/science.1146930 CrossRefGoogle Scholar
  5. Bertozzi M, Broggi A (1998) GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection. IEEE Trans Image Process 7(1):62–81. doi: 10.1109/83.650851 CrossRefGoogle Scholar
  6. Brutzer S, Höferlin B, Heidemann G (2011) Evaluation of background subtraction techniques for video surveillance. IEEE conference on computer vision and pattern recognition, pp 1937–1944. doi: 10.1109/CVPR.2011.5995508
  7. Butler DJ, Wulff J, Stanley GB, Black MJ (2012) A naturalistic open source movie for optical flow evaluation. In: 2012 European conference on computer vision, pp 611–625. doi: 10.1007/978-3-642-33783-3_44
  8. Caltech Pedestrian Detection Benchmark. http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/. Accessed 26 June 2017
  9. Cappelli R (2015) Fingerprint sample synthesis. In: Li SZ, Jain AK (eds) Encyclopedia of biometrics, 2nd ed. Springer, New York, pp 668–679Google Scholar
  10. Charalambous CC, Bharath AA (2016) A data augmentation methodology for training machine/deep learning gait recognition algorithms. In: 2016 British Machine Vision conference. doi: 10.5244/C.30.110
  11. Chen C, Seff A, Kornhauser A, Xiao J (2015) DeepDriving: learning affordance for direct perception in autonomous driving. In: 2015 IEEE international conference on computer vision, pp 2722–2730. doi: 10.1109/ICCV.2015.312
  12. Chen W, Wang H, Li Y, Su H, Wang Z, Tu C, Lischinski D, Cohen-Or D, Chen B (2016) Synthesizing training images for boosting human 3D pose estimation. arXiv:1604.02703
  13. Cheung E, Wong TK, Beral A, Wang X, Manocha D (2016) LCrowdV: generating labeled videos for simulation-based crowd behavior learning. arXiv:1606.08998
  14. COCO—Common Objects in Context. http://mscoco.org/. Accessed 26 June 2017
  15. Correa M, Ruiz-del-Solar J, Verschae R (2016) A realistic virtual environment for evaluating face analysis systems under dynamic conditions. Pattern Recognit 52:160–173. doi: 10.1016/j.patcog.2015.11.008 CrossRefGoogle Scholar
  16. Courty N, Allain P, Creusot C, Corpetti T (2014) Using the AGORASET dataset: assessing for the quality of crowd video analysis methods. Pattern Recognit Lett 44:161–170. doi: 10.1016/j.patrec.2014.01.004 CrossRefGoogle Scholar
  17. Creusot C, Courty N (2013) Ground truth for pedestrian analysis and application to camera calibration. In: IEEE conference on computer vision and pattern recognition workshops, pp 712–718. doi: 10.1109/CVPRW.2013.108
  18. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition, pp 886–893. doi: 10.1109/CVPR.2005.177
  19. Danielsson O, Aghazadeh O (2014) Human pose estimation from RGB input using synthetic training data. arXiv:1405.1213
  20. Datondji SRE, Dupuis Y, Subirats P, Vasseur P (2016) A survey of vision-based traffic monitoring of road intersections. IEEE Trans Intell Transp Syst 17(10):2681–2698. doi: 10.1109/TITS.2016.2530146 CrossRefGoogle Scholar
  21. Dosovitskiy A, Springenberg JT, Tatarchenko M, Brox T (2017) Learning to generate chairs, tables and cars with convolutional networks. IEEE Trans Pattern Anal Mach Intell 39(4):692–705. doi: 10.1109/TPAMI.2016.2567384 Google Scholar
  22. Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915–1929. doi: 10.1109/TPAMI.2012.231 CrossRefGoogle Scholar
  23. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645. doi: 10.1109/TPAMI.2009.167 CrossRefGoogle Scholar
  24. Fernández C, Baiget P, Roca FX, Gonzàlez J (2011) Augmenting video surveillance footage with virtual agents for incremental event evaluation. Pattern Recognit Lett 32:878–889. doi: 10.1016/j.patrec.2010.09.027 CrossRefGoogle Scholar
  25. Ferrer MA, Diaz-Cabrera M, Morales A (2015) Static signature synthesis: a neuromotor inspired approach for biometrics. IEEE Trans Pattern Anal Mach Intell 37(3):667–680. doi: 10.1109/TPAMI.2014.2343981 CrossRefGoogle Scholar
  26. Gaidon A, Wang Q, Cabon Y, Vig E (2016) Virtual worlds as proxy for multi-object tracking analysis. In: IEEE conference on computer vision and pattern recognition, pp 4340–4349. doi: 10.1109/CVPR.2016.470
  27. Galbally J, Plamondon R, Fierrez J, Ortega-Garcia J (2012a) Synthetic on-line signature generation. Part I: methodology and algorithms. Pattern Recognit 45:2610–2621. doi: 10.1016/j.patcog.2011.12.011 CrossRefGoogle Scholar
  28. Galbally J, Fierrez J, Ortega-Garcia J, Plamondon R (2012b) Synthetic on-line signature generation. Part II: experimental validation. Pattern Recognit 45:2622–2632. doi: 10.1016/j.patcog.2011.12.007 CrossRefGoogle Scholar
  29. Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(59):1–35MathSciNetzbMATHGoogle Scholar
  30. Ghifary M (2016) Domain adaptation and domain generalization with representation learning. Dissertation, Victoria University of Wellington, New ZealandGoogle Scholar
  31. Gopalan R, Li R, Patel VM, Chellappa R (2015) Domain adaptation for visual recognition. Found Trends\({\textregistered }\) in Comput Graph Vis 8(4):285–378. doi: 10.1561/0600000057
  32. Gou C, Wang K, Yao Y, Li Z (2016) Vehicle license plate recognition based on extremal regions and restricted Boltzmann machines. IEEE Trans Intell Transp Syst 17(4):1096–1107. doi: 10.1109/TITS.2015.2496545 CrossRefGoogle Scholar
  33. Gould S, Rodgers J, Cohen D, Elidan G, Koller D (2008) Multi-class segmentation with relative location prior. Int J Comput Vision 80(3):300–316. doi: 10.1007/s11263-008-0140-x CrossRefGoogle Scholar
  34. Goyette N, Jodoin PM, Porikli F, Konrad J, Ishwar P (2014) A novel video dataset for change detection benchmarking. IEEE Trans Image Process 23(11):4663–4679. doi: 10.1109/TIP.2014.2346013 MathSciNetCrossRefGoogle Scholar
  35. Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. In: 2016 IEEE conference on computer vision and pattern recognition, pp 2315–2324. doi: 10.1109/CVPR.2016.254
  36. Halim Z, Kalsoom R, Bashir S, Abbas G (2016) Artificial intelligence techniques for driving safety and vehicle crash prediction. Artif Intell Rev 46(3):351–387. doi: 10.1007/s10462-016-9467-9 CrossRefGoogle Scholar
  37. Haltakov V, Unger C, Ilic S (2013) Framework for generation of synthetic ground truth data for driver assistance applications. In: 35th German conference on pattern recognition. doi: 10.1007/978-3-642-40602-7_35
  38. Handa A, Pătrăucean V, Badrinarayanan V, Stent S, Cipolla R (2015) SceneNet: understanding real world indoor scenes with synthetic data. arXiv:1511.07041
  39. Handa A, Pătrăucean V, Badrinarayanan V, Stent S, Cipolla R (2016) Understanding real world indoor scenes with synthetic data. In: IEEE conference on computer vision and pattern recognition, pp 4077-4085. doi: 10.1109/CVPR.2016.442
  40. Hattori H, Boddeti VN, Kitani K, Kanade T (2015) Learning scene-specific pedestrian detectors without real data. In: IEEE conference on computer vision and pattern recognition, pp 3819–3827. doi: 10.1109/CVPR.2015.7299006
  41. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, pp 770–778. doi: 10.1109/CVPR.2016.90
  42. ImageNet. http://www.image-net.org/. Accessed 26 June 2017
  43. INRIA Person Dataset. http://pascal.inrialpes.fr/data/human/. Accessed 26 June 2017
  44. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2016) Reading text in the wild with convolutional neural networks. Int J Comput Vis 116:1–20. doi: 10.1007/s11263-015-0823-z MathSciNetCrossRefGoogle Scholar
  45. Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014) Synthetic data and artificial neural networks for natural scene text recognition. arXiv:1406.2227
  46. Johnson-Roberson M, Barto C, Mehta R, Sridhar SN, Vasudevan R (2016) Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? arXiv:1610.01983
  47. Jones N (2014) Computer science: the learning machines. Nature 505(7482):146–148CrossRefGoogle Scholar
  48. Kaneva B, Torralba A, Freeman WT (2011) Evaluation of image features using a photorealistic virtual world. In: 2011 IEEE international conference on computer vision, pp 2282–2289. doi: 10.1109/ICCV.2011.6126508
  49. Karamouzas I, Overmars M (2012) Simulating and evaluating the local behavior of small pedestrian groups. IEEE Trans Vis Comput Gr 18(3):394–406. doi: 10.1109/TVCG.2011.133 CrossRefGoogle Scholar
  50. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, vol 25 (NIPS 2012). doi: 10.1145/3065386
  51. LeCun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436–444. doi: 10.1038/nature14539 CrossRefGoogle Scholar
  52. Liu Y, Wang K, Shen D (2016) Visual tracking based on dynamic coupled conditional random field model. IEEE Trans Intell Transp Syst 17(3):822–833. doi: 10.1109/TITS.2015.2488287 CrossRefGoogle Scholar
  53. Loshchilov I, Hutter F (2016) Online batch selection for faster training of neural networks. arXiv:1511.06343
  54. Lowry S, Sünderhauf N, Newman P, Leonard JJ, Cox D, Corke P, Milford MJ (2016) Visual place recognition: a survey. IEEE Trans Rob 32(1):1–19. doi: 10.1109/TRO.2015.2496823 CrossRefGoogle Scholar
  55. Luo J, Tang J, Tjahjadi T, Xiao X (2016) Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis. Pattern Recognit 60:361–377. doi: 10.1016/j.patcog.2016.05.030 CrossRefGoogle Scholar
  56. Mahendran A, Bilen H, Henriques JF, Vedaldi A (2016) ResearchDoom and CocoDoom: learning computer vision with games. arXiv:1610.02431
  57. Marín J, Vázquez D, Gerónimo D, López AM (2010) Learning appearance in virtual scenarios for pedestrian detection. In: 2010 IEEE conference on computer vision and pattern recognition, pp 137–144. doi: 10.1109/CVPR.2010.5540218
  58. Mayer N, Ilg E, Häusser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: IEEE conference on computer vision and pattern recognition, pp 4040–4048. doi: 10.1109/CVPR.2016.438
  59. Model I, Shamir L (2015) Comparison of data set bias in object recognition benchmarks. IEEE Access 3:1953–1962. doi: 10.1109/ACCESS.2015.2491921 CrossRefGoogle Scholar
  60. Movshovitz-Attias Y, Kanade T, Sheikh Y (2016) How useful is photo-realistic rendering for visual learning? arXiv:1603.08152
  61. Neves J, Narducci F, Barra S, Proença H (2016) Biometric recognition in surveillance scenarios: a survey. Artif Intell Rev 46(4):515–541. doi: 10.1007/s10462-016-9474-x CrossRefGoogle Scholar
  62. Peng X, Sun B, Ali K, Saenko K (2015) Learning deep object detectors from 3D models. In: 2015 IEEE international conference on computer vision, pp 1278–1286. doi: 10.1109/ICCV.2015.151
  63. Pepik B, Benenson R, Ritschel T, Schiele B (2015) What is holding back convnets for detection? arXiv:1508.02844
  64. Pinto N, Barhomi Y, Cox DD, DiCarlo JJ (2011) Comparing state-of-the-art visual features on invariant object recognition tasks. In: IEEE workshop on applications of computer vision, pp 463–470. doi: 10.1109/WACV.2011.5711540
  65. Prendinger H, Gajananan K, Zaki AB, Fares A, Molenaar R, Urbano D, van Lint H, Gomaa W (2013) Tokyo Virtual Living Lab: designing smart cities based on the 3D Internet. IEEE Internet Comput 17(6):30–38. doi: 10.1109/MIC.2013.87 CrossRefGoogle Scholar
  66. Qiu W, Yuille A (2016) UnrealCV: connecting computer vision to Unreal Engine. In: 2016 ECCV workshop on virtual/augmented reality for visual artificial intelligence, pp 909-916. doi: 10.1007/978-3-319-49409-8_75
  67. Qureshi F, Terzopoulos D (2008) Smart camera networks in virtual reality. Proc IEEE 96(10):1640–1656. doi: 10.1109/JPROC.2008.928932 CrossRefGoogle Scholar
  68. Ragheb H, Velastin S, Remagnino P, Ellis T (2008) ViHASi: virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods. In: ACM/IEEE international conference on distributed smart cameras, pp 1–10. doi: 10.1109/ICDSC.2008.4635730
  69. Ramezani M, Yaghmaee F (2016) A review on human action analysis in videos for retrieval applications. Artif Intell Rev 46(4):485–514. doi: 10.1007/s10462-016-9473-y CrossRefGoogle Scholar
  70. Rematas K, Ritschel T, Fritz M, Tuytelaars T (2014) Image-based synthesis and re-synthesis of viewpoints guided by 3D models. In: 2014 IEEE conference on computer vision and pattern recognition, pp 3898–3905. doi: 10.1109/CVPR.2014.498
  71. Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. doi: 10.1109/TPAMI.2016.2577031 CrossRefGoogle Scholar
  72. Ren X, Chen K, Sun J (2016) A CNN based scene Chinese text recognition algorithm with synthetic data engine. arXiv:1604.01891
  73. Richter SR, Vineet V, Roth S, Koltun V (2016) Playing for data: ground truth from computer games. In: 2016 European conference on computer vision, pp 102–118. doi: 10.1007/978-3-319-46475-6_7
  74. Ros G, Sellart L, Materzynska J, Vazquez D, Lopez AM (2016) The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: 2016 IEEE conference on computer vision and pattern recognition, pp 3234–3243. doi: 10.1109/CVPR.2016.352
  75. Rozantsev A, Lepetit V, Fua P (2015) On rendering synthetic images for training an object detector. Comput Vis Image Underst 137:24–37. doi: 10.1016/j.cviu.2014.12.006 CrossRefGoogle Scholar
  76. Shafaei A, Little JJ, Schmidt M (2016) Play and learn: using video games to train computer vision models. In: 2016 The British machine vision conference. doi: 10.5244/C.30.26
  77. Shotton J, Girshick R, Fitzgibbon A, Sharp T, Cook M, Finocchio M, Moore R, Kohli P, Criminisi A, Kipman A, Blake A (2013) Efficient human pose estimation from single depth images. IEEE Trans Pattern Anal Mach Intell 35(12):2821–2840. doi: 10.1109/TPAMI.2012.241 CrossRefGoogle Scholar
  78. Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. arXiv:1604.03540
  79. Sizikova E, Singh VK, Georgescu B, Halber M, Ma K, Chen T (2016) Enhancing place recognition using joint intensity—depth analysis and synthetic data. In: ECCV workshop on virtual/augmented reality for visual artificial intelligence, pp 901–908. doi: 10.1007/978-3-319-49409-8_74
  80. Smelik RM, Tutenel T, Bidarra R, Benes B (2014) A survey on procedural modeling for virtual worlds. Comput Graphics Forum 33(6):31–50. doi: 10.1111/cgf.12276 CrossRefGoogle Scholar
  81. Sobral A, Vacavant A (2014) A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput Vis Image Underst 122:4–21. doi: 10.1016/j.cviu.2013.12.005 CrossRefGoogle Scholar
  82. Starzyk W, Qureshi F (2013) Software laboratory for camera networks research. IEEE J Emerg Select Top Circuits Syst 3(2):284–293. doi: 10.1109/JETCAS.2013.2256827 CrossRefGoogle Scholar
  83. Sun B, Peng X, Saenko K (2015) Generating large scale image datasets from 3D CAD models. In: CVPR 2015 Workshop on the future of datasets in visionGoogle Scholar
  84. Sun B, Saenko K (2014) From virtual to reality: fast adaptation of virtual object detectors to real domains. In: 2014 British machine vision conference. doi: 10.5244/C.28.82
  85. Su H, Qi CR, Li Y, Guibas L (2015) Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: IEEE international conference on computer vision, pp 2686–2694. doi: 10.1109/ICCV.2015.308
  86. Szeliski R (2010) Computer vision: algorithms and applications. Springer, New YorkzbMATHGoogle Scholar
  87. Taylor GR, Chosak AJ, Brewer PC (2007) OVVV: using virtual worlds to design and evaluate surveillance systems. In: 2007 IEEE conference on computer vision and pattern recognition, pp 1–8. doi: 10.1109/CVPR.2007.383518
  88. Thacker NA, Clark AF, Barron JL, Beveridge JR, Courtney P, Crum WR, Ramesh V, Clark C (2008) Performance characterization in computer vision: a guide to best practices. Comput Vis Image Underst 109(3):305–334. doi: 10.1016/j.cviu.2007.04.006 CrossRefGoogle Scholar
  89. The KITTI Vision Benchmark Suite. http://www.cvlibs.net/datasets/kitti/. Accessed 26 June 2017
  90. The PASCAL Visual Object Classes homepage. http://host.robots.ox.ac.uk/pascal/VOC/. Accessed 26 June 2017
  91. Torralba A, Efros AA (2011) Unbiased look at dataset bias. In: 2011 IEEE conference on computer vision and pattern recognition, pp 1521–1528. doi: 10.1109/CVPR.2011.5995347
  92. Vacavant A, Chateau T, Wilhelm A, Lequièvre L (2013) A benchmark dataset for outdoor foreground background extraction. In: ACCV 2012 workshops, Lecture Notes in Computer Science vol 7728, pp 291–300. doi: 10.1007/978-3-642-37410-4_25
  93. Vázquez D (2013) Domain adaptation of virtual and real worlds for pedestrian detection. Dissertation, Universitat de Barcelona, SpainGoogle Scholar
  94. Vázquez D, López AM, Marín J, Ponsa D, Gerónimo D (2014) Virtual and real world adaptation for pedestrian detection. IEEE Trans Pattern Anal Mach Intell 36(4):797–809. doi: 10.1109/TPAMI.2013.163 CrossRefGoogle Scholar
  95. Veeravasarapu VSR, Hota RN, Rothkopf C, Visvanathan R (2015a) Model validation for vision systems via graphics simulation. arXiv:1512.01401
  96. Veeravasarapu VSR, Hota RN, Rothkopf C, Visvanathan R (2015b) Simulations for validation of vision systems. arXiv:1512.01030
  97. Veeravasarapu VSR, Rothkopf C, Visvanathan R (2016) Model-driven simulations for deep convolutional neural networks. arXiv:1605.09582
  98. Venetianer PL, Deng H (2010) Performance evaluation of an intelligent video surveillance system - a case study. Comput Vis Image Underst 114(11):1292–1302. doi: 10.1016/j.cviu.2010.07.010 CrossRefGoogle Scholar
  99. Wang F-Y (2004) Parallel system methods for management and control of complex systems. Control Decis 19(5):485–489zbMATHGoogle Scholar
  100. Wang F-Y (2010) Parallel control and management for intelligent transportation systems: concepts, architectures, and applications. IEEE Trans Intell Transp Syst 11(3):630–638. doi: 10.1109/TITS.2010.2060218 CrossRefGoogle Scholar
  101. Wang F-Y (2013) Parallel control: a method for data-driven and computational control. Acta Automatica Sinica 39(4):293–302. doi: 10.3724/SP.J.1004.2013.00293 CrossRefGoogle Scholar
  102. Wang K, Huang W, Tian B, Wen D (2012) Measuring driving behaviors from live video. IEEE Intell Syst 27(5):75–80. doi: 10.1109/MIS.2012.100 CrossRefGoogle Scholar
  103. Wang X, Wang M, Li W (2014) Scene-specific pedestrian detection for static video surveillance. IEEE Trans Pattern Anal Mach Intell 36(2):361–374. doi: 10.1109/TPAMI.2013.124 CrossRefGoogle Scholar
  104. Wang F-Y, Wang X, Li L, Li L (2016) Steps toward parallel intelligence. IEEE/CAA J Automatica Sinica 3(4):345–348. doi: 10.1109/JAS.2016.7510067 MathSciNetCrossRefGoogle Scholar
  105. Wang K, Liu Y, Gou C, Wang F-Y (2016) A multi-view learning approach to foreground detection for traffic surveillance applications. IEEE Trans Veh Technol 65(6):4144–4158. doi: 10.1109/TVT.2015.2509465 CrossRefGoogle Scholar
  106. Wang F-Y, Zhang JJ, Zheng X, Wang X, Yuan Y, Dai X, Zhang J, Yang L (2016) Where does AlphaGo go: from Church-Turing Thesis to AlphaGo Thesis and beyond. IEEE/CAA J Automatica Sinica 3(2):113–120. doi: 10.1109/JAS.2016.7471613 CrossRefGoogle Scholar
  107. Wang F-Y, Zhang J, Wei Q, Zheng X, Li L (2017) PDP: parallel dynamic programming. IEEE/CAA J Automatica Sinica 4(1):1–5. doi: 10.1109/JAS.2017.7510310 MathSciNetCrossRefGoogle Scholar
  108. Wang K, Yao Y (2015) Video-based vehicle detection approach with data-driven adaptive neuro-fuzzy networks. Int J Pattern Recognit Artif Intell. doi: 10.1142/S0218001415550150
  109. Wulff J, Butler DJ, Stanley GB, Black MJ (2012) Lessons and insights from creating a synthetic optical flow benchmark. In: 2012 ECCV workshop on unsolved problems in optical flow and stereo estimation, pp 168–177. doi: 10.1007/978-3-642-33868-7_17
  110. Xu J, Vázquez D, López AM, Marín J, Ponsa D (2014) Learning a part-based pedestrian detector in a virtual world. IEEE Trans Intell Transp Syst 15(5):2121–2131. doi: 10.1109/TITS.2014.2310138 CrossRefGoogle Scholar
  111. Xu J, Ramos S, Vázquez D, López AM (2014) Domain adaptation of deformable part-based models. IEEE Trans Pattern Anal Mach Intell 36(12):2367–2380. doi: 10.1109/TPAMI.2014.2327973 CrossRefGoogle Scholar
  112. Yang L, Wang F-Y (2007) Driving into intelligent spaces with pervasive communications. IEEE Intell Syst 22(1):12–15. doi: 10.1109/MIS.2007.8 CrossRefGoogle Scholar
  113. Zeng X, Ouyang W, Wang M, Wang X (2014) Deep learning of scene-specific classifier for pedestrian detection. In: 2014 European conference on computer vision, pp 472-487. doi: 10.1007/978-3-319-10578-9_31
  114. Zhang N, Wang F-Y, Zhu F, Zhao D, Tang S (2008) DynaCAS: computational experiments and decision support for ITS. IEEE Intell Syst 23(6):19–23. doi: 10.1109/MIS.2008.101 CrossRefGoogle Scholar
  115. Zhu W, Wang F-Y (2012) The fourth type of covering-based rough sets. Inf Sci 201:80–92. doi: 10.1016/j.ins.2012.01.026 MathSciNetCrossRefzbMATHGoogle Scholar
  116. Zitnick CL, Vedantam R, Parikh D (2016) Adopting abstract images for semantic scene understanding. IEEE Trans Pattern Anal Mach Intell 38(4):627–638. doi: 10.1109/TPAMI.2014.2366143 CrossRefGoogle Scholar
  117. Zuo J, Schmid NA, Chen X (2007) On generation and analysis of synthetic iris images. IEEE Trans Inf Forensics Secur 2(1):77–90. doi: 10.1109/TIFS.2006.890305 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2017

Authors and Affiliations

  • Kunfeng Wang
    • 1
  • Chao Gou
    • 1
  • Nanning Zheng
    • 2
  • James M. Rehg
    • 3
  • Fei-Yue Wang
    • 1
    • 4
  1. 1.The State Key Laboratory of Management and Control for Complex Systems, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.Institute of Artificial Intelligence and Robotics (IAIR)Xi’an Jiaotong UniversityXi’anChina
  3. 3.School of Interactive ComputingGeorgia Institute of TechnologyAtlantaUSA
  4. 4.Research Center for Computational Experiments and Parallel Systems TechnologyNational University of Defense TechnologyChangshaChina

Personalised recommendations