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.
Similar content being viewed by others
References
Allain P, Courty N, Corpetti T (2012) AGORASET: a dataset for crowd video analysis. In: 2012 ICPR international workshop on pattern recognition and crowd analysis
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
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
Bainbridge WS (2007) The scientific research potential of virtual worlds. Science 317(5837):472–476. doi:10.1126/science.1146930
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
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
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
Caltech Pedestrian Detection Benchmark. http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/. Accessed 26 June 2017
Cappelli R (2015) Fingerprint sample synthesis. In: Li SZ, Jain AK (eds) Encyclopedia of biometrics, 2nd ed. Springer, New York, pp 668–679
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
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
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
Cheung E, Wong TK, Beral A, Wang X, Manocha D (2016) LCrowdV: generating labeled videos for simulation-based crowd behavior learning. arXiv:1606.08998
COCO—Common Objects in Context. http://mscoco.org/. Accessed 26 June 2017
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
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
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
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
Danielsson O, Aghazadeh O (2014) Human pose estimation from RGB input using synthetic training data. arXiv:1405.1213
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
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
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
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
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
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
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
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
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
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):1–35
Ghifary M (2016) Domain adaptation and domain generalization with representation learning. Dissertation, Victoria University of Wellington, New Zealand
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
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
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
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
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
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
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
Handa A, Pătrăucean V, Badrinarayanan V, Stent S, Cipolla R (2015) SceneNet: understanding real world indoor scenes with synthetic data. arXiv:1511.07041
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
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
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
ImageNet. http://www.image-net.org/. Accessed 26 June 2017
INRIA Person Dataset. http://pascal.inrialpes.fr/data/human/. Accessed 26 June 2017
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
Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014) Synthetic data and artificial neural networks for natural scene text recognition. arXiv:1406.2227
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
Jones N (2014) Computer science: the learning machines. Nature 505(7482):146–148
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
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
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
LeCun Y, Bengio Y, Hinton GE (2015) Deep learning. Nature 521(7553):436–444. doi:10.1038/nature14539
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
Loshchilov I, Hutter F (2016) Online batch selection for faster training of neural networks. arXiv:1511.06343
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
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
Mahendran A, Bilen H, Henriques JF, Vedaldi A (2016) ResearchDoom and CocoDoom: learning computer vision with games. arXiv:1610.02431
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
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
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
Movshovitz-Attias Y, Kanade T, Sheikh Y (2016) How useful is photo-realistic rendering for visual learning? arXiv:1603.08152
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
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
Pepik B, Benenson R, Ritschel T, Schiele B (2015) What is holding back convnets for detection? arXiv:1508.02844
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
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
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
Qureshi F, Terzopoulos D (2008) Smart camera networks in virtual reality. Proc IEEE 96(10):1640–1656. doi:10.1109/JPROC.2008.928932
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
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
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
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
Ren X, Chen K, Sun J (2016) A CNN based scene Chinese text recognition algorithm with synthetic data engine. arXiv:1604.01891
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
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
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
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
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
Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. arXiv:1604.03540
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
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
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
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
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 vision
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
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
Szeliski R (2010) Computer vision: algorithms and applications. Springer, New York
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
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
The KITTI Vision Benchmark Suite. http://www.cvlibs.net/datasets/kitti/. Accessed 26 June 2017
The PASCAL Visual Object Classes homepage. http://host.robots.ox.ac.uk/pascal/VOC/. Accessed 26 June 2017
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
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
Vázquez D (2013) Domain adaptation of virtual and real worlds for pedestrian detection. Dissertation, Universitat de Barcelona, Spain
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
Veeravasarapu VSR, Hota RN, Rothkopf C, Visvanathan R (2015a) Model validation for vision systems via graphics simulation. arXiv:1512.01401
Veeravasarapu VSR, Hota RN, Rothkopf C, Visvanathan R (2015b) Simulations for validation of vision systems. arXiv:1512.01030
Veeravasarapu VSR, Rothkopf C, Visvanathan R (2016) Model-driven simulations for deep convolutional neural networks. arXiv:1605.09582
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
Wang F-Y (2004) Parallel system methods for management and control of complex systems. Control Decis 19(5):485–489
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 61533019 and No. 71232006).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, K., Gou, C., Zheng, N. et al. Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives. Artif Intell Rev 48, 299–329 (2017). https://doi.org/10.1007/s10462-017-9569-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-017-9569-z