Camera parameters estimation from pose detections

Автор: Shalimova Ekaterina Alekseevna, Shalnov Evgeny Vadimovich, Konushin Anton Sergeevich

Журнал: Компьютерная оптика @computer-optics

Рубрика: Обработка изображений, распознавание образов

Статья в выпуске: 3 т.44, 2020 года.

Бесплатный доступ

Some computer vision tasks become easier with known camera calibration. We propose a method for camera focal length, location and orientation estimation by observing human poses in the scene. Weak requirements to the observed scene make the method applicable to a wide range of scenarios. Our evaluation shows that even being trained only on synthetic dataset, the proposed method outperforms known solution. Our experiments show that using only human poses as the input also allows the proposed method to calibrate dynamic visual sensors.

Camera calibration, dynamic vision sensor, video surveillance

Короткий адрес: https://sciup.org/140250002

IDR: 140250002   |   DOI: 10.18287/2412-6179-CO-600

Список литературы Camera parameters estimation from pose detections

  • CMU graphics lab motion capture database. Source: (http://mocap.cs.cmu.edu/).
  • Baltieri D, Vezzani R, Cucchiara R. 3dPES: 3D people dataset for surveillance and forensics. Proceedings of the 1st International ACM Workshop on Multimedia access to 3D Human Objects 2011: 59-64. DOI: 10.1145/2072572.2072590
  • Berclaz J, Fleuret F, Turetken E, Fua P. Multiple object tracking using k-shortest paths optimization. IEEE Trans Pattern Anal Machine Intell 2011; 33(9): 1806-1819. DOI: 10.1109/TPAMI.2011.21
  • Cao Z, Simon T, Wei S-E, Sheikh Y. Realtime multi-person 2D pose estimation using part affinity fields. Proc IEEE Conf Comp Vis Patt Recogn 2017: 7291-7299. DOI: 10.1109/CVPR.2017.143
  • Caprile B, Torre V. Using vanishing points for camera calibration. Int J Comp Vis 1990; 4(2): 127-139. DOI: 10.1007/BF00127813
  • Delbruck T. Frame-free dynamic digital vision. Proceedings of International Symposium on Secure-Life Electronics, Advanced Electronics for Quality Life and Society 2008: 21-26.
  • Dubskа́ M, Herout A, Sochor J. Automatic camera calibration for traffic understanding. Proceedings of the British Machine Vision Conference 2014; 4: 8.
  • DOI: 10.5244/C.28.42
  • Fleuret F, Berclaz J, Lengagne R, Fua P. Multi-camera people tracking with a probabilistic occupancy map. IEEE Trans Pattern Anal Machine Intell 2008; 30(2): 267-282.
  • DOI: 10.1109/TPAMI.2007.1174
  • Hoiem D, Efros AA, Hebert M. Putting objects in perspective. Int J Comp Vis 2008; 80(1): 3-15.
  • DOI: 10.1109/CVPR.2006.232
  • Hold-Geoffroy Y, Sunkavalli K, Eisenmann J, Fisher M, Gambaretto E, Hadap S, Lalonde J-F. A perceptual measure for deep single image camera calibration. Proc IEEE Conf Comp Vis Pattern Recogn 2018: 2354-2363.
  • DOI: 10.1109/CVPR.2018.00250
  • Huang S, Ying X, Rong J, Shang Z, Zha H. Camera calibration from periodic motion of a pedestrian. Proc IEEE Conf Comp Vis Pattern Recogn 2016: 3025-3033.
  • DOI: 10.1109/CVPR.2016.330
  • Li B, Peng K, Ying X, Zha H. Simultaneous vanishing point detection and camera calibration from single images. In Book: Bebis G, Boyle R, Parvin B, Koracin D, Chung R, Hammound R, Hussain M, Kar-Han T, Crawfis R, Thalmann D, Kao D, Avila L, eds. Advances in visual computing. Berlin, Heidelberg: Springer-Verlag; 2010: 151-160.
  • DOI: 10.1007/978-3-642-17274-8_15
  • Li S, Nguyen VH, Ma M, Jin C-B, Do TD, Kim H. A simplified nonlinear regression method for human height estimation in video surveillance. EURASIP Journal on Image and Video Processing 2015; 2015(1): 32.
  • DOI: 10.1186/s13640-015-0086-1
  • Liu J, Collins RT, Liu Y. Surveillance camera autocalibration based on pedestrian height distributions. British Machine Vision Conference (BMVC) 2011; 2: 117.
  • DOI: 10.5244/C.25.117
  • Liu J, Collins RT, Liu Y. Robust autocalibration for a surveillance camera network. 2013 IEEE Workshop on Applications of Computer Vision (WACV) 2013: 433-440.
  • DOI: 10.1109/WACV.2013.6475051
  • Lv F, Zhao T, Nevatia R. Self-calibration of a camera from video of a walking human. Object Recognition Supported by User Interaction for Service Robots 2002; 1: 562-567.
  • DOI: 10.1109/ICPR.2002.1044793
  • Mueggler E. Event-based vision for high-speed robotics. PhD thesis. University of Zurich; 2017.
  • Pricasariu V, Reid I. FastHOG-a real-time GPU implementation of HOG. Source: áhttp://www.robots.ox.ac.uk/~lav/Papers/prisacariu_reid_tr2310_09/prisacariu_reid_tr2310_09.pdfñ.
  • Shalnov E, Konushin A. Convolutional neural network for camera pose estimation from object detections. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences 2017: 1-6.
  • DOI: 10.5194/isprs-archives-XLII-2-W4-1-2017
  • Sochor J, Jurа́nek R, Herout A. Traffic surveillance camera calibration by 3D model bounding box alignment for accurate vehicle speed measurement. Computer Vision and Image Understanding 2017; 161: 87-98.
  • DOI: 10.1016/j.cviu.2017.05.015
  • Tsai RY. An efficient and accurate camera calibration technique for 3D machine vision. Proc IEEE Conf Comp Vis Pattern Recogn 1986: 364-374.
  • Wei S-E, Ramakrishna V, Kanade T, Sheikh Y. Convolutional pose machines. Proc IEEE Conf Comp Vis Pattern Recogn 2016: 4724-4732.
  • DOI: 10.1109/CVPR.2016.511
  • Workman S, Greenwell C, Zhai M, Baltenberger R, Jacobs N. DEEPFOCAL: A method for direct focal length estimation. IEEE Int Conf Image Process (ICIP) 2015: 1369-1373.
  • DOI: 10.1109/ICIP.2015.7351024
  • Workman S, Zhai M, Jacobs N. Horizon lines in the wild. Proc British Machine Vis Conf 2016: 20.
  • DOI: 10.5244/c.30.20
  • Yan H, Zhang Y, Zhang S, Zhao S, Zhang L. Focal length estimation guided with object distribution on FocaLens dataset. Journal of Electronic Imaging 2017; 26(3): 033018.
  • DOI: 10.1117/1.JEI.26.3.033018
  • Zhang Z. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Machine Intell 2000; 22: 1330-1334.
  • DOI: 10.1109/34.888718
Еще
Статья научная