Generating synthetic image data
作者： Ian Cinnamon , Bruno Brasil Ferrari Faviero , Simanta Gautam
DOI:
关键词:
摘要: According to an aspect, a method comprises: generating 2D projection from 3D representation of object, wherein the comprises edgemapped representation, generating, with generative adversarial neural network (GAN), and based on projection, simulated image appears as though object has been scanned by detection device, combining background form synthesized image, was captured outputting image.
lens.org 参考文章(46)
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, None, You Only Look Once: Unified, Real-Time Object Detection arXiv: Computer Vision and Pattern Recognition. ,(2015)
Zhengrong Ying, Julia Pavlovich, Baoming Hong, David Schafer, Detecting concealed threats ,(2008)
Tom Carrell, Andreas Varnavas, Graeme Penney, Method and system to assist 2d-3d image registration ,(2013)
Ross Girshick, Fast R-CNN international conference on computer vision. pp. 1440- 1448 ,(2015) , 10.1109/ICCV.2015.169
Aidan Doyle, Alexandre Filiatrault, Luc Perron, Michel Bouchard, Dan Gudmundson, Method and apparatus for providing threat image projection (tip) in a luggage screening system, and luggage screening system implementing same ,(2007)
Edward D. Franco, William Z. Chang, Jolyon A. Browne, Robert A. Armistead, Joseph Bendahan, Systems and methods for automated, rapid detection of high-atomic-number materials ,(2010)
Luc Perron, Dan Gudmundson, User interface for use in security screening providing image enhancement capabilities and apparatus for implementing same ,(2007)
Zhengrong Ying, Julia Pavlovich, Ram Naidu, Object classification using two-dimensional projection ,(2010)
Abdo A. Husseiny, Zeinab A. Sabri, Edwin D. Stevens, Detection of concealed explosives and contraband ,(1995)