[Pose Estimation] Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image, CVPR 2017
컨볼루션 네트워크를 이용한 3차원 인간 자세 추정 (텐서플로우를 이용한 구현) 자료이다. Convolutional Pose Machine을 이용하여 3차원 좌표상에 인간의 자세를 추정하는 과정이다.소스코드는 깃에 공개되어있다. 깃 : https://github.com/DenisTome/Lifting-from-the-Deep-release프로젝트 페이지 : http://www0.cs.ucl.ac.uk/staff/D.Tome/papers/LiftingFromTheDeep.html Abstract We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jo..
2017.11.27
[참고자료] Bone age detection 대회
참고자료 : http://www.16bit.ai/blog/ml-and-future-of-radiology There is a lot of hype around machine learning these days. Indeed, “machine learning” and “deep learning” are at the top of the Gartner Hype Cycle for Emerging Technologies in 2017. 1Kevin Kelly from Wired magazine went as far as to say “The business plans of the next 10,000 startups are easy to forecast: take X and add AI” . While this ..
2017.11.27
[참고자료] Image Segmentation
출처 : https://github.com/tkwoo/segmentation-visualization-training tkwoo/visualization-segmentation-process Segmentation visualization, keras, augmentation, fine tuning - tkwoo/visualization-segmentation-process github.com 텐서플로우와 케라스를 이용하여 Image Segmentation 하는 과정을 시각적으로 확인해보기
2017.11.27