SpherePHD : applying CNNs on a spherical polyhedron representation of 360$^\circ$ images = 정이십면체 기반 360도 이미지 표현 및 CNN 적용 방법applying CNNs on a spherical polyhedron representation of 360$^\circ$ images

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 93
  • Download : 0
Omni-directional cameras have many advantages over conventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have been proposed recently to apply convolutional neural networks (CNNs) to omni-directional images for various visual tasks. However, most of them use image representations defined in the Euclidean space after transforming the omni-directional views originally formed in the non-Euclidean space. This transformation leads to shape distortion due to nonuniform spatial resolving power and the loss of continuity. These effects make existing convolution kernels experience difficulties in extracting meaningful information. This paper presents a novel method to resolve such problems of applying CNNs to omni-directional images. The proposed method utilizes a spherical polyhedron to represent omni-directional views. This method minimizes the variance of the spatial resolving power on the sphere surface, and includes new convolution and pooling methods for the proposed representation. The proposed method can also be adopted by any existing CNN-based methods. The feasibility of the proposed method is demonstrated through classification, detection, and semantic segmentation tasks with synthetic and real datasets.
Advisors
Yoon, Kuk-Jinresearcher윤국진researcher
Description
한국과학기술원 :기계공학과,
Publisher
한국과학기술원
Issue Date
2020
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 기계공학과, 2020.2,[v, 33 p. :]

Keywords

Omni-directional image▼aCNN▼aNon-euclidean deep learning▼aclassification▼aobject detection▼asemantic segmentation▼adepth estimation; 전방향 영상▼a합성곱 신경망▼a비유클리드 심층 학습 기법▼a객체 분류▼a객체 탐지▼a의미론적 영역 분할 기법▼a깊이 지도 생성

URI
http://hdl.handle.net/10203/284068
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=910880&flag=dissertation
Appears in Collection
ME-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0