Cited 0 time in webofscience Cited 0 time in scopus

Deep learning integral imaging for three-dimensional visualization, object detection, and segmentation

Title
Deep learning integral imaging for three-dimensional visualization, object detection, and segmentation
Authors
Yi, FaliuJeong, OngeeMoon, InkyuJavidi, Bahram
DGIST Authors
Yi, Faliu; Jeong, Ongee; Moon, Inkyu; Javidi, Bahram
Issue Date
2021-11
Citation
Optics and Lasers in Engineering, 146, 106695
Type
Article
Author Keywords
3D integral imaging3D image reconstructionTarget visualizationInstance segmentationConvolutional neural networks
Keywords
OCCLUDED OBJECTS3-DRECONSTRUCTIONRECOGNITIONDISPLAY
ISSN
0143-8166
Abstract
A depth slice image that is computationally reconstructed from an integral imaging system consists of focused and out of focus areas. The unfocused areas affect three-dimensional (3D) image analyses and visualization including 3D object detection, extraction, and tracking. In this work, we present a deep learning integral imaging system that can reconstruct a 3D image without the out of focus areas and can accomplish target detection and segmentation at the same time. A Mask-Regional Convolutional Neural Network (Mask-RCNN) deep learning algorithm was trained using a public dataset and applied to detect and segment multiple targets in two-dimensional (2D) elemental images in the integral imaging system. The 3D images were then reconstructed using segmented elemental images with the target detected. The proposed method works well in the presence of partial occlusions. Experimental results show the performance of the proposed scheme. © 2021 Elsevier Ltd
URI
http://hdl.handle.net/20.500.11750/13756
DOI
10.1016/j.optlaseng.2021.106695
Publisher
Elsevier BV
Related Researcher
  • Author Moon, Inkyu Intelligent Imaging and Vision Systems Laboratory
  • Research Interests
Files:
There are no files associated with this item.
Collection:
Department of Robotics and Mechatronics EngineeringIntelligent Imaging and Vision Systems Laboratory1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE