A Study on Data Augmentation for Object Detection based on Image Synthesis using 3D model
碩士 === 國立中興大學 === 資訊科學與工程學系所 === 107 === In this thesis, we validate the idea of using 3D models to generate 2D image dataset for training object detection model as a mechanism of data augmentation. The idea is to rotate 3D models to generate images of different angles and synthesize the images with...
Main Authors: | Shu-Yi Wu, 吳書逸 |
---|---|
Other Authors: | Yao-Chung Fan |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/5de7rf |
Similar Items
-
Interactive 3D Modeling System based on Augmented Reality Technologies for Fundamental Shape Objects
by: Tzu-Yi Wu, et al.
Published: (2017) -
Synthesis of navigable 3-D environments from human-augmented image data
by: Antone, Matthew E
Published: (2005) -
Point Cloud Data Augmentation for Safe 3D Object Detection using Geometric Techniques
by: Kapoor, Shrayash
Published: (2021) -
Perspective Transformation Data Augmentation for Object Detection
by: Ke Wang, et al.
Published: (2020-01-01) -
Augmented 3D Objecte in Painting by Example-based Texture Synthesis
by: 邱雅菁
Published: (2007)