YOLORIS: YOLO for Real-time Instance Segmentation
碩士 === 國立交通大學 === 資訊科學與工程研究所 === 108 === In recent years, image segmentation has become an important issue, and been used in many fields like self-driving cars, computer vision, video tracking, medical use and so on. Therefore, there are many researchers devote themselves into this challenge. Image...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/yyu3py |
id |
ndltd-TW-108NCTU5394001 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-108NCTU53940012019-11-26T05:16:53Z http://ndltd.ncl.edu.tw/handle/yyu3py YOLORIS: YOLO for Real-time Instance Segmentation 基於YOLO物體偵測進行即時的實例分割 Lu, Yan-Ting 盧彥廷 碩士 國立交通大學 資訊科學與工程研究所 108 In recent years, image segmentation has become an important issue, and been used in many fields like self-driving cars, computer vision, video tracking, medical use and so on. Therefore, there are many researchers devote themselves into this challenge. Image segmentation is to classify image in pixel-wise, making machine to learn and realize locations and classes of instances in images. However, predicting instances precisely is a critical issue. There are many papers work on it, but most of them focus on accuracy instead of speed, needing lots of hardware to support. In this paper, we present a real-time and good performance method that only need one GPU to support which is based on YOLOv3. Tsai, Wen-Jiin Chen, Hua-Tsung 蔡文錦 陳華總 2019 學位論文 ; thesis 27 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立交通大學 === 資訊科學與工程研究所 === 108 === In recent years, image segmentation has become an important issue, and been used in many fields like self-driving cars, computer vision, video tracking, medical use and so on. Therefore, there are many researchers devote themselves into this challenge. Image segmentation is to classify image in pixel-wise, making machine to learn and realize locations and classes of instances in images. However, predicting instances precisely is a critical issue. There are many papers work on it, but most of them focus on accuracy instead of speed, needing lots of hardware to support.
In this paper, we present a real-time and good performance method that only need one GPU to support which is based on YOLOv3.
|
author2 |
Tsai, Wen-Jiin |
author_facet |
Tsai, Wen-Jiin Lu, Yan-Ting 盧彥廷 |
author |
Lu, Yan-Ting 盧彥廷 |
spellingShingle |
Lu, Yan-Ting 盧彥廷 YOLORIS: YOLO for Real-time Instance Segmentation |
author_sort |
Lu, Yan-Ting |
title |
YOLORIS: YOLO for Real-time Instance Segmentation |
title_short |
YOLORIS: YOLO for Real-time Instance Segmentation |
title_full |
YOLORIS: YOLO for Real-time Instance Segmentation |
title_fullStr |
YOLORIS: YOLO for Real-time Instance Segmentation |
title_full_unstemmed |
YOLORIS: YOLO for Real-time Instance Segmentation |
title_sort |
yoloris: yolo for real-time instance segmentation |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/yyu3py |
work_keys_str_mv |
AT luyanting yolorisyoloforrealtimeinstancesegmentation AT lúyàntíng yolorisyoloforrealtimeinstancesegmentation AT luyanting jīyúyolowùtǐzhēncèjìnxíngjíshídeshílìfēngē AT lúyàntíng jīyúyolowùtǐzhēncèjìnxíngjíshídeshílìfēngē |
_version_ |
1719296650172694528 |