• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Lu, Zhoumin (Lu, Zhoumin.) [1] | Xu, Haiping (Xu, Haiping.) [2] | Liu, Genggeng (Liu, Genggeng.) [3] (Scholars:刘耿耿)

Indexed by:

EI Scopus SCIE

Abstract:

It is widely acknowledged that object segmentation is a significant research field for computer vision and a key process for many other visual tasks. In the past unsupervised single-image segmentation, there are often cases where the segmentation result is not good. In the current supervised single-image segmentation, it is necessary to rely on a large number of data annotations and long-term training of the model. Then, people attempted to segment simultaneously the common regions from multiple images. On the one hand, it does not need to use a large amount of labeled data to train in advance. On the other hand, it utilizes the consistency constraint between images to better obtain the object information. This idea can generate better performance than the traditional one did, resulting in many methods related to object co-segmentation. This paper reviews some classic and effective object co-segmentation methods, including saliency-based approaches, joint-processing-based approaches, graph-based approaches, and others. For different methods, we select two or three related models to elaborate, such as a model based on random walks. Moreover, in order to exhibit and evaluate these methods objectively and comprehensively, we not only summarize them in the form of flowcharts and algorithm summaries, but also compare their performance with visualization methods and evaluation metrics, such as intersection-over-union, consistency error, and precision-recall rate. From the experiment, we also attempt to clarify and analyze the existing problems. Finally, we point out the challenges and directions and open new venues for future researchers in thefield.

Keyword:

Computer vision joint processing model evaluation object co-segmentation saliency semantic segmentation

Community:

  • [ 1 ] [Lu, Zhoumin]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China
  • [ 2 ] [Liu, Genggeng]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China
  • [ 3 ] [Lu, Zhoumin]Fujian Prov Key Lab Network Comp & Intelligent In, Fuzhou 350116, Fujian, Peoples R China
  • [ 4 ] [Liu, Genggeng]Fujian Prov Key Lab Network Comp & Intelligent In, Fuzhou 350116, Fujian, Peoples R China
  • [ 5 ] [Xu, Haiping]Minjiang Univ, Coll Math & Data Sci, Fuzhou 350108, Fujian, Peoples R China

Reprint 's Address:

  • 刘耿耿

    [Liu, Genggeng]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China;;[Liu, Genggeng]Fujian Prov Key Lab Network Comp & Intelligent In, Fuzhou 350116, Fujian, Peoples R China

Show more details

Version:

Related Keywords:

Related Article:

Source :

IEEE ACCESS

ISSN: 2169-3536

Year: 2019

Volume: 7

Page: 62875-62893

3 . 7 4 5

JCR@2019

3 . 4 0 0

JCR@2023

ESI Discipline: ENGINEERING;

ESI HC Threshold:150

JCR Journal Grade:1

CAS Journal Grade:2

Cited Count:

WoS CC Cited Count: 5

SCOPUS Cited Count: 8

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 0

Online/Total:130/10048525
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1