Multi-class Video Objects Segmentation Based on Conditional Random Fields

Video object segmentation has been widely used in many fields. A conditional random fields (CRF) model is proposed to achieve accurate multi-class segmentation of video objects in the complex environment. By using CRF, the color, texture, motion characteristics and neighborhood relations of objects...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Sensors & transducers Ročník 163; číslo 1; s. 74
Hlavní autoři: He, Zhiwei, Xu, Lijun, Zhao, Wei, Gao, Mingyu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Toronto IFSA Publishing, S.L 01.01.2014
Témata:
Algorithms
Classification
Color
Dealing
Energy use
Mathematical models
Neighborhoods
Protein folding
Random variables
Segmentation
Standard deviation
Surface layer
Texture
Transducers
ISSN:2306-8515, 1726-5479, 1726-5479
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Video object segmentation has been widely used in many fields. A conditional random fields (CRF) model is proposed to achieve accurate multi-class segmentation of video objects in the complex environment. By using CRF, the color, texture, motion characteristics and neighborhood relations of objects are modeled to construct the corresponding energy functions in both the temporal and spatial domains. The model is trained with annotated samples by using LogitBoost classifier. The energy function is amended by adding a constraint factor which is used to indicate the interaction between two adjacent images in the video sequence. Experimental results show that the proposed algorithm can achieve high performance for multi-class objects segmentation in videos under complex environment. It can also get good recognition results when dealing with multi-viewed objects or serious sheltered objects. [PUBLICATION ABSTRACT]
Bibliografie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:2306-8515
1726-5479
1726-5479