Segmentation of bottom shadow of vehicle based on improved PSO-MBCV algorithm

Meng Yin Fu; Lu Jin; Mei Ling Wang; Yi Yang

doi:10.3969/j.issn.1001-506X.2014.07.34

Segmentation of bottom shadow of vehicle based on improved PSO-MBCV algorithm

Meng Yin Fu^*, Lu Jin, Mei Ling Wang, Yi Yang

^*Corresponding author for this work

School of Automation

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

The current segmentation algorithms of bottom shadow of vehicle have poor robustness, meanwhile, the multilevel thresholds segmentation algorithm of maximum between-class variance (MBCV) method does not determine automatically the number of the thresholds. Therefore, firstly, the peak adaptive method based on image histogram is used to determine the number of thresholds; then, the number is considered as the particle dimension of the particle swarm optimization (PSO) algorithm, and the bottom shadow of vehicles based on an improved PSO-MBCV algorithm is proposed. The results show that the misclassification error (ME) can be deduced and the bottom shadow of vehicles can be effectively segmented.

Original language	English
Pages (from-to)	1439-1445
Number of pages	7
Journal	Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics
Volume	36
Issue number	7
DOIs	https://doi.org/10.3969/j.issn.1001-506X.2014.07.34
Publication status	Published - Jul 2014

Keywords

Maximum between-class variance (MBCV)
Misclassification error (ME)
Particle swarm optimization (PSO) algorithm
Peak adaptive method

Access to Document

10.3969/j.issn.1001-506X.2014.07.34

Cite this

@article{0c6caa0726884f9aae09c0e78b31b7ff,

title = "Segmentation of bottom shadow of vehicle based on improved PSO-MBCV algorithm",

abstract = "The current segmentation algorithms of bottom shadow of vehicle have poor robustness, meanwhile, the multilevel thresholds segmentation algorithm of maximum between-class variance (MBCV) method does not determine automatically the number of the thresholds. Therefore, firstly, the peak adaptive method based on image histogram is used to determine the number of thresholds; then, the number is considered as the particle dimension of the particle swarm optimization (PSO) algorithm, and the bottom shadow of vehicles based on an improved PSO-MBCV algorithm is proposed. The results show that the misclassification error (ME) can be deduced and the bottom shadow of vehicles can be effectively segmented.",

keywords = "Maximum between-class variance (MBCV), Misclassification error (ME), Particle swarm optimization (PSO) algorithm, Peak adaptive method",

author = "Fu, {Meng Yin} and Lu Jin and Wang, {Mei Ling} and Yi Yang",

year = "2014",

month = jul,

doi = "10.3969/j.issn.1001-506X.2014.07.34",

language = "English",

volume = "36",

pages = "1439--1445",

journal = "Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics",

issn = "1001-506X",

publisher = "Chinese Institute of Electronics",

number = "7",

}

TY - JOUR

T1 - Segmentation of bottom shadow of vehicle based on improved PSO-MBCV algorithm

AU - Fu, Meng Yin

AU - Jin, Lu

AU - Wang, Mei Ling

AU - Yang, Yi

PY - 2014/7

Y1 - 2014/7

N2 - The current segmentation algorithms of bottom shadow of vehicle have poor robustness, meanwhile, the multilevel thresholds segmentation algorithm of maximum between-class variance (MBCV) method does not determine automatically the number of the thresholds. Therefore, firstly, the peak adaptive method based on image histogram is used to determine the number of thresholds; then, the number is considered as the particle dimension of the particle swarm optimization (PSO) algorithm, and the bottom shadow of vehicles based on an improved PSO-MBCV algorithm is proposed. The results show that the misclassification error (ME) can be deduced and the bottom shadow of vehicles can be effectively segmented.

AB - The current segmentation algorithms of bottom shadow of vehicle have poor robustness, meanwhile, the multilevel thresholds segmentation algorithm of maximum between-class variance (MBCV) method does not determine automatically the number of the thresholds. Therefore, firstly, the peak adaptive method based on image histogram is used to determine the number of thresholds; then, the number is considered as the particle dimension of the particle swarm optimization (PSO) algorithm, and the bottom shadow of vehicles based on an improved PSO-MBCV algorithm is proposed. The results show that the misclassification error (ME) can be deduced and the bottom shadow of vehicles can be effectively segmented.

KW - Maximum between-class variance (MBCV)

KW - Misclassification error (ME)

KW - Particle swarm optimization (PSO) algorithm

KW - Peak adaptive method

UR - http://www.scopus.com/inward/record.url?scp=84905382991&partnerID=8YFLogxK

U2 - 10.3969/j.issn.1001-506X.2014.07.34

DO - 10.3969/j.issn.1001-506X.2014.07.34

M3 - Article

AN - SCOPUS:84905382991

SN - 1001-506X

VL - 36

SP - 1439

EP - 1445

JO - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

JF - Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics

IS - 7

ER -

Segmentation of bottom shadow of vehicle based on improved PSO-MBCV algorithm

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this