In this paper, a feature named Non-Redundant Gradient Semantic Local Binary Patterns (NRGSLBP) is proposed for human detection as a modified version of the conventional Semantic Local Binary Patterns (SLBP). Calculations of this feature are performed for both intensity and gradient magnitude image so that texture and gradient information are combined. Moreover, and to the best of our knowledge, non-redundant patterns are adopted on SLBP for the first time, allowing better discrimination. Compared with SLBP, no additional cost of the feature dimensions of NRGSLBP is necessary, and the calculation complexity is considerably smaller than that of other features. Experimental results on several datasets show that the detection rate of our proposed feature outperforms those of other features such as Histogram of Orientated Gradient (HOG), Histogram of Templates (HOT), Bidirectional Local Template Patterns (BLTP), Gradient Local Binary Patterns (GLBP), SLBP and Covariance matrix (COV).
Jiu XU
Waseda University
Ning JIANG
Waseda University
Wenxin YU
Waseda University
Heming SUN
Waseda University
Satoshi GOTO
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Jiu XU, Ning JIANG, Wenxin YU, Heming SUN, Satoshi GOTO, "Human Detection Method Based on Non-Redundant Gradient Semantic Local Binary Patterns" in IEICE TRANSACTIONS on Fundamentals,
vol. E98-A, no. 8, pp. 1735-1742, August 2015, doi: 10.1587/transfun.E98.A.1735.
Abstract: In this paper, a feature named Non-Redundant Gradient Semantic Local Binary Patterns (NRGSLBP) is proposed for human detection as a modified version of the conventional Semantic Local Binary Patterns (SLBP). Calculations of this feature are performed for both intensity and gradient magnitude image so that texture and gradient information are combined. Moreover, and to the best of our knowledge, non-redundant patterns are adopted on SLBP for the first time, allowing better discrimination. Compared with SLBP, no additional cost of the feature dimensions of NRGSLBP is necessary, and the calculation complexity is considerably smaller than that of other features. Experimental results on several datasets show that the detection rate of our proposed feature outperforms those of other features such as Histogram of Orientated Gradient (HOG), Histogram of Templates (HOT), Bidirectional Local Template Patterns (BLTP), Gradient Local Binary Patterns (GLBP), SLBP and Covariance matrix (COV).
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E98.A.1735/_p
Copy
@ARTICLE{e98-a_8_1735,
author={Jiu XU, Ning JIANG, Wenxin YU, Heming SUN, Satoshi GOTO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Human Detection Method Based on Non-Redundant Gradient Semantic Local Binary Patterns},
year={2015},
volume={E98-A},
number={8},
pages={1735-1742},
abstract={In this paper, a feature named Non-Redundant Gradient Semantic Local Binary Patterns (NRGSLBP) is proposed for human detection as a modified version of the conventional Semantic Local Binary Patterns (SLBP). Calculations of this feature are performed for both intensity and gradient magnitude image so that texture and gradient information are combined. Moreover, and to the best of our knowledge, non-redundant patterns are adopted on SLBP for the first time, allowing better discrimination. Compared with SLBP, no additional cost of the feature dimensions of NRGSLBP is necessary, and the calculation complexity is considerably smaller than that of other features. Experimental results on several datasets show that the detection rate of our proposed feature outperforms those of other features such as Histogram of Orientated Gradient (HOG), Histogram of Templates (HOT), Bidirectional Local Template Patterns (BLTP), Gradient Local Binary Patterns (GLBP), SLBP and Covariance matrix (COV).},
keywords={},
doi={10.1587/transfun.E98.A.1735},
ISSN={1745-1337},
month={August},}
Copy
TY - JOUR
TI - Human Detection Method Based on Non-Redundant Gradient Semantic Local Binary Patterns
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1735
EP - 1742
AU - Jiu XU
AU - Ning JIANG
AU - Wenxin YU
AU - Heming SUN
AU - Satoshi GOTO
PY - 2015
DO - 10.1587/transfun.E98.A.1735
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E98-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2015
AB - In this paper, a feature named Non-Redundant Gradient Semantic Local Binary Patterns (NRGSLBP) is proposed for human detection as a modified version of the conventional Semantic Local Binary Patterns (SLBP). Calculations of this feature are performed for both intensity and gradient magnitude image so that texture and gradient information are combined. Moreover, and to the best of our knowledge, non-redundant patterns are adopted on SLBP for the first time, allowing better discrimination. Compared with SLBP, no additional cost of the feature dimensions of NRGSLBP is necessary, and the calculation complexity is considerably smaller than that of other features. Experimental results on several datasets show that the detection rate of our proposed feature outperforms those of other features such as Histogram of Orientated Gradient (HOG), Histogram of Templates (HOT), Bidirectional Local Template Patterns (BLTP), Gradient Local Binary Patterns (GLBP), SLBP and Covariance matrix (COV).
ER -