![](bg1.png)
SCHOG Feature for Pedestrian Detection
Ryuichi Ozaki and Kazunori Onoguchi
Graduate School of Science and Technology, Hirosaki University, 3 Bunkyo-cho, Hirosaki, Aomori, 036-8561, Japan
Keywords:
Pedestrian detection, Co-occurrence Histograms of Oriented Gradients, Similarity, Support Vector Machine.
Abstract:
Co-occurrence Histograms of Oriented Gradients(CoHOG) has succeeded in describing the detailed shape of
the object by using a co-occurrence of features. However, unlike HOG, it does not consider the difference of
gradient magnitude between the foreground and the background. In addition, the dimension of the CoHOG
feature is also very large. In this paper, we propose Similarity Co-occurrence Histogram of Oriented Gradi-
ents(SCHOG) considering the similarity and co-occurrence of features. Unlike CoHOG which quantize edge
gradient direction to eight directions, SCHOG quantize it to four directions. Therefore, the feature dimen-
sion for the co-occurrence between edge gradient direction decreases greatly. In addition to the co-occurrence
between edge gradient directions the binary code representing the similarity between features is introduced.
In this paper, we use the pixel intensity, the edge gradient magnitude and the edge gradient direction as the
similarity. In spite of reducing the resolution of the edge gradient direction, SCHOG realizes higher perfor-
mance and lower dimension than CoHOG by adding this similarity. We have focused on pedestrian detection
in this paper. However, this method is also applicable to various object recognition by introducing various
kind of similarity. In experiments using the INRIA Person Dataset, SCHOG is evaluated in comparison with
the conventional CoHOG.
1 INTRODUCTION
Recently, a pedestrian detection system have been
put to practical use as a vehicle safety device(Hattori
et al., 2009). Since features expressing characteris-
tics of a person well is important in these system,
various features for pedestrian detection have been
proposed. T.Ojala et al. proposed the Local Binary
Pattern(LBP)(Ojala et al., 1996) representing the re-
lation between the intensity of an interest pixel and
the intensity of eight adjacent pixels. This feature
has been studied in various ways because it’s robust
to illumination change and it’s implemented easily.
Y.Cao et al. proposed the Advanced LBP(Cao Yun-
yun, 2011) which is robust to noise and low inten-
sity. N.Dalal proposed HOG(Dalal and Triggs, 2005)
feature which is robust to the change of the pedes-
trian’s posture and the change of the illumination by
generating the histogram of the edge gradient ori-
entation in each block and normalizing each block
for every cell. They also proposed the feature fo-
cusing on the gradient orientation of the time se-
ries(Dalal et al., 2006). T.Watanabe et al. proposed
CoHOG feature that represented the co-occurrence of
gradient orientation and showed high performance for
pedestrian detection. As other features using the co-
occurrence, T.Kobayashi et al. proposed a Gradient
Local Auto-Correlation(GLAC)(Kobayashiand Otsu,
2008) which calculated the autocorrelation of the po-
sition and edge gradient orientation. K.Yamaguchi
et al. proposed a two-dimensional gradient orienta-
tion histogram using polar coordinates which can ex-
press small difference(K. Yamaguchi, 2011). S.Walk
et al. proposed the Color Self-Similarity(CSS)(Walk
et al., 2010) feature using the similarity of HSV his-
togram in the local area. As mentioned above, the
co-occurrence of feature is effective for improving
the performance of pedestrian detection. However,
there is a problem that the dimension of the feature
increases significantly.
In this paper, we propose SCHOG which consists
of the co-occurrence of edge gradient direction and
the similarity. Although SCHOG quantizes edge gra-
dient direction to the half of CoHOG, it can represent
the shape of the object more finely than CoHOG by
adding the similarity to the co-occurrenceof edge gra-
dient direction. Because the similarity is represented
by the binary code, the dimension of SCHOG is a
half of the conventional CoHOG in spite of adding the
similarity. We evaluate three kind of similarity, such
as the pixel intensity, the edge gradient magnitude and
the edge gradient direction in the experiment. These
60
Ozaki R. and Onoguchi K..
SCHOG Feature for Pedestrian Detection.
DOI: 10.5220/0004813000600066
In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods (ICPRAM-2014), pages 60-66
ISBN: 978-989-758-018-5
Copyright
c
2014 SCITEPRESS (Science and Technology Publications, Lda.)