Takahiro Okabe

Dr. Takahiro Okabe


Research Focus & Metrics

Academic Career Length

36Years (1991-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 May 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
TMTetsu Matsukawa
Tetsu Matsukawa
TOTakahiro Okabe
Takahiro Okabe
ESEinoshin Suzuki
Einoshin Suzuki
YSYoichi Sato
Yoichi Sato
Describing the color and textural information of a person image is one of the most crucial aspects of person re-identification (re-id). Although a covariance descriptor has been successfully applied to person re-id, it loses the local structure of a region and mean information of pixel features, both of which tend to be the major discriminative information for person re-id. In this paper, we present novel meta-descriptors based on a hierarchical Gaussian distribution of pixel features, in which both mean and covariance information are included in patch and region level descriptions. More specifically, the region is modeled as a set of multiple Gaussian distributions, each of which represents the appearance of a local patch. The characteristics of the set of Gaussian distributions are again described by another Gaussian distribution. Because the space of Gaussian distribution is not a linear space, we embed the parameters of the distribution into a point of Symmetric Positive Definite (SPD) matrix manifold in both steps. We show, for the first time, that normalizing the scale of the SPD matrix enhances the hierarchical feature representation on this manifold. Additionally, we develop feature norm normalization methods with the ability to alleviate the biased trends that exist on the SPD matrix descriptors. The experimental results conducted on five public datasets indicate the effectiveness of the proposed descriptors and the two types of normalizations.

12 January 2015 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
FLFeng Lu
Feng Lu
YMYasuyuki Matsushita
Yasuyuki Matsushita
ISImari Sato
Imari Sato
TOTakahiro Okabe
Takahiro Okabe
YSYoichi Sato
Yoichi Sato
We propose an uncalibrated photometric stereo method that works with general and unknown isotropic reflectances. Our method uses a pixel intensity profile, which is a sequence of radiance intensities recorded at a pixel under unknown varying directional illumination. We show that for general isotropic materials and uniformly distributed light directions, the geodesic distance between intensity profiles is linearly related to the angular difference of their corresponding surface normals, and that the intensity distribution of the intensity profile reveals reflectance properties. Based on these observations, we develop two methods for surface normal estimation; one for a general setting that uses only the recorded intensity profiles, the other for the case where a BRDF database is available while the exact BRDF of the target scene is still unknown. Quantitative and qualitative evaluations are conducted using both synthetic and real-world scenes, which show the state-of-the-art accuracy of smaller than 10 degree without using reference data and 5 degree with reference data for all 100 materials in MERL database.

16 August 2005
Verified
Conference Paper
Closed access
TOTakahiro Okabe
Takahiro Okabe
TST. Shizuno
T. Shizuno
TKT. Kitamura
T. Kitamura

1 December 2016
Verified
Conference Paper
Closed access
KMKayano Maeda
Kayano Maeda
TOTakahiro Okabe
Takahiro Okabe
Acquiring the light transport (LT) of a scene is important for various applications such as radiometric analysis, image-based relighting, and controlling appearance of the scene. The multispectral LT, i.e. the LT in multiple primary colors enables us not only to enhance the color gamut but also to investigate wavelength-dependent interactions between light and a scene. In this paper, we propose a method for acquiring the multispectral LT by using a single off-the-shelf multi-primary DLP (Digital Light Processing) projector; it does not require any self-built equipment, geometric registration, and temporal synchronization. Specifically, based on the rapid color switch due to a rotating color wheel in the projector, we present a method for estimating the spectral properties of the projector in a non-destructive manner, and a method for acquiring the images of a scene illuminated only by one of the primary colors. We conducted a number of experiments by using real images, and confirmed that our method works well and the acquired multispectral LT is effective for radiometric analysis and image-based relighting.

1 December 1991 in IEEE Transactions on Nuclear Science
Verified
Journal Article
Closed access
MKM. Kato
M. Kato
KWKenji Watanabe
Kenji Watanabe
TOTakahiro Okabe
Takahiro Okabe

17 May 2022
Verified
Book Chapter
Closed access
PDF file
HTHirochika Tanikawa
Hirochika Tanikawa
RKRyo Kawahara
Ryo Kawahara
TOTakahiro Okabe
Takahiro Okabe