Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 481 - 500 of about 727 ／ All the affair displays >>

Face recognition based on virtual frontal view generation using LVTM with local patches clustering

Xi Li, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (PRMU) 2012.2.9

Event date： 2012

Language：English Presentation type：Oral presentation (general)

Venue：東北大学

One of the major difficulties encountered by face recognition is the varying poses caused by in-depth rotations.
The intra-person appearance differences caused by rotations are often larger than the inter-person differences, which makes
the traditional face recognition methods such as eigen-face infeasible. This paper presents a framework for face recognition
across pose based on virtual frontal view generation using Local View Transition Model(LVTM) with local patches clustering.
Previous study on LVTM shows that more accurate appearance transition model can be achieved by first dividing the original
face image plane into overlapping local patch regions and then the learned transition models for each patch are aggregated for
the final transformation. In this paper we show that the accuracy the appearance transition model and the recognition rate can
be further improved by better exploiting the inherent linear relationship between frontal-nonfrontal face image pairs. This is
achieved based on the observation that variations in appearance caused by pose are closely related to the corresponding 3D
face structure and intuitively frontal-nonfrontal pairs from more similar local 3D face structures should have a stronger linear
relationship. For each specific location, instead of learning a common transformation as in LVTM, the corresponding local
patches are first clustered based on appearance similarity distance metric and then the transition models are learned separately
for each cluster. In the testing stage, each local patch for the input nonfrontal probe image is transformed using the learned
local view transition model corresponding to the most visually similar cluster. The experimental results on real life face dataset
demonstrate the effectiveness of the proposed method.

A study on a method for high-accuracy detection of a pedestrian holding an umbrella with generative learning

Hidefumi Yoshida, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takashi Machida, Yoshiko Kojima

IEICE Technical Report (PRMU) 2012.9.3

A Study on Event Detection in a Sports Game using Twitter

Taishi Tomita, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

HCG Symposium 2012 2012.12.11

Estimation of the human performance for pedestrian detectability based on visual search and motion features International conference

Masashi Wakayama, Daisuke Deguchi, Keisuke Doman, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

21st IAPR International Conference on Pattern Recognition (ICPR2012) 2012.11.14

Event date： 2012

Language：English Presentation type：Poster presentation

Venue：Tsukuba, Japan

This paper proposes a method for estimating the human performance of pedestrian detectability from in-vehicle camera images in order to warn a driver of the positions of pedestrians in an appropriate timing. By introducing features related to visual search and motion of the target, the proposed method estimates the detectability of pedestrians accurately. Support Vector Regression (SVR) is used to estimate the detectability. Here, SVR is trained using features calculated by the proposed method with the ground truth obtained through experiments with human subjects. From experiments using in-vehicle camera images, we confirmed that the proposed features were effective to estimate the detectability of pedestrians.

A Preliminary Study on Image Features for Visibility Estimation of Traffic Signals in Raining Conditions

Ryuhei Sato, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

2012 IEICE General Conference 2012.3.22

Looking back on past PRMU Algorithm Contests

Daisuke Deguchi, Yoshinari Kameda, Itaru Kitahara, Kazuaki Kondo, Atsushi Shimada, Shinsaku Hiura

IEICE Technical Report (PRMU) 2012.9.3

Detection and classification of repetitious human motions combining shift variant and invariant features International conference

Ichiro Ide, Taku Kuhara, Daisuke Deguchi, Tomokazu Takahashi, Hiroshi Murase

3rd International Conference on Emerging Security Technologies (EST2012) 2012.9

多数決型co-trainingによる道路標識検出器の構築に関する検討

児島勇司, 出口大輔, 井手一郎, 村瀬洋

画像の認識・理解シンポジウム(MIRU) 2012.8.8

顔と体の姿勢情報を利用した人物動画像からの視線方向推定に関する検討

船津暢宏, 高橋友和, 出口大輔, 井手一郎, 村瀬洋

画像の認識・理解シンポジウム(MIRU) 2012.8.8

Event date： 2012

Language：Japanese Presentation type：Poster presentation

Venue：福岡国際会議場

カメラを用いて人物の視線方向を推定する技術が注目されている．これに関して，低解像度や遮蔽などが原因で画像中から人物の目領域を検出するのが困難な場合に，顔の向きを視線方向の代わりとして利用する研究がある．しかしながら，実際には顔の向きの他にも，体の向きやそれらの時間変化，人物がおかれている状況なども視線方向に影響を与える要因として考えられる．そこで本研究では，これらの情報を利用して視線方向をより高精度に推定することを目的としている．発表ではそれらの要因のうち，特に顔の向きと体の向き着目し，体に対する顔の向きと視線方向との関係を被験者実験により調査した結果について報告する．さらに，その調査結果に基づいた視線方向推定を行い，その推定誤差を評価した．その結果，体に対する顔の向きを利用した場合，顔の向きを視線方向として利用する場合よりも推定誤差が平均 14.9 度小さくなることを確認した．

Estimation of traffic sign visibility considering global features in an entire scene

Keisuke Doman, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

15th Meeting on Image Recognition & Understanding (MIRU2012) 2012.8.8

過去の車載カメラ映像との時空間差分による不特定障害物検出

久徳遙矢, 出口大輔, 高橋友和, 目加田慶人, 井手一郎, 村瀬洋

画像の認識・理解シンポジウム(MIRU) 2012.8.7

Event date： 2012

Language：Japanese Presentation type：Poster presentation

Venue：福岡国際会議場

本研究の目的は，前方を向いた車載カメラ映像から障害物を検出することである．車載カメラ映像からの障害物検出に関する研究は広く行なわれているが，多くは車両や人物といった特定の検出対象の見えを学習して行なうものであり，事前に学習することができない，段ボール箱や積荷の落下物などの不特定の障害物への対応はできない．そこで提案手法では，同一地点における過去の車載カメラ映像との差分を用いて不特定の前方障害物を検出する．しかし，過去の走行映像は走行位置の違いによる視点のずれを含み，直接的に差分を求めることは困難である．そこで，まず既存手法により現在と過去の映像中のフレーム間対応付けを行なう．そして，対応付いたフレーム同士の道路面を射影変換によって位置合わせする．最後に，対象までの距離を考慮した道路面時空間画像差分により障害物を検出する．評価実験から，ボールなどの不特定の障害物を検出できることを確認した．

Visibility Estimation of Traffic Signals in Rainy Conditions Considering the Visual Noise

Ryuhei Sato, Keisuke Doman, Daisuke Deguchi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase, Yukimasa Tamatsu

15th Meeting on Image Recognition & Understanding (MIRU2012) 2012.8.7

Robust Face Super-Resolution Using Free-Form Deformations For Low-Quality Surveillance Video International conference

Tomonari Yoshida, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

2012 IEEE International Conference on Multimedia and Expo (ICME2012) 2012.7.10

Cook-Log Video Summarization by Removing Temporal Redundancy

Yasuhiro Hayashi, Keisuke Doman, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (DE) 2012.6.6

Construction of a local attraction map according to social visual attention International conference

Ichiro Ide, Jiani Wang, Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Hiroshi Murase

5th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2012) 2012.5

A study on General Obstacle Detection by Spatio-Temporal Subtraction with Past In-Vehicle Camera Image Sequence

Haruya Kyutoku, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (PRMU) 2012.3.30

Method for displaying Images on Urban Structures by Augmented Reality

Hiroyuki Uchiyama, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Takahito Kawanishi, Kunio Kashino

IEICE Technical Report (PRMU) 2012.3.29

A Study on Spatio-Temporal CoHOG Features for Recognition of Generic Objects in Video

Shogo Nakamura, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (PRMU) 2011.12.15

PRMU Algorithm Contest 2010 "Lock on targets! - object tracking -"

Daisuke Deguchi, Hiroshi Murase, Kazuaki Umeda, Masataka Saito, Kenichiro Fuji, Shingo Yamashita, Yuki Suetsugu, Syota Takai, Ryuta Sato, Takuma Maruyama

IEICE Technical Report (PRMU) 2011.3

Pedestrian Detection from In-vehicle Camera Images using Scene Context Information

Daisuke Hamada, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

2011 IEICE General Conference 2011.3

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -