Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 461 - 480 of about 713 ／ All the affair displays >>

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

A Preliminary Study on the Relationship between Gaze Direction and Head Pose with Respect to Body

Nobuhiro Funatsu, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

2012 IEICE General Conference 2012.3.21

A Study on Facial Image Search Using Attributes Based on Impression

Yasunori Ozaki, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

2012 IEICE General Conference 2012.3.21

Super-resolution using facial pose variation

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

2012 IEICE General Conference 2012.3.21

A study on region-based matching for scene duplicate detection from news videos

Haruka Kumagai, Keisuke Doman, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (MVE) 2012.3.12

Digital Camera-Working for Cooking Videos Based on the Determination of Target Areas According to the Cooking Process

Wataru Hyogo, Yasuhiro Hayashi, Masafumi Noda, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (MVE) 2012.3.12

Extraction of Speech Shots Focusing on Visual and Audio Features within and between Shots

Shogo Kumagai, Keisuke Doman, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (MVE) 2012.3.12

Video retrieval by generic object recognition using spatio-temporal CoHOG features

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

Dynamic Image Processing for Real Application workshop (DIA2012) 2012.3.9

A Study on Image Features Considering Properties of Visual Search for Estimation of Pedestrian Detectability

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

Dynamic Image Processing for Real Application workshop (DIA2012) 2012.3.8

Prediction of driving behavior using gaze information and vehicle information

Tatsuki Kamisaka, Masafumi Noda, Yoshito Mekada, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

Dynamic Image Processing for Real Application workshop (DIA2012) 2012.3.8

Integration of generative learning and multiple pose classifiers for pedestrian detection International conference

Hidefumi Yoshida, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Kunihiro Goto, Yoshikatsu Kimura, Takashi Naito

International Conference on Computer Vision Theory and Applications (VISAPP) 2012 2012.2.26

Event date： 2012

Language：English Presentation type：Oral presentation (general)

Venue：Rome, Italy

Recently, pedestrian detection from in-vehicle camera images is becoming an important technology in ITS (Intelligent Transportation System).
However, it is difficult to detect pedestrians stably due to the variety of their poses and their backgrounds.
To tackle this problem, we propose a method to detect various pedestrians from in-vehicle camera images by using multiple classifiers corresponding to various pedestrian pose classes.
Since pedestrians’ pose varies widely, it is difficult to construct a single classifier that can detect pedestrians with various poses stably.
Therefore, this paper constructs multiple classifiers optimized for variously posed pedestrians by classifying pedestrian images into multiple pose classes.
Also, to reduce the bias and the cost for preparing numerous pedestrian images for each pose class for learning, the proposed method employs a generative learning method.
Finally, the proposed method constructs multiple classifiers by using the synthesized pedestrian images.
Experimental results showed that the detection accuracy of the proposed method outperformed comparative methods, and we confirmed that the proposed method could detect variously posed pedestrians stably.

DOI： 10.5220/0003817305670572

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.

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

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．

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -