Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 461 - 480 of about 698 ／ All the affair displays >>

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.

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

3-D Line Segment Reconstruction Using an In-Vehicle Camera for Free Space Detection International conference

Hiroyuki Uchiyama, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

2011 IEEE Intelligent Vehicles Symposium (IV2011) 2011.6.6

Event date： 2011

Language：English Presentation type：Poster presentation

Venue：Baden-Baden, Germany

Free space detection is very important for vehicle navigation and safe driving. 3-D line segment reconstruction
of a street is important for the free space detection because a street-view includes many line segments. For the free space
detection, we propose a method for reconstructing 3-D line segments in a streetscape using a monocular in-vehicle camera.
The 3-D reconstruction of the line segments is achieved by using each three images from an image sequence. Once accurate
camera poses of these images are obtained, one of the remaining crucial problems is to match the line segments between the
images correctly. A strategy for finding correspondence of the line segments is as follows: First, the correspondences of line
segment candidates are searched by using a two-view constraint. However, the two-view constraint has difficulty on determining
an unique correspondence geometrically. Therefore, the candidates of the line segment correspondences are reduced using
a three-view constraint. In order to improve the accuracy, the proposed method exploits a color feature of the line segment
and a preliminary knowledge of the vehicle motion. Finally, the line segments are reconstructed using the correspondences.
From an experimental result, we confirmed the effectiveness of the proposed method. Application to the free space detection
demonstrated the usefulness of the reconstructed line segments.

Intelligent Traffic Sign Detector: Adaptive Learning Based on Online Gathering of Training Samples International conference

Daisuke Deguchi, Mitsunori Shirasuna, Keisuke Doman, Ichiro Ide, Hiroshi Murase

2011 IEEE Intelligent Vehicles Symposium (IV2011) 2011.6.6

Event date： 2011

Language：English Presentation type：Poster presentation

Venue：Baden-Baden, Germany

This paper proposes an intelligent traffic sign detector using adaptive learning based on online gathering of training samples from in-vehicle camera image sequences. To detect traffic signs accurately from in-vehicle camera images, various training samples of traffic signs are needed. In addition, to reduce false alarms, various background images should also be prepared before constructing the detector. However, since their appearances vary widely, it is difficult to obtain them exhaustively by manual intervention. Therefore, the proposed method simultaneously obtains both traffic sign images and background images from in-vehicle camera images. Especially, to reduce false alarms, the proposed method gathers background images that were easily mis-detected by a previously constructed traffic sign detector, and re-trains the detector by using them as negative samples. By using retrospectively tracked traffic sign images and background images as positive and negative training samples, respectively, the proposed method constructs a highly accurate traffic sign detector automatically. Experimental results showed the effectiveness of the proposed method.

GPGPUによる高速画像処理

出口大輔

日本ロボット学会ロボット工学セミナー第62回シンポジウム「ロボットに使える画像処理技術の最前線」 2011.5.30

Event date： 2011

Language：Japanese Presentation type：Oral presentation (general)

Venue：東京大学武田先端知ビル5F 武田ホール

GPUを汎用計算に利用しようという試みであるGPGPU（General Purpose computing on GPUs）は，近年のGPUの高性能化およびその入手しやすさという特徴から，幅広い分野で高速計算に利用されるようになってきた．一方，画像処理アルゴリズムの多くは並列計算可能なものが多く，少しアルゴリズムを工夫することでCPUの数十倍の高速化を達成できるものも多く存在する．そこで，本講演ではGPGPUを手軽に利用できるCUDAを開発環境として利用し，実例を交えながら計算コストの高い画像処理を簡単に高速化できることを示す．

A Study on Road Image Generation by Mosaicing of In-Vehicle Camera Images Using Aerial Image as a Reference

Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

IEICE Technical Report (PRMU) 2011.5.20

Road Image Update using In-vehicle Camera Images and Aerial Image International conference

Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima, Takashi Naito

2011 IEEE Intelligent Vehicles Symposium (IV2011) 2011.6.7

Event date： 2011

Language：English Presentation type：Poster presentation

Venue：Baden-Baden, Germany

Road image is becoming important for several
applications such as car navigation systems, traffic environment
research, city modeling. Usually, a road image can be obtained
from an aerial image but the resolution of the aerial image is
often low, or it contains occlusions by obstacles. Therefore, the
update of road image is required. In this paper, we propose a
road image mosaicing method using in-vehicle camera images
and an aerial image. We first perform image registration of road
regions between these images, and then, we generate a large road
image by performing image mosaicing of road regions in invehicle
camera images. In an experiment, we achieved resolution
improvement and occlusions removal, and also succeeded in
update of a large road image.

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

Pedestrian Detection with Generative Learning Method Considering Varying Pose

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

2011 IEICE General Conference 2011.3

Person Re-identification at a Room Entrance by Adaptive Feature Selection

Takuya Honda, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (PRMU) 2011.3

Proposal of a Sight-seeing Map with Visual Classification and Presentation of Photos on the Web

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

IEICE Technical Report (MVE) 2011.3

Scene Segmentation of a Wedding Party Video by Scenario-based Matching with Example Videos

Kazuki Sawai, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (MVE) 2011.3

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -