Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 61 - 80 of about 727 ／ All the affair displays >>

Detection of Birds in a 3D Environment Referring to Audio-Visual Information International conference

Yasutomo Kawanishi, Ichiro Ide, Baidong Chu, Chihaya Matsuhira, Marc A. Kastner, Takahiro Komamizu, Daisuke Deguchi

18th IEEE International Conference on Advanced Video and Signal-Based Surveillance 2022.11.29

Event date： 2022

Language：English Presentation type：Oral presentation (general)

Venue：Universidad Autónoma de Madrid (Hybrid)

We propose a method to detect birds in a 3D environment referring to both audio information observed from a microphone array and visual information observed from a panorama camera. In general, in panorama images, birds appear relatively too small to be detected accurately even with the state-of-the-art deep learning models. Thus, the proposed method takes a two step approach where the birds are first roughly located referring to audio information by Sound Source Localization (SSL), and then image detection is applied within its vicinity. Through evaluation on a dataset annotated with bounding boxes surrounding the birds, we show that the proposed method improves detection performance of birds that appear in relatively small sizes in the image, in both accuracy and processing speed.

DOI： 10.1109/AVSS56176.2022.9959510

人物姿勢に着目した後ろ向き人物の注視領域推定

弓矢隼大, 出口大輔, 川西康友, 村瀬洋

コンピュータビジョンとイメージメディア研究会(CVIM) 2022.11.19

A Preliminary Study on 4D Scene Modeling from Live-action Video Including Pedestrians

田中来樹, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

IEICE General Conference 2021.3.12

LFIR2Pose: Pose Estimation from an Extremely Low-Resolution FIR Image Sequence International conference

Saki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa

25th International Conference on Pattern Recognition 2021.1.13

Event date： 2021

Language：English Presentation type：Poster presentation

Venue：Milan, Italy (Virtual)

In this paper, we propose a method for human pose estimation from a Low-resolution Far-InfraRed (LFIR) image sequence captured by a 16 × 16 FIR sensor array. Human body estimation from such a single LFIR image is a hard task. For training the estimation model, annotation of the human pose to the images is also a difficult task for human. Thus, we propose the LFIR2Pose model which accepts a sequence of LFIR images and outputs the human pose of the last frame, and also propose an automatic annotation system for the model training. Additionally, considering that the scale of human body motion is largely different among body parts, we also propose a loss function focusing on the difference. Through an experiment, we evaluated the human pose estimation accuracy using an original data set, and confirmed that human pose can be estimated accurately from an LFIR image sequence.

Median-Shape Representation Learning for Category-Level Object Pose Estimation in Cluttered Environments International conference

Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Ayako Amma, Hiroshi Murase

25th International Conference on Pattern Recognition 2021.1.13

Event date： 2021

Language：English Presentation type：Poster presentation

Venue：Milan, Italy (Virtual)

In this paper, we propose an occlusion-robust pose
estimation method of an unknown object instance in an
object category from a depth image. In a cluttered
environment, objects are often occluded mutually. For
estimating the pose of an object in such a situation, a
method that de-occludes the unobservable area of the object
would be effective. However, there are two difficulties;
occlusion causes offset between the actual object center
and the center of its observable area, and different
instances in a category may have different shapes. To cope
with these difficulties, we propose a two-stage
Encoder-Decoder model to extract features with objects
whose centers are aligned to the image center. In the
model, we also propose the Median-shape Reconstructor as
the second stage to absorb shape variations in a category.
By evaluating the method with both a large-scale virtual
dataset and a real dataset, we confirmed the proposed
method achieves good performance on pose estimation of an
occluded object from a depth image.

OMEga-GAN: Object Manifold Embedding GAN for Image Generation by Disentangling Parameters into Pose and Shape Manifolds International conference

Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

25th International Conference on Pattern Recognition 2021.1.13

Event date： 2021

Language：English Presentation type：Poster presentation

Venue：Milan, Italy (Virtual)

In this paper, we propose Object Manifold Embedding GAN (Ω-GAN) to generate images of variously shaped and arbitrarily posed objects from a noise variable sampled from a distribution defined over the pose and the shape manifolds in a vector space. We introduce Parametric Manifold Sampling to sample noise variables from a distribution over the pose manifold to conditionally generate object images in arbitrary poses by tuning the pose parameter. We also introduce Object Identity Loss for clearly disentangling the pose and shape parameters, which allows us to maintain the shape of the object instance when only the pose parameter is changed. Through evaluation, we confirmed that the proposed Ω-GAN could generate variously shaped object images in arbitrary poses by changing the pose and shape parameters independently. We also introduce an application of the proposed method for object pose estimation, through which we confirmed that the object poses in the generated images are accurate.

A Study on Product Image Impression Estimation considering the Customer's Attributes

中本麻友, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, 中澤満, チェヨンナム, シュテンガービヨン

IEICE General Conference 2021.3.10

A Preliminary Study on Belongings Category and Weight Recognition based on Walking Skeleton Trajectory

水野雅也, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase, 井下哲夫

IEICE General Conference 2021.3.11

A Preliminary Study on Eye Contact Detection for Distant Pedestrians using an In-vehicle Camera

畑隆聖, Daisuke Deguchi, Takatsugu Hirayama, Yasutomo Kawanishi, Hiroshi Murase

IEICE General Conference 2021.3.11

個人差を考慮した歩き方からの手荷物の重さ推定の検討

水野雅也, 川西康友, 出口大輔, 村瀬洋

パターン認識・メディア理解研究会(PRMU) 2021.12.17

人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

弓矢隼大, 川西康友, 出口大輔, 村瀬洋, 細野峻司

第24回画像の認識・理解シンポジウム(MIRU) 2021.7.30

情報エントロピーにもとづく車両歩行者インタラクションモデルの検討

新村文郷, 赤井直紀, 川西康友, 平山高嗣, 劉海龍, 出口大輔, 村瀬洋

第22回計測自動制御学会システムインテグレーション部門講演会 2021.12.16

観衆の顔向きの時空間統合によるステージ上の注目対象及び注目度の推定

武田一馬, 川西康友, 平山高嗣, 出口大輔, 井手一郎, 村瀬洋, 柏野邦夫

パターン認識・メディア理解研究会(PRMU) 2021.12.17

人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

弓矢隼大, 川西康友, 出口大輔, 村瀬洋, 細野峻司

コンピュータビジョンとイメージメディア研究会(CVIM) 2021.5.21

人物姿勢と注視対象配置制約に基づく後ろ向き人物の注視領域推定

弓矢隼大, 川西康友, 出口大輔, 村瀬洋, 細野峻司

第24回画像の認識・理解シンポジウム(MIRU) 2021.7.30

歩き方の特徴に着目した所持物の種類・重さ認識の検討

水野雅也, 川西康友, 出口大輔, 村瀬洋, 井下哲夫

第24回画像の認識・理解シンポジウム(MIRU) 2021.7.29

Pointedness of an Image: Measuring How Pointy an Image is Perceived International conference

Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

HCII 2021 2021.7.29

Event date： 2021

Language：English Presentation type：Poster presentation

Venue：Virtual

For computers to understand human perception, metrics that can capture human perception well are important. However, there are few metrics that characterize the visual perception of humans towards images. Therefore, in this paper, we propose a novel concept and a metric of pointedness of an image, which describes how pointy an image is perceived. The algorithm is inspired by the Features from Accelerated Segment Test (FAST) algorithm for corner detection which looks on the number of continuous neighboring darker pixels surrounding each pixel. We assume that this number would be proportional to the perceived pointedness in the region around the pixel. We evaluated our method towards how well it could capture the human perception of images. To compare the method with similar metrics that describe shapes, we prepared silhouette images of both artificial shapes and natural objects. The results showed that the proposed method gave nearly equivalent perceptual performance to other metrics and also worked in a larger variety of images.

DOI： https://doi.org/10.1007/978-3-030-78635-9_20

姿勢変化の連続性に着目した人物姿勢推定器の能動学習

森太郎, 出口大輔, 川西康友, 井手一郎, 村瀬洋, 井下哲夫

第24回画像の認識・理解シンポジウム(MIRU) 2021.7.28

Tell as you imagine: Sentence imageability-aware image captioning International conference

Kazuki Umemura, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

27th Int. Conf. on Multimedia Modeling (MMM2021) 2021.6.24

Imageability Estimation using Visual and Language Features International conference

Chihaya Matsuhira, Marc A. Kastner, Ichiro Ide, Yasutomo Kawanishi, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

2020 International Conference on Multimedia Retrieval 2020.10.28

Event date： 2020

Language：English Presentation type：Poster presentation

Venue：Dublin, Ireland (Virtual)

Imageability is a concept from Psycholinguistics quantizing the human perception of words. However, existing datasets are created through subjective experiments and are thus very small. Therefore, methods to automatically estimate the imageability can be helpful. For an accurate automatic imageability estimation, we extend the idea of a psychological hypothesis called Dual-Coding Theory, that discusses the connection of our perception towards visual information
and language information, and also focus on the relationship between the pronunciation of a word and its imageability. In this research, we propose a method to estimate imageability of words
using both visual and language features extracted from corresponding data. For the estimation, we use visual features extracted from low- and high-level image features, and language features extracted from textual features and phonetic features of words. Evaluations how that our proposed method can estimate imageability more accurately than comparative methods, implying the contribution of each feature to the imageability.

DOI： 10.1145/3372278.3390731

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -