Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 121 - 140 of about 727 ／ All the affair displays >>

運転者による歩行者の見つけやすさ向上のためのヘッドライトシステム

前田高志, 平山高嗣, 川西康友, 出口大輔, 井手一郎, 村瀬洋

動的画像処理実利用化ワークショップ(DIA) 2019.3.7

Event date： 2019

Language：Japanese Presentation type：Oral presentation (general)

Venue：北九州国際会議場

夜間における歩行者の交通死亡事故が多発しており，その原因として運転者による歩行者の視認が困難であることが挙げられる．近年，通常の前方照射に加えて選択的照射が可能なヘッドライトが開発されており，その技術を活かして歩行者に選択的に光を照射することで歩行者の見つけやすさを向上させることが考えられる．我々はこれまでに点滅に着目して効果的な照射法を検討し，特定の周波数において点滅光の照射が効果的であることを確認しているが， 1 つの固定された周辺光条件しか想定していなかった．そこで本研究では，周辺光条件ごとに効果的な点滅照射を分析する．具体的には，運転環境を模擬した臨場感のある仮想環境において 6 種類の周辺光条件を設定し，通常のロービーム照射，ハイビーム照射および 7 種類の点滅周波数を用いて実験を行なった．実験結果から，点滅照射が見つけやすさ向上に有効であることや，異なる周辺光条件では効果的な周波数が異なることを確認した．

SNS投稿写真のVisual Conceptに基づく時空間類似地域マイニング

陳璐, 川西康友, 井手一郎, 平山高嗣, 道満恵介, 出口大輔, 村瀬洋

データ工学と情報マネジメントに関するフォーラム（DEIM） 2019.3.4

Event date： 2019

Language：Japanese Presentation type：Oral presentation (general)

Venue：ホテルオークラJRハウステンボス

旅行を計画する際，満足のいく計画を立てるためには，旅先の雰囲気を予め把握することが重要である．ある地域の訪問予定時の雰囲気が，既に知っている地域のある時期の雰囲気と似ていることが分かれば，その地域の訪問時の雰囲気を直感的に把握することできる．これを実現するため，我々は旅行者の体験を反映した大量のSNS投稿写真に着目した．具体的には，写真に付随する時空間情報を用いて写真をクラスタリングし「時期情報付き地域」を獲得し，写真のVisual Conceptに基づいて時空間類似地域をマイニングすることで，時期を考慮した類似地域の組を獲得する手法を提案する．手法の有用性を示すため，Flickr に投稿された写真を用いて時空間類似地域マイニング実験を行った．また，被験者実験を通して，提案手法の妥当性を確認した．

画像付き料理レシピの地域属性推定の検討

伊藤耀一朗, 道満恵介, 川西康友, 平山高嗣, 井手一郎, 出口大輔, 村瀬洋

データ工学と情報マネジメントに関するフォーラム（DEIM） 2019.3.4

Event date： 2019

Language：Japanese Presentation type：Oral presentation (general)

Venue：ホテルオークラJRハウステンボス

近年,投稿型料理レシピポータルサイトが普及している.ウェブ上には膨大な数の料理レシピが存在し,
掲載されている料理の種類は多岐にわたる.しかし,それに伴い,サイト利用者が検索の際に目的とする料理レシピ
件数を絞りこむことが難しくなりつつある.そこで本研究では,地域属性(スペイン料理,中華料理など)ごとに料
理の味や見た目が大きく異なることに着目し,料理レシピがもつ多様な情報から,機械学習を用いて作成される料理
の地域属性を推定する手法を提案する.学習には,料理の完成画像から得られた画像特徴,素材一覧から得られた素
材特徴,調理手順文の動詞から得られた手順特徴の 3 つを組み合わせて用いる.結果として,これら 3 つの全特徴を
用いた手法で 8 割近い推定精度が得られることを確認した.

Hard Negative Mining from in-Vehicle Camera Images based on Multiple Observations of Background Patterns International conference

Masashi Hontani, Haruya Kyutoku, David Robert Wong, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

International Conference on Computer Vision Theory and Applications (VISAPP) 2019 2019.2.26

Event date： 2019

Language：English Presentation type：Oral presentation (general)

Venue：Vienna House Diplomat Prague, Prague, Czech Republic

In recent years, the demand for highly accurate pedestrian detectors has increased due to the development of advanced driving support systems.
For the training of an accurate pedestrian detector, it is important to collect a large number of training samples.
To support this, this paper proposes a ``hard negative'' mining method to automatically extract background images which tend to be erroneously detected as pedestrians.
Negative samples are selected based on the assumption that frequent patterns observed multiple times in the same location are most likely parts of the background scene.
As a result of an evaluation using in-vehicle camera images captured along the same route, we confirmed that the proposed method can automatically collect false positive samples accurately.
We also confirmed that a highly accurate detector can be constructed using the additional negative samples.

Next Viewpoint Recommendation by Pose Ambiguity Minimization for Accurate Object Pose Estimation International conference

Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Ayako Amma, Norimasa Kobori

International Conference on Computer Vision Theory and Applications (VISAPP) 2019 2019.2.25

Event date： 2019

Language：English Presentation type：Oral presentation (general)

Venue：Vienna House Diplomat Prague, Prague, Czech Republic

3D object pose estimation by using a depth sensor is one of the important tasks in activities by robots. To reduce the pose ambiguity of an estimated object pose, several methods for multiple viewpoint pose estimation have been proposed. However, these methods need to select the viewpoints carefully to obtain better results. If the pose of the target object is ambiguous from the current observation, we could not decide where we should move the sensor to set as the next viewpoint. In this paper, we propose a best next viewpoint recommendation method by minimizing the pose ambiguity of the object by making use of the current pose estimation result as a latent variable. We evaluated viewpoints recommended by the proposed method and confirmed that it helps us to gain better pose estimation results than several comparative methods on a synthetic dataset.

Pedestrian Intensive Scanning for Active-scan LIDAR International conference

Taiki Yamamoto, Fumito Shinmura, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

International Conference on Computer Vision Theory and Applications (VISAPP) 2019 2019.2.25

Event date： 2019

Language：English Presentation type：Poster presentation

Venue：Vienna House Diplomat Prague, Prague, Czech Republic

In recent years, LIDAR is playing an important role as a sensor for understanding environments of a vehicle’s surroundings. Active-scan LIDAR is being actively developed as a LIDAR that can control the laser irradiation direction arbitrary and rapidly. In comparison with conventional uniform-scan LIDAR (e.g. Velodyne HDL-64e), Active-scan LIDAR enables us to densely scan even distant pedestrians. In addition, if appropriately controlled, this sensor has the potential to reduce unnecessary laser irradiations towards non-target objects. Although there are some preliminary studies on pedestrian scanning strategy for Active-scan LIDARs, in the best of our knowledge, an efficient method has not been realized yet. Therefore, this paper proposes a novel pedestrian scanning method based on orientation aware pedestrian likelihood estimation using the orientation-wise pedestrian’s shape models with local distribution of measured points. To evaluate the effectiveness of the proposed method, we conducted experiments by simulating Active-scan LIDAR using point-clouds from the KITTI dataset. Experimental results showed that the proposed method outperforms conventional methods.

電動車いす運転の熟達に伴う視行動変化の分析

前川大和, 赤井直紀, モラレスルイス洋一, 平山高嗣, 出口大輔, 川西康友, 井手一郎, 村瀬洋

画像の認識・理解シンポジウム(MIRU) 2019.8.1

Event date： 2019

Language：Japanese Presentation type：Poster presentation

Venue：グランキューブ大阪（大阪府立国際会議場）

近年，先進国を中心に高齢化が進んでおり，電動車いすの需要が高まっている．しかし，電動車いすの利便性は高い一方で，事故が多発している．自動車の事故は視覚的な認知ミスが原因であることが多く，電動車いすも自動車と同様に運転者の視覚的な認知を支援することが事故防止に有効であると考えられる．また，熟練運転者と非熟練運転者の視行動に差異があることが知られており，熟練者の視行動に基づいて，運転者の視覚的な認知の支援をすることができると考えられる．本研究では，電動車いす運転における熟練者の視行動のモデル化を目指し，リスクが複数存在する箇所である死角あり狭路で運転する場合を想定して，熟達に伴う視行動の変化を3次元空間上で分析した．その結果，熟達するほど複数のリスクに対してバランスよく注意を払うことを確認した．

Class Augmentation For Semantic Segmentation by Integrating Multiple Methods

Wang Qishen, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

2019.12.12

環境認識に関する基礎と最近の動向

出口大輔

日本機械学会東海支部講習会 2019.12.5

Scene-Adaptive Driving Area Prediction based on Automatic Label Acquisition from Driving Information International conference

Takuya Migishima, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

5th IAPR Asian Conference on Pattern Recognition (ACPR2019) 2019.11.28

Semantic Segmentation of Railway Images Considering Temporal Continuity International conference

Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukoujima, Nozomi Nagamine

5th IAPR Asian Conference on Pattern Recognition (ACPR2019) 2019.11.27

An Analysis of How Driver Experience Affects Eye-Gaze Behavior for Robotic Wheelchair Operation International conference

Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

2019 IEEE International Conference on Computer Vision (ICCV) Workshops 2019.11.2

Event date： 2019

Language：English Presentation type：Poster presentation

Venue：COEX Convention Center, Seoul, Korea

Drivers obtain information on surrounding environment using their eyesights. Experienced eye-gaze behavior is needed when driving at places where multiple risks exist to prepare for and avoid them. In this work, we analyze the change in eye-gaze behavior in such situations while a driver gains experience on the operation of a robotic wheelchair. Accurate distance information in the traffic environment is important to analyze the eye-gaze behavior. However, almost all previous works analyze eye-gaze behavior in a 2D environment, so they could not obtain accurate distance information. For this reason, we analyze eye-gaze behavior in 3D space. Concretely, we developed a novel eye-gaze behavior analysis platform based on a robotic wheelchair and estimated the driver's attention in 3D space. We try to analyze the eye-gaze behavior considering a useful field-of-view in 3D space based on the distance information instead of only the fixation point to investigate the objects that a driver implicitly pays attention to and from where s/he focuses on them. Results show that novice drivers pay attention to a single risk at a time. In contrast, they pay more attention to multiple risks simultaneously as they gain experience. Additionally, we discuss what features are effective to model the eye-gaze behavior based on the results.

DOI： 10.1109/ICCVW.2019.00545

Exemplar-based Pseudo-Viewpoint Rotation for White-Cane User Recognition from a 2D Human Pose Sequence International conference

Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

The 16-th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS) 2019.9.20

Similar Seasonal-Geo-Region Mining based on Visual Concepts in Social Media Photos International conference

Yasutomo Kawanishi, Ichiro Ide, Chen Lu, Takatsugu Hirayama, Keisuke Doman, Daisuke Deguchi, Hiroshi Murase

5th IEEE Conference on Multimedia BigData 2019.9.11

A Preliminary Study on Pedestrian Abnormal Behavior Recognition based on Pose Heatmap from Surveillance Camera Images

Onur Temuroglu, Yasutomo Kawanishi, Daisuke Deguchi, Takatsugu Hirayama, Ichiro Ide, Hiroshi Murase, Mayuu Iwasaki, Atsushi Tsukada

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.10

A Preliminary Study on Pseudo-Viewpoint Conversion for White-Cane User Recognition from Arbitrary Viewpoints

Naoki Nishida, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Jun Piao

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.10

A Study on Human Skeleton Estimation from an Extremely Low-Resolution FIR Image Sequence for Monitoring Systems

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

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.10

An Analysis of Simultaneous Image Matching on Various Datasets for Person Re-identification

Nik Mohd Zarifie Hashim, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.10

Event date： 2019

Language：English Presentation type：Oral presentation (general)

Venue：大同大学

Person re-identification is becoming a focus topic in many discussions recently. It becomes a vital role in public surveillance for identifying people across the street, inside supermarkets, and airports. Person re-identification aims to match person images captured at several non-overlapping camera views. For this reason, many advanced types of research had been competing to cope with the best solution for identifying multiple persons. Due to the redundant and mismatching which occurred in the traditional individual image matching scheme, the simultaneous image matching [1, 2] provides a solution which could avoid this downside. In this study, we analyze the performance of the simultaneous image matching on various datasets. We also evaluate a new image mask for feature extraction of SDALF.

Analysis of the Eye-gaze Behaviors of Robotic Wheelchair Drivers Considering the Geometric Relation with a Focused Object

Yamato Maekawa, Naoki Akai, Takatsugu Hirayama, Luis Yoichi Morales, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.10

CityWalks: An Extended Dataset for Attribute-aware Semantic Segmentation

Mahmud Dwi Sulistiyo, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Takatsugu Hirayama, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2019.9.9

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -