Faculty Profiles - Deguchi Daisuke

Presentations -

Division display 221 - 240 of about 713 ／ All the affair displays >>

A Study on an Efficient Pedestrian Scanning Method by Active Scan LIDAR

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

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017 2017.9.7

A food image dataset tagged with attractiveness scores according to view-points (in Japanese)

Ichiro Ide, Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Daisuke Deguchi, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017 2017.9.7

An analysis on deep learning based action recognition from extremely low-resolution thermal image sequence

Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017 2017.9.7

Improvement of an attractiveness estimation method of food photos by using gaze information during preference experiments

Akinori Sato, Takatsugu Hirayama, Keisuke Doman, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017 2017.9.7

Toward Zero-shot Gaits Translation by Onomatopoeia Based on the Relationship between Phoneme and Body-Parts Movement

Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

Tokai-Section Joint Conference on Electrical, Electronics, Information, and Related Engineering 2017 2017.9.7

Action Recognition from Extremely Low-Resolution Thermal Image Sequence International conference

Takayuki Kawashima, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS2017) 2017.9.1

Event date： 2017

Language：English Presentation type：Poster presentation

Venue：Carlo V Castle, Lecce, Italy

This paper proposes a Deep Learning-based action recognition method from an extremely low-resolution thermal image sequence. The method recognizes daily actions by humans (e.g. walking, sitting down, standing up, etc.) and abnormal actions (e.g. falling down) without privacy concerns. While privacy concerns can be ignored, it is difficult to compute feature points and to obtain a clear edge of the human body from an extremely low-resolution thermal image. To address these problems, this paper proposes a Deep Learning-based action recognition method that combines convolution layers and an LSTM layer for learning spatio-temporal representation, whose inputs are the thermal images and their frame differences cropped by the gravity center of human regions. The effectiveness of the proposed method was confirmed through experiments.

DOI： 10.1109/AVSS.2017.8078497

Transifexを利用したコミュニティ翻訳

出口大輔

JTF 翻訳支援ツール説明会 2017.8.21

Estimation of the attractiveness of food photography focusing on main ingredients International conference

Kazuma Takahashi, Keisuke Doman, Yasutomo Kawanishi, Takatsugu Hirayama, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

9th Workshop on Cooking and Eating Activities (CEA2017) in conjunction with IJCAI2017 2017.8.20

Trajectory Ensemble: カメラネットワーク上での一時的な見えの変化に頑健な多人数追跡

川西康友, 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) 2017.8.10

車両周辺環境の違いに対する歩行者検出器の信頼度推定に関する初期検討

久徳遙矢, 川西康友, 出口大輔, 井手一郎, 加藤一樹, 村瀬洋

画像の認識・理解シンポジウム(MIRU) 2017.8.10

3DCNNを用いた低解像度点群からの歩行者検出

建部好輝, 出口大輔, 川西康友, 井手一郎, 村瀬洋, 酒井映

画像の認識・理解シンポジウム(MIRU) 2017.8.9

低解像度顔画像群からの集団の注目位置推定に向けて

児玉祐樹, 川西康友, 平山高嗣, 出口大輔, 井手一郎, 村瀬洋, 永野秀尚, 柏野邦夫

画像の認識・理解シンポジウム(MIRU) 2017.8.9

超低解像度温度画像系列を用いた家庭内人物行動認識に関する検討

川島昂之, 川西康友, 出口大輔, 井手一郎, 村瀬洋, 相澤知禎, 川出雅人

画像の認識・理解シンポジウム(MIRU) 2017.8.9

医用画像処理からの巣立ち

出口大輔

第36回日本医用画像工学会大会（JAMIT2017） 2017.7.29

Event date： 2017

Language：Japanese Presentation type：Oral presentation (general)

本講演では，医用画像処理に軸足を置いた研究から私自身経験の無いITS研究分野に挑戦したこれまでの経験を紹介するとともに，そこで感じた研究分野を変えることの難しさ，新しいことへの挑戦の楽しさ，人との繋がりの大切さ，などについてまとめる．私自身は，名古屋大学工学部の4年生として鳥脇研究室の門をくぐり，博士号取得まで一貫して医用画像処理，特に気管支内視鏡ナビゲーションシステムの開発と関連するセグメンテーション技術の開発に取り組んできた．その後，縁あってコンピュータービジョン・パターン認識などの研究に軸足を移し，現在ではITSに関連する研究にも取り組んでいる．その間，研究分野を変えることの難しさや，新しいことに挑戦する楽しさを再認識することができた．特に，新しい人との繋がりは自身を大きく成長させてくれたと考えている．このような私自身のこれまでの経験が，今後新しい研究分野に挑戦する研究者の皆様の助けになれば幸いである．

Headgear Recognition by Decomposing Human Images in the Thermal Infrared Spectrum International conference

Brahmastro Kresnaraman, Yasutomo Kawanishi, Daisuke Deguchi, Tomokazu Takahashi, Yoshito Mekada, Ichiro Ide, Hiroshi Murase

15th International Conference on Quality in Research (QiR2017) 2017.7.26

Event date： 2017

Language：English Presentation type：Oral presentation (general)

Venue：Bali, Indonesia

Surveillance systems play a critical role in security and surveillance. A surveillance system with cameras that work in the visible spectrum is sufficient for most cases. However, problems may arise during the night, or in areas with less than ideal illumination conditions. Cameras with thermal infrared technology can be a better option in these situations since they do not rely on illumination to observe the environment. Furthermore, in our daily lives, it is common for humans to wear headgears such as glasses, masks, and hats. In surveillance, such headgears can be a hindrance to the identification of a person, and hence pose a certain degree of risk. This is not ideal in areas where the identity of a person is important, for example, in a bank. Therefore, in this paper we propose a headgear recognition method using an innovative decomposition approach on thermal infrared images. The decomposition method is based on Robust Principal Component Analysis, a modification of the popular Principal Component Analysis. The proposed method performs decomposition on a human image and isolates headgears in the image for recognition purposes. Experiments were conducted to evaluate the capability of the proposed method. The results show a positive outcome when compared with other methods.

DOI： 10.1109/QIR.2017.8168475

Trajectory Ensemble: Multiple Persons Consensus Tracking across Non-overlapping Multiple Cameras over Randomly Dropped Camera Networks International conference

Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

1st Workshop on Target Re-Identification and Multi-Target Multi-Camera Tracking 2017.7.21

Event date： 2017

Language：English Presentation type：Poster presentation

Venue：Hawaii Convention Center

Multiple person tracking over a camera network is usually performed by matching person images between adjacent cameras. It easily fails by a temporal appearance change of the persons caused by environmental illumination and observation orientation of a camera. To solve this problem, matching person images across not only adjacent cameras but also cameras multiple hops away in the camera network is effective, but such relaxation of spatiotemporal cues also cause tracking failure due to the increase of matching candidates. To avoid the failure, we introduce Random Camera Drop" to generate different camera networks which relax the spatio-temporal cues partially and randomly. We then, integrate tracking results over the networks to a consensus tracking result by a novel concept "Trajectory Ensemble", an extension of unsupervised ensemble learning for the multiple person tracking over a camera network problem. We evaluated the framework on several virtual datasets generated from a public dataset, "Shinpuhkan 2014 dataset" and confirmed that the proposed method achieves the highest tracking results among several comparative methods."

A study on keypoint matching with light field information

Masayuki Shimizu, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEICE Technical Report (PRMU) 2017.6.23

Toward Description of Gaits by Onomatopoeia Based on the Relationship\\between Phoneme and Body-Parts Movement

Hirotaka Kato, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Ichiro Ide, Daisuke Deguchi, Hiroshi Murase

IEICE Technical Report (PRMU) 2017.6.22

Monocular Localization within Sparse Voxel Maps International conference

David Robert Wong, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

2017 IEEE Intelligent Vehicles Symposium (IV2017) 2017.6.12

Event date： 2017

Language：English Presentation type：Poster presentation

Venue：Redondo Beach, California, USA

We introduce a method that uses a single camera to localize a vehicle within a pre-constructed map consisting of a voxel occupancy grid and road-line marker positions. Sophisticated mapping hardware is capable of creating high accuracy 3D maps of road environments, but localizing a vehicle within such maps is one of the challenges at the forefront of automated driving. A solution which is robust to dynamic environments, while using only inexpensive sensors, is a difficult problem. In addition, maps that enable precise localization consume a lot of data which is impractical for the expansive environments encountered in real-world road networks. We show how using the area of edge regions shared between rendered views of a compact voxel map and in-vehicle camera images can be coupled with non-linear optimization methods to determine the camera position and pose.

Active Scan LIDARを用いた歩行者検出のための効率的スキャン手法

山本大貴, 新村文郷, 出口大輔, 川西康友, 井手一郎, 村瀬洋

画像センシングシンポジウム(SSII) 2017.6.9

Event date： 2017

Language：Japanese Presentation type：Poster presentation

Venue：パシフィコ横浜アネックスホール

LIDAR は,対象までの距離や反射特性を測る環境認識センサであり,対象の 3 次元形状を分析できるため,これを用いた歩行者検出の研究が行われている.近年,LASER 光の照射方向を瞬時に制御可能な Active Scan LIDAR の開発が進められている.本研究では, Active Scan LIDAR を用いて歩行者から効率よく距離データを得るためのスキャン手法の開発を目的とする.
Active Scan LIDAR を用いた歩行者検出の実現に向けて,歩行者の形状による歩行者尤度推定,及び歩行者存在確率に基づく効率的なスキャン手法を提案する.
Active Scan LIDARを模擬した評価実験を行ったところ，全体を一定にスキャンする比較手法にくらべ，的中率，領域重なり率，歩行者抽出率すべての向上を確認でき，歩行者を効率的にスキャンできていることを確認した．

　 PREV - NEXT 　

<Deguchi Daisuke>

Presentations -