Action planning of autonomous robots that take pictures for construction of real-world knowledge database

• Project/Area Number: 26880004
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Intelligent robotics
• Research Institution: The University of Tokyo
• Principal Investigator: Kanezaki Asako 東京大学, 情報理工学(系)研究科, 助教 (00738073)
• Project Period (FY): 2014-08-29 – 2016-03-31
• Project Status: Completed (Fiscal Year 2015)
• Budget Amount: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000); Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
• Keywords: ロボットビジョン / 三次元物体認識 / 物体検出 / 物体認識 / 自律移動ロボット / 人工知能

Outline of Final Research Achievements

First, we proposed an optimization method for estimating the parameters that typically appear in graph theoretical formulations of the matching problem for object detection. Although several methods have been proposed to optimize parameters for graph matching in a way to promote correct correspondences and to restrict wrong ones, our approach is novel in the sense that it aims at improving performance in the more general task of object detection. We presented this work at 3DV 2014 and also achieved 30th (2015) RSJ Young Investigation Excellence Award. Second, to detect unknown objects in the real world, we proposed a new method for obtaining object candidates in 3D space. Our method requires no learning, has no limitation of object properties such as compactness or symmetry, and therefore produces object candidates using a completely general approach. We presented this work at IROS 2015 and also published open source code.

Research Products

• [Presentation] Kinect等の色距離センサを用いた点群処理と3D物体認識-ベーシックな手法と最新動向・ソフトウェアの紹介- (2016)
  • Author(s): 金崎朝子
  • Organizer: 第22回 画像センシングシンポジウム（SSII2016）
  • Place of Presentation: パシフィコ横浜 (神奈川、横浜)
  • Year and Date: 2016-06-08
  • Invited
• [Presentation] RGBD画像処理と三次元物体認識の研究紹介 (2015)
  • Author(s): 金崎朝子
  • Organizer: 公益社団法人 精密工学会 大規模環境の３次元計測と認識・モデル化技術専門委員会 第20回定例研究会
  • Place of Presentation: 東京大学本郷キャンパス (東京、本郷)
  • Year and Date: 2015-12-16
  • Invited
• [Presentation] 三次元情報を活用した物体検出の三手法 (2015)
  • Author(s): 金崎朝子
  • Organizer: Vision Enginieering Workshop (ViEW)
  • Place of Presentation: パシフィコ横浜 (神奈川、横浜)
  • Year and Date: 2015-12-04
• [Presentation] 3D Selective Search for Obtaining Object Candidates (2015)
  • Author(s): Asako Kanezaki and Tatsuya Harada
  • Organizer: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015)
  • Place of Presentation: Hamburg (Germany)
  • Year and Date: 2015-09-29
  • Int'l Joint Research
• [Presentation] 三次元画像からの物体検出と三次元特徴量 (2015)
  • Author(s): 金崎朝子
  • Organizer: 第9回 次世代コンピュータ支援診断ソフトウェア臨床使用・評価プラットフォーム研究会
  • Place of Presentation: 東京大学医学部附属病院 (東京、本郷)
  • Year and Date: 2015-06-13
  • Invited
• [Presentation] ロボットの目をつくる―RGBD画像処理による三次元世界の物体認識 (2015)
  • Author(s): 金崎朝子
  • Organizer: 第21回 画像センシングシンポジウム（SSII2015）
  • Place of Presentation: パシフィコ横浜 (神奈川、横浜)
  • Year and Date: 2015-06-12
  • Invited
• [Presentation] グラフマッチング学習を用いたRGB-D画像からの物体検出 (2015)
  • Author(s): 金崎 朝子, Emanuele Rodola, 原田 達也
  • Organizer: 第20回ロボティクスシンポジア
  • Place of Presentation: 軽井沢プリンスホテルウエスト（長野県、軽井沢）
  • Year and Date: 2015-03-16
• [Presentation] Learning Similarities for Rigid and Non-Rigid Object Detection (2014)
  • Author(s): Asako Kanezaki, Emanuele Rodola, Daniel Cremers, and Tatsuya Harada
  • Organizer: International Conference on 3D Vision (3DV 2014)
  • Place of Presentation: 東京大学生産技術研究所（東京、駒場）
  • Year and Date: 2014-12-11
• [Presentation] Mirror Reflection Invariant HOG descriptors for Object Detection (2014)
  • Author(s): Asako Kanezaki, Yusuke Mukuta, and Tatsuya Harada.
  • Organizer: IEEE 21th International Conference on Image Processing (ICIP 2014)
  • Place of Presentation: Paris(France)
  • Year and Date: 2014-10-28
• [Presentation] 対応点集合類似度学習を用いた剛体・非剛体物体検出 (2014)
  • Author(s): 金崎 朝子, Emanuele Rodola, Daniel Cremers, 原田 達也
  • Organizer: Pattern Recognition and Media Understanding (PRMU)
  • Place of Presentation: 幕張メッセ国際会議場（千葉県、美浜区）
  • Year and Date: 2014-10-09
• [Presentation] RGB-D画像からの物体検出における対応点集合類似度の学習 (2014)
  • Author(s): 金崎 朝子, Emanuele Rodola, 原田 達也
  • Organizer: the 32th Annual Conference of the Robotics Society of Japan (RSJ)
  • Place of Presentation: 九州産業大学（福岡、博多）
  • Year and Date: 2014-09-06