35_3_9.dvi

Size: px
Start display at page:

Download "35_3_9.dvi"

Transcription

1 180 Vol. 35 No. 3, pp , 2017 Image Recognition by Deep Learning Hironobu Fujiyoshi and Takayoshi Yamashita Chubu University Scale-Invariant Feature Transform SIFT Histogram of Oriented Gradients HOG handcrafted feature 2010 Deep learning handcrafted feature 2. [1] Deep Learning, Image Classification, Object Detection, Semantic Segmentation Kasugai shi, Aichi Triplet loss function [2] 2. 2 Haar-like [3] AdaBoost HOG [4] Support Vector Machine SVM 2 JRSJ Vol. 35 No. 3 8 Apr., 2017

2 Bag-of-Features BoF [5] [6] Vector of Locally Aggregated Descriptors VLAD [7] , SIFT [8] 2016 Learned Invariant Feature Transform LIFT [9] SIFT 3. ILSVRC ImageNet Large Scale Visual Recognition Challenge 1, ,000 classification 2012 Convolutional Neural Network CNN [10] ILSVRC2012 CNN AlexNet [11] ,000 1, , AlexNet AlexNet [11] AlexNet [11] AlexNet VGG[12] 19 GoogLeNet [13] ResNet [14] 152 ResNet 3.56% 5.1% 4 AlexNet 4. CNN Region Proposal CNN

3 182 5 Faster R-CNN 7 YOLO 6 [17] 8 SSD [19] Regions with Convolutional Neural Network R-CNN [15] Selective search [16] AlexNet VGGNet Selective search CNN Selective search Faster R-CNN [17] 5 Region Proposal Network RPN RPN RPN 6 k RPN RPN Region Proposal 2016 Single Shot CNN YOLO YouOnlyLookOnce [18] ,024 i, j i, j x, y, w, h YOLO Single Shot Multi-Box Detector SSD [19] 8 SSD SSD 9 SSD JRSJ Vol. 35 No Apr., 2017

4 深層学習による画像認識 183 図 10 Fully Convolutional Network FCN の構造 によりこれらの情報が統合され 細かな情報が欠落してい る 物体認識においては これらの詳細な情報は不要であ るが セメンティクセグメンテーションのタスクでは重要 な情報である そこで FCN は ネットワークの途中の特 徴マップを最終層で統合する処理を行う FCN はこの統合 に用いる特徴マップのサイズにより FCN-32s FCN-16s 図 9 SSD による物体検出結果 文献 [19] より引用 FCN-8s とある FCN-8s では 3 回めにプーリングした特 徴マップと 4 回めにプーリングした特徴マップを最終層の 5. セマンティックセグメンテーション 入力に加える このとき すべての特徴マップのサイズを れてきた そして 高精度なセマンティックセグメンテー 3 回めにプーリングした特徴マップに合わせるために 4 回 めにプーリングした特徴マップを 2 倍拡大し 最終層手前 の特徴マップを 4 倍拡大する これらの特徴マップをチャ ションを実現するには時間がかかると考えられていた し ネル方向に連結しでコンボリューション処理を行い 元画 かしながら 他のタスクと同様に 深層学習よる手法が提 像と同じサイズのセグメンテーション結果を出力する 案され 従来手法を上回る性能を達成している CNN が 注目された 2012 年に 3 層構造の CNN により得られた特 FCN は中間層の特徴マップを記憶しておく必要があり メモリ使用量が大きい SegNet [22] [23] は 中間層の特徴 徴マップとスーパーピクセル手法を組み合わせた手法が提 マップを記憶する必要がないエンコーダ デコーダ構成を コンピュータビジョン分野において セマンティックセグ メンテーションは難易度の高いタスクであり 長年研究さ 案された [20] この手法では 複数のネットワークと別の している 図 11 (a) のように SegNet のエンコーダ側では 手法との統合が必要であり 複雑な処理を必要とする 畳み込み処理とプーリング処理を繰り返し行う 一方 デ Fully Convolutional Network FCN [21] は CNN のみ を用いて end-to-end で学習およびラベリングが可能な手法 である FCN の構造を図 10 に示す FCN は 全結合層を コーダ側では エンコーダ側で生成された特徴マップをデ 有しないネットワーク構造となっている 入力画像に対し 11 (b) のようにエンコーダ側のプーリングは選択された位 て 畳み込み層およびプーリング層を繰り返し行うことで 置を記憶しておき デコーダ側で特徴マップ拡大する際に 生成される特徴マップのサイズは小さくなる 元の画像と 対応する位置にのみ値を挿入する これにより 中間層の 同じサイズにするために 特徴マップを最終層で 32 倍に拡 特徴マップを利用せずに 詳細な情報を復元することがで 大処理し 畳み込み処理を行う これをデコンボリューショ きる ンと呼ぶ 最終層は ラベンリングしたい各クラスの確率 化を図っている 一般的に CNN の中間層の特徴マップは入 PSPNet [24] は エンコーダ側で得られた特徴マップを拡 大する際に 複数のスケールで拡大する Pyramid Pooling Module によりスケールの異なる情報を捉えることができ る Pyramid Pooling Module は 図 12 のようにエンコー ダ側で元画像に対して縦および横のサイズがそれぞれ 1/8 に縮小された特徴マップを で 力層に近いほど詳細な情報を捉えている プーリング処理 プーリングする そして それぞれの特徴マップに対して マップを出力する 確率マップは各画素におけるクラスの 存在確率となるように学習している このように特徴マッ プの拡大を行うと 粗いセグメンテーション結果となる そ こで 中間層の特徴マップを統合して用いることで高精度 日本ロボット学会誌 35 巻 3 号 コンボリューション処理で拡大し 元の画像サイズのセグ メンテーション結果を出力する これらの処理において 図 年 4 月

5 [27] 11 SegNet 12 PSPNet [24] 14 SegNet [23] PSPNet 2016 ILSVRC Scene Parsing Cityscapes Dataset [25] CNN CRFasRNN [26] CNN Conditional Random Field CRF CRF CNN end-to-end CNN [27] 13 Faster R-CNN end-to-end 14 SegNet 6. end-to-end JRSJ Vol. 35 No Apr., 2017

6 185 [1] vol.48, no.sig16, pp.1 24, [ 2 ] D. Cheng, Y. Gong, S. Zhou, J. Wang and N. Zheng: Person re-identification by multi-channel parts-based cnn with improved triplet loss function, IEEE Conference on Computer Vision and Pattern Recognition, pp , [ 3 ] P. Viola and M. Jones: Rapid object detection using a boosted cascade of simple features, IEEE Computer Society Computer Vision and Pattern Recognition, vol.1, pp , [ 4 ] N. Dalal and B. Triggs: Histograms of Oriented Gradients for Human Detection, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.1, pp , [ 5 ] G. Csurka, C.R. Dance, L. Fan, J. Willamowski and C. Bray: Visual Categorization with Bags of Keypoints, ECCV Workshop on Statistical Learning in Computer Vision, pp.1 22, [ 6 ] F. Perronnin and C. Dance: Fisher Kernels on Visual Vocabularies for Image Categorization, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, [7] H.Jégou, F. Perronnin, M. Douze, J. Sánchez, P. Pérez and C. Schmid: Aggregating Local Image Descriptors into Compact Codes, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.34, no.9, pp , [ 8 ] D.G. Lowe: Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, vol.60, pp , [ 9 ] K.M. Yi, E. Trulls, V. Lepetit and P. Fua: LIFT: Learned Invariant Feature Transform, European Conference on Computer Vision, vol.9910, pp , [10] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner: Gradientbased learning applied to document recognition, Proc. of the IEEE, vol.86, no.11, pp , [11] A. Krizhevsky, I. Sutskever and G.E. Hinton: Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, pp , [12] K. Simonyan and A. Zisserman: Very deep convolutional networks for large-scale image recognition, arxiv preprint arxiv: , [13] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich: Going deeper with convolutions, IEEE Conference on Computer Vision and Pattern Recognition, pp.1 9, [14] K. He, X. Zhang, S. Ren and J. Sun: Deep residual learning for image recognition, IEEE Conference on Computer Vision and Pattern Recognition, pp , [15] R. Girshick, J. Donahue, T. Darrell and J. Malik: Rich feature hierarchies for accurate object detection and semantic segmentation, IEEE conference on computer vision and pattern recognition, pp , [16] J.R.R. Uijlings, K.E.A. Van De Sande, T. Gevers and A.W.M. Smeulders: Selective search for object recognition, International journal of computer vision, vol.104, no.2, pp , [17] S. Ren, K. He, R. Girshick and J. Sun: Faster R-CNN: Towards real-time object detection with region proposal networks, Advances in neural information processing systems, pp.91 99, [18] J. Redmon, S. Divvala, R. Girshick and A. Farhadi: You only look once: Unified, real-time object detection, IEEE Conference on Computer Vision and Pattern Recognition, pp , [19] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu and A.C. Berg: SSD: Single shot multibox detector, European Conference on Computer Vision, pp.21 37, [20] C. Farabet, C. Couprie, L. Najman and Y. LeCun: Learning hierarchical features for scene labeling, IEEE transactions on pattern analysis and machine intelligence, vol.35, no.8, pp , [21] J. Long, E. Shelhamer and T. Darrell: Fully convolutional networks for semantic segmentation, IEEE Conference on Computer Vision and Pattern Recognition, pp , [22] V. Badrinarayanan, A. Kendall and R. Cipolla: SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, arxiv preprint arxiv: , [23] A. Kendall, V. Badrinarayanan and R. Cipolla: Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder- Decoder Architectures for Scene Understanding, arxiv preprint arxiv: , [24] H. Zhao, J. Shi, X. Qi, X. Wang and J. Jia: Pyramid Scene Parsing Network, arxiv preprint arxiv: , [25] The Cityscapes Dataset, [26] S. Zheng, S. Jayasumana, B. Romera-Paredes, V. Vineet, Z. Su, D. Du and P.H. Torr: Conditional Random Fields as Recurrent Neural Networks, IEEE International Conference on Computer Vision, pp , [27] J. Dai, K. He and J. Sun: Instance-aware semantic segmentation via multi-task network cascades, IEEE Conference on Computer Vision and Pattern Recognition, pp , Hironobu Fujiyoshi Postdoctoral Fellow Takayoshi Yamashita PRMU

untitled

untitled c ILSVRC LeNet 1. 1 convolutional neural network 1980 Fukushima [1] [2] 80 LeCun (back propagation) LeNet [3, 4] LeNet 2. 2.1 980 8579 6 6 01 okatani@vision.is.tohoku.ac.jp (simple cell) (complex cell)

More information

03_特集2_3校_0929.indd

03_特集2_3校_0929.indd MEDICAL IMAGING TECHNOLOGY Vol. 35 No. 4 September 2017 187 CT 1 1 convolutional neural network; ConvNet CT CT ConvNet 2D ConvNet CT ConvNet CT CT Med Imag Tech 35 4 : 187 193, 2017 1. CT MR 1 501-1194

More information

IPSJ SIG Technical Report Vol.2010-CVIM-170 No /1/ Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Ta

IPSJ SIG Technical Report Vol.2010-CVIM-170 No /1/ Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Ta 1 1 1 1 2 1. Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Takayuki Okatani 1 and Koichiro Deguchi 1 This paper presents a method for recognizing the pose of a wire harness

More information

Convolutional Neural Network A Graduation Thesis of College of Engineering, Chubu University Investigation of feature extraction by Convolution

Convolutional Neural Network A Graduation Thesis of College of Engineering, Chubu University Investigation of feature extraction by Convolution Convolutional Neural Network 2014 3 A Graduation Thesis of College of Engineering, Chubu University Investigation of feature extraction by Convolutional Neural Network Fukui Hiroshi 1940 1980 [1] 90 3

More information

画像分野におけるディープラーニングの新展開

画像分野におけるディープラーニングの新展開 画像分野におけるディープラーニングの新展開 MathWorks Japan アプリケーションエンジニアリング部テクニカルコンピューティング 太田英司 2017 The MathWorks, Inc. 1 画像分野におけるディープラーニングの新展開 物体認識 ( 画像全体 ) 物体の検出と認識物体認識 ( ピクセル単位 ) CNN (Convolutional Neural Network) R-CNN

More information

本文6(599) (Page 601)

本文6(599) (Page 601) (MIRU2008) 2008 7 525 8577 1 1 1 E-mail: matsuzaki@i.ci.ritsumei.ac.jp, shimada@ci.ritsumei.ac.jp Object Recognition by Observing Grasping Scene from Image Sequence Hironori KASAHARA, Jun MATSUZAKI, Nobutaka

More information

Duplicate Near Duplicate Intact Partial Copy Original Image Near Partial Copy Near Partial Copy with a background (a) (b) 2 1 [6] SIFT SIFT SIF

Duplicate Near Duplicate Intact Partial Copy Original Image Near Partial Copy Near Partial Copy with a background (a) (b) 2 1 [6] SIFT SIFT SIF Partial Copy Detection of Line Drawings from a Large-Scale Database Weihan Sun, Koichi Kise Graduate School of Engineering, Osaka Prefecture University E-mail: sunweihan@m.cs.osakafu-u.ac.jp, kise@cs.osakafu-u.ac.jp

More information

LBP 2 LBP 2. 2 Local Binary Pattern Local Binary pattern(lbp) [6] R

LBP 2 LBP 2. 2 Local Binary Pattern Local Binary pattern(lbp) [6] R DEIM Forum 24 F5-4 Local Binary Pattern 6 84 E-mail: {tera,kida}@ist.hokudai.ac.jp Local Binary Pattern (LBP) LBP 3 3 LBP 5 5 5 LBP improved LBP uniform LBP.. Local Binary Pattern, Gradient Local Auto-Correlations,,,,

More information

IPSJ SIG Technical Report Vol.2009-CVIM-167 No /6/10 Real AdaBoost HOG 1 1 1, 2 1 Real AdaBoost HOG HOG Real AdaBoost HOG A Method for Reducing

IPSJ SIG Technical Report Vol.2009-CVIM-167 No /6/10 Real AdaBoost HOG 1 1 1, 2 1 Real AdaBoost HOG HOG Real AdaBoost HOG A Method for Reducing Real AdaBoost HOG 1 1 1, 2 1 Real AdaBoost HOG HOG Real AdaBoost HOG A Method for Reducing number of HOG Features based on Real AdaBoost Chika Matsushima, 1 Yuji Yamauchi, 1 Takayoshi Yamashita 1, 2 and

More information

(MIRU2010) Geometric Context Randomized Trees Geometric Context Rand

(MIRU2010) Geometric Context Randomized Trees Geometric Context Rand (MIRU2010) 2010 7 Geometric Context Randomized Trees 487-8501 1200 E-mail: {fukuta,ky}@vision.cs.chubu.ac.jp, hf@cs.chubu.ac.jp Geometric Context Randomized Trees 10 3, Geometric Context, Abstract Image

More information

[1] SBS [2] SBS Random Forests[3] Random Forests ii

[1] SBS [2] SBS Random Forests[3] Random Forests ii Random Forests 2013 3 A Graduation Thesis of College of Engineering, Chubu University Proposal of an efficient feature selection using the contribution rate of Random Forests Katsuya Shimazaki [1] SBS

More information

IPSJ SIG Technical Report Vol.2013-CVIM-187 No /5/30 1,a) 1,b), 1,,,,,,, (DNN),,,, 2 (CNN),, 1.,,,,,,,,,,,,,,,,,, [1], [6], [7], [12], [13]., [

IPSJ SIG Technical Report Vol.2013-CVIM-187 No /5/30 1,a) 1,b), 1,,,,,,, (DNN),,,, 2 (CNN),, 1.,,,,,,,,,,,,,,,,,, [1], [6], [7], [12], [13]., [ ,a),b),,,,,,,, (DNN),,,, (CNN),,.,,,,,,,,,,,,,,,,,, [], [6], [7], [], [3]., [8], [0], [7],,,, Tohoku University a) omokawa@vision.is.tohoku.ac.jp b) okatani@vision.is.tohoku.ac.jp, [3],, (DNN), DNN, [3],

More information

Microsoft PowerPoint - SSII_harada pptx

Microsoft PowerPoint - SSII_harada pptx The state of the world The gathered data The processed data w d r I( W; D) I( W; R) The data processing theorem states that data processing can only destroy information. David J.C. MacKay. Information

More information

(MIRU2008) HOG Histograms of Oriented Gradients (HOG)

(MIRU2008) HOG Histograms of Oriented Gradients (HOG) (MIRU2008) 2008 7 HOG - - E-mail: katsu0920@me.cs.scitec.kobe-u.ac.jp, {takigu,ariki}@kobe-u.ac.jp Histograms of Oriented Gradients (HOG) HOG Shape Contexts HOG 5.5 Histograms of Oriented Gradients D Human

More information

IS1-09 第 回画像センシングシンポジウム, 横浜,14 年 6 月 2 Hough Forest Hough Forest[6] Random Forest( [5]) Random Forest Hough Forest Hough Forest 2.1 Hough Forest 1 2.2

IS1-09 第 回画像センシングシンポジウム, 横浜,14 年 6 月 2 Hough Forest Hough Forest[6] Random Forest( [5]) Random Forest Hough Forest Hough Forest 2.1 Hough Forest 1 2.2 IS1-09 第 回画像センシングシンポジウム, 横浜,14 年 6 月 MI-Hough Forest () E-mail: ym@vision.cs.chubu.ac.jphf@cs.chubu.ac.jp Abstract Hough Forest Random Forest MI-Hough Forest Multiple Instance Learning Bag Hough Forest

More information

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. TRECVID2012 Instance Search {sak

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. TRECVID2012 Instance Search {sak THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. TRECVID2012 Instance Search 599 8531 1 1 E-mail: {sakata,matozaki}@m.cs.osakafu-u.ac.jp, {kise,masa}@cs.osakafu-u.ac.jp

More information

% 2 3 [1] Semantic Texton Forests STFs [1] ( ) STFs STFs ColorSelf-Simlarity CSS [2] ii

% 2 3 [1] Semantic Texton Forests STFs [1] ( ) STFs STFs ColorSelf-Simlarity CSS [2] ii 2012 3 A Graduation Thesis of College of Engineering, Chubu University High Accurate Semantic Segmentation Using Re-labeling Besed on Color Self Similarity Yuko KAKIMI 2400 90% 2 3 [1] Semantic Texton

More information

<4D F736F F F696E74202D B B836A F82C982E682E CC835E E93E089E6919C94468EAF82C98AD682B782E98CA48B F18F6F94C5816A2E >

<4D F736F F F696E74202D B B836A F82C982E682E CC835E E93E089E6919C94468EAF82C98AD682B782E98CA48B F18F6F94C5816A2E > ディープラーニングによる船舶のタンク ホールド内画像認識に関する研究 国 研究開発法 海上 港湾 航空技術研究所海上技術安全研究所 沖 平 勝 智之 次 1. 背景 2. ニューラルネットワークによる画像認識 ( 物体検出 ) 概要 A)R- B)Fast R-とFaster R- 3. タンク ホールド内画像認識処理システム 4. タンク ホールド内画像認識実験 I 5. タンク ホールド内画像認識実験

More information

bag-of-words bag-of-keypoints Web bagof-keypoints Nearest Neighbor SVM Nearest Neighbor SIFT Nearest Neighbor bag-of-keypoints Nearest Neighbor SVM 84

bag-of-words bag-of-keypoints Web bagof-keypoints Nearest Neighbor SVM Nearest Neighbor SIFT Nearest Neighbor bag-of-keypoints Nearest Neighbor SVM 84 Bag-of-Keypoints Web G.Csurka bag-of-keypoints Web Bag-of-keypoints SVM 5.% Web Image Classification with Bag-of-Keypoints Taichi joutou and Keiji yanai Recently, need for generic image recognition is

More information

Google Goggles [1] Google Goggles Android iphone web Google Goggles Lee [2] Lee iphone () [3] [4] [5] [6] [7] [8] [9] [10] :

Google Goggles [1] Google Goggles Android iphone web Google Goggles Lee [2] Lee iphone () [3] [4] [5] [6] [7] [8] [9] [10] : THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.,, 182-8585 1-5-1 E-mail: {maruya-t,akiyama-m}@mm.inf.uec.ac.jp, yanai@cs.uec.ac.jp SURF Bag-of-Features

More information

(b) BoF codeword codeword BoF (c) BoF Fergus Weber [11] Weber [12] Weber Fergus BoF (b) Fergus [13] Fergus 2. Fergus 2. 1 Fergus [3]

(b) BoF codeword codeword BoF (c) BoF Fergus Weber [11] Weber [12] Weber Fergus BoF (b) Fergus [13] Fergus 2. Fergus 2. 1 Fergus [3] * A Multimodal Constellation Model for Generic Object Recognition Yasunori KAMIYA, Tomokazu TAKAHASHI,IchiroIDE, and Hiroshi MURASE Bag of Features (BoF) BoF EM 1. [1] Part-based Graduate School of Information

More information

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2013-CVIM-186 No /3/15 EMD 1,a) SIFT. SIFT Bag-of-keypoints. SIFT SIFT.. Earth Mover s Distance

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2013-CVIM-186 No /3/15 EMD 1,a) SIFT. SIFT Bag-of-keypoints. SIFT SIFT.. Earth Mover s Distance EMD 1,a) 1 1 1 SIFT. SIFT Bag-of-keypoints. SIFT SIFT.. Earth Mover s Distance (EMD), Bag-of-keypoints,. Bag-of-keypoints, SIFT, EMD, A method of similar image retrieval system using EMD and SIFT Hoshiga

More information

IPSJ SIG Technical Report Vol.2012-CG-149 No.13 Vol.2012-CVIM-184 No /12/4 3 1,a) ( ) DB 3D DB 2D,,,, PnP(Perspective n-point), Ransa

IPSJ SIG Technical Report Vol.2012-CG-149 No.13 Vol.2012-CVIM-184 No /12/4 3 1,a) ( ) DB 3D DB 2D,,,, PnP(Perspective n-point), Ransa 3,a) 3 3 ( ) DB 3D DB 2D,,,, PnP(Perspective n-point), Ransac. DB [] [2] 3 DB Web Web DB Web NTT NTT Media Intelligence Laboratories, - Hikarinooka Yokosuka-Shi, Kanagawa 239-0847 Japan a) yabushita.hiroko@lab.ntt.co.jp

More information

Real AdaBoost HOG 2009 3 A Graduation Thesis of College of Engineering, Chubu University Efficient Reducing Method of HOG Features for Human Detection based on Real AdaBoost Chika Matsushima ITS Graphics

More information

色の類似性に基づいた形状特徴量CS-HOGの提案

色の類似性に基づいた形状特徴量CS-HOGの提案 IS3-04 第 18 回 画 像 センシングシンポジウム, 横 浜, 2012 年 6 月 CS-HOG CS-HOG : Color Similarity-based HOG feature Yuhi Goto, Yuji Yamauchi, Hironobu Fujiyoshi Chubu University E-mail: yuhi@vision.cs.chubu.ac.jp Abstract

More information

3 2 2 (1) (2) (3) (4) 4 4 AdaBoost 2. [11] Onishi&Yoda [8] Iwashita&Stoica [5] 4 [3] 3. 3 (1) (2) (3)

3 2 2 (1) (2) (3) (4) 4 4 AdaBoost 2. [11] Onishi&Yoda [8] Iwashita&Stoica [5] 4 [3] 3. 3 (1) (2) (3) (MIRU2012) 2012 8 820-8502 680-4 E-mail: {d kouno,shimada,endo}@pluto.ai.kyutech.ac.jp (1) (2) (3) (4) 4 AdaBoost 1. Kanade [6] CLAFIC [12] EigenFace [10] 1 1 2 1 [7] 3 2 2 (1) (2) (3) (4) 4 4 AdaBoost

More information

Presentation Title

Presentation Title 画像のためのディープラーニング ( 深層学習 ) ~ CNN/R-CNN による物体の認識と検出 ~ MathWorks Japan アプリケーションエンジニアリング部テクニカルコンピューティング 太田英司 2017 The MathWorks, Inc. 1 機械学習 Machine Learning 人間が自然に行っている学習能力と同様の機能をコンピュータで実現しようとする技術 手法 ( ) イヌ

More information

untitled

untitled DEIM Forum 2019 I2-4 305-8573 1-1-1 305-8573 1-1-1 305-8573 1-1-1 ( ) 151-0053 1-3-15 6F 101-8430 2-1-2 CNN LSTM,,,, Measuring Beginner Friendliness / Visiual Intelligibility of Web Pages explaining Academic

More information

SICE東北支部研究集会資料(2017年)

SICE東北支部研究集会資料(2017年) 307 (2017.2.27) 307-8 Deep Convolutional Neural Network X Detecting Masses in Mammograms Based on Transfer Learning of A Deep Convolutional Neural Network Shintaro Suzuki, Xiaoyong Zhang, Noriyasu Homma,

More information

IPSJ SIG Technical Report Vol.2017-CVIM-207 No /5/10 GAN 1,a) 2,b) Generative Adversarial Networks GAN GAN CIFAR-10 10% GAN GAN Stacked GAN Sta

IPSJ SIG Technical Report Vol.2017-CVIM-207 No /5/10 GAN 1,a) 2,b) Generative Adversarial Networks GAN GAN CIFAR-10 10% GAN GAN Stacked GAN Sta 1,a) 2,b) Generative Adversarial Networks CIFAR-10 10% Stacked Stacked 8.9% CNN 1. ILSVRC 1000 50000 5000 Convolutional Neural Network(CNN) [3] Stacked [4] 1 2 a) y.kono@chiba-u.jp b) kawa@faculty.chiba-u.jp

More information

要 旨 題目深層学習による人物検出学籍番号 T 氏名海住嘉希指導教員白井英俊近年 深層学習による画像認識が高い精度で成果を挙げていることで注目されている 本研究では 深層学習によって物体認識を行う三つの手法を用いて実装を行った そして 三つの手法の実装結果から人物検出に焦点をあて これら

要 旨 題目深層学習による人物検出学籍番号 T 氏名海住嘉希指導教員白井英俊近年 深層学習による画像認識が高い精度で成果を挙げていることで注目されている 本研究では 深層学習によって物体認識を行う三つの手法を用いて実装を行った そして 三つの手法の実装結果から人物検出に焦点をあて これら 2016 年度 卒業論文 深層学習による人物検出 指導教員白井英俊教授 中京大学工学部電気電子工学科 学籍番号 T213021 氏名 海住嘉希 (2017 年 1 月 ) 要 旨 題目深層学習による人物検出学籍番号 T213021 氏名海住嘉希指導教員白井英俊近年 深層学習による画像認識が高い精度で成果を挙げていることで注目されている 本研究では 深層学習によって物体認識を行う三つの手法を用いて実装を行った

More information

PowerPoint Presentation

PowerPoint Presentation ディープラーニングの 実践的な適用ワークフロー MathWorks Japan テクニカルコンサルティング部縣亮 2015 The MathWorks, Inc. 1 アジェンダ ディープラーニングとは?( おさらい ) ディープラーニングの適用ワークフロー ワークフローの全体像 MATLAB によるニューラルネットワークの構築 学習 検証 配布 MATLAB ではじめるメリット 試行錯誤のやりやすさ

More information

IPSJ SIG Technical Report Vol.2011-CVIM-177 No /5/ TRECVID2010 SURF Bag-of-Features 1 TRECVID SVM 700% MKL-SVM 883% TRECVID2010 MKL-SVM A

IPSJ SIG Technical Report Vol.2011-CVIM-177 No /5/ TRECVID2010 SURF Bag-of-Features 1 TRECVID SVM 700% MKL-SVM 883% TRECVID2010 MKL-SVM A 1 1 TRECVID2010 SURF Bag-of-Features 1 TRECVID SVM 700% MKL-SVM 883% TRECVID2010 MKL-SVM Analysis of video data recognition using multi-frame Kazuya Hidume 1 and Keiji Yanai 1 In this study, we aim to

More information

(MIRU2009) cuboid cuboid SURF 6 85% Web. Web Abstract Extracting Spatio-te

(MIRU2009) cuboid cuboid SURF 6 85% Web. Web Abstract Extracting Spatio-te (MIRU2009) 2009 7 182 8585 1 5 1 E-mail: noguchi-a@mm.cs.uec.ac.jp, yanai@cs.uec.ac.jp cuboid cuboid SURF 6 85% Web. Web Abstract Extracting Spatio-temporal Local Features Considering Consecutiveness of

More information

Haiku Generation Based on Motif Images Using Deep Learning Koki Yoneda 1 Soichiro Yokoyama 2 Tomohisa Yamashita 2 Hidenori Kawamura Scho

Haiku Generation Based on Motif Images Using Deep Learning Koki Yoneda 1 Soichiro Yokoyama 2 Tomohisa Yamashita 2 Hidenori Kawamura Scho Haiku Generation Based on Motif Images Using Deep Learning 1 2 2 2 Koki Yoneda 1 Soichiro Yokoyama 2 Tomohisa Yamashita 2 Hidenori Kawamura 2 1 1 School of Engineering Hokkaido University 2 2 Graduate

More information

( ) /

( ) / NAIST-IS-MT1551073 2017 3 16 ( ) / , NAIST-IS-MT1551073, 2017 3 16. i 80% ii Finding Important People in a Video using a Deep Neural Network with Conditional Random Field Atsushi Nishida Abstract Finding

More information

,,.,.,,.,.,.,.,,.,..,,,, i

,,.,.,,.,.,.,.,,.,..,,,, i 22 A person recognition using color information 1110372 2011 2 13 ,,.,.,,.,.,.,.,,.,..,,,, i Abstract A person recognition using color information Tatsumo HOJI Recently, for the purpose of collection of

More information

untitled

untitled IS2-26 第 19 回 画 像 センシングシンポジウム, 横 浜,2013 年 6 月 SVM E-mail: yuhi@vision.cs.chubu.ac.jp Abstract SVM SVM SVM SVM HOG B-HOG HOG SVM 6.1% 17 1 Intelligent Transport System(ITS: ) 2005 Dalal HOG SVM[1] [2] HOG

More information

1 (PCA) 3 2 P.Viola 2) Viola AdaBoost 1 Viola OpenCV 3) Web OpenCV T.L.Berg PCA kpca LDA k-means 4) Berg 95% Berg Web k-means k-means

1 (PCA) 3 2 P.Viola 2) Viola AdaBoost 1 Viola OpenCV 3) Web OpenCV T.L.Berg PCA kpca LDA k-means 4) Berg 95% Berg Web k-means k-means Web, Web k-means 62% Associating Faces and Names in Web Photo News Akio Kitahara and Keiji Yanai We propose a system which extracts faces and person names from news articles with photographs on the Web

More information

2 Fig D human model. 1 Fig. 1 The flow of proposed method )9)10) 2.2 3)4)7) 5)11)12)13)14) TOF 1 3 TOF 3 2 c 2011 Information

2 Fig D human model. 1 Fig. 1 The flow of proposed method )9)10) 2.2 3)4)7) 5)11)12)13)14) TOF 1 3 TOF 3 2 c 2011 Information 1 1 2 TOF 2 (D-HOG HOG) Recall D-HOG 0.07 HOG 0.16 Pose Estimation by Regression Analysis with Depth Information Yoshiki Agata 1 and Hironobu Fujiyoshi 1 A method for estimating the pose of a human from

More information

Microsoft PowerPoint - cvim_harada pptx

Microsoft PowerPoint - cvim_harada pptx 1 2 Flickr reaches 6 billion photos on 1 Aug, 2011. http://www.flickr.com/photos/eon60/6000000000/ 3 4 http://www.dpchallenge.com/image.php?image_id=997702 5 6 http://www.image-net.org/challenges/lsvrc/2011/pascal_ilsvrc_2011.pptx

More information

SICE東北支部研究集会資料(2013年)

SICE東北支部研究集会資料(2013年) 280 (2013.5.29) 280-4 SURF A Study of SURF Algorithm using Edge Image and Color Information Yoshihiro Sasaki, Syunichi Konno, Yoshitaka Tsunekawa * *Iwate University : SURF (Speeded Up Robust Features)

More information

IPSJ SIG Technical Report iphone iphone,,., OpenGl ES 2.0 GLSL(OpenGL Shading Language), iphone GPGPU(General-Purpose Computing on Graphics Proc

IPSJ SIG Technical Report iphone iphone,,., OpenGl ES 2.0 GLSL(OpenGL Shading Language), iphone GPGPU(General-Purpose Computing on Graphics Proc iphone 1 1 1 iphone,,., OpenGl ES 2.0 GLSL(OpenGL Shading Language), iphone GPGPU(General-Purpose Computing on Graphics Processing Unit)., AR Realtime Natural Feature Tracking Library for iphone Makoto

More information

PowerPoint プレゼンテーション

PowerPoint プレゼンテーション 東京大学大学院情報理工学系研究科創造情報学専攻講師中山英樹 1. 画像認識分野における deep learning の歴史 2. 一般画像認識 :Deep learning 以前と以後で何が変わったか Bag-of-visual-words (VLAD, Fisher Vector) Convolutional neural network (ConvNets) 3. 最新の動向 今後の展望 ILSVRC

More information

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. Wang Jiani {jwang,mnod

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. Wang Jiani {jwang,mnod THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. Wang Jiani 464 8601 500 8288 1 38 E-mail: {jwang,mnoda}@murase.m.is.nagoya-u.ac.jp, {ddeguchi,ide,murase}@is.nagoya-u.ac.jp

More information

,,,,,,,,,,,,,,,,,,, 976%, i

,,,,,,,,,,,,,,,,,,, 976%, i 20 Individual Recognition using positions of facial parts 1115081 2009 3 5 ,,,,,,,,,,,,,,,,,,, 976%, i Abstract Individual Recognition using positions of facial parts YOSHIHIRO Arisawa A facial recognition

More information

PowerPoint プレゼンテーション

PowerPoint プレゼンテーション 東京大学大学院情報理工学系研究科創造情報学専攻中山英樹 1. 画像認識分野におけるdeep learningの歴史と発展 2. 畳み込みニューラルネット (CNN) を用いた転移学習 3. 実践方法 2 1. 画像認識分野におけるdeep learningの歴史と発展 2. 畳み込みニューラルネット (CNN) を用いた転移学習 3. 実践方法 3 制約をおかない実世界環境の画像を単語で記述 一般的な物体やシーン

More information

yoo_graduation_thesis.dvi

yoo_graduation_thesis.dvi 200 3 A Graduation Thesis of College of Engineering, Chubu University Keypoint Matching of Range Data from Features of Shape and Appearance Yohsuke Murai 1 1 2 2.5D 3 2.1 : : : : : : : : : : : : : : :

More information

2.2 6).,.,.,. Yang, 7).,,.,,. 2.3 SIFT SIFT (Scale-Invariant Feature Transform) 8).,. SIFT,,. SIFT, Mean-Shift 9)., SIFT,., SIFT,. 3.,.,,,,,.,,,., 1,

2.2 6).,.,.,. Yang, 7).,,.,,. 2.3 SIFT SIFT (Scale-Invariant Feature Transform) 8).,. SIFT,,. SIFT, Mean-Shift 9)., SIFT,., SIFT,. 3.,.,,,,,.,,,., 1, 1 1 2,,.,.,,, SIFT.,,. Pitching Motion Analysis Using Image Processing Shinya Kasahara, 1 Issei Fujishiro 1 and Yoshio Ohno 2 At present, analysis of pitching motion from baseball videos is timeconsuming

More information

No. 3 Oct The person to the left of the stool carried the traffic-cone towards the trash-can. α α β α α β α α β α Track2 Track3 Track1 Track0 1

No. 3 Oct The person to the left of the stool carried the traffic-cone towards the trash-can. α α β α α β α α β α Track2 Track3 Track1 Track0 1 ACL2013 TACL 1 ACL2013 Grounded Language Learning from Video Described with Sentences (Yu and Siskind 2013) TACL Transactions of the Association for Computational Linguistics What Makes Writing Great?

More information

Presentation Title

Presentation Title ディープラーニングによる画像認識の基礎と実践ワークフロー MathWorks Japan アプリケーションエンジニアリング部アプリケーションエンジニア福本拓司 2018 The MathWorks, Inc. 1 一般的におこなわれる目視による評価 製造ライン 医用データ 作業現場 インフラ 研究データ 現場での目視 大量画像の収集 専門家によるチェック 2 スマートフォンで撮影した映像をその場で評価

More information

Computational Semantics 1 category specificity Warrington (1975); Warrington & Shallice (1979, 1984) 2 basic level superiority 3 super-ordinate catego

Computational Semantics 1 category specificity Warrington (1975); Warrington & Shallice (1979, 1984) 2 basic level superiority 3 super-ordinate catego Computational Semantics 1 category specificity Warrington (1975); Warrington & Shallice (1979, 1984) 2 basic level superiority 3 super-ordinate category preservation 1 / 13 analogy by vector space Figure

More information

12_39.dvi

12_39.dvi Vol. 52 No. 12 3588 3592 (Dec. 2011) Web 1, 1 1 2 1 1 1 Web GPS Creation of a Sight-seeing Map with Visual Classification of Photos on the Web Jiani Wang, 1, 1 Masafumi Noda, 1 Tomokazu Takahashi, 2 Daisuke

More information

HOG HOG LBP LBP 4) LBP LBP Wang LBP HOG LBP 5) LBP LBP 1 r n 1 n, 1

HOG HOG LBP LBP 4) LBP LBP Wang LBP HOG LBP 5) LBP LBP 1 r n 1 n, 1 1 1 1 Shwartz Histgrams of Oriented Gradients HOG PLS PLS KPLS INRIA PLS KPLS KPLS PLS Pedestrian Detection Using Kernel Partial Least Squares Analysis Takashi Abe, 1 Takayuki Okatani 1 and Kouichiro Deguchi

More information

4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q

4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q x-means 1 2 2 x-means, x-means k-means Bayesian Information Criterion BIC Watershed x-means Moving Object Extraction Using the Number of Clusters Determined by X-means Clustering Naoki Kubo, 1 Kousuke

More information

先端人工知能論Ⅰ

先端人工知能論Ⅰ 情報 システム工学概論画像 映像認識のモデル化 2017/11/13 知能機械情報学専攻機械情報工学科 ( 機械 B) 原田達也 Results (2012) http://www.isi.imi.i.u-tokyo.ac.jp/pattern/ilsvrc2012/index.html 1. brown bear 2. Tibetan mastiff 3. sloth bear 4. American

More information

Presentation Title

Presentation Title 基礎から始める機械学習 深層学習 MathWorks Japan アプリケーションエンジニア井原瑞希 2018 The MathWorks, Inc. 1 Outline 機械学習の基礎 教師あり学習と教師なし学習 教師あり学習 回帰と分類 Case1: 特徴が明確な場合の数値の分類 ニューラルネットワーク以外の機械学習 Case2: 特徴が不明瞭な場合の信号分類 ニューラルネットワーク Case3:

More information

Microsoft PowerPoint - pr_12_template-bs.pptx

Microsoft PowerPoint - pr_12_template-bs.pptx 12 回パターン検出と画像特徴 テンプレートマッチング 領域分割 画像特徴 テンプレート マッチング 1 テンプレートマッチング ( 図形 画像などの ) 型照合 Template Matching テンプレートと呼ばれる小さな一部の画像領域と同じパターンが画像全体の中に存在するかどうかを調べる方法 画像内にある対象物体の位置検出 物体数のカウント 物体移動の検出などに使われる テンプレートマッチングの計算

More information

IPSJ SIG Technical Report Vol.2017-MUS-116 No /8/24 MachineDancing: 1,a) 1,b) 3 MachineDancing MachineDancing MachineDancing 1 MachineDan

IPSJ SIG Technical Report Vol.2017-MUS-116 No /8/24 MachineDancing: 1,a) 1,b) 3 MachineDancing MachineDancing MachineDancing 1 MachineDan MachineDancing: 1,a) 1,b) 3 MachineDancing 2 1. 3 MachineDancing MachineDancing 1 MachineDancing MachineDancing [1] 1 305 0058 1-1-1 a) s.fukayama@aist.go.jp b) m.goto@aist.go.jp 1 MachineDancing 3 CG

More information

1 Kinect for Windows M = [X Y Z] T M = [X Y Z ] T f (u,v) w 3.2 [11] [7] u = f X +u Z 0 δ u (X,Y,Z ) (5) v = f Y Z +v 0 δ v (X,Y,Z ) (6) w = Z +

1 Kinect for Windows M = [X Y Z] T M = [X Y Z ] T f (u,v) w 3.2 [11] [7] u = f X +u Z 0 δ u (X,Y,Z ) (5) v = f Y Z +v 0 δ v (X,Y,Z ) (6) w = Z + 3 3D 1,a) 1 1 Kinect (X, Y) 3D 3D 1. 2010 Microsoft Kinect for Windows SDK( (Kinect) SDK ) 3D [1], [2] [3] [4] [5] [10] 30fps [10] 3 Kinect 3 Kinect Kinect for Windows SDK 3 Microsoft 3 Kinect for Windows

More information

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s 1 1 1, Extraction of Transmitted Light using Parallel High-frequency Illumination Kenichiro Tanaka 1 Yasuhiro Mukaigawa 1 Yasushi Yagi 1 Abstract: We propose a new sharpening method of transmitted scene

More information

IPSJ SIG Technical Report Vol.2015-MPS-103 No.29 Vol.2015-BIO-42 No /6/24 Deep Convolutional Neural Network 1,a) 1,b),c) X CT (Computer Aided D

IPSJ SIG Technical Report Vol.2015-MPS-103 No.29 Vol.2015-BIO-42 No /6/24 Deep Convolutional Neural Network 1,a) 1,b),c) X CT (Computer Aided D Deep Convolutional Neural Network 1,a) 1,b),c) X CT (Computer Aided Diagnosis : CAD) CAD Deep Convolutional Neural Network (DCNN) DCNN CT DCNN DCNN Support Vector Machine DCNN, Anaysis for Deep Convolutional

More information

IPSJ SIG Technical Report Vol.2010-CVIM-171 No /3/19 1. Web 1 1 Web Web Web Multiple Kernel Learning(MKL) Web ( ) % MKL 68.8% Extractin

IPSJ SIG Technical Report Vol.2010-CVIM-171 No /3/19 1. Web 1 1 Web Web Web Multiple Kernel Learning(MKL) Web ( ) % MKL 68.8% Extractin 1. Web 1 1 Web Web Web Multiple Kernel Learning(MKL) Web ( ) 200 57.2% MKL 68.8% Extracting Spatio-Temporal Local Features for Classifying Web Video Shots Akitsugu Noguchi 1 and Keiji Yanai 1 Nowadays,

More information

Outline ACL 2017 ACL ACL 2017 Chairs/Presidents

Outline ACL 2017 ACL ACL 2017 Chairs/Presidents ACL 2017, 2017/9/7 Outline ACL 2017 ACL ACL 2017 Chairs/Presidents ACL ACL he annual meeting of the Association for Computational Linguistics (Computational Linguistics) (Natural Language Processing) /

More information

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2016-HPC-155 No /8/8 1,a) Convolutional Neural Network (CNN) CNN Stochastic Gradient Descent

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2016-HPC-155 No /8/8 1,a) Convolutional Neural Network (CNN) CNN Stochastic Gradient Descent 1,a) 1 3 3 1 Convolutional Neural Network (CNN) CNN Stochastic Gradient Descent (SGD) SGD GPU CNN SGD SGD CNN SPRINT CNN TSUBAME-KFC/DL 116 CNN 8% 1. Deep Learning (DL) Deep Neural Network (DNN) [1] []

More information

Mastering the Game of Go without Human Knowledge ( ) AI 3 1 AI 1 rev.1 (2017/11/26) 1 6 2

Mastering the Game of Go without Human Knowledge ( ) AI 3 1 AI 1 rev.1 (2017/11/26) 1 6 2 6 2 6.1........................................... 3 6.2....................... 5 6.2.1........................... 5 6.2.2........................... 9 6.2.3................. 11 6.3.......................

More information

untitled

untitled 34 3 1 2016 4 JRSJ Vol. 34 No. 3 2 Apr., 2016 34 3 3 2016 4 JRSJ Vol. 34 No. 3 4 Apr., 2016 34 3 5 2016 4 JRSJ Vol. 34 No. 3 6 Apr., 2016 34 3 7 2016 4 JRSJ Vol. 34 No. 3 8 Apr., 2016 34 3 9 2016 4 JRSJ

More information

JRSJ Vol. 22 No. 5 2 July, 2004

JRSJ Vol. 22 No. 5 2 July, 2004 22 5 1 2004 7 JRSJ Vol. 22 No. 5 2 July, 2004 22 5 3 2004 7 JRSJ Vol. 22 No. 5 4 July, 2004 22 5 5 2004 7 JRSJ Vol. 22 No. 5 6 July, 2004 _ 106367500190 8 57896 seminarrsj.or.jp 113 0033 2 19 7 2F TEL

More information

Systems Research for Cyber-Physical Systems

Systems Research for Cyber-Physical Systems 自動運転システムにおける 高性能計算技術の応用 加藤真平 名古屋大学大学院情報科学研究科 准教授 Velodyne HDL-64e (3D LIDAR) Velodyne HDL-32e (3D LIDAR) JAVAD RTK-GNSS (GNSS/GPS) HOKUYO UTM-30LX (LIDAR) Point Grey Ladybug 5 (Camera) IBEO LUX 8L (3D

More information

光学

光学 Fundamentals of Projector-Camera Systems and Their Calibration Methods Takayuki OKATANI To make the images projected by projector s appear as desired, it is e ective and sometimes an only choice to capture

More information

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2 CHLAC 1 2 3 3,. (CHLAC), 1).,.,, CHLAC,.,. Suspicious Behavior Detection based on CHLAC Method Hideaki Imanishi, 1 Toyohiro Hayashi, 2 Shuichi Enokida 3 and Toshiaki Ejima 3 We have proposed a method for

More information

(a) (b) 2 2 (Bosch, IR Illuminator 850 nm, UFLED30-8BD) ( 7[m] 6[m]) 3 (PointGrey Research Inc.Grasshopper2 M/C) Hz (a) (b

(a) (b) 2 2 (Bosch, IR Illuminator 850 nm, UFLED30-8BD) ( 7[m] 6[m]) 3 (PointGrey Research Inc.Grasshopper2 M/C) Hz (a) (b (MIRU202) 202 8 AdrianStoica 89 0395 744 89 0395 744 Jet Propulsion Laboratory 4800 Oak Grove Drive, Pasadena, CA 909, USA E-mail: uchino@irvs.ait.kyushu-u.ac.jp, {yumi,kurazume}@ait.kyushu-u.ac.jp 2 nearest

More information

3: 2: 2. 2 Semi-supervised learning Semi-supervised learning [5,6] Semi-supervised learning Self-training [13] [14] Self-training Self-training Semi-s

3: 2: 2. 2 Semi-supervised learning Semi-supervised learning [5,6] Semi-supervised learning Self-training [13] [14] Self-training Self-training Semi-s THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. 599-8531 1-1 E-mail: tsukada@m.cs.osakafu-u.ac.jp, {masa,kise}@cs.osakafu-u.ac.jp Semi-supervised learning

More information

1 Bin Bin APC Pick task 3 Stow task 2 Pick task Bin 2. 2 Stow task Stow task APC 2016 Tote 12 Bin Bin Stow task

1 Bin Bin APC Pick task 3 Stow task 2 Pick task Bin 2. 2 Stow task Stow task APC 2016 Tote 12 Bin Bin Stow task THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. [ ] Amazon Picking Challenge 2016 487 8501 1200 Preferred Networks 100 0004 1 6 1 2F 113 8656 7 3 1 E-mail:

More information

21 Pitman-Yor Pitman- Yor [7] n -gram W w n-gram G Pitman-Yor P Y (d, θ, G 0 ) (1) G P Y (d, θ, G 0 ) (1) Pitman-Yor d, θ, G 0 d 0 d 1 θ Pitman-Yor G

21 Pitman-Yor Pitman- Yor [7] n -gram W w n-gram G Pitman-Yor P Y (d, θ, G 0 ) (1) G P Y (d, θ, G 0 ) (1) Pitman-Yor d, θ, G 0 d 0 d 1 θ Pitman-Yor G ol2013-nl-214 No6 1,a) 2,b) n-gram 1 M [1] (TG: Tree ubstitution Grammar) [2], [3] TG TG 1 2 a) ohno@ilabdoshishaacjp b) khatano@maildoshishaacjp [4], [5] [6] 2 Pitman-Yor 3 Pitman-Yor 1 21 Pitman-Yor

More information

Gaze Head Eye (a) deg (b) 45 deg (c) 9 deg 1: - 1(b) - [5], [6] [7] Stahl [8], [9] Fang [1], [11] Itti [12] Itti [13] [7] Fang [1],

Gaze Head Eye (a) deg (b) 45 deg (c) 9 deg 1: - 1(b) - [5], [6] [7] Stahl [8], [9] Fang [1], [11] Itti [12] Itti [13] [7] Fang [1], 1 1 1 Structure from Motion - 1 Ville [1] NAC EMR-9 [2] 1 Osaka University [3], [4] 1 1(a) 1(c) 9 9 9 c 216 Information Processing Society of Japan 1 Gaze Head Eye (a) deg (b) 45 deg (c) 9 deg 1: - 1(b)

More information

Computer Security Symposium October ,a) 1,b) Microsoft Kinect Kinect, Takafumi Mori 1,a) Hiroaki Kikuchi 1,b) [1] 1 Meiji U

Computer Security Symposium October ,a) 1,b) Microsoft Kinect Kinect, Takafumi Mori 1,a) Hiroaki Kikuchi 1,b) [1] 1 Meiji U Computer Security Symposium 017 3-5 October 017 1,a) 1,b) Microsoft Kinect Kinect, Takafumi Mori 1,a) Hiroaki Kikuchi 1,b) 1. 017 5 [1] 1 Meiji University Graduate School of Advanced Mathematical Science

More information

Silhouette on Image Object Silhouette on Images Object 1 Fig. 1 Visual cone Fig. 2 2 Volume intersection method Fig. 3 3 Background subtraction Fig. 4

Silhouette on Image Object Silhouette on Images Object 1 Fig. 1 Visual cone Fig. 2 2 Volume intersection method Fig. 3 3 Background subtraction Fig. 4 Image-based Modeling 1 1 Object Extraction Method for Image-based Modeling using Projection Transformation of Multi-viewpoint Images Masanori Ibaraki 1 and Yuji Sakamoto 1 The volume intersection method

More information

一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGIN

一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGIN 一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS 信学技報 IEICE Technical Report PRMU2017-36,SP2017-12(2017-06)

More information

5A3 セマンティックセグメンテーションによる牡蠣生育予測のための データセット作成の基礎検討 Preliminary Investigation of Dataset Creation to Predict Oysters Growth by Semantic Segmentation 大阪府立大

5A3 セマンティックセグメンテーションによる牡蠣生育予測のための データセット作成の基礎検討 Preliminary Investigation of Dataset Creation to Predict Oysters Growth by Semantic Segmentation 大阪府立大 5A3 セマンティックセグメンテーションによる牡蠣生育予測のための データセット作成の基礎検討 Preliminary Investigation of Dataset Creation to Predict Oysters Growth by Semantic Segmentation 大阪府立大学 梁志鵬佐賀亮介 Zhipeng Liang and Ryosuke Saga Osaka Prefecture

More information

スライド 1

スライド 1 CNN を用いた弱教師学習による画像領域分割 下田和, 柳井啓司 電気通信大学 大学院情報理工学 研究科 総合情報学専攻 c 2015 UEC Tokyo. Convolutional Neural Network CNN クラス分類タスクにおいてトップの精度 CNN の応用 ( 物体位置の認識 ) 物体検出 物体に BB を付与 領域分割 ピクセル単位の認識 CNN を用いた領域分割 CNN による完全教師ありのセグメンテーション

More information

A Graduation Thesis of College of Engineering, Chubu University Pose Estimation by Regression Analysis with Depth Information Yoshiki Agata

A Graduation Thesis of College of Engineering, Chubu University Pose Estimation by Regression Analysis with Depth Information Yoshiki Agata 2011 3 A Graduation Thesis of College of Engineering, Chubu University Pose Estimation by Regression Analysis with Depth Information Yoshiki Agata CG [2] [3][4] 3 3 [1] HOG HOG TOF(Time Of Flight) iii

More information

2. 30 Visual Words TF-IDF Lowe [4] Scale-Invarient Feature Transform (SIFT) Bay [1] Speeded Up Robust Features (SURF) SIFT 128 SURF 64 Visual Words Ni

2. 30 Visual Words TF-IDF Lowe [4] Scale-Invarient Feature Transform (SIFT) Bay [1] Speeded Up Robust Features (SURF) SIFT 128 SURF 64 Visual Words Ni DEIM Forum 2012 B5-3 606 8510 E-mail: {zhao,ohshima,tanaka}@dl.kuis.kyoto-u.ac.jp Web, 1. Web Web TinEye 1 Google 1 http://www.tineye.com/ 1 2. 3. 4. 5. 6. 2. 30 Visual Words TF-IDF Lowe [4] Scale-Invarient

More information

IPSJ SIG Technical Report Vol.2013-CVIM-188 No /9/2 1,a) D. Marr D. Marr 1. (feature-based) (area-based) (Dense Stereo Vision) van der Ma

IPSJ SIG Technical Report Vol.2013-CVIM-188 No /9/2 1,a) D. Marr D. Marr 1. (feature-based) (area-based) (Dense Stereo Vision) van der Ma ,a) D. Marr D. Marr. (feature-based) (area-based) (Dense Stereo Vision) van der Mark [] (Intelligent Vehicle: IV) SAD(Sum of Absolute Difference) Intel x86 CPU SSE2(Streaming SIMD Extensions 2) CPU IV

More information

2008 : 80725872 1 2 2 3 2.1.......................................... 3 2.2....................................... 3 2.3......................................... 4 2.4 ()..................................

More information

1(a) (b),(c) - [5], [6] Itti [12] [13] gaze eyeball head 2: [time] [7] Stahl [8], [9] Fang [1], [11] 3 -

1(a) (b),(c) - [5], [6] Itti [12] [13] gaze eyeball head 2: [time] [7] Stahl [8], [9] Fang [1], [11] 3 - Vol216-CVIM-22 No18 216/5/12 1 1 1 Structure from Motion - 1 8% Tobii Pro TX3 NAC EMR ACTUS Eye Tribe Tobii Pro Glass NAC EMR-9 Pupil Headset Ville [1] EMR-9 [2] 1 Osaka University Gaze Head Eye (a) deg

More information

(fnirs: Functional Near-Infrared Spectroscopy) [3] fnirs (oxyhb) Bulling [4] Kunze [5] [6] 2. 2 [7] [8] fnirs 3. 1 fnirs fnirs fnirs 1

(fnirs: Functional Near-Infrared Spectroscopy) [3] fnirs (oxyhb) Bulling [4] Kunze [5] [6] 2. 2 [7] [8] fnirs 3. 1 fnirs fnirs fnirs 1 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. fnirs Kai Kunze 599 8531 1 1 223 8526 4 1 1 E-mail: yoshimura@m.cs.osakafu-u.ac.jp, kai@kmd.keio.ac.jp,

More information

IPSJ SIG Technical Report Vol.2010-MPS-77 No /3/5 VR SIFT Virtual View Generation in Hallway of Cybercity Buildings from Video Sequen

IPSJ SIG Technical Report Vol.2010-MPS-77 No /3/5 VR SIFT Virtual View Generation in Hallway of Cybercity Buildings from Video Sequen VR 1 1 1 1 1 SIFT Virtual View Generation in Hallway of Cybercity Buildings from Video Sequences Sachiyo Yoshida, 1 Masami Takata 1 and Joe Kaduki 1 Appearance of Three-dimensional (3D) building model

More information

Vol1-CVIM-172 No.7 21/5/ Shan 1) 2 2)3) Yuan 4) Ancuti 5) Agrawal 6) 2.4 Ben-Ezra 7)8) Raskar 9) Image domain Blur image l PSF b / = F(

Vol1-CVIM-172 No.7 21/5/ Shan 1) 2 2)3) Yuan 4) Ancuti 5) Agrawal 6) 2.4 Ben-Ezra 7)8) Raskar 9) Image domain Blur image l PSF b / = F( Vol1-CVIM-172 No.7 21/5/27 1 Proposal on Ringing Detector for Image Restoration Chika Inoshita, Yasuhiro Mukaigawa and Yasushi Yagi 1 A lot of methods have been proposed for restoring blurred images due

More information

1 Table 1: Identification by color of voxel Voxel Mode of expression Nothing Other 1 Orange 2 Blue 3 Yellow 4 SSL Humanoid SSL-Vision 3 3 [, 21] 8 325

1 Table 1: Identification by color of voxel Voxel Mode of expression Nothing Other 1 Orange 2 Blue 3 Yellow 4 SSL Humanoid SSL-Vision 3 3 [, 21] 8 325 社団法人人工知能学会 Japanese Society for Artificial Intelligence 人工知能学会研究会資料 JSAI Technical Report SIG-Challenge-B3 (5/5) RoboCup SSL Humanoid A Proposal and its Application of Color Voxel Server for RoboCup SSL

More information

& 3 3 ' ' (., (Pixel), (Light Intensity) (Random Variable). (Joint Probability). V., V = {,,, V }. i x i x = (x, x,, x V ) T. x i i (State Variable),

& 3 3 ' ' (., (Pixel), (Light Intensity) (Random Variable). (Joint Probability). V., V = {,,, V }. i x i x = (x, x,, x V ) T. x i i (State Variable), .... Deeping and Expansion of Large-Scale Random Fields and Probabilistic Image Processing Kazuyuki Tanaka The mathematical frameworks of probabilistic image processing are formulated by means of Markov

More information

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.,,

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.,, THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.,, 464 8601 470 0393 101 464 8601 E-mail: matsunagah@murase.m.is.nagoya-u.ac.jp, {ide,murase,hirayama}@is.nagoya-u.ac.jp,

More information

日本感性工学会論文誌

日本感性工学会論文誌 J-STAGE 2019.03.05 Transactions of Japan Society of Kansei Engineering J-STAGE Advance Published Date: 2019.03.05 doi: 10.5057/jjske.TJSKE-D-18-00071 Automatic Affective Image Captioning System using Emotion

More information

(4) ω t(x) = 1 ω min Ω ( (I C (y))) min 0 < ω < C A C = 1 (5) ω (5) t transmission map tmap 1 4(a) 2. 3 2. 2 t 4(a) t tmap RGB 2 (a) RGB (A), (B), (C)

(4) ω t(x) = 1 ω min Ω ( (I C (y))) min 0 < ω < C A C = 1 (5) ω (5) t transmission map tmap 1 4(a) 2. 3 2. 2 t 4(a) t tmap RGB 2 (a) RGB (A), (B), (C) (MIRU2011) 2011 7 890 0065 1 21 40 105-6691 1 1 1 731 3194 3 4 1 338 8570 255 346 8524 1836 1 E-mail: {fukumoto,kawasaki}@ibe.kagoshima-u.ac.jp, ryo-f@hiroshima-cu.ac.jp, fukuda@cv.ics.saitama-u.ac.jp,

More information

34 (2017 ) Advances in machine learning technologies make inductive programming a reality. As opposed to the conventional (deductive) programming, the

34 (2017 ) Advances in machine learning technologies make inductive programming a reality. As opposed to the conventional (deductive) programming, the 34 (2017 ) Advances in machine learning technologies make inductive programming a reality. As opposed to the conventional (deductive) programming, the development process for inductive programming is such

More information

(3.6 ) (4.6 ) 2. [3], [6], [12] [7] [2], [5], [11] [14] [9] [8] [10] (1) Voodoo 3 : 3 Voodoo[1] 3 ( 3D ) (2) : Voodoo 3D (3) : 3D (Welc

(3.6 ) (4.6 ) 2. [3], [6], [12] [7] [2], [5], [11] [14] [9] [8] [10] (1) Voodoo 3 : 3 Voodoo[1] 3 ( 3D ) (2) : Voodoo 3D (3) : 3D (Welc 1,a) 1,b) Obstacle Detection from Monocular On-Vehicle Camera in units of Delaunay Triangles Abstract: An algorithm to detect obstacles by using a monocular on-vehicle video camera is developed. Since

More information

DEIM Forum 2012 E Web Extracting Modification of Objec

DEIM Forum 2012 E Web Extracting Modification of Objec DEIM Forum 2012 E4-2 670 0092 1 1 12 E-mail: nd11g028@stshse.u-hyogo.ac.jp, {dkitayama,sumiya}@shse.u-hyogo.ac.jp Web Extracting Modification of Objects for Supporting Map Browsing Junki MATSUO, Daisuke

More information

b4-deeplearning-embedded-c-mw

b4-deeplearning-embedded-c-mw ディープラーニングアプリケーション の組み込み GPU/CPU 実装 アプリケーションエンジニアリング部町田和也 2015 The MathWorks, Inc. 1 アジェンダ MATLAB Coder/GPU Coder の概要 ディープニューラルネットワークの組み込み実装ワークフロー パフォーマンスに関して まとめ 2 ディープラーニングワークフローのおさらい Application logic

More information

IPSJ SIG Technical Report GPS LAN GPS LAN GPS LAN Location Identification by sphere image and hybrid sensing Takayuki Katahira, 1 Yoshio Iwai 1

IPSJ SIG Technical Report GPS LAN GPS LAN GPS LAN Location Identification by sphere image and hybrid sensing Takayuki Katahira, 1 Yoshio Iwai 1 1 1 1 GPS LAN GPS LAN GPS LAN Location Identification by sphere image and hybrid sensing Takayuki Katahira, 1 Yoshio Iwai 1 and Hiroshi Ishiguro 1 Self-location is very informative for wearable systems.

More information