untitled

Size: px

Start display at page:

Download "untitled"

さなえふしはら
5 years ago
Views:

1 (Robot Vision) Vision ( (computer) Machine VisionComputer Vision ( ) ( ) ( ) ( ) ( ) 1

2 DTV 2

3 DTV D 3

4 ( ( ( ( ( DTV D 4

5 () 5

6 A B C D E F G H I A B C D E F G H I I = A + D + G - C - F - I J = A + B + C - G - H - I = I + J = arctan ( I J 6

7 () Roberts (1964) 7

8 Laplacian mask 16 8

9 Edge Background subtraction Fitting Bezer Curve 9

10 10

11 2 H x, y = (det( A ) k ( tr( A )) 2 R x Rx R y A = w( u, v) 2 u v Rx R y R y W : u,v : k : 0.04 Rx Ry Harrisoperator Harris 1. (x, y) 2. 3., 11

12 12 Lucas Kanade f(x,y): g(x,y):lk u,v:( ( ) ( ) = u,v,, SAD v y u x g v y u x f e x b a x' + = f e y x d c b a y x ' (, ): (,) (a,b,c,d): (e,f):

13 Docomo P902isN902isSH902is 13

14 DoCoMo FOMA P902is DoCoMo HP: 14

15 15

16 16

17 17

18 HarrWavelet 18

19 -1,0,1 101 HarrWavelet 19

20 HarrWavelet 20

21 21

22 22

23 Human vision vs Computer vision 以前の迷信デジタルコンピュータは画面の端から順に見ていく人は一目で重要な部分だけに目が行きそこだけを詳しく見るしかし大量の学習データを必要とする学デをす３ＤCG生成プロセスに利用される顔器官輪郭検出顔器官輪郭検出標準ワイヤーフレーム３Ｄレンジデータ３Ｄレンジデータと合わせて３Ｄレンジデタと合わせて２Ｄ画像画像 OKAO Vision 顔器官輪郭検出３Ｄモデル生成画像に整合表情を合成標準ワイヤーフレームを対応点が輪郭点に合致するように変形あらかじめ決められた各点の移動量パターンに従い３Ｄモデルを変形 2005 MITSIMITSI-TOSHIBA PAVILION / dentsu / dentsu tec 23

24 OKAO Vision OKAO Vision 2005 MITSI-TOSHIBA TOSHIBA PAVILION / dentsu / dentsu tec 24

25 mapping robot working robot keypoint 25

26 Scale Invariant Feature Transform example : n=2 26

27 27

Detection Hessian-based interest point localization L xx (x,y,σ) is the Laplacian of Gaussian of the image It is the convolution of the Gaussian second order derivative with the image Lindeberg

28 Detection Hessian-based interest point localization L xx (x,y,σ) is the Laplacian of Gaussian of the image It is the convolution of the Gaussian second order derivative with the image Lindeberg showed Gaussian function is optimal for scale-space analysis This paper argues that Gaussian is overrated since the property that no new structures can appear while going to lower resolution is not proven in 2D case 28

29 Detection Approximated second order derivatives with box filters (mean/average filter) 57 Detection Scale analysis with constant image size 9 x 9, 15 x 15, 21 x 21, 27 x x 39, 51 x 51 1 st octave 2 nd octave 29

30 Detection Non-maximum suppression and interpolation Blob-like feature detector 59 Description Orientation Assignment Circular neighborhood of radius 6s around dthe interest tpoint (s = the scale at which the point was detected) x response y response Side length = 4s Cost 6 operation to 60 compute the response 30

31 Description Dominant orientation The Haar wavelet responses are represented as vectors Sum all responses within a sliding orientation window covering an angle of 60 degree The two summed response yield a new vector The longest vector is the dominant orientation Second longest is ignored 61 Description Splittheinterestregionupinto4x4squaresub-regions the interest region into 4 square sub regions with 5 x 5 regularly spaced sample points inside Calculate Haar wavelet response d x and d y Weight the response with a Gaussian kernel centered at the interest point Sum the response over each sub-region for d x and d y separately tl feature vector of length th32 In order to bring in information about the polarity of the intensity changes, extract the sum of absolute value of the responses feature vector of length 64 Normalize the vector into unit length 62 31

32 Description 63 32

(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