+ All Categories
Home > Documents > 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0...

3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0...

Date post: 25-Sep-2020
Category:
Upload: others
View: 0 times
Download: 0 times
Share this document with a friend
15
3D Model Assisted Image Segmentation Srimal Jayawardena Di Yang Marcus Hutter Australian National University srimal(dot)jayawardena(at)anu(dot)edu(dot)au http://users.cecs.anu.edu.au/ ˜ srimalj DICTA 2011 Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 1 / 15
Transcript
Page 1: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

3D Model Assisted Image Segmentation

Srimal Jayawardena Di Yang Marcus HutterAustralian National University

srimal(dot)jayawardena(at)anu(dot)edu(dot)auhttp://users.cecs.anu.edu.au/˜srimalj

DICTA 2011

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 1 / 15

Page 2: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

The problem

Segmenting a mostly homogeneous (same color/texture) object intoparts is a hard problem.

(a) Original Image (b) Segmentated into parts

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 2 / 15

Page 3: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Methodology Overview

Pose estimation(hierarchically minimise gradient based loss)

Contour detection

Segmented parts

Photo of known object

(Input)

3D CAD Model (Input)

Project 3D model parts (initialise contour detection)

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 3 / 15

Page 4: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Gradient Loss for Pose EstimationLet θ parameterize the pose of the 3D model w.r.t the camera.

(a) 3D Model Gradients GN(θ) (b) Photo Gradients GI

Loss at pose θ,

Lg(θ) := 1− (corr( GN(θ) , GI ))2 ∈ [0, 1]

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 4 / 15

Page 5: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

3D Model Gradients

(a) Φx(u, v,θ) (b) ∂Φx(u,v,θ)∂u

(c) ∂Φx(u,v,θ)∂v

(d) Φy(u, v,θ) (e) ∂Φy(u,v,θ)

∂u(f) ∂Φy(u,v,θ)

∂v

(g) Φz(u, v,θ) (h) ∂Φz(u,v,θ)∂u

(i) ∂Φz(u,v,θ)∂v

(j) GN(θ)

GN (θ)(u, v) = ||∇Φ(u, v,θ)||kk (1)

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 5 / 15

Page 6: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Photo Gradients

(a) Real photo (b) SyntheticUsing grayscale intensity

(c) Real ∂I∂u

(d) Synthetic ∂I∂u

(e) Real ∂I∂v

(f) Synthetic ∂I∂v

)

(g) Real GI (h) Synthetic GI

GI(u, v) = ||∇I(u, v)||kk (2)

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 6 / 15

Page 7: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Overlays and Smoothing

(a) Real (b) n=0 (c) n=2

(d) Synthetic (e) n=0 (f) n=2

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 7 / 15

Page 8: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Loss Landscapes

0.975

0.98

0.985

0.99

0.995

1

-15 -10 -5 0 5 10 15

Loss

Valu

e

Percentage shift in x direction from known pose

n = 0n = 1n = 2

(a) 2-norm

0.75

0.8

0.85

0.9

0.95

1

-15 -10 -5 0 5 10 15

Loss

Valu

ePercentage shift in x direction from known pose

n = 0n = 1n = 2

(b) 1-norm

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 8 / 15

Page 9: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Hierarchical Optimization

(a) Photo (b) Background removed

(c) n=2 (d) n=1 (e) n=0

(f) Final fine pose n=0

Next: Initialise a Level Set Evolution contour detection from projected 3Dmodel parts

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 9 / 15

Page 10: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Contour DetectionLevel Set Evolution without re-initialization [Li et al., 2005, CVPR]

Row 1: Level set function, Row 2: Zero level curve

(a) Initialisation (b) (c) (d) Final

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 10 / 15

Page 11: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Results

(a) Initialisation (b) Result (c) Benchmark GC (d) Benchmark LS

(e) Initialisation (f) Result (g) Benchmark GC (h) Benchmark LS

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 11 / 15

Page 12: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Results

(a) Initialisation (b) Result (c) Benchmark GC (d) Benchmark LS

(e) Initialisation (f) Result (g) Benchmark GC (h) Benchmark LS

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 12 / 15

Page 13: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Accuracy

Part segmentation results for two views of a Mazda Astina.

Accuracy = 1−(

No.Misclassified.P ixelsNo.Ground.Truth.P ixels

)Part Side View Semi Profile Avg.Fender 97.7% 97.6% 97.7%Front door 98.1% 95.3% 96.7%Back door 96.8% 93.6% 95.2%Mud flap 97.3% 95.1% 96.2%Front window 97.8% 97.5% 97.7%Back window 99.5% 93.9% 96.7%

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 13 / 15

Page 14: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

Discussion

Challenges - High amount of reflections and noiseA closer initialisation curve - better resultsFuture work - simlutaneous pose estimation and segmentation

Thank you!

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 14 / 15

Page 15: 3D Model Assisted Image Segmentation · (a) Photo (b) Background removed (c) n=2 (d) n=1 (e) n=0 (f) Final fine pose n=0 Next: Initialise a Level Set Evolution contour detection

References I

Li, C., Xu, C., Gui, C., and Fox, M. (2005).

Level set evolution without re-initialization: a new variationalformulation.

In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEEComputer Society Conference on, volume 1, pages 430 – 436 vol. 1.

Srimal Jayawardena Australian National University 3D Model Assted. Img. Seg. DICTA 2011 15 / 15


Recommended