Professional Documents
Culture Documents
Geiger2011IV Slides
Geiger2011IV Slides
2 StereoScan: Approach
2 StereoScan: Approach
Goal:
Real-time 3d from stereo video on a single CPU
Applications:
Environment mapping / place recognition
Scene understanding
Goal:
Real-time 3d from stereo video on a single CPU
Applications:
Environment mapping / place recognition
Scene understanding
[3d Recording for Archeological Fieldwork, Pollefeys et al.] [Building Rome in a Day, Agarwal et al.]
Structure-from-Motion
Monocular ⇒ requires motion
Multiple views of a single object
Computationally demanding
Stixel World
Compact medium-level representation
Integration: Multiple Kalman filters
Can not represent overhanging structures
or strongly curved roads
2 StereoScan: Approach
frame 2
image plane
frame 1 frame 1
frame 2
image plane
frame 1 frame 1
Feature matching:
Detect interest points using non-maximum-suppression
Match 4 images in a ’space-time’ circle
Use epipolar constraints for left ↔ right matching
Accept if last feature coincides with first feature
Feature matching:
Detect interest points using non-maximum-suppression
Match 4 images in a ’space-time’ circle
Use epipolar constraints for left ↔ right matching
Accept if last feature coincides with first feature
Feature matching:
Detect interest points using non-maximum-suppression
Match 4 images in a ’space-time’ circle
Use epipolar constraints for left ↔ right matching
Accept if last feature coincides with first feature
Feature matching:
Detect interest points using non-maximum-suppression
Match 4 images in a ’space-time’ circle
Use epipolar constraints for left ↔ right matching
Accept if last feature coincides with first feature
Feature matching:
Detect interest points using non-maximum-suppression
Match 4 images in a ’space-time’ circle
Use epipolar constraints for left ↔ right matching
Accept if last feature coincides with first feature
frame 2
image plane
frame 1 frame 1
N
2
2
X
(l)
(r )
min
xi − π (l) (Xi ; r, t)
+
xi − π (r ) (Xi ; r, t)
r,t
i=1
frame 2
image plane
frame 1 frame 1
2 StereoScan: Approach
4
Kitt et al. 2010
3.5 our method
our method (2 scales) Stage Time
3
Filter 6.0 ms
Running time (s)
2.5
NMS 12 ms
2
Matching 1 2.8 ms
1.5 Matching 2 10.7 ms
1 Refinement 5.1 ms
0.5 Total time 36.6 ms
0
0 5000 10000 15000
Number of features
1
10
Kitt et al. 2010
our method
0
10
Stage Time
Running time (s)
RANSAC 3.8 ms
−1
10
Refinement 0.4 ms
Kalman filter 0.1 ms
−2
10 Total time 4.3 ms
−3
10
0 50 100 150 200 250 300 350 400
Number of features
80
70
60
z [meters]
50
40
30
20
10 GPS/IMU
Kitt et al. 2010
0
our method
−120 −100 −80 −60 −40 −20 0
x [meters]
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 23/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24
Conclusion and Future Work
Conclusion:
Proposed a real-time 3D
reconstruction algorithm
Real-time on a single CPU
Large-scale stereo imagery
Code: www.cvlibs.net
Future Work:
Handle dynamic objects
Integrate multiple frames
3d urban scene
understanding (CVPR’11)
Thank you!
StereoScan: Dense 3d in Real-time – Source code: www.cvlibs.net 24/24