Multiple view geometry in computer visiond
Multiple view geometry in computer visiond
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIGGRAPH '05 ACM SIGGRAPH 2005 Emerging technologies
Automatic Panoramic Image Stitching using Invariant Features
International Journal of Computer Vision
Throwable panoramic ball camera
SIGGRAPH Asia 2011 Emerging Technologies
Human-centric panoramic imaging stitching
AH '12 Proceedings of the 3rd Augmented Human International Conference
BallCam!: dynamic view synthesis from spinning cameras
Adjunct proceedings of the 25th annual ACM symposium on User interface software and technology
| Hi-index | 0.00 |
We place a small wireless camera inside an American football to capture the ball's point-of-view during flight to augment a spectator's experience of the game of football. To this end, we propose a robust video synthesis algorithm that leverages the unique constraints of fast spinning cameras to obtain a stabilized bird's eye point-of-view video clip. Our algorithm uses a coarse-to-fine image homography computation technique to progressively register images. We then optimize an energy function defined over pixel-wise color similarity and distance to image borders, to find optimal image seams to create panoramic composite images. Our results show that we can generate realistic videos from a camera spinning at speeds of up to 600 RPM.