ABSTRACT
We present a video stabilization algorithm for ball camera systems that undergo extreme egomotion during sports play. In particular, we focus on the BallCam system which is an American football embedded with an action camera at the tip of the ball. We propose an activity-aware video stabilization algorithm which is able to understand the current activity of the BallCam, which uses estimated activity labels to inform a robust video stabilization algorithm. Activity recognition is performed with a deep convolutional neural network, which uses optical flow.
Supplemental Material
- Kitani, K., Horita, K., Koike, H.: Ballcam!: dynamic view synthesis from spinning cameras. In: Adjunct proceedings of the 25th annual ACM symposium on User interface software and technology, ACM (2012) Google ScholarDigital Library
- Poleg, Y., Ephrat, A., Peleg, S., Arora, C.: Compact cnn for indexing egocentric videos. In: WACV. (2016)Google Scholar
- Grundmann, M., Kwatra, V., Essa, I.: Auto-directed video stabilization with robust l1 optimal camera paths. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2011) Google ScholarDigital Library
- Farnebäck, G.: Two-frame motion estimation based on polynomial expansion. In: Image analysis. Springer (2003) 363--370 Google ScholarDigital Library
Index Terms
- Activity-Aware Video Stabilization for BallCam
Recommendations
Video segmentation and stabilization for BallCam
AH '17: Proceedings of the 8th Augmented Human International ConferenceWe present a video stabilization algorithm for ball camera systems that undergo extreme egomotion during sports play. In particular, we focus on the BallCam system which is an American football embedded with an action camera at the tip of the ball. We ...
BallCam!: dynamic view synthesis from spinning cameras
UIST Adjunct Proceedings '12: Adjunct proceedings of the 25th annual ACM symposium on User interface software and technologyWe are interested in generating novel video sequences from a ball's point of view for sports domains. Despite the challenge of extreme camera motion, we show that we can leverage the periodicity of spinning cameras to generate a stabilized ball point-of-...
Video stabilization using epipolar geometry
We present a new video stabilization technique that uses projective scene reconstruction to treat jittered video sequences. Unlike methods that recover the full three-dimensional geometry of the scene, this model accounts for simple geometric relations ...
Comments