Detection and Classification of Motion Boundaries
Abstract
We segment the trajectory of a moving object into piece-wise smooth motion intervals separated by motion boundaries . Motion boundaries are classified into various types, including starts, stops, pauses, and discontinuous changes of motion due to force impulses. We localize and classify motion boundaries by fitting a mixture of two polynomials near the boundary. Given a classification of motion boundaries, we use naive physical rules to infer a set of changing contact relationships which explain the observed motion. We show segmentation and classification results for several image sequences of a basketball undergoing gravitational and nongravitational motion.
Cite
Text
Mann and Jepson. "Detection and Classification of Motion Boundaries." AAAI Conference on Artificial Intelligence, 2002. doi:10.5555/777092.777210Markdown
[Mann and Jepson. "Detection and Classification of Motion Boundaries." AAAI Conference on Artificial Intelligence, 2002.](https://mlanthology.org/aaai/2002/mann2002aaai-detection/) doi:10.5555/777092.777210BibTeX
@inproceedings{mann2002aaai-detection,
title = {{Detection and Classification of Motion Boundaries}},
author = {Mann, Richard and Jepson, Allan D.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2002},
pages = {764-769},
doi = {10.5555/777092.777210},
url = {https://mlanthology.org/aaai/2002/mann2002aaai-detection/}
}