High-Orders Motion Analysis (eBook)

This book shows how different types of motion can be disambiguated into their components in a richer way than that currently possible in computer vision.

Previous research of motion analysis has generally not yet considered the basic nature of higher orders of motion such as acceleration. Hence, this book introduces an approximation of the acceleration field using established optical flow techniques. Further, acceleration is decomposed into radial and tangential based on geometry and propagated as a general motion descriptor; this book shows the capability for differentiating different types of motion both on synthesized data and real image sequences.

Beyond acceleration, the higher orders of motion flow and their continuant parts are investigated for further revealing the chaotic motion fields. Naturally, it is possible to extend this notion further: to detect higher orders of image motion. In this respect, this book shows how jerk and snap can be obtained from image sequences. The derived results on test images and heel strike detection in gait analysis illustrate the ability of higher-order motion, which provide the basis for the following research and applications in the future.

We hope that the publication of this book will bring a new perspective to researchers and graduate students in the field of video analysis in computer vision.

Yan Sun is an assistant professor in the School of Computer Engineering and Science, Shanghai University, China. She obtained her Ph.D. degree in 2018 from the University of Southampton, UK, under the supervision of Professor Mark Nixon and Professor Jonathon Hare.

She received Shanghai Pujiang Program in 2020. She has managed 1 National Natural Science Foundation Project in 2021 and participated in National High-tech Programs and MIIT Special Program for Ships as a key researcher. She has hosted the IEEE-WIE at the 15th Chinese Conference on Biometrics Recognition.

Her research interests mainly focus on computer vision, image processing, analyzing different types of motion in videos, including gait analysis, action recognition, object tracking, etc. Currently, she has published nearly 20 peer-reviewed articles in top journals and conferences, including Pattern Recognition and other top journals and conferences.

---

This book shows how different types of motion can be disambiguated into their components in a richer way than that currently possible in computer vision.Previous research of motion analysis has generally not yet considered the basic nature of higher orders of motion such as acceleration. Hence, this book introduces an approximation of the acceleration field using established optical flow techniques. Further, acceleration is decomposed into radial and tangential based on geometry and propagated as a general motion descriptor; this book shows the capability for differentiating different types of motion both on synthesized data and real image sequences.Beyond acceleration, the higher orders of motion flow and their continuant parts are investigated for further revealing the chaotic motion fields. Naturally, it is possible to extend this notion further: to detect higher orders of image motion. In this respect, this book shows how jerk and snap can be obtained from image sequences. The derived results on test images and heel strike detection in gait analysis illustrate the ability of higher-order motion, which provide the basis for the following research and applications in the future.We hope that the publication of this book will bring a new perspective to researchers and graduate students in the field of video analysis in computer vision.