Date on Master's Thesis/Doctoral Dissertation


Document Type

Doctoral Dissertation

Degree Name

Ph. D.


Computer Engineering and Computer Science

Degree Program

Computer Science and Engineering, PhD

Committee Chair

Frigui, Hichem

Committee Co-Chair (if applicable)

Zhang, Xiang

Committee Member

Zhang, Xiang

Committee Member

Nasraoui, Olfa

Committee Member

Park, Juw Won

Committee Member

Zhang, Harry

Author's Keywords

CPR; medical simulation videos; activity detection and recognition; cardio pulmonary resuscitation; machine learning


In this thesis, we propose a framework to detect and retrieve CPR activity scenes from medical simulation videos. Medical simulation is a modern training method for medical students, where an emergency patient condition is simulated on human-like mannequins and the students act upon. These simulation sessions are recorded by the physician, for later debriefing. With the increasing number of simulation videos, automatic detection and retrieval of specific scenes became necessary. The proposed framework for CPR scene retrieval, would eliminate the conventional approach of using shot detection and frame segmentation techniques. Firstly, our work explores the application of Histogram of Oriented Gradients in three dimensions (HOG3D) to retrieve the scenes containing CPR activity. Secondly, we investigate the use of Local Binary Patterns in Three Orthogonal Planes (LBPTOP), which is the three dimensional extension of the popular Local Binary Patterns. This technique is a robust feature that can detect specific activities from scenes containing multiple actors and activities. Thirdly, we propose an improvement to the above mentioned methods by a combination of HOG3D and LBP-TOP. We use decision level fusion techniques to combine the features. We prove experimentally that the proposed techniques and their combination out-perform the existing system for CPR scene retrieval. Finally, we devise a method to detect and retrieve the scenes containing the breathing bag activity, from the medical simulation videos. The proposed framework is tested and validated using eight medical simulation videos and the results are presented.