ALmabrok Essa Essa, Sidike Paheding, Daniel P Prince



Download Project (1004 KB)


Rapid advances in the area of sensor technology have enabled the use of video acquisition systems to create large datasets for analysis. However, processing big data requires extensive effort for human analysts. On the other hand, it is observed that many data, such as high-frame rate video, contain redundancy that cause extra work for analysis. Therefore, there is a need to develop an automated frame selection technique to reduce work load. In this research, we develop a method that can extract the most important and meaningful video frames from a large amount of data, while removing the insignificant ones to ease further analysis. These key frames can be selected based on the statistical analysis such as computing the mean and variance among a set of frames or between subsequent frames. We believe this technology benefits the computational performance of many real-world data processing systems, especially in current big data problems.

Publication Date


Project Designation

Graduate Research

Primary Advisor

Vijayan K. Asari

Primary Advisor's Department

Electrical and Computer Engineering


Stander Symposium project

Frame Redundancy Elimination Technology for Big Data Analysis