Multi class activity classification in videos using Motion History Image generation
This work addresses action recognition for applications in security and entertainment, but it is incremental as it builds on the well-established MHI framework without introducing major innovations.
The paper tackled the problem of multi-class activity classification in videos by using Motion History Images (MHI) to capture temporal and activity information, and demonstrated its effectiveness with a classifier across six different activities in a single video.
Human action recognition has been a topic of interest across multiple fields ranging from security to entertainment systems. Tracking the motion and identifying the action being performed on a real time basis is necessary for critical security systems. In entertainment, especially gaming, the need for immediate responses for actions and gestures are paramount for the success of that system. We show that Motion History image has been a well established framework to capture the temporal and activity information in multi dimensional detail enabling various usecases including classification. We utilize MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video. We analyze the classifier performance and identify usecases where MHI struggles to generate the appropriate activity image and discuss mechanisms and future work to overcome those limitations.