Early Recognition of Human Activities from First-Person Videos Using Onset Representations
This work addresses the need for predicting human activities in real-time from first-person videos to prevent harmful events, representing an incremental advancement in activity prediction methods.
The paper tackles the problem of early recognition of human activities from first-person videos by introducing the concept of 'onset' to summarize pre-activity observations, resulting in improved and earlier recognition performance as demonstrated in experiments.
In this paper, we propose a methodology for early recognition of human activities from videos taken with a first-person viewpoint. Early recognition, which is also known as activity prediction, is an ability to infer an ongoing activity at its early stage. We present an algorithm to perform recognition of activities targeted at the camera from streaming videos, making the system to predict intended activities of the interacting person and avoid harmful events before they actually happen. We introduce the novel concept of 'onset' that efficiently summarizes pre-activity observations, and design an approach to consider event history in addition to ongoing video observation for early first-person recognition of activities. We propose to represent onset using cascade histograms of time series gradients, and we describe a novel algorithmic setup to take advantage of onset for early recognition of activities. The experimental results clearly illustrate that the proposed concept of onset enables better/earlier recognition of human activities from first-person videos.