Trajectory Aligned Features For First Person Action Recognition

TL;DR

This paper introduces a novel trajectory-based feature representation for first person action recognition in egocentric videos, improving accuracy without requiring hand/object segmentation.

Contribution

The proposed method uses simple point tracking to derive features that outperform existing techniques by over 11% in accuracy on public datasets.

Findings

Achieved over 11% performance improvement on public datasets.

Effective in recognizing actions even without visible hands or objects.

Does not require segmentation of hands or objects.

Abstract

Egocentric videos are characterised by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. Recognizing action of the wearer from egocentric videos is an important problem. Unstructured movement of the camera due to natural head motion of the wearer causes sharp changes in the visual field of the egocentric camera causing many standard third person action recognition techniques to perform poorly on such videos. Objects present in the scene and hand gestures of the wearer are the most important cues for first person action recognition but are difficult to segment and recognize in an egocentric video. We propose a novel representation of the first person actions derived from feature trajectories. The features are simple to compute using standard point tracking and does not assume segmentation of hand/objects or recognizing object or hand pose unlike in many previous approaches. We train a bag of words classifier with the proposed features and report a performance improvement of more than 11% on publicly available datasets. Although not designed for the particular case, we show that our technique can also recognize wearer's actions when hands or objects are not visible.