Detecting Hands in Egocentric Videos: Towards Action Recognition

TL;DR

This paper presents a novel method for detecting hands in egocentric videos, combining skin modeling and CNNs, to improve action recognition despite challenges like lighting and appearance variability.

Contribution

The paper introduces a new hand detection approach that integrates skin modeling with CNNs, achieving competitive results on egocentric video data.

Findings

Achieves competitive hand detection accuracy on UNIGE-HANDS dataset.

Effectively handles lighting variations and hand appearance variability.

Combines skin modeling with CNNs for improved detection performance.

Abstract

Recently, there has been a growing interest in analyzing human daily activities from data collected by wearable cameras. Since the hands are involved in a vast set of daily tasks, detecting hands in egocentric images is an important step towards the recognition of a variety of egocentric actions. However, besides extreme illumination changes in egocentric images, hand detection is not a trivial task because of the intrinsic large variability of hand appearance. We propose a hand detector that exploits skin modeling for fast hand proposal generation and Convolutional Neural Networks for hand recognition. We tested our method on UNIGE-HANDS dataset and we showed that the proposed approach achieves competitive hand detection results.