A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video
This survey helps researchers and practitioners in computer vision by summarizing recent advances and datasets in the emerging domain of egocentric video.
The paper provides a broad overview of computer vision algorithms for egocentric video, addressing problems like object recognition, activity detection, and video summarization, and collects and compares evaluation results and benchmark datasets.
Recent technological advances have made lightweight, head mounted cameras both practical and affordable and products like Google Glass show first approaches to introduce the idea of egocentric (first-person) video to the mainstream. Interestingly, the computer vision community has only recently started to explore this new domain of egocentric vision, where research can roughly be categorized into three areas: Object recognition, activity detection/recognition, video summarization. In this paper, we try to give a broad overview about the different problems that have been addressed and collect and compare evaluation results. Moreover, along with the emergence of this new domain came the introduction of numerous new and versatile benchmark datasets, which we summarize and compare as well.