Is First Person Vision Challenging for Object Tracking?

By Matteo Dunnhofer, Antonino Furnari, Giovanni Maria Farinella, Christian Micheloni. 2020

27 citations recorded by the source corpus.

Understanding human-object interactions is fundamental in First Person Vision (FPV). Tracking algorithms which follow the objects manipulated by the camera wearer can provide useful cues to effectively model such interactions. Visual tracking solutions available in the computer vision literature have significantly improved their performance in the last years for a large variety of target objects and tracking scenarios. However, despite a few previous attempts to exploit trackers in FPV applications, a methodical analysis of the performance of state-of-the-art trackers in this domain is still missing. In this paper, we fill the gap by presenting the first systematic study of object tracking in FPV. Our study extensively analyses the performance of recent visual trackers and baseline FPV trackers with respect to different aspects and considering a new performance measure. This is achieved through TREK-150, a novel benchmark dataset composed of 150 densely annotated video sequences. Our results show that object tracking in FPV is challenging, which suggests that more research efforts should be devoted to this problem so that tracking could benefit FPV tasks.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Aside from daily life activity, prior ego datasets focus on conversation [170], inter-person interactions [66, 168, 194, 231], place localization [183, 208], multimodal sensor data [124, 166, 204], human hands [16, 134] human-object interaction [106, 184], and object tracking [56].”
MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain (2022, background): “In some cases, detecting the active objects manipulated by the human without considering the object class [82] can be useful, for example when the taxonomy of the object classes is difﬁcult to obtain or to initialize a tracker [19].”