PrISM-Tracker
نویسندگان
چکیده
A user often needs training and guidance while performing several daily life procedures, e.g., cooking, setting up a new appliance, or doing COVID test. Watch-based human activity recognition (HAR) can track users' actions during these procedures. However, out of the box, state-of-the-art HAR struggles from noisy data less-expressive that are part tasks. This paper proposes PrISM-Tracker, procedure-tracking framework augments existing models with (1) graph-based procedure representation (2) user-interaction module to handle model uncertainty. Specifically, PrISM-Tracker extends Viterbi algorithm update state probabilities based on time-series outputs by leveraging graph embeds time information as prior. Moreover, identifies moments classes uncertainty asks for improve tracking accuracy. We tested in two procedures: latte-making an engineering lab study wound care skin cancer patients at clinic. The results showed effectiveness proposed utilizing transition graphs steps efficacy using simulated input enhance performance. work is first step toward human-in-the-loop intelligent systems guiding users complicated procedural
منابع مشابه
GLAST Tracker ∗
The Large Area Telescope (LAT) on board the Gamma-ray Large-Area Space Telescope (GLAST) is a pair-conversion gamma-ray detector designed to explore the gamma-ray universe in the 20 MeV– 300 GeV energy band. The Tracker subsystem of the LAT will perform tracking of electron and positrons to determine the origin of the gamma-ray. The design and performance of the GLAST LAT Tracker are described ...
متن کاملVIS-Tracker: A Wearable Vision-Inertial Self-Tracker
We present a demonstrated and commercially viable self-tracker, using robust software that fuses data from inertial and vision sensors. Compared to infrastructurebased trackers, self-trackers have the advantage that objects can be tracked over an extremely wide area, without the prohibitive cost of an extensive network of sensors or emitters to track them. So far most AR research has focused on...
متن کاملSputnik Tracker: Having a Companion Improves Robustness of the Tracker
Tracked objects rarely move alone. They are often temporarily accompanied by other objects undergoing similar motion. We propose a novel tracking algorithm called Sputnik Tracker. It is capable of identifying which image regions move coherently with the tracked object. This information is used to stabilize tracking in the presence of occlusions or fluctuations in the appearance of the tracked o...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies
سال: 2022
ISSN: ['2474-9567']
DOI: https://doi.org/10.1145/3569504