Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information
By: Neelima Prasad , Jarek Reynolds , Neel Karsanbhai and more
Potential Business Impact:
Tracks all parts of objects and their links.
We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/
Similar Papers
Online Segment Any 3D Thing as Instance Tracking
CV and Pattern Recognition
Helps robots understand moving objects in 3D.
HEIR: Learning Graph-Based Motion Hierarchies
CV and Pattern Recognition
Learns how things move by breaking it down.
Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing
CV and Pattern Recognition
Keeps workers safe while cameras watch jobs.