CVFeb 28, 2023

Tracking Fast by Learning Slow: An Event-based Speed Adaptive Hand Tracker Leveraging Knowledge in RGB Domain

arXiv:2302.14430v12 citationsh-index: 28
Originality Incremental advance
AI Analysis

This work addresses hand tracking for fast-moving hands in real-world applications, offering a novel dataset and method but is incremental as it builds on existing RGB-based knowledge.

The paper tackled 3D hand tracking with fast motion by using an event camera to overcome motion blur in RGB videos, achieving superior performance over existing RGB-based and event-based methods in fast hand tracking tasks.

3D hand tracking methods based on monocular RGB videos are easily affected by motion blur, while event camera, a sensor with high temporal resolution and dynamic range, is naturally suitable for this task with sparse output and low power consumption. However, obtaining 3D annotations of fast-moving hands is difficult for constructing event-based hand-tracking datasets. In this paper, we provided an event-based speed adaptive hand tracker (ESAHT) to solve the hand tracking problem based on event camera. We enabled a CNN model trained on a hand tracking dataset with slow motion, which enabled the model to leverage the knowledge of RGB-based hand tracking solutions, to work on fast hand tracking tasks. To realize our solution, we constructed the first 3D hand tracking dataset captured by an event camera in a real-world environment, figured out two data augment methods to narrow the domain gap between slow and fast motion data, developed a speed adaptive event stream segmentation method to handle hand movements in different moving speeds, and introduced a new event-to-frame representation method adaptive to event streams with different lengths. Experiments showed that our solution outperformed RGB-based as well as previous event-based solutions in fast hand tracking tasks, and our codes and dataset will be publicly available.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes