Labits: Layered Bidirectional Time Surfaces Representation for Event Camera-based Continuous Dense Trajectory Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhongyang, Qiu, Jiacheng, Cui, Shuyang, Luo, Yijun, Rahman, Tauhidur
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910742432710656
author Zhang, Zhongyang
Qiu, Jiacheng
Cui, Shuyang
Luo, Yijun
Rahman, Tauhidur
author_facet Zhang, Zhongyang
Qiu, Jiacheng
Cui, Shuyang
Luo, Yijun
Rahman, Tauhidur
contents Event cameras provide a compelling alternative to traditional frame-based sensors, capturing dynamic scenes with high temporal resolution and low latency. Moving objects trigger events with precise timestamps along their trajectory, enabling smooth continuous-time estimation. However, few works have attempted to optimize the information loss during event representation construction, imposing a ceiling on this task. Fully exploiting event cameras requires representations that simultaneously preserve fine-grained temporal information, stable and characteristic 2D visual features, and temporally consistent information density, an unmet challenge in existing representations. We introduce Labits: Layered Bidirectional Time Surfaces, a simple yet elegant representation designed to retain all these features. Additionally, we propose a dedicated module for extracting active pixel local optical flow (APLOF), significantly boosting the performance. Our approach achieves an impressive 49% reduction in trajectory end-point error (TEPE) compared to the previous state-of-the-art on the MultiFlow dataset. The code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Labits: Layered Bidirectional Time Surfaces Representation for Event Camera-based Continuous Dense Trajectory Estimation
Zhang, Zhongyang
Qiu, Jiacheng
Cui, Shuyang
Luo, Yijun
Rahman, Tauhidur
Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Event cameras provide a compelling alternative to traditional frame-based sensors, capturing dynamic scenes with high temporal resolution and low latency. Moving objects trigger events with precise timestamps along their trajectory, enabling smooth continuous-time estimation. However, few works have attempted to optimize the information loss during event representation construction, imposing a ceiling on this task. Fully exploiting event cameras requires representations that simultaneously preserve fine-grained temporal information, stable and characteristic 2D visual features, and temporally consistent information density, an unmet challenge in existing representations. We introduce Labits: Layered Bidirectional Time Surfaces, a simple yet elegant representation designed to retain all these features. Additionally, we propose a dedicated module for extracting active pixel local optical flow (APLOF), significantly boosting the performance. Our approach achieves an impressive 49% reduction in trajectory end-point error (TEPE) compared to the previous state-of-the-art on the MultiFlow dataset. The code will be released upon acceptance.
title Labits: Layered Bidirectional Time Surfaces Representation for Event Camera-based Continuous Dense Trajectory Estimation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2412.08849