Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Imaging Multistep s‑Triazine Oligomerization via Cobalt-Assisted Deamination and Selective C-C Coupling.

Precision chemistry·2026
Same author

Composite probiotics improve growth performance and enhance immune and antioxidant capacity in weaned yaks by modulating rumen microbiota and their metabolites.

BMC microbiology·2026
Same author

Dendritic nonlinearities mitigate communication costs.

Patterns (New York, N.Y.)·2026
Same author

HAD: Hierarchical Asymmetric Distillation to Bridge Spatio-Temporal Gaps in Event-Based Object Tracking.

IEEE transactions on neural networks and learning systems·2026
Same author

Multi-Pattern Generalization in CO<sub>2</sub>‑EOR: Physically Consistent Surrogate for Saturation-Field Evolution.

ACS omega·2026
Same author

Diselenide-bridged mesoporous silica nanoplatform for baicalin delivery facilitates spinal cord injury repair via CHCHD2-mediated mitochondrial homeostasis restoration.

Materials today. Bio·2026

相关实验视频

Updated: Jan 17, 2026

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow
13:02

Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

Published on: February 27, 2016

12.9K

SNNTracker:在线高速多对象跟踪与尖摄像头

Yajing Zheng, Chengen Li, Jiyuan Zhang

    IEEE transactions on pattern analysis and machine intelligence
    |September 16, 2025
    PubMed
    概括

    SNNTracker是一种新的尖端神经网络 (SNN) 算法,可以为尖端摄像头实现强大的多对象跟踪 (MOT). 它通过直接处理事件流,在具有挑战性的条件下实现高精度,超过现有的实时感知方法.

    科学领域:

    • 神经形态工程的神经形态工程
    • 计算机视觉 计算机视觉

    背景情况:

    • 传统的多对象跟踪 (MOT) 方法因运动模糊和低率而难以处理高速场景.
    • 尖峰摄像机提供连续的时空数据,但现有的基于尖峰的MOT算法在实时性能和时间连续性方面存在局限性.

    研究的目的:

    • 介绍SNNTracker,这是第一个基于完全尖端神经网络 (SNN) 的MOT算法,专为尖端摄像头设计.
    • 通过直接处理尖端流来实现低延迟,高速和强大的多对象跟踪.

    主要方法:

    • 开发了SNNTracker,集成了一个基于动态神经场 (DNF) 的注意力机制来进行检测.
    • 采用基于赢家获取全部 (WTA) 的跟踪模块,具有在线尖峰时刻依赖可塑性 (STDP),用于适应性轨迹学习.
    • 直接处理原始尖峰流,避免中间图像重建.

    主要成果:

    • SNNTracker获得了超过96%的MOTA分数,一些序列达到100%,超过了基于ANN和SNN的最新方法.
    • 在遮蔽,照明变化和暂时物体消失的情况下展示了强大的跟踪.
    • 在新建的尖摄像头MOT数据集上验证了性能,涵盖了各种现实世界的场景.

    结论:

    更多相关视频

    Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
    08:32

    Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

    Published on: June 15, 2020

    13.3K
    A Protocol for Real-time 3D Single Particle Tracking
    10:16

    A Protocol for Real-time 3D Single Particle Tracking

    Published on: January 3, 2018

    15.3K

    相关实验视频

    Last Updated: Jan 17, 2026

    Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow
    13:02

    Three-dimensional Particle Tracking Velocimetry for Turbulence Applications: Case of a Jet Flow

    Published on: February 27, 2016

    12.9K
    Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
    08:32

    Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

    Published on: June 15, 2020

    13.3K
    A Protocol for Real-time 3D Single Particle Tracking
    10:16

    A Protocol for Real-time 3D Single Particle Tracking

    Published on: January 3, 2018

    15.3K
  • SNNTracker推进了神经形态视觉的实时感知,特别是在超高速环境中.
  • 尖端驱动的SNN为低延迟,高速和无标签的多对象跟踪提供了显著的优势.
  • 拟议的方法为机器人和自动驾驶领域更高效,更准确的追踪系统铺平了道路.