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

Overlapping Community Detection in Vehicular Social Networks Based on Graph Attention Autoencoder.

Sensors (Basel, Switzerland)·2025
Same author

Lane Detection Based on ECBAM_ASPP Model.

Sensors (Basel, Switzerland)·2025
Same author

Uniform zinc oxide nanowire arrays grown on nonepitaxial surface with general orientation control.

Nano letters·2013
Same author

[American head and neck surgery progress of in 2012].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2013
Same author

A compact thermo-optical multimode-interference silicon-based 1 × 4 nano-photonic switch.

Optics express·2013
Same author

Experimental demonstration of 110-Gb/s unsynchronized band-multiplexed superchannel coherent optical OFDM/OQAM system.

Optics express·2013

相关实验视频

Updated: Jan 9, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.1K

基于深度学习技术的行人轨迹预测方法的审查

Xiang Gu1, Chao Li2, Long Gao2,3

  • 1Yongyou School, Nantong Institute of Technology, Nantong 226001, China.

Sensors (Basel, Switzerland)
|December 11, 2025
PubMed
概括

深度学习模型显著提升自动驾驶的行人轨迹预测,优于传统方法. 本调查分析了RNN,GAN,GCN和变压器,为未来的研究提供了一个框架.

关键词:
自动驾驶自动驾驶的自动驾驶.深度学习是一种深度学习.预测行人轨迹的预测审查 审查 审查 审查 审查 审查

更多相关视频

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.8K
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

9.1K

相关实验视频

Last Updated: Jan 9, 2026

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.1K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.8K
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

9.1K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器人技术 机器人技术 机器人技术

背景情况:

  • 预测行人轨迹对于自动驾驶和智能城市系统至关重要.
  • 深度学习模型在处理复杂的行为和社会互动方面已经超越了传统方法.

研究的目的:

  • 系统地审查和批判性地分析基于深度学习的行人轨迹预测方法.
  • 为循环神经网络 (RNN),生成对抗网络 (GANs),图形卷积网络 (GCNs) 和变压器模型提供结构化检查.
  • 为评估这些方法提供一个比较分析框架.

主要方法:

  • 对用于行人轨迹预测的深度学习模型的系统文献综述.
  • 对四个关键模型家族的分析:RNN,GAN,GCN和变压器.
  • 开发一个比较框架,根据标准化标准评估优势和局限性.
  • 数据集和评估指标的全面分类.

主要成果:

  • 深度学习模型在多模式行为和社会互动预测方面表现出卓越的表现.
  • 对比分析揭示了RNN,GAN,GCN和变压器的明显优缺点.
  • 识别数据集和评估指标中的既定实践和新兴趋势.

结论:

  • 深度学习是行人轨迹预测的主要方法.
  • 未来的研究应该集中在语义场景理解,模型可转移性和精度效率权衡上.
  • 这项调查提供了历史视角,并指导了未来的研究方向.