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

Aliasing01:18

Aliasing

107
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
107

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

A Transition Structure from Stripline to Substrate-Integrated Waveguide Based on LTCC.

Micromachines·2026
Same author

Design of a Dual-Band Broadband Antenna Based on Structure Reuse.

Micromachines·2026
Same author

Design of Dual Continuous-Mode Class-J Power Amplifiers with Harmonic Matching Networks for X and Ku Bands.

Micromachines·2025
Same author

Language-Driven Cross-Attention for Visible-Infrared Image Fusion Using CLIP.

Sensors (Basel, Switzerland)·2025
Same author

Antenna Array Design Based on Low-Temperature Co-Fired Ceramics.

Micromachines·2024
Same author

Compact Bandwidth-Enhanced 180-Degree Phase Shifter Using Edge-Coupled Multi-Microstrip and Artificial Transmission Line.

Micromachines·2023

相关实验视频

Updated: May 24, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.4K

实时处理平台的硬件加速器用于合成孔径雷达目标检测任务.

Yue Zhang1, Yunshan Tang2, Yue Cao1

  • 1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China.

Micromachines
|March 6, 2025
PubMed
概括

一个新型的低功耗加速器可以在空中平台上使用深度学习在合成孔径雷达 (SAR) 图像中实时检测物体. 这解决了电力限制,实现了有效的目标识别,以加强监控.

关键词:
卷积神经网络 (CNN) 是一种神经网络.合成光圈雷达 (SAR) 图像成像目标检测任务 目标检测任务

更多相关视频

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

7.7K
Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

234

相关实验视频

Last Updated: May 24, 2025

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
06:25

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

8.4K
Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar
07:14

Tracking Infiltration Front Depth Using Time-lapse Multi-offset Gathers Collected with Array Antenna Ground Penetrating Radar

Published on: May 1, 2018

7.7K
Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
14:44

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible

Published on: May 13, 2025

234

科学领域:

  • 人工智能的人工智能
  • 计算机工程 计算机工程
  • 遥感 遥感 遥感 遥感

背景情况:

  • 深度学习对象检测算法对于合成孔径雷达 (SAR) 图像分析至关重要.
  • 实时监控需要在平台上处理SAR数据,但当前的GPU解决方案超过了空中/卫星应用的功率预算.

研究的目的:

  • 设计一种低功耗,低延迟的加速器,用于基于深度学习的SAR对象检测.
  • 为了在功率受限的空载和卫星SAR平台上实现实时目标检测.

主要方法:

  • 开发了一种处理引擎 (PE),用于在现场可编程门数组 (FPGA) 上高效的多维卷积并行计算.
  • 实现了独特的内存配置和适合FPGA的数据流模式,以优化内存访问并减少延迟.
  • 在基于Virtex 7 690t芯片的加速器上部署了Yolov5s SAR物体检测算法.

主要成果:

  • 加速器的动态功耗仅为7瓦.
  • 实时检测能力为每秒52.19张图像,用于512×512张SAR图像.
  • 实现了对卷积计算时间和整体延迟的显著减少.

结论:

  • 设计的加速器有效地满足了在空载和卫星平台上实时SAR对象检测的低功率和低延迟要求.
  • 这项工作使SAR图像的有效,机载分析成为可能,从而推进实时监控能力.