• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于 SAD 的立体视觉机在可编程片上系统 (SoPC) 上。

SAD-based stereo vision machine on a System-on-Programmable-Chip (SoPC).

机构信息

State Key Laboratory of Fluid Power Transmission and Control, Zhejiang University, Hangzhou 310027, China.

出版信息

Sensors (Basel). 2013 Mar 4;13(3):3014-27. doi: 10.3390/s130303014.

DOI:10.3390/s130303014
PMID:23459385
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC3658728/
Abstract

This paper, proposes a novel solution for a stereo vision machine based on the System-on-Programmable-Chip (SoPC) architecture. The SOPC technology provides great convenience for accessing many hardware devices such as DDRII, SSRAM, Flash, etc., by IP reuse. The system hardware is implemented in a single FPGA chip involving a 32-bit Nios II microprocessor, which is a configurable soft IP core in charge of managing the image buffer and users' configuration data. The Sum of Absolute Differences (SAD) algorithm is used for dense disparity map computation. The circuits of the algorithmic module are modeled by the Matlab-based DSP Builder. With a set of configuration interfaces, the machine can process many different sizes of stereo pair images. The maximum image size is up to 512 K pixels. This machine is designed to focus on real time stereo vision applications. The stereo vision machine offers good performance and high efficiency in real time. Considering a hardware FPGA clock of 90 MHz, 23 frames of 640 × 480 disparity maps can be obtained in one second with 5 × 5 matching window and maximum 64 disparity pixels.

摘要

本文提出了一种基于片上可编程系统(SoPC)架构的立体视觉机器的新解决方案。SOPC 技术通过 IP 复用为访问 DDRII、SSRAM、Flash 等许多硬件设备提供了极大的便利。系统硬件在单个 FPGA 芯片中实现,其中包含 32 位 Nios II 微处理器,它是负责管理图像缓冲区和用户配置数据的可配置软 IP 核。绝对差值(SAD)算法用于密集视差图计算。算法模块的电路由基于 Matlab 的 DSP Builder 建模。通过一组配置接口,该机器可以处理许多不同大小的立体对图像。最大图像尺寸可达 512 K 像素。该机器专注于实时立体视觉应用。立体视觉机器在实时应用中具有良好的性能和效率。考虑到硬件 FPGA 时钟为 90 MHz,使用 5×5 匹配窗口和最大 64 个视差像素,每秒可获得 23 帧 640×480 视差图。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/fba37f44be31/sensors-13-03014f12a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/3fe585d97270/sensors-13-03014f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/c9480c6d9057/sensors-13-03014f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/5daa224b84d4/sensors-13-03014f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/7087b1f09ffc/sensors-13-03014f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/00f96f8bc57e/sensors-13-03014f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/2bea56ebeb38/sensors-13-03014f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/aac179d69694/sensors-13-03014f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/c1873e7f2dfe/sensors-13-03014f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/db69e7da7368/sensors-13-03014f9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/99478ac64638/sensors-13-03014f10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/999d2d280795/sensors-13-03014f11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/fba37f44be31/sensors-13-03014f12a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/3fe585d97270/sensors-13-03014f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/c9480c6d9057/sensors-13-03014f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/5daa224b84d4/sensors-13-03014f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/7087b1f09ffc/sensors-13-03014f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/00f96f8bc57e/sensors-13-03014f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/2bea56ebeb38/sensors-13-03014f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/aac179d69694/sensors-13-03014f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/c1873e7f2dfe/sensors-13-03014f8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/db69e7da7368/sensors-13-03014f9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/99478ac64638/sensors-13-03014f10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/999d2d280795/sensors-13-03014f11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/771c/3658728/fba37f44be31/sensors-13-03014f12a.jpg

相似文献

1
SAD-based stereo vision machine on a System-on-Programmable-Chip (SoPC).基于 SAD 的立体视觉机在可编程片上系统 (SoPC) 上。
Sensors (Basel). 2013 Mar 4;13(3):3014-27. doi: 10.3390/s130303014.
2
Parametric dense stereovision implementation on a system-on chip (SoC).基于片上系统 (SoC) 的参数密集型立体视觉实现。
Sensors (Basel). 2012;12(2):1863-84. doi: 10.3390/s120201863. Epub 2012 Feb 10.
3
Real-Time FPGA Accelerated Stereo Matching for Temporal Statistical Pattern Projector Systems.用于时间统计模式投影仪系统的实时 FPGA 加速立体匹配。
Sensors (Basel). 2021 Sep 26;21(19):6435. doi: 10.3390/s21196435.
4
Disparity map generation from illumination variant stereo images using efficient hierarchical dynamic programming.利用高效分层动态规划从光照变化的立体图像生成视差图。
ScientificWorldJournal. 2014;2014:513417. doi: 10.1155/2014/513417. Epub 2014 Oct 20.
5
Analog VLSI implementation for stereo correspondence between 2-D images.
IEEE Trans Neural Netw. 1996;7(2):266-77. doi: 10.1109/72.485630.
6
A Comparison and Evaluation of Stereo Matching on Active Stereo Images.主动立体图像的立体匹配比较与评价。
Sensors (Basel). 2022 Apr 26;22(9):3332. doi: 10.3390/s22093332.
7
Five-Direction Occlusion Filling with Five Layer Parallel Two-Stage Pipeline for Stereo Matching with Sub-Pixel Disparity Map Estimation.用于具有亚像素视差图估计的立体匹配的五层并行两阶段流水线五方向遮挡填充
Sensors (Basel). 2022 Nov 8;22(22):8605. doi: 10.3390/s22228605.
8
Depth from a Motion Algorithm and a Hardware Architecture for Smart Cameras.运动算法和智能相机硬件架构的深度
Sensors (Basel). 2018 Dec 23;19(1):53. doi: 10.3390/s19010053.
9
Stereo Imaging Using Hardwired Self-Organizing Object Segmentation.使用硬连线自组织目标分割的立体成像。
Sensors (Basel). 2020 Oct 15;20(20):5833. doi: 10.3390/s20205833.
10
Real-time system for high-image resolution disparity estimation.用于高图像分辨率视差估计的实时系统。
IEEE Trans Image Process. 2007 Jan;16(1):280-5. doi: 10.1109/tip.2006.884931.

引用本文的文献

1
Stereo Imaging Using Hardwired Self-Organizing Object Segmentation.使用硬连线自组织目标分割的立体成像。
Sensors (Basel). 2020 Oct 15;20(20):5833. doi: 10.3390/s20205833.
2
Monocular Stereo Measurement Using High-Speed Catadioptric Tracking.基于高速折反射跟踪的单目立体测量
Sensors (Basel). 2017 Aug 9;17(8):1839. doi: 10.3390/s17081839.
3
The Impact of 3D Stacking and Technology Scaling on the Power and Area of Stereo Matching Processors.3D堆叠和技术缩放对立体匹配处理器功耗及面积的影响

本文引用的文献

1
Parametric dense stereovision implementation on a system-on chip (SoC).基于片上系统 (SoC) 的参数密集型立体视觉实现。
Sensors (Basel). 2012;12(2):1863-84. doi: 10.3390/s120201863. Epub 2012 Feb 10.
2
GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection.GOLD:一种用于通用障碍物和车道检测的并行实时立体视觉系统。
IEEE Trans Image Process. 1998;7(1):62-81. doi: 10.1109/83.650851.
Sensors (Basel). 2017 Feb 22;17(2):426. doi: 10.3390/s17020426.
4
Parallel Hough Transform-based straight line detection and its FPGA implementation in embedded vision.基于并行 Hough 变换的直线检测及其在嵌入式视觉中的 FPGA 实现。
Sensors (Basel). 2013 Jul 17;13(7):9223-47. doi: 10.3390/s130709223.