首页> 外文会议>IEEE International Conference on Computer and Communications >Design of high-speed real-time sensor image processing based on FPGA and DDR3
【24h】

Design of high-speed real-time sensor image processing based on FPGA and DDR3

机译:基于FPGA和DDR3的高速实时传感器图像处理设计

获取原文

摘要

Field-Programmable Gate Array (FPGA) plays a very important role in sensor data acquisition and processing with its rich interface resources and excellent parallel processing ability. In general, the FPGA is responsible for driving the sensor, processing the pixel data in parallel and then transfer the pixel data to the upper computer. However, with the high speed and real-time requirements of image acquisition system, color image processing by traditional personal computer (PC) cannot achieve the maximum video display frame rate. This problem is obvious for those of high resolution sensors. At the same time, the pixel data transmission between the FPGA and PC will become unstable and then make frame lost when the frame rate increases. Given the advantage of FPGA in parallel processing, this design will implement sensor video processing pipeline (VPP) with the FPGA, and select the technically mature, large capacity, high speed storage device double data rate (DDR3) to cache image data. The experimental result shows that the FPGA-based video pipeline processing and DDR3 frame cache application can increase the video frame rate and improve the transmission stability of video data.
机译:现场可编程门阵列(FPGA)具有丰富的接口资源和出色的并行处理能力,在传感器数据的采集和处理中起着非常重要的作用。通常,FPGA负责驱动传感器,并行处理像素数据,然后将像素数据传输到上位机。但是,由于图像采集系统的高速和实时性要求,传统个人计算机(PC)进行的彩色图像处理无法实现最大的视频显示帧速率。对于高分辨率传感器来说,这个问题是显而易见的。同时,当帧速率增加时,FPGA和PC之间的像素数据传输将变得不稳定,从而使帧丢失。鉴于FPGA在并行处理中的优势,该设计将在FPGA上实现传感器视频处理管线(VPP),并选择技术成熟,大容量,高速存储设备的双倍数据速率(DDR3)来缓存图像数据。实验结果表明,基于FPGA的视频流水线处理和DDR3帧缓存应用可以提高视频帧率,提高视频数据的传输稳定性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号