【24h】

High-speed target tracking base on FPGA

机译:基于FPGA的高速目标跟踪

获取原文

摘要

Imaging based target tracking by a robotics is an interesting and popular topic. While the high computational power requirement of imaging processing algorithm is still a big limitation, some flying robot like micro aerial vehicles also has a payload limitation, so the high weight computer and GPU is no longer a good choice. This paper present a high speed ball target tracking system based on FPGA. With a CMOS sensor, the original frame can be transfer to the FPGA port. After the video streams go through the parallel image processing core, the color and corner features can be extracted. By comparing with the predefined target's pattern, the target can be detected. AXI bus can transfer the detected target's feature to the ARM core in the ZYNQ device. The PID controller embedded in ARM core can be used to control the Pan-tilt header to move the target to the center of frame.
机译:机器人技术基于图像的目标跟踪是一个有趣且受欢迎的话题。尽管成像处理算法对高计算能力的要求仍然是一个很大的限制,但像微型飞行器这样的飞行机器人也有有效载荷的限制,因此高重量的计算机和GPU不再是一个不错的选择。本文提出了一种基于FPGA的高速球目标跟踪系统。使用CMOS传感器,可以将原始帧传输到FPGA端口。视频流经过并行图像处理核心后,可以提取颜色和边角特征。通过与预定目标的模式进行比较,可以检测到目标。 AXI总线可以将检测到的目标功能转移到Z​​YNQ设备中的ARM内核。嵌入在ARM内核中的PID控制器可用于控制Pan-tilt标头将目标移动到帧中心。

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