Zynq- real time edge detection system based on execution of the image reconstructed from the sequence. Although the object edge detection is an essential tool in computer vision, edge detection results in the negative image frame noise significantly. Further, due to the high computational complexity of an image filtering operation, implemented in the hardware configuration of the re-configurable hardware it is necessary. In this portion, the proposed dynamic Zynq embedded system reconfiguration capability to detect according to the input image frame to the noise level of the different density filters perform during runtime bit stream re Configuration.The results show that the accuracy of edge detection is highly evaluated. We analyze various noise density levels, and the results show that the edge detection results of the proposed filter bit stream are more accurate, while effectively providing computing capacity to support the real-time processing of the image frame. In the configuration time, CPU usage, and hardware resource utilization performance test results were compared.

Zynq-实时边缘检测系统，基于从序列中重建图像的执行。尽管对象边缘检测是计算机视觉中必不可少的工具，但是边缘检测会显着导致负像框噪声。此外，由于图像过滤操作的高计算复杂度，因此在可重配置硬件的硬件配置中实现是必要的。在这一部分中，建议的动态Zynq嵌入式系统重新配置功能可以根据输入图像帧检测到运行时比特流重新配置期间执行的不同密度滤波器的噪声水平。结果表明，对边缘检测的准确性进行了高度评价。我们分析各种噪声密度水平，结果表明，所提出的滤波器比特流的边缘检测结果更加准确，同时有效地提供了计算能力来支持图像帧的实时处理。在配置时间，CPU使用率和硬件资源利用性能测试结果进行了比较。