Font Size: a A A

Hardware Accelerated Ceramic Tube Omnidirectional Defect Detection System Based On Zynq

Posted on:2019-05-13Degree:MasterType:Thesis
Country:ChinaCandidate:J C TanFull Text:PDF
GTID:2381330572495151Subject:Electronic Science and Technology
Abstract/Summary:PDF Full Text Request
Surface defect detection of ceramic materials has always been a difficult problem in the industrial production.There are many shortcomings in traditional detection methods,such as low efficiency and high labor cost,so it is difficult to guarantee high quality products.In this paper,we use the Zynq platform for small ceramic tubes that are difficult to detect.Designed and implemented to accelerate omnidirectional ceramic tube defect detection system based Zynq hardware platform.The research contents are as follows:1.The architecture of the comprehensive defect detection system based on Zynq hardware acceleration ceramic tube was research.The architecture design of the omni-directional detection system of ceramic tube was realized by using image acquisition system,power-off protection,optical part and image processing hardware platform.2.Detection algorithms for small ceramic tubes are studied.Firstly,the difference method is used to remove the background image.Secondly,according to the characteristics of the noise in the graph,we decide to use median filter to process the image.Thirdly,we choose the appropriate threshold segmentation method based on the characteristics of grayscale histogram.Then use the Canny algorithm to perform edge detection on the image.Finally,we analyzed the image connected domain labeling algorithm,and select the appropriate parallel execution of the marking algorithm.3.The implementation scheme of Zynq hardware-accelerated ceramic tube omnidirectional defect detection system was research.This paper introduces the collaborative design process of software and hardware,divides the software and hardware of the system,and introduces the AXI4 communication protocol and the VDMA IP core in detail.The FPGA hardware algorithm for defect detection was designed with Vivado HLS,and the implementation process of the algorithm is introduced in detail.4.Designed an embedded Linux platform and Qt graphical interface,and used it to test the systemThe results show that the system can detect the scratch and defect of the target quickly,and the frame rate of ceramic tube defect detection is more than 60fps at 150MHz FPGA clock frequency.
Keywords/Search Tags:ceramic tube, machine vision, Zynq, defect detection
PDF Full Text Request
Related items